CN116388112B - Abnormal supply end power-off method, device, electronic equipment and computer readable medium - Google Patents

Abstract

Embodiments of the present disclosure disclose abnormal supply end power outage methods, devices, electronic equipment and computer-readable media. A specific implementation of the method includes: determining the average value of each power capacity in the power capacity sequence as the power capacity average; determining the average value of each first power consumption in the first power consumption sequence as the power consumption average; Determine the average value of each first power consumption in the first power consumption sequence that is greater than the average power consumption as the upper average power consumption; add the average power capacity and the upper average power consumption to the initial power information; The initial information is subjected to data cleaning processing to generate power information; the power information is input into the pre-trained target power information generation model to obtain the target power information; the target power information is input into the pre-trained power result information generation model to obtain the power Result information; power off the supply end. This implementation mode can promptly cut off power to some abnormal supply terminals.

Description

Abnormal supply side power outage method, device, electronic equipment and computer-readable medium

Technical field

Embodiments of the present disclosure relate to the field of computer technology, and specifically relate to abnormal supply end power outage methods, devices, electronic equipment and computer-readable media.

Background technique

Powering off the abnormal supply end can reduce the waste of power by the abnormal supply end. At present, the usual way to power off an abnormal supply end is to identify whether the supply end is an abnormal supply end according to the basic power information provided by the supply end and according to preset rules, and then cut off power to the abnormal supply end.

However, there are usually the following technical problems with the above approach:

First, the accuracy and timeliness of the basic power information provided by the supplier cannot be guaranteed, resulting in low accuracy in identifying abnormal supply terminals through the basic power information provided by the supplier, making it difficult to cut off power to some abnormal supply terminals in a timely manner. ;

Second, since the electricity attribute values in the electricity attribute value sequence included in the basic electricity information may be abnormal (for example, missing, too large, too small, etc.), the anomalies identified through the abnormal basic electricity information The accuracy of the supply side is low, making it difficult to power off some abnormal supply sides;

Third, since basic power information includes a large amount of information that is irrelevant to the preset rules, when identifying an abnormal supply end, it is necessary to filter out information related to the preset rules from a large amount of irrelevant information, resulting in a waste of calculations. resource;

Fourth, the preset rules take into account that there are fewer situations corresponding to abnormal supply terminals, and the accuracy of identifying abnormal supply terminals is low, making it difficult to power off some abnormal supply terminals.

The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.

Contents of the invention

This Summary is provided to introduce in simplified form concepts that are later described in detail in the Detailed Description. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solutions, nor is it intended to be used to limit the scope of the claimed technical solutions.

Some embodiments of the present disclosure propose abnormal supply-end power outage methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the background art section above.

In a first aspect, some embodiments of the present disclosure provide a method for abnormal supply side power outage. The method includes: obtaining basic power information of the supply side, where the above basic power information includes: power capacity sequence, first power consumption sequence , the power capacity in the above-mentioned power capacity sequence corresponds to a time granularity within the first preset time period, and the first power consumption in the above-mentioned first power consumption sequence corresponds to a time granularity within the first preset time period; The average value of each power capacity in the above-mentioned power capacity sequence is determined as the average power capacity; the average value of each first power consumption in the above-mentioned first power consumption sequence is determined as the average power consumption; the above-mentioned first power consumption sequence is determined as the average power consumption. The average value of each first power consumption greater than the above-mentioned average power consumption is determined as the upper average value of power consumption; the above-mentioned average power capacity and the above-mentioned upper average value of power consumption are added to the initial power information, wherein the above-mentioned initial power information Initially empty; perform data cleaning processing on the above-mentioned initial power information to generate power information; input the above-mentioned power information into the pre-trained target power information generation model to obtain the target power information; input the above-mentioned target power information into the pre-trained In the power result information generation model, the power result information is obtained; in response to determining that the power result information satisfies the preset abnormal condition, the power supply end is powered off.

In a second aspect, some embodiments of the present disclosure provide an abnormal supply-end power outage device. The device includes: an acquisition unit configured to acquire basic power information of the supply end, where the above-mentioned basic power information includes: power capacity sequence, third A power consumption sequence, the power capacity in the power capacity sequence corresponds to a time granularity within a first preset time period, and the first power consumption in the first power consumption sequence corresponds to a time granularity within the first preset time period. A time granularity; the first determination unit is configured to determine the average value of each power capacity in the above-mentioned power capacity sequence as the average power capacity; the second determination unit is configured to determine each first value in the above-mentioned first power consumption sequence. The average value of the electric power consumption is determined as the average electric power consumption; the third determination unit is configured to determine the average value of each first electric power consumption in the above-mentioned first electric power consumption sequence that is greater than the above-described average electric power consumption as the electric power consumption. The average value of the quantity; the adding unit is configured to add the above-mentioned average value of power capacity and the above-mentioned average value of power consumption to the initial power information, wherein the above-mentioned initial information of power is initially empty; the data cleaning unit is configured to add the above-mentioned average value of power consumption to the initial power information. The information is subjected to data cleaning processing to generate power information; the first input unit is configured to input the above-mentioned power information into a pre-trained target power information generation model to obtain the target power information; the second input unit is configured to input the above-mentioned power information The target power information is input into the pre-trained power result information generation model to obtain the power result information; the power outage unit is configured to perform power outage processing on the supply end in response to determining that the power result information satisfies the preset abnormal condition.

In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device on which one or more programs are stored. When one or more programs are processed by one or more The processor executes, causing one or more processors to implement the method described in any implementation manner of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.

The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the abnormal supply terminal power-off methods of some embodiments of the present disclosure, some abnormal supply terminals can be powered off in a timely manner. Specifically, the reason why it is difficult to cut off power to some abnormal supply terminals in time is that the accuracy and timeliness of the basic power information provided by the supply terminal cannot be guaranteed, resulting in abnormal supply terminals identified through the basic power information provided by the supply terminal. Less accurate. Based on this, the abnormal supply end power outage method in some embodiments of the present disclosure first obtains basic power information of the supply end. Wherein, the above-mentioned basic power information includes: a power capacity sequence and a first power consumption sequence. The power capacity in the above-mentioned power capacity sequence corresponds to a time granularity within a first preset time period. The third power consumption sequence in the above-mentioned first power consumption sequence One power consumption corresponds to one time granularity within the first preset time period. As a result, power grid terminals can directly obtain basic power information with small time granularity (one day, half a month, one month, etc.) and high accuracy. Secondly, the average value of each power capacity in the above power capacity sequence is determined as the power capacity mean value. Next, the average value of each first power consumption in the first power consumption sequence is determined as the average power consumption value. Immediately afterwards, the average value of each first power consumption in the above-mentioned first power consumption sequence that is greater than the above-mentioned average power consumption is determined as the upper average value of power consumption. Then, the above average power capacity value and the above average power consumption value are added to the initial power information. Among them, the above-mentioned initial power information is initially empty. As a result, timely and highly accurate initial power information can be obtained based on basic power information with smaller time granularity and higher accuracy, so that abnormal supply terminals can be subsequently identified based on the initial power information. Then, data cleaning processing is performed on the above-mentioned initial power information to generate power information. Thus, the power information after data cleaning can be obtained, so as to reduce the complexity of the subsequent target power information generation model. Afterwards, the above-mentioned power information is input into the pre-trained target power information generation model to obtain the target power information. In this way, the target power information can be obtained, so that the subsequent power result information generation model uses the target power information as input instead of the power information, which can reduce the complexity of the power result information generation model. Then, the above target power information is input into the pre-trained power result information generation model to obtain the power result information. In this way, the power result information can be obtained, so that the abnormal supply end can be subsequently identified through the power result information. Finally, in response to determining that the above-mentioned power result information satisfies the preset abnormal conditions, the above-mentioned supply end is powered off. In this way, the abnormal supply end can be powered off. Therefore, time-sensitive initial power information can be obtained based on basic power information with smaller time granularity. Therefore, more accurate abnormal supply terminals can be identified, and some abnormal supply terminals can be powered off in a timely manner.

Description of drawings

The above and other features, advantages, and aspects of various embodiments of the present disclosure will become more apparent with reference to the following detailed description taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It is to be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

Figure 1 is a flow chart of some embodiments of an abnormal supply end power outage method according to the present disclosure;

Figure 2 is a schematic structural diagram of some embodiments of an abnormal supply end power outage device according to the present disclosure;

3 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of the present disclosure.

It should also be noted that, for convenience of description, only the parts related to the invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that concepts such as “first” and “second” mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units. Or interdependence.

It should be noted that the modifications of "one" and "plurality" mentioned in this disclosure are illustrative and not restrictive. Those skilled in the art will understand that unless the context clearly indicates otherwise, it should be understood as "one or Multiple”.

The names of messages or information exchanged between multiple devices in the embodiments of the present disclosure are for illustrative purposes only and are not used to limit the scope of these messages or information.

The present disclosure will be described in detail below in conjunction with embodiments with reference to the accompanying drawings.

Referring to FIG. 1 , a process 100 of some embodiments of an abnormal supply end power outage method according to the present disclosure is shown. The abnormal supply-side power-off method includes the following steps:

Step 101: Obtain basic power information of the supply side.

In some embodiments, the execution body of the abnormal supply side power outage method (for example, the power grid terminal) can obtain the basic power information of the supply side from the terminal device through a wired connection or a wireless connection. Wherein, the above-mentioned basic power information may include but is not limited to at least one of the following: power capacity sequence, first power consumption sequence, second power consumption sequence, first power consumption attribute value sequence, capacity reduction sequence, target power capacity , the second electricity consumption attribute value sequence, the regional electricity consumption sequence, and the regional electricity consumption attribute value sequence. Here, the grid terminal may be a terminal that supplies power to the supply end. The supply side can be the terminal running the powered device. The power capacity in the above power capacity sequence corresponds to a time granularity within the first preset time period. The first power consumption in the first power consumption sequence corresponds to a time granularity within the first preset time period. The power capacity in the power capacity sequence may be the operating capacity when the powered device is operated at the supply end. The operating capacity may be the actual operating capacity of the powered device. The first power consumption in the first power consumption sequence may be the power required by the supply end to operate the powered device. The second power consumption in the second power consumption sequence may be the power required by the supply end to operate the powered device at a time granularity corresponding to the second preset time period. The first power attribute value in the first power attribute value sequence may be the power attribute value (electricity fee) required by the supply end to operate the powered device at a time granularity within the first preset time period. The capacity reduction in the capacity reduction sequence may be the reduced operating capacity when the supply end operates the powered device at a time granularity corresponding to the first preset time period. The target power capacity may be the operating capacity of the current supply end when operating the powered device. The second power consumption attribute value in the second power consumption attribute value sequence may be the power consumption attribute value (electricity fee) required by the supply end to operate the powered device at a time granularity within the second preset time period. The regional power consumption in the regional power consumption sequence may be the power required by a supply end of the same type as the above-mentioned supply end to operate the powered device at a time granularity within the first preset time period. The regional power attribute value in the regional power attribute value sequence may be the power attribute value required by a supply end of the same type as the above-mentioned supply end to operate the powered device at a time granularity within the first preset time period ( electricity bill). For example, the above time granularity can be but is not limited to: one day, one week, and half a month. The above-mentioned first preset time period may be 2022.5.1-2022.6.1. The above-mentioned first preset time period may also be 2022.7.1-2023.1.1. The above-mentioned first preset time period may be 2022.1.1-2023.1.1. The above-mentioned second preset time period may be 2022.4.1-2022.5.1. The above-mentioned second preset time period may also be 2022.1.1-2022.7.1. The above-mentioned second time period can also be 2021.1.1-2022.1.1. The powered device may include but is not limited to at least one of the following: mobile phone, tablet computer, mobile Internet device (Mobile Internet Device, MID), fan, etc.

Step 102: Determine the average value of each power capacity in the power capacity sequence as the power capacity average value.

In some embodiments, the above-mentioned execution subject may determine the average value of each power capacity in the above-mentioned power capacity sequence as the average power capacity value.

Step 103: Determine the average value of each first power consumption in the first power consumption sequence as the average power consumption.

In some embodiments, the execution subject may determine the average value of each first power consumption in the first power consumption sequence as the average power consumption.

Step 104: Determine the average value of each first power consumption in the first power consumption sequence that is greater than the average power consumption as the upper average value of power consumption.

In some embodiments, the execution subject may determine the average value of each first power consumption in the first power consumption sequence that is greater than the average power consumption as the upper average value of power consumption.

Step 105: Add the average power capacity and the upper average power consumption to the initial power information.

In some embodiments, the execution subject may add the average power capacity and the average power consumption to the initial power information. Among them, the above-mentioned initial power information is initially empty. The above-mentioned initial power information may be information obtained after data preprocessing of the above-mentioned basic power information.

Optionally, before step 106, the above method also includes:

In the first step, the above-mentioned first sequence of electricity attribute values is updated to generate a first updated sequence of electricity attribute values.

In some embodiments, the execution subject may update the first sequence of power attribute values to generate a first updated sequence of power attribute values.

In practice, the above-mentioned execution subject may update the above-mentioned first electricity attribute value sequence through the following sub-steps to generate a first updated electricity attribute value sequence:

The first sub-step is to perform the following determination steps for each first power attribute value in the above-mentioned first power attribute value sequence:

The first determining step is to determine the first electricity attribute value sequence with the above-mentioned first electricity attribute value removed as the first target electricity attribute value sequence.

The second determination step is to determine the difference between the first target power attribute value and the first power attribute value as the first target power attribute value in the first target power attribute value sequence. 1. Electricity attribute difference.

The third determination step is to determine the first power attribute value as the first central power attribute value in response to determining that the number of first power attribute differences that satisfy the preset difference condition is greater than the preset difference number. Wherein, the above-mentioned preset difference condition may be that the first electrical attribute difference is less than the preset difference. For example, the above preset difference value may be 20. The above-mentioned preset difference number may be 10.

The second sub-step is to determine each of the determined first center power consumption attribute values as a first center power consumption attribute value group.

The third sub-step is to perform the following processing steps for each first power attribute value in the above-mentioned first power attribute value sequence:

The first processing step is to determine, for each first center power attribute value in the first center power attribute value group, the difference between the first center power attribute value and the first power attribute value as the first power attribute value. A center attribute difference.

The second processing step is to determine the above-mentioned first power attribute value as the first abnormal power attribute value in response to determining that each of the determined first center attribute differences satisfies the preset distance condition. Wherein, the above-mentioned preset distance condition may be that each determined first center attribute difference value is greater than the preset maximum difference value. For example, the preset maximum difference value may be 100.

The fourth sub-step is to remove each determined first abnormal electricity attribute value from the above-mentioned first electricity attribute value sequence to obtain a first updated electricity attribute value sequence.

The relevant technical content in step 105 is an inventive point of the embodiment of the present disclosure, and solves the second technical problem mentioned in the background art, "making it difficult to power off some abnormal supply terminals". The factors that make it difficult to cut off power to some abnormal supply terminals are often as follows: Because the electricity attribute values in the electricity attribute value sequence included in the basic electricity information may be abnormal (for example, missing, too large, too small, etc.) , the accuracy of abnormal supply terminals identified through abnormal basic power information is low. If the above factors are solved, the effect of cutting off power to some abnormal supply terminals can be achieved. In order to achieve this effect, first, each first central power attribute value in the first power attribute value sequence can be determined to classify the first power attribute value in the first power attribute value sequence. A center for each category of each first center power attribute value in the center power attribute value group. Then, based on the distance between the first electricity attribute value in the first electricity attribute value sequence and each central electricity attribute value being greater than the preset maximum difference, the abnormal first user in the first electricity attribute value sequence can be determined. Electrical property value. Finally, each abnormal first power attribute value may be removed from the first power attribute value sequence, so as to remove abnormal data in the first power attribute value sequence. Therefore, a relatively accurate first electricity attribute value sequence can be obtained, so that a more accurate abnormal supply end can be identified later based on the basic electricity information including the relatively accurate first electricity attribute value sequence. Therefore, some abnormal supply terminals can be powered off.

In the second step, the sum of each first power consumption in the above-mentioned first power consumption sequence is determined as the first total power consumption.

In some embodiments, the execution subject may determine the sum of each first power consumption in the first power consumption sequence as the first total power consumption.

The third step is to determine the sum of each second power consumption in the above-mentioned second power consumption sequence as the second total power consumption.

In some embodiments, the execution subject may determine the sum of each second power consumption in the second power consumption sequence as the second total power consumption.

The fourth step is to determine the ratio of the above-mentioned first total electricity consumption to the above-mentioned second total electricity consumption as the year-on-year total electricity consumption.

In some embodiments, the execution subject may determine the ratio of the first total power consumption and the second total power consumption as the total power consumption year-on-year.

The fifth step is to determine the average value of each first updated power attribute value in the first updated power attribute value sequence as the average power attribute value.

In some embodiments, the execution subject may determine the average value of each first updated power attribute value in the first updated power attribute value sequence as the average power attribute value.

The sixth step is to determine the average value of each first updated electricity attribute value in the above-mentioned first updated electricity attribute value sequence that is greater than the above-mentioned average value of the electricity attribute as the upper average value of the electricity attribute.

In some embodiments, the execution subject may determine the average value of each first updated power attribute value in the sequence of first updated power attribute values that is greater than the average value of the power attribute as the upper mean value of the power attribute.

The seventh step is to determine the ratio of the largest first updated electricity attribute value in the above-mentioned first updated electricity attribute value sequence to the smallest first updated electricity attribute value in the above-mentioned first updated electricity attribute value sequence as the electricity consumption. Attribute ratio.

In some embodiments, the execution subject may combine the largest first updated power attribute value in the sequence of first updated power attribute values with the smallest first updated power attribute value in the sequence of first updated power attribute values. The ratio of is determined as the electricity attribute ratio.

The eighth step is to add the above-mentioned total electricity consumption year-on-year, the above-mentioned average value of electricity consumption attributes and the above-mentioned electricity consumption attribute ratio to the above-mentioned initial electricity information.

In some embodiments, the above execution subject may add the above total power consumption year-on-year, the above average power consumption attribute, and the above power consumption attribute ratio to the above power initial information.

Optionally, the above method also includes:

In the first step, the above-mentioned second electricity attribute value sequence is updated to generate a second updated electricity attribute value sequence.

In some embodiments, the above-mentioned executive director may update the above-mentioned second sequence of electricity consumption attribute values to generate a second updated sequence of electricity consumption attribute values. In practice, the specific implementation method of updating the above-mentioned second power attribute value sequence and the technical effects brought about can be referred to step 105 in the above-mentioned embodiment, and will not be described again here.

In the second step, the number of capacity reductions in the above capacity reduction sequence is determined as the number of capacity reductions.

In some embodiments, the execution subject may determine the number of capacity reductions in the capacity reduction sequence as the number of capacity reductions.

The third step is to determine the sum of each capacity reduction capacity in the above capacity reduction sequence as the total capacity reduction capacity.

In some embodiments, the execution subject may determine the sum of each capacity reduction capacity in the capacity reduction sequence as the total capacity reduction capacity.

The fourth step is to determine the ratio of the total capacity reduction to the target power capacity as the capacity reduction ratio.

In some embodiments, the execution subject may determine the ratio of the total capacity reduction to the target power capacity as the capacity reduction ratio.

The fifth step is to determine the sum of each first updated power attribute value in the above-mentioned first updated power attribute value sequence as the first total power attribute value.

In some embodiments, the execution subject may determine the sum of each first updated power attribute value in the sequence of first updated power attribute values as the first total power attribute value.

The sixth step is to determine the sum of each second updated power attribute value in the above-mentioned second updated power attribute value sequence as the second total power attribute value.

In some embodiments, the execution subject may determine the sum of each second updated power attribute value in the second updated power attribute value sequence as the second total power attribute value.

The seventh step is to determine the ratio of the above-mentioned first total electricity consumption attribute value and the above-mentioned second total electricity consumption attribute value as the total electricity consumption attribute year-on-year.

In some embodiments, the execution subject may determine the ratio of the first total power consumption attribute value and the second total power consumption attribute value as the total power consumption attribute ratio.

Step 8: For each first power consumption in the above-mentioned first power consumption sequence, determine the ratio of the above-mentioned first power consumption to the previous first power consumption of the above-mentioned first power consumption as the first power consumption. Electricity usage ratio.

In some embodiments, the execution subject may, for each first power consumption in the first power consumption sequence, combine the first power consumption with the previous first power consumption of the first power consumption. The ratio of is determined as the first power consumption ratio.

In the ninth step, the average value of the determined first power consumption ratios is determined as the power consumption change rate.

In some embodiments, the above execution subject may determine the average value of each determined first power consumption ratio as the power consumption change rate.

The tenth step is to add the above-mentioned number of capacity reductions, the above-mentioned capacity reduction ratio, the above-mentioned year-on-year total electricity consumption attributes, and the above-mentioned electricity consumption change rate to the above-mentioned initial power information.

In some embodiments, the execution subject may add the number of capacity reductions, the capacity reduction ratio, the total power consumption attribute year-on-year, and the power consumption change rate to the initial power information.

Optionally, the above method also includes:

In the first step, the average value of each regional electricity consumption in the above-mentioned regional electricity consumption sequence is determined as the average regional electricity consumption.

In some embodiments, the above-mentioned execution subject may determine the average value of each regional power consumption in the above-mentioned regional power consumption sequence as the regional average power consumption.

In the second step, the square of each region's electricity consumption in the above-mentioned regional electricity consumption sequence is determined as the regional electricity consumption square value, and a regional electricity consumption square value sequence is obtained.

In some embodiments, the execution subject may determine the square of each region's electricity consumption in the region's electricity consumption sequence as the regional electricity consumption square value, thereby obtaining a region's electricity consumption square value sequence.

The third step is to determine the sum of the square values of electricity consumption in each region in the above sequence of squared values of regional electricity consumption as the sum of squares of regional electricity consumption.

In some embodiments, the above execution subject may determine the sum of the square values of each regional power consumption in the above sequence of regional power consumption square values as the regional sum of square power consumption values.

The fourth step is to determine the sum of the regional electricity consumption in the above-mentioned regional electricity consumption sequence as the regional electricity consumption sum value.

In some embodiments, the execution subject may determine the sum of the regional electricity consumption in the regional electricity consumption sequence as the regional electricity consumption sum value.

The fifth step is to determine the square of the sum of the above-mentioned regional electricity consumption values as the square value of the regional electricity consumption sum.

In some embodiments, the above execution subject may determine the square of the above regional power consumption sum value as the regional power consumption sum square value.

The sixth step is to determine the ratio of the sum of squares of electricity consumption in the above-mentioned area to the sum of squares of electricity consumption in the above-mentioned areas as the regional electricity consumption concentration.

In some embodiments, the above-mentioned execution subject may determine the ratio of the above-mentioned regional sum of squares of electricity consumption to the above-mentioned regional sum of squares of electricity consumption as the regional electricity consumption concentration.

The seventh step is to determine the average value of each regional electricity attribute value in the above-mentioned regional electricity attribute value sequence as the average regional electricity attribute value.

In some embodiments, the execution subject may determine the average value of each regional electricity attribute value in the sequence of regional electricity attribute values as the average regional electricity attribute value.

The eighth step is to generate a regional electricity consumption attribute value concentration ratio based on the above-mentioned regional electricity consumption attribute value sequence.

In some embodiments, the above-mentioned execution subject may generate a regional power consumption attribute value concentration degree based on the above-mentioned regional power consumption attribute value sequence. In practice, first, the above-mentioned execution subject can determine the square of each regional electricity attribute value in the above-mentioned regional electricity attribute value sequence as the regional electricity attribute square value, and obtain a regional electricity attribute square value sequence. Secondly, the execution subject may determine the sum of the square values of each regional electricity attribute in the sequence of regional electricity attribute square values as the sum of squares of the regional electricity attributes. Next, the execution subject may determine the sum of the regional electricity attribute values in the regional electricity attribute value sequence as the regional electricity attribute sum value. Then, the above execution subject may determine the square of the above regional power consumption attribute sum value as the regional power consumption attribute sum square value. Finally, the above-mentioned execution subject may determine the ratio of the above-mentioned regional electricity consumption attribute sum-square value to the above-mentioned regional electricity consumption attribute sum-square value as the regional electricity consumption attribute value concentration degree.

The ninth step is to add the above-mentioned regional electricity consumption average, the above-mentioned regional electricity consumption concentration, the above-mentioned regional electricity attribute average value, and the above-mentioned regional electricity consumption attribute value concentration to the above-mentioned initial electricity information.

In some embodiments, the execution subject may add the regional power consumption average, the regional power consumption concentration, the regional power attribute average, and the regional power attribute value concentration to the initial power information. The above-mentioned initial power information may also include but is not limited to at least one of the following: first user proportion, first power consumption number, and second power consumption number. Here, the first user proportion may be the sum of the total number of first users (the total number of households that have canceled their accounts on the supply side) and the number of second users (the total number of households that are currently using electricity on the supply side) within the first preset time period. ratio. The first power usage number may be the number of first power usages (theft power usage) within the third preset time period. The second power consumption number may be the number of second power consumption (default power consumption) within the third preset time period. The third preset time period may be the sum of the above-mentioned first preset time period and the above-mentioned second preset time period.

Step 106: Perform data cleaning processing on the initial power information to generate power information.

In some embodiments, the execution subject may perform data cleaning processing on the initial power information to generate power information. In practice, first, the execution subject may remove the total power consumption attribute year-on-year and the power consumption change rate from the power initial information to generate power update information. Then, the execution subject may remove empty information from the power update information to generate power information. Thus, the year-on-year total power consumption attributes, the change rate of power consumption, and the empty information can be removed to reduce the complexity of the target power information generation model.

Step 107: Input the power information into the pre-trained target power information generation model to obtain the target power information.

In some embodiments, the execution subject may input the power information into a pre-trained target power information generation model to obtain the target power information. The above target power information generation model may be a neural network model that takes power information as input and uses target power information as output. The above target power information may include: information included in the power information that satisfies a preset quantity condition. The above-mentioned preset quantity condition may be each piece of information corresponding to the first preset quantity of weights in the weight sequence corresponding to the power information. The weight in the above weight sequence can represent the importance of the information included in the power information. The above-mentioned weight sequence may be a sequence in which various pieces of information included in the power information are sorted from large to small in weight. For example, the preset number could be 15.

Optionally, the pre-trained target power information generation model can be trained through the following steps:

The first step is to obtain the training sample set.

In some embodiments, the above-mentioned execution subject may obtain the training sample set from the terminal device through a wired connection or a wireless connection. Among them, the training samples in the above training sample set include: sample power information and sample target power information. Here, the sample target power information may be a sample label corresponding to the sample power information.

The second step is to determine the initial target power information generation model.

In some embodiments, the above-mentioned execution subject may determine an initial target power information generation model. The above-mentioned initial target power information generation model may be a neural network model that uses sample power information as input and initial target power information as output. The above-mentioned initial target power information generation model may include: an initial weight generation model and an initial selection model.

The above-mentioned initial weight generation model may be a first custom model that uses sample power information as input and initial weight information as output. Here, the initial weight information may represent each weight corresponding to each piece of information included in the sample power information. The first custom model can be divided into three layers:

The first layer: input layer, used to receive sample power information and input the sample power information to the second layer.

The second layer: the processing layer, including: the first sub-model and the second sub-model. The first sub-model may be a gradient boosting model that uses sample power information as input and first weight information as output. The second sub-model may be a classifier model that uses sample power information as input and second weight information as output. The first weight information may include but is not limited to: a first weight set. The first weight in the first weight set may be a weight of information included in the corresponding sample power information generated through the first sub-model. The second weight information may include but is not limited to: a second weight set. The second weight in the second weight set may be a weight of information included in the corresponding sample power information generated through the second sub-model. Here, the first weight included in the first weight information may correspond to the second weight included in the second weight information. The first weight included in the first weight information may correspond to the information included in the sample power information. For example, the first sub-model can be an XGBoost (eXtreme GradientBoosting, extreme gradient boosting) model. The second sub-model can be an RF (Random Forest) model.

The third layer, the output layer, is used to: first, receive the first weight information and the second weight information output by the second layer. Next, for each first weight included in the above-mentioned first weight information, the average value of the above-mentioned first weight and the second weight corresponding to the above-mentioned first weight is determined as the average weight. Then, each determined average weight is determined as initial weight information. Finally, the initial weight information is used as the output of the entire first custom model.

The above-mentioned initial selection model may be a model that takes initial weight information and sample power information as inputs and uses initial target power information as output. The above initial selection model can be used to: first, sort the weights included in the initial weight information in descending order to obtain a transit weight sequence. Then, a preset number of individual weights in the above-mentioned transit weight sequence are determined as a transit weight group. Afterwards, for each transfer weight in the above-mentioned transfer weight group, the information corresponding to the above-mentioned transfer weight included in the sample power information is determined as the target information. Finally, each determined target information is determined as initial target power information.

The third step is to select training samples from the above training sample set.

In some embodiments, the execution subject may select training samples from the training sample set. In practice, the above execution subject can randomly select training samples from the above training sample set.

The fourth step is to input the sample power information included in the above training samples into the above initial weight information generation model to obtain the initial weight information.

In some embodiments, the execution subject may input the sample power information included in the training sample into the initial weight information generation model to obtain the initial weight information.

The fifth step is to input the above-mentioned initial weight information and the sample power information included in the above-mentioned training samples into the above-mentioned initial selection model to obtain initial target power information.

In some embodiments, the execution subject may input the initial weight information and the sample power information included in the training samples into the initial selection model to obtain the initial target power information.

The sixth step is to determine a first difference value between the initial target power information and the sample target power information included in the training sample based on the preset first loss function.

In some embodiments, the execution subject may determine a first difference value between the initial target power information and the sample target power information included in the training sample based on a preset first loss function. Among them, the preset first loss function can be but is not limited to: mean square error loss function (MSE), hinge loss function (SVM), cross entropy loss function (CrossEntropy), 0-1 loss function, absolute value loss function , logarithmic loss function, square loss function, exponential loss function, etc.

The seventh step is to adjust the network parameters of the initial target power information generation model in response to determining that the first difference value satisfies the first preset condition.

In some embodiments, the execution subject may adjust the network parameters of the initial target power information generation model in response to determining that the first difference value satisfies the first preset condition. Wherein, the first preset condition may be that the first difference value is greater than the first preset difference value. For example, the difference between the above-mentioned first difference value and the first preset difference value may be calculated. On this basis, back propagation, gradient descent and other methods are used to adjust the network parameters of the above initial target power information generation model. It should be noted that the backpropagation algorithm and gradient descent method are well-known technologies that are widely researched and applied at present, and will not be described again here. There is no limitation on the setting of the first preset difference value. For example, the first preset difference value may be 0.1.

The optional technical content in step 107 serves as an inventive point of the embodiment of the present disclosure, and solves the third technical problem mentioned in the background art, "resulting in a waste of computing resources." Factors that lead to a waste of computing resources are often as follows: Since basic power information includes a large amount of information that is irrelevant to preset rules, when identifying an abnormal supply end, it is necessary to filter out a large amount of irrelevant information that is related to preset rules. Information. If the above factors are solved, the effect of reducing the waste of computing resources can be achieved. In order to achieve this effect, first, the weight corresponding to each information included in the power information can be obtained through the first sub-model and the second sub-model included in the first predefined model. Then, more accurate initial weight information can be obtained by taking into account the weights output by the first sub-model and the second sub-model through the third layer output of the first predefined model. Afterwards, the target power information can be selected from each information included in the power information through the initial selection model. Finally, the target power information generation model can be obtained by training the initial weight generation model and the initial selection model included in the initial target power information generation model. Therefore, the present disclosure can obtain each piece of information with a high degree of importance in the power information through the trained target power information generation model. Therefore, only considering the more important power information can reduce the waste of computing resources.

Optionally, in response to determining that the first difference value does not satisfy the first preset condition, the initial target power information generation model is determined as the trained target power information generation model.

In some embodiments, the execution subject may determine the initial target power information generation model as the trained target power information generation model in response to determining that the first difference value does not satisfy the first preset condition.

Step 108: Input the target power information into the pre-trained power result information generation model to obtain the power result information.

In some embodiments, the execution subject may input the target power information into a pre-trained power result information generation model to obtain the power result information. The power result information generation model may be a neural network model that takes target power information as input and uses power result information as output. The above-mentioned power result information may be, but is not limited to: first result information and second result information. Here, the first result information may indicate that the supply end is an abnormal supply end. The second result information may indicate that the supply end is not an abnormal supply end. The abnormal supply end may be a supply end with abnormal power consumption.

Optionally, the pre-trained power result information generation model can be trained through the following steps:

The first step is to obtain the training sample set.

In some embodiments, the above-mentioned execution subject may obtain the training sample set from the terminal device through a wired connection or a wireless connection. Among them, the training samples in the above training sample set include: sample target power information and sample power result information.

The second step is to determine the initial power result information generation model.

In some embodiments, the execution entity described above may determine an initial power result information generation model. The above-mentioned initial power result information generation model may be a neural network model that takes sample target power information as input and initial power result information as output. The above-mentioned initial power result information generation model may include: an initial target weight generation model, an initial fusion model, and an initial labeling model.

The above-mentioned initial target weight generation model may be a second custom model that uses sample target power information as input and initial target weight information as output. Here, the initial target weight information may represent each weight corresponding to each piece of information included in the sample target power information. The above second custom model can be divided into three layers:

The first layer: input layer, used to receive sample target power information and input the sample target power information to the second layer.

The second layer: the processing layer, including: the first target sub-model and the second target sub-model. The first target sub-model may be a multi-layer feedforward neural network model with sample target power information as input and first target weight information as output. The second target sub-model may be a gradient boosting model that uses sample target power information as its output and second target weight information as its output. The first target weight information may include but is not limited to: a first target weight set. The first target weight in the first target weight set may be a weight of information included in the corresponding sample target power information generated through the first target sub-model. The second target weight information may include but is not limited to: a second target weight set. The second target weight in the second target weight set may be the weight of information included in the corresponding sample target power information generated through the second target sub-model. Here, the first target weight included in the first target weight information may correspond to the second target weight included in the second target weight information. The first target weight included in the first target weight information may correspond to the information included in the sample target power information. For example, the first target sub-model may be a BP (back propagation, multi-layer feedforward neural network) model. The second target sub-model can be an XGBoost (eXtreme Gradient Boosting) model.

The third layer, the output layer, is used to: first, receive the first target weight information and the second target weight information output by the second layer. Next, for each first target weight included in the above-mentioned first target weight information, the average value of the above-mentioned first target weight and the second target weight corresponding to the above-mentioned first target weight is determined as the average target weight. Then, each determined target weight is determined as initial target weight information. Finally, the initial target weight information is used as the output of the entire second custom model.

The above-mentioned initial fusion model may be a model that takes sample target power information and initial target weight information as input and uses initial fusion information as output. Here, the above-mentioned initial fusion model is used to: firstly, for each information included in the above-mentioned sample target power information, determine the product of the above-mentioned information and the average target weight corresponding to the above-mentioned information included in the above-mentioned initial target weight information as the power weight value. Then, the sum of the determined respective power weight values is determined as the initial fusion information.

The above-mentioned initial labeling model may be a model that takes initial fusion information as input and initial power result information as output. Here, the above-mentioned initial marking model is used to: firstly, in response to determining that the above-mentioned initial fusion information satisfies the preset marking condition, determine the first result information as the initial power result information. Then, in response to determining that the above-mentioned initial fusion information does not satisfy the above-mentioned preset flag condition, the second result information is determined as the initial power result information. Wherein, the above-mentioned preset marking condition may be that the initial fusion information is less than the preset marking value. For example, the default marker value may be 0.5.

The third step is to select training samples from the above training sample set.

In some embodiments, the execution subject may select training samples from the training sample set. In practice, the above execution subject can randomly select training samples from the above training sample set.

The fourth step is to input the sample target power information included in the above training sample into the above initial target weight generation model to obtain the initial target weight information.

In some embodiments, the execution subject may input the sample target power information included in the training sample into the initial target weight generation model to obtain the initial target weight information.

The fifth step is to input the sample target power information included in the above training sample and the above initial target weight information into the above initial fusion model to obtain initial fusion information.

In some embodiments, the execution subject may input the sample target power information included in the training sample and the initial target weight information into the initial fusion model to obtain initial fusion information.

The sixth step is to input the above-mentioned initial fusion information into the above-mentioned initial labeling model to obtain the initial power result information.

In some embodiments, the execution subject may input the initial fusion information into the initial marking model to obtain initial power result information.

The seventh step is to determine the second difference value between the above-mentioned initial power result information and the sample power result information included in the above-mentioned training sample based on the preset second loss function.

In some embodiments, the execution subject may determine a second difference value between the initial power result information and the sample power result information included in the training sample based on a preset second loss function. Among them, the preset second loss function can be but is not limited to: mean square error loss function (MSE), hinge loss function (SVM), cross entropy loss function (CrossEntropy), 0-1 loss function, absolute value loss function , logarithmic loss function, square loss function, exponential loss function, etc.

Step 8: In response to determining that the second difference value satisfies the second preset condition, adjust the network parameters of the initial power result information generation model.

In some embodiments, the execution subject may adjust the network parameters of the initial power result information generation model in response to determining that the second difference value satisfies the second preset condition. The second preset condition may be that the second difference value is greater than the second preset difference value. For example, the difference between the above-mentioned second difference value and the second preset difference value may be calculated. On this basis, methods such as back propagation and gradient descent are used to adjust the network parameters of the above initial power result information generation model. It should be noted that the backpropagation algorithm and gradient descent method are well-known technologies that are widely researched and applied at present, and will not be described again here. There is no limitation on the setting of the second preset difference value. For example, the second preset difference value may be 0.1.

The optional technical content in step 108 serves as an inventive point of the embodiment of the present disclosure and solves the fourth technical problem mentioned in the background art, "It is difficult to power off some abnormal supply terminals." The factors that make it difficult to power off some abnormal supply terminals are often as follows: the preset rules take into account that there are fewer situations corresponding to the abnormal supply terminals, and the accuracy of the identified abnormal supply terminals is low. If the above factors are solved, the effect of cutting off power to some abnormal supply terminals can be achieved. In order to achieve this effect, first, the weight corresponding to each information included in the target power information can be obtained through the first target sub-model and the second target sub-model included in the second predefined model. Then, more accurate initial target weight information can be obtained by taking into account the weights output by the first target sub-model and the second target sub-model through the third layer output of the second predefined model. Afterwards, the initial fusion information characterizing the abnormal situation on the supply side can be obtained through the initial fusion model. Then, the abnormal supply end can be marked through the initial marking model. Finally, the power result information generation model can be obtained by training the initial target weight generation model, the initial fusion model and the initial labeling model including the initial power result information generation model. Therefore, the present disclosure can identify abnormal supply terminals through the trained power result information generation model, which is more accurate than identifying abnormal supply terminals through preset rules. Therefore, some abnormal supply terminals can be powered off.

Optionally, in response to determining that the second difference value satisfies the second preset condition, the initial power result information generation model is determined as the trained power result information generation model.

In some embodiments, the execution subject may determine the initial power result information generation model as the trained power result information generation model in response to determining that the second difference value satisfies the second preset condition.

Step 109: In response to determining that the power result information satisfies the preset abnormal conditions, perform power-off processing on the supply end.

In some embodiments, the execution subject may perform power-off processing on the supply end in response to determining that the power result information satisfies a preset abnormal condition. Wherein, the above-mentioned preset abnormal condition may be that the above-mentioned power result information is the first result information.

The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the abnormal supply terminal power-off methods of some embodiments of the present disclosure, some abnormal supply terminals can be powered off in a timely manner. Specifically, the reason why it is difficult to cut off power to some abnormal supply terminals in time is that the accuracy and timeliness of the basic power information provided by the supply terminal cannot be guaranteed, resulting in abnormal supply terminals identified through the basic power information provided by the supply terminal. Less accurate. Based on this, the abnormal supply end power outage method in some embodiments of the present disclosure first obtains basic power information of the supply end. Wherein, the above-mentioned basic power information includes: a power capacity sequence and a first power consumption sequence. The power capacity in the above-mentioned power capacity sequence corresponds to a time granularity within a first preset time period. The third power consumption sequence in the above-mentioned first power consumption sequence One power consumption corresponds to one time granularity within the first preset time period. As a result, power grid terminals can directly obtain basic power information with small time granularity (one day, half a month, one month, etc.) and high accuracy. Secondly, the average value of each power capacity in the above power capacity sequence is determined as the power capacity mean value. Next, the average value of each first power consumption in the first power consumption sequence is determined as the average power consumption value. Immediately afterwards, the average value of each first power consumption in the above-mentioned first power consumption sequence that is greater than the above-mentioned average power consumption is determined as the upper average value of power consumption. Then, the above average power capacity value and the above average power consumption value are added to the initial power information. Among them, the above-mentioned initial power information is initially empty. As a result, timely and highly accurate initial power information can be obtained based on basic power information with smaller time granularity and higher accuracy, so that abnormal supply terminals can be subsequently identified based on the initial power information. Then, data cleaning processing is performed on the above-mentioned initial power information to generate power information. Thus, the power information after data cleaning can be obtained, so as to reduce the complexity of the subsequent target power information generation model. Afterwards, the above-mentioned power information is input into the pre-trained target power information generation model to obtain the target power information. In this way, the target power information can be obtained, so that the subsequent power result information generation model uses the target power information as input instead of the power information, which can reduce the complexity of the power result information generation model. Then, the above target power information is input into the pre-trained power result information generation model to obtain the power result information. In this way, the power result information can be obtained, so that the abnormal supply end can be subsequently identified through the power result information. Finally, in response to determining that the above-mentioned power result information satisfies the preset abnormal conditions, the above-mentioned supply end is powered off. In this way, the abnormal supply end can be powered off. Therefore, time-sensitive initial power information can be obtained based on basic power information with smaller time granularity. Therefore, more accurate abnormal supply terminals can be identified, and some abnormal supply terminals can be powered off in a timely manner.

With further reference to Figure 2, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an abnormal supply end power outage device. These abnormal supply end power outage device embodiments are the same as those methods shown in Figure 1 Corresponding to the embodiment, the abnormal supply-side power-off device can be applied to various electronic devices.

As shown in Figure 2, the abnormal supply end power outage device 200 in some embodiments includes: an acquisition unit 201, a first determination unit 202, a second determination unit 203, a third determination unit 204, an adding unit 205, a data cleaning unit 206, The first input unit 207, the second input unit 208 and the power-off unit 209. Wherein, the acquisition unit 201 is configured to acquire the basic power information of the supply end, where the above-mentioned basic power information includes: a power capacity sequence and a first power consumption sequence, and the power capacity in the above-mentioned power capacity sequence corresponds to the first preset time period. A time granularity within the first power consumption sequence, the first power consumption in the above-mentioned first power consumption sequence corresponds to a time granularity within the first preset time period; the first determination unit 202 is configured to calculate each power in the above-mentioned power capacity sequence. The average value of the capacity is determined as the average power capacity; the second determination unit 203 is configured to determine the average value of each first power consumption in the above-mentioned first power consumption sequence as the average power consumption; the third determination unit 204, It is configured to determine the average value of each first power consumption in the above-mentioned first power consumption sequence that is greater than the above-mentioned average power consumption as the upper average value of power consumption; the adding unit 205 is configured to add the above-mentioned average power capacity and the above-mentioned average power consumption. The upper average value of power consumption is added to the initial power information, wherein the above-mentioned initial power information is initially empty; the data cleaning unit 206 is configured to perform data cleaning processing on the above-mentioned initial power information to generate power information; the first input unit 207 , is configured to input the above-mentioned power information into the pre-trained target power information generation model to obtain the target power information; the second input unit 208 is configured to input the above-mentioned target power information into the pre-trained power result information generation model. , to obtain the power result information; the power-off unit 209 is configured to perform power-off processing on the above-mentioned supply end in response to determining that the above-mentioned power result information satisfies the preset abnormal condition.

It can be understood that the units recorded in the abnormal supply end power outage device 200 correspond to the various steps in the method described with reference to FIG. 1 . Therefore, the operations, features and beneficial effects described above for the method are also applicable to the abnormal supply end power outage device 200 and the units included therein, and will not be described again here.

Referring now to FIG. 3 , a schematic structural diagram of an electronic device (eg, a power grid terminal) 300 suitable for implementing some embodiments of the present disclosure is shown. Electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (such as car navigation terminals) and other mobile terminals as well as fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG. 3 is only an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG. 3 , the electronic device 300 may include a processing device (eg, central processing unit, graphics processor, etc.) 301 , which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 302 or from a storage device 308 . The program in the memory (RAM) 303 executes various appropriate actions and processes. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, ROM 302 and RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304 .

Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration An output device 307 such as a computer; a storage device 308 including a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although FIG. 3 illustrates electronic device 300 with various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided. Each block shown in Figure 3 may represent one device, or may represent multiple devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In some such embodiments, the computer program may be downloaded and installed from the network via communication device 309, or from storage device 308, or from ROM 302. When the computer program is executed by the processing device 301, the above-described functions defined in the methods of some embodiments of the present disclosure are performed.

It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device . Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the client and server can communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium. (e.g., communications network) interconnection. Examples of communications networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or developed in the future network of.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains basic power information at the supply end, where the basic power information includes: a power capacity sequence. , the first power consumption sequence, the power capacity in the above-mentioned power capacity sequence corresponds to a time granularity within the first preset time period, and the first power consumption in the above-mentioned first power consumption sequence corresponds to the first preset time period A time granularity within; determine the average value of each power capacity in the above-mentioned power capacity sequence as the average power capacity; determine the average value of each first power consumption in the above-mentioned first power consumption sequence as the average power consumption; The average value of each first power consumption in the above-mentioned first power consumption sequence that is greater than the above-mentioned average power consumption is determined as the upper average value of power consumption; the above-mentioned average power capacity and the above-mentioned upper average value of power consumption are added to the initial power information. , wherein the above-mentioned initial power information is initially empty; the above-mentioned initial power information is subjected to data cleaning processing to generate power information; the above-mentioned power information is input into a pre-trained target power information generation model to obtain the target power information; the above-mentioned target The power information is input into the pre-trained power result information generation model to obtain the power result information; in response to determining that the power result information satisfies the preset abnormal conditions, the power supply end is powered off.

Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof, Also included are conventional procedural programming languages—such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In situations involving remote computers, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer, such as an Internet service provider. connected via the Internet).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented in software or hardware. The described unit can also be provided in a processor. For example, it can be described as: a processor includes an acquisition unit, a first determination unit, a second determination unit, a third determination unit, an adding unit, a data cleaning unit, a first Input unit, second input unit and power outage unit. The names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the acquisition unit may also be described as “obtaining basic power information at the supply end.”

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical device (CPLD) and so on.

The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles applied. Persons skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to technical solutions composed of specific combinations of the above technical features, and should also cover the above-mentioned technical solutions without departing from the above-mentioned inventive concept. Other technical solutions formed by any combination of technical features or their equivalent features. For example, a technical solution is formed by replacing the above features with technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to).

Claims (7)

1. An abnormal supply end power-off method comprises the following steps:

acquiring basic power information of a supply end, wherein the basic power information comprises: the power capacity in the power capacity sequence corresponds to a time granularity in a first preset time period, and the first power in the first power sequence corresponds to a time granularity in the first preset time period;

determining an average value of each power capacity in the power capacity sequence as a power capacity average value;

determining an average value of all the first electric quantities in the first electric quantity sequence as an average value of the electric quantities;

determining an average value of all the first electric quantities larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities;

adding the power capacity average value and the power consumption upper average value into power initial information, wherein the power initial information is initially empty;

performing data cleaning processing on the electric power initial information to generate electric power information;

inputting the power information into a pre-trained target power information generation model to obtain target power information;

inputting the target power information into a pre-trained power result information generation model to obtain power result information;

And responding to the fact that the power result information meets a preset abnormal condition, and performing power-off processing on the supply end.

2. The method of claim 1, wherein the power base information further comprises: the second electricity consumption sequence and the first electricity attribute value sequence; and

before the data cleansing process is performed on the power initial information to generate power information, the method further includes:

updating the first electrical attribute value sequence to generate a first updated electrical attribute value sequence;

determining the sum of all the first electric quantities in the first electric quantity sequence as a first total electric quantity;

determining the sum of the second power consumption in the second power consumption sequence as a second total power consumption;

determining the ratio of the first total power consumption to the second total power consumption as the same ratio of the total power consumption;

determining an average value of each first updated electricity attribute value in the first updated electricity attribute value sequence as an electricity attribute average value;

determining the average value of each first updated electricity attribute value larger than the average value of the electricity attribute in the first updated electricity attribute value sequence as the average value of the electricity attribute;

Determining the ratio of the largest first updated electricity utilization attribute value in the first updated electricity utilization attribute value sequence to the smallest first updated electricity utilization attribute value in the first updated electricity utilization attribute value sequence as an electricity utilization attribute ratio;

and adding the total electricity consumption homonymy, the electricity consumption attribute upper average value and the electricity consumption attribute ratio to the electric power initial information.

3. The method of claim 2, wherein the power base information further comprises: a sequence of volume reduction capacities, a target power capacity, and a sequence of second power usage attribute values; and

the method further comprises the steps of:

updating the second power utilization attribute value sequence to generate a second updated power utilization attribute value sequence;

determining the number of volume reduction capacities in the volume reduction capacity sequence as volume reduction times;

determining the sum of the volume-reducing capacities in the volume-reducing capacity sequence as the volume-reducing total capacity;

determining a ratio of the reduced-volume total capacity to the target power capacity as a reduced-volume duty cycle;

determining a sum of the first updated electrical attribute values in the sequence of first updated electrical attribute values as a first total electrical attribute value;

determining a sum of the second updated electrical attribute values in the sequence of second updated electrical attribute values as a second total electrical attribute value;

Determining the ratio of the first total electricity utilization attribute value and the second total electricity utilization attribute value as the total electricity utilization attribute same ratio;

for each first electric quantity in the first electric quantity sequence, determining the ratio of the first electric quantity to the last first electric quantity of the first electric quantity as a first electric quantity ratio;

determining an average value of the determined first electric quantity ratios as an electric quantity change rate;

and adding the volume reduction times, the volume reduction ratio, the total electricity utilization attribute homoratio and the electricity utilization change rate to the electric power initial information.

4. A method according to claim 3, wherein the power base information further comprises: a region electricity consumption sequence and a region electricity consumption attribute value sequence; and

the method further comprises the steps of:

determining an average value of the power consumption of each area in the area power consumption sequence as an average value of the power consumption of the area;

determining the square of the power consumption of each area in the area power consumption sequence as an area power consumption square value, and obtaining an area power consumption square value sequence;

determining the sum of the square values of the power consumption of each area in the square value sequence of the power consumption of the area as the square sum of the power consumption of the area;

Determining the sum of the regional power consumption in the regional power consumption sequence as the regional power consumption sum value;

determining the square of the regional power consumption sum as a regional power consumption sum square value;

determining the ratio of the square sum value of the regional power consumption to the square sum value of the regional power consumption as regional power consumption concentration;

determining the average value of all the regional power utilization attribute values in the regional power utilization attribute value sequence as the regional power utilization attribute average value;

generating regional electricity attribute value concentration based on the regional electricity attribute value sequence;

and adding the regional power consumption average value, the regional power consumption concentration, the regional power consumption attribute average value and the regional power consumption attribute value concentration to the electric power initial information.

5. An abnormal supply end power-off device, comprising:

an acquisition unit configured to acquire power basic information of a supply terminal, wherein the power basic information includes: the power capacity in the power capacity sequence corresponds to a time granularity in a first preset time period, and the first power in the first power sequence corresponds to a time granularity in the first preset time period;

A first determination unit configured to determine an average value of the individual power capacities in the power capacity sequence as a power capacity average value;

a second determining unit configured to determine an average value of each first electric quantity in the first electric quantity sequence as an electric quantity average value;

a third determining unit configured to determine an average value of each first electric quantity larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities;

an adding unit configured to add the power capacity average value and the power consumption upper average value to power initial information, wherein the power initial information is initially empty;

a data cleansing unit configured to perform data cleansing processing on the power initial information to generate power information;

a first input unit configured to input the power information into a pre-trained target power information generation model to obtain target power information;

a second input unit configured to input the target power information into a pre-trained power result information generation model to obtain power result information;

and the power-off unit is configured to perform power-off processing on the supply end in response to determining that the power result information meets a preset abnormal condition.

6. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.

7. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-4.