CN115112962A - A non-invasive load identification method, system, storage medium and device - Google Patents

Abstract

The present invention provides a non-intrusive load identification method, system, storage medium and device. The method includes: acquiring first power operation data of an object to be identified in a target monitoring area during an action; Suppose the current standard load and its corresponding voltage compensation method and standard load characteristics are extracted from the load characteristic fingerprint database; the first power operation data is compensated according to the voltage compensation method; the current load characteristics and standard load are extracted from the compensated power operation data. The features are compared to determine the load identification result of the object to be identified. By implementing the present invention, the extraction accuracy and load identification accuracy of the non-intrusive load identification electric appliance feature are improved.

Description

A non-invasive load identification method, system, storage medium and device

technical field

The invention relates to the technical field of intelligent power consumption, and in particular to a non-invasive load identification method, system, storage medium and device.

Background technique

The Non-Intrusive Load Monitoring (NILM) system monitors each or each type of indoor electrical equipment by disassembling the working conditions and power consumption of each electrical equipment in the user, collecting and analyzing the total current and terminal voltage of the user's electricity consumption. The power consumption and working status of electrical appliances, so as to grasp the power consumption status and electricity consumption rules of each or each type of electrical appliances, so that users can clearly understand the structure of electricity consumption, and rationally arrange production and life; for consumers, It can track electricity costs in real time and understand the flow of electricity in various households.

However, the current non-intrusive load monitoring system is only suitable for user power load monitoring at a stable voltage level. According to practical experience, the background voltage of an electrical appliance is different each time it is turned on and off, which causes the same electrical appliance to sometimes have a large deviation of the characteristic quantity under different voltage levels, which is easy to cause load identification. errors, thereby reducing the accuracy of load identification in intrusive load monitoring systems. Therefore, how to ensure the accuracy of non-intrusive load identification under different voltage levels has become an urgent problem to be solved.

SUMMARY OF THE INVENTION

Therefore, the technical problem to be solved by the present invention is to overcome the defect of low load identification accuracy of non-intrusive load monitoring under different voltage levels in the prior art, thereby providing a non-intrusive load identification method, system and storage medium and equipment.

To achieve the above object, the present invention provides the following technical solutions:

In a first aspect, an embodiment of the present invention provides a non-intrusive load identification method, including: acquiring first power operation data of an object to be identified in a target monitoring area during an action; Extract the current standard load and its corresponding voltage compensation method and standard load characteristics from the feature fingerprint database; compensate the first power operation data according to the voltage compensation method; extract the current load characteristics and the power operation data from the compensated power operation data. The standard load characteristics are compared to determine the load identification result of the object to be identified.

Optionally, before acquiring the first power operation data of the object to be identified in the target monitoring area during the action, the non-intrusive load identification method further includes: monitoring the second power operation data of the target monitoring area, the The second electric power operation data includes at least: active power; according to the variation of the active power, determine whether the object to be identified has acted; when the object to be identified has acted, obtain the first movement period of the object to be identified in the target monitoring area during the action Power operation data.

Optionally, when the voltage compensation mode is no compensation, the compensating the first power operation data according to the voltage compensation mode includes: not compensating the first power operation data.

Optionally, the first power operation data includes at least: the current voltage value after the object to be identified has acted; when the voltage compensation mode is compensated, the Compensating the power operation data includes: acquiring a standard voltage corresponding to the current standard load; determining a compensation parameter according to the standard voltage and the current voltage; and compensating the first power operation data according to the compensation parameter.

Optionally, the first power operation data further includes: the change of active power and the change of reactive power before and after the action of the object to be identified; the compensation of the first power operation data according to the compensation parameter , which includes: respectively compensating the active power variation and the reactive power variation according to the compensation parameter, to obtain the compensated active power variation and the reactive power variation.

Optionally, the extracting the current load feature from the compensated power operation data and comparing it with the standard load feature to determine the load identification result of the object to be identified includes: judging whether the current load feature belongs to the Within the preset range of the standard load characteristics; when the current conforming feature belongs to the preset range of the standard load characteristics, it is determined that the object to be identified is the current standard load.

Optionally, the non-invasive load identification method further includes: when the current conforming feature does not belong to the preset range of the standard load feature, re-extracting the current standard load and its corresponding feature from the preset load feature fingerprint library. voltage compensation method and standard load characteristics.

In a second aspect, an embodiment of the present invention provides a non-intrusive load identification system, including: an acquisition module for acquiring first power operation data of an object to be identified in a target monitoring area during an action; an extraction module for The current standard load and its corresponding voltage compensation method and standard load characteristics are extracted from the preset load characteristic fingerprint database corresponding to the target monitoring area; the processing module is used for performing the first electric power operation data according to the voltage compensation method. Compensation; a matching module, configured to extract the current load characteristic from the compensated electric power operation data and compare it with the standard load characteristic, so as to determine the load identification result of the object to be identified.

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the first aspect of the embodiment of the present invention. Non-intrusive load identification method.

In a fourth aspect, an embodiment of the present invention provides a computer device, including: a memory and a processor, the memory and the processor are connected in communication with each other, the memory stores computer instructions, and the processor executes the The computer instructions are executed, so as to execute the non-invasive load identification method described in the first aspect of the embodiments of the present invention.

The technical scheme of the present invention has the following advantages:

The non-intrusive load identification method provided by the present invention includes: obtaining the first power operation data of the object to be identified in the target monitoring area during the action period; extracting the current standard load and Its corresponding voltage compensation method and standard load characteristics; compensate the first power operation data according to the voltage compensation method; extract the current load characteristics from the compensated power operation data and compare the standard load characteristics to determine the load identification of the object to be identified result. The voltage compensation method is determined according to the current standard load in the preset load characteristic fingerprint database, and then the first power operation data is compensated according to the voltage compensation method to obtain the current load characteristic at the standard voltage level. By converting the load characteristics under different voltage levels to the load characteristics under the same voltage level, and then comparing the current load characteristics after compensation with the standard load characteristics, the extraction accuracy of the non-intrusive load identification electrical characteristics and the load identification are improved. precision.

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

FIG. 1 is a flowchart of a specific example of a non-invasive load identification method in an embodiment of the present invention;

FIG. 2 is a flowchart of another specific example of the non-invasive load identification method in the embodiment of the present invention;

3 is a flowchart of another specific example of the non-invasive load identification method in the embodiment of the present invention;

4 is a schematic diagram of a model of each electrical load characteristic fingerprint database in an embodiment of the present invention;

Fig. 5 is the model schematic diagram of the load characteristic fingerprint database of electric cooker and microwave oven in the embodiment of the present invention;

Fig. 6 is the schematic diagram of the load characteristic extraction data of electric cooker and induction cooker in the embodiment of the present invention;

7 is a schematic block diagram of a specific example of a non-intrusive load identification system in an embodiment of the present invention;

FIG. 8 is a composition diagram of a specific example of a computer device provided by an embodiment of the present invention.

Detailed ways

The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

An embodiment of the present invention provides a non-invasive load identification method, as shown in FIG. 1 , including the following steps:

Step S10: Acquire the first power operation data of the object to be identified in the target monitoring area during the action period.

电流基波相角序列

电流二次谐波幅值序列

电流二次谐波相角序列

电流三次谐波幅值序列

电流三次谐波相角序列

电流四次谐波幅值序列

电流四次谐波相角序列

电流五次谐波幅值序列

电流五次谐波相角序列

其中t为时间，单位为秒。设置一特征组

In a specific embodiment, the data acquisition equipment installed at the user's electrical upstream entrance conducts a sampling frequency f ₁ and alternating current frequency f ₂ working environment to measure the voltage and current at the home entrance main line. Periodic sampling to form a voltage sampling sequence u ₁ (k) and a current sampling sequence i ₁ (k), where k is the sampling point number, the sampling frequency f ₁ ranges from 0.4kHz to 50kHz, and the alternating current frequency f ₂ The value is 50Hz. Then, according to the collected voltage sampling sequence u ₁ (k) and current sampling sequence i ₁ (k), the characteristic quantities of the object to be identified, that is, the active power per second, the effective value of the reactive power per second, and the fundamental wave current per second, are calculated. Amplitude and phase angle, second current harmonic amplitude and phase angle per second, third current harmonic amplitude and phase angle per second, fourth current harmonic amplitude and phase angle per second, fifth current harmonic per second wave amplitude and phase angle, and sort the above characteristic quantities according to time to form active power sequence P ₁ (t), reactive power sequence Q ₁ (t), and current fundamental wave amplitude sequence

Current fundamental phase angle sequence

Current second harmonic amplitude sequence

Current second harmonic phase angle sequence

Current third harmonic amplitude sequence

Current third harmonic phase angle sequence

Current fourth harmonic amplitude sequence

Current fourth harmonic phase angle sequence

Current fifth harmonic amplitude sequence

Current fifth harmonic phase angle sequence

where t is time in seconds. Set up a feature group

Used to represent the set of feature quantities per second. Then, the event monitoring is realized through the active power sequence P ₁ (t), to determine whether the object to be identified is moving, and to obtain the first power operation data of the object to be identified in the target monitoring area (ie, the user) before and after startup and shutdown. The specific process is as follows,

Step S01: Monitor second power operation data of the target monitoring area, where the second power operation data at least include: active power.

Step S02: According to the variation of the active power, it is determined whether the action of the object to be identified occurs.

Step S03: when the object to be identified moves, acquire first power operation data of the object to be identified in the target monitoring area during the action period.

In the embodiment of the present invention, first calculate the change ΔP ₁ (t) of the active sequence P ₁ (t) at time t, and detect whether ΔP ₁ (t) is greater than the active event start threshold P _start , if it is determined that ΔP ₁ (t)> P _{start ,} record the current time as the event start time t _event-on , record the voltage at the current time as U _start , and set the event flag flag _event =1. After the event starts, check whether the active sequence changes ΔP ₁ (t), ΔP ₁ (t-1), and ΔP ₁ (t-2) at time t, t-1, and t-2 are all smaller than the end of the active event. Threshold P _end, that is, it is determined that ΔP ₁ (t)<P _end and ΔP ₁ (t-1)<P _end and ΔP ₁ (t-2)<P _end , then record the current time as the event end time t _event-off , Record the actual value Ω(t _event-off ) of the feature group at this time, record the current voltage as U _end, set the event flag flag _event = 0; set the current voltage value after the action of the object to be identified as U _change , if the event is on If U _start ≥ U _end , then U _change = U _end ; in the same way, if U _start <U _end , then U _change = U _start . Further, after it is determined that the object to be identified moves, the first power operation data of the object to be identified in the target monitoring area during the action period is obtained, and the load identification result of the object to be identified is determined. In the embodiment of the present invention, the first power operation data includes the current voltage value U _change after the object to be identified moves, the change in active power ΔP ₂ before and after the object to be identified moves, and the change in reactive power before and after the object to be identified moves ΔQ ₂ .

In the embodiment of the present invention, the calculation formula of the active power variation before and after the action of the object to be identified is: ΔP ₂ =P(t _event-off )-P(t _event-on ), where P(t _event-off ) represents the active power value after the object to be identified acts, and P(t _event-on ) represents the active power value before the object to be identified acts.

Further, the calculation formula of the reactive power variation before and after the action of the object to be identified is: ΔQ ₂ =Q(t _event-off )-Q(t _event-on ), wherein Q(t _event-off ) represents the to-be-identified object The reactive power value after the action of the object, Q(t _event-on ) represents the reactive power value before the action of the object to be identified.

Step S11: Extract the current standard load and its corresponding voltage compensation mode and standard load characteristic from the preset load characteristic fingerprint database corresponding to the target monitoring area.

In a specific embodiment, all the electrical appliances in the user under the standard voltage are regarded as the current standard load, and the standard load characteristics of all the electrical appliances in the user under the standard voltage are obtained in advance, and the preset load characteristic fingerprint database is established according to the above standard load characteristics. . At the same time, the voltage compensation method can be determined according to the working principle of the current standard load. For example, when the current standard load is a resistance load, a motor load or a converter load without voltage feedback control, the voltage of the current standard load can be determined. The compensation mode is no compensation; when the current standard load is a converter load with voltage feedback control, the voltage compensation mode of the current standard load is with compensation.

Step S12: Compensate the first power operation data according to the voltage compensation method.

In a specific embodiment, when the voltage compensation mode is no compensation, the first power operation data is not compensated; when the voltage compensation mode is with compensation, the first power operation data is compensated according to the voltage compensation mode, as shown in FIG. 2 . shown, including the following steps:

Step S121: Obtain the standard voltage corresponding to the current standard load.

Step S122: Determine compensation parameters according to the standard voltage and the current voltage.

Step S123: Compensate the first power operation data according to the compensation parameter.

其中，U_standard表示标准电压，U_change表示当前电压。在本发明实施例中，标准电压可以为220V，也可以为110V，具体标准电压可根据当地的电压标准确定。之后根据补偿参数b分别对待辨识对象动作前后的有功功率变化量ΔP₂、待辨识对象动作前后的无功功率变化量ΔQ₂进行平方补偿，得到补偿后的有功功率变化量ΔP₃、补偿后的无功功率变化量ΔQ₃。In the embodiment of the present invention, after it is determined that the voltage compensation mode is with compensation, the compensation parameters are first calculated according to the standard voltage and the current voltage

Among them, U _standard represents the standard voltage, and U _change represents the current voltage. In this embodiment of the present invention, the standard voltage may be 220V or 110V, and the specific standard voltage may be determined according to local voltage standards. Then, according to the compensation parameter b, the active power change ΔP ₂ before and after the action of the object to be identified and the reactive power change ΔQ ₂ before and after the action of the object to be identified are squarely compensated to obtain the compensated active power change ΔP ₃ , and the compensated active power change ΔP 3 . Reactive power variation ΔQ ₃ .

Specifically, the compensation formula of the active power change ΔP ₂ before and after the action of the object to be identified is:

Further, the compensation formula of the reactive power variation ΔQ ₂ before and after the action of the object to be identified is:

Step S13 : extracting the current load characteristic from the compensated electric power operation data and comparing the standard load characteristic to determine the load identification result of the object to be identified.

In a specific embodiment, the current load characteristics (that is, the amount of change in active power after compensation, the amount of change in reactive power after compensation) are extracted from the compensated power operation data, and after the current load characteristics are extracted, according to the current load characteristics. The comparative relationship between the load characteristics and the standard load characteristics determines the load identification result of the object to be identified. Specifically, the process of determining the load identification result of the object to be identified, as shown in Figure 3, includes the following steps:

Step S131: Determine whether the current load characteristic belongs to the preset range of the standard load characteristic.

Step S132: When the current conforming feature falls within the preset range of the standard load feature, determine that the object to be identified is the current standard load.

Step S133: When the current conforming feature does not belong to the preset range of the standard load feature, re-extract the current standard load and its corresponding voltage compensation mode and standard load feature from the preset load feature fingerprint database.

In the embodiment of the present invention, the existing multivariate Gaussian model is first used to calculate the mean value, covariance and cutoff frequency P _n corresponding to the standard load in the preset load characteristic fingerprint database. Then calculate the probability P _test that the current load feature belongs to the standard load. If P _test ≥P _n , the object to be identified is determined to be the current standard load; if P _test <P _n , it is determined that the object to be identified does not belong to the current standard load, and the Execute step S11, continue to traverse other standard loads in the preset load characteristic fingerprint database, and determine its corresponding voltage compensation method and standard load characteristics according to the re-determined current standard load, and then continue to determine whether the object to be identified belongs to the re-determined current standard load. Standard load, until the load identification result of the object to be identified is determined, stop traversing other standard loads in the preset load characteristic fingerprint database.

The non-intrusive load identification method provided by the present invention includes: obtaining the first power operation data of the object to be identified in the target monitoring area during the action period; extracting the current standard load and Its corresponding voltage compensation method and standard load characteristics; compensate the first power operation data according to the voltage compensation method; extract the current load characteristics from the compensated power operation data and compare the standard load characteristics to determine the load identification of the object to be identified result. The voltage compensation method is determined according to the current standard load in the preset load characteristic fingerprint database, and then the first power operation data is compensated according to the voltage compensation method to obtain the current load characteristic at the standard voltage level. By converting the load characteristics under different voltage levels to the load characteristics under the same voltage level, and then comparing the current load characteristics after compensation with the standard load characteristics, the extraction accuracy of the non-intrusive load identification electrical characteristics and the load identification are improved. precision.

Further, in order to verify the effectiveness of a non-invasive load identification method proposed by the present invention. The method is developed and verified by using the Matlab 2019a development platform and m programming language, and the test and verification of this embodiment are completed using a PC equipped with an Intel Xeon-X5650 2.6GHz CPU and 24G memory.

The embodiments of the present invention carry out technical verification around a certain household load operation scenario. The verification background is that there is a rice cooker (with compensation) and a microwave oven (without compensation) in the family.

m≥2为j+2维向量，其中j为电流高次谐波组数，建立均值为μ∈Rⁿ，协方差矩阵为Σ∈Sⁿ，概率密度函数为

的多元高斯模型。The construction method of the load characteristic fingerprint database model for rice cookers and microwave ovens is as follows: For these two kinds of electrical appliances, the field operation data of the electrical appliances are obtained, and the voltage-compensated active power changes ΔP ₃ and reactive power changes ΔQ ₃ before and after the operation of the electrical appliances are to be identified. , the ratio of the amplitude of the current higher harmonics to the amplitude change of the fundamental wave

m≥2 is a j+2-dimensional vector, where j is the number of current high-order harmonic groups, the established mean is μ∈R ⁿ , the covariance matrix is Σ∈S ⁿ , and the probability density function is

The multivariate Gaussian model.

n表示第n个电器；in,

n represents the nth electrical appliance;

The schematic diagram of the model of each electrical load characteristic fingerprint library is shown in Figure 4 (represented by the active power and reactive power as the abscissa and ordinate). For the nth cluster (the nth class of electrical appliances), we set a cut-off probability Pn, and the probability of a point in space for this cluster is P. If P>Pn, we think that this point belongs to this cluster, that is, the feature point represents The electrical appliance is electrical appliance n. If P<Pn, we think that this point does not belong to this cluster, that is, the electrical appliance represented by this feature point is not electrical appliance n. Among them, Pn is calculated by the multivariate Gaussian model.

Specifically, the schematic diagram of the model of the load feature fingerprint library containing the rice cooker (for voltage compensation) and the microwave oven is shown in Figure 5 (represented by active power and reactive power as the abscissa and ordinate, and other dimension parameters are omitted). The complete model parameters of the two appliances are shown in the table below.

Table 1 Mean value of each dimension feature of rice cooker

Table 2. Each dimension feature covariance matrix of rice cooker

Table 3 The mean value of each dimension feature of microwave oven

Table 4. Each dimension feature covariance matrix of microwave oven

The schematic diagram of the load feature extraction data of rice cooker and induction cooker with two voltage levels (represented by active power and reactive power as abscissa and ordinate) is shown in Figure 6. As can be seen from Figure 6, for the rice cooker that needs to compensate the voltage change, when the voltage level is U1=221V, the cluster center of the rice cooker is (482.3W, 5.97Var), and when the voltage level is U2=230V, the The cluster center of the rice cooker is (522W, 6.47Var). Once the electrical appliances that need to be compensated for the load characteristic voltage are not compensated, once the operating data at one voltage level is used to create the load characteristic fingerprint database, it will cause extraction at another voltage level. The resulting load features are not in the load feature fingerprint database, which results in missed identification and reduces the accuracy of non-intrusive load identification.

An embodiment of the present invention also provides a non-invasive load identification system, as shown in FIG. 7 , including:

The acquisition module 1 is used for acquiring the first power operation data of the object to be identified in the target monitoring area during the action period. For details, refer to the relevant description of step S10 in the above-mentioned embodiment, which is not repeated here.

The extraction module 2 is used for extracting the current standard load and its corresponding voltage compensation mode and standard load characteristic from the preset load characteristic fingerprint database corresponding to the target monitoring area. For details, refer to the relevant description of step S20 in the above embodiment, and details are not repeated here.

The processing module 3 is configured to compensate the first power operation data according to the voltage compensation method. For details, refer to the relevant description of step S30 in the above-mentioned embodiment, which is not repeated here.

The matching module 4 is used for extracting the current load characteristic from the compensated electric power operation data and comparing it with the standard load characteristic, so as to determine the load identification result of the object to be identified. For details, please refer to the relevant description of step S40 in the foregoing embodiment, which will not be repeated here.

The non-intrusive load identification system provided by the present invention determines the voltage compensation method according to the current standard load in the preset load characteristic fingerprint database, and then compensates the first power operation data according to the voltage compensation method to obtain the current load characteristics under the standard voltage level. . By converting the load characteristics under different voltage levels to the load characteristics under the same voltage level, and then comparing the current load characteristics after compensation with the standard load characteristics, the extraction accuracy of the non-intrusive load identification electrical characteristics and the load identification are improved. precision.

An embodiment of the present invention also provides a computer device. As shown in FIG. 8, the device may include a processor 61 and a memory 62, where the processor 61 and the memory 62 may be connected through a bus or in other ways. In FIG. 8, the connection through the bus is example.

The processor 61 may be a central processing unit (Central Processing Unit, CPU). The processor 61 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or Other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above types of chips.

As a non-transitory computer-readable storage medium, the memory 62 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as corresponding program instructions/modules in the embodiments of the present invention. The processor 61 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 62, ie, implements the non-intrusive load identification method in the above method embodiments.

The memory 62 may include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required by at least one function; the storage data area may store data created by the processor 61 and the like. Additionally, memory 62 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 62 may optionally include memory located remotely from processor 61, which may be connected to processor 61 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, intranets, mobile communication networks, and combinations thereof.

One or more modules are stored in the memory 62, and when executed by the processor 61, execute the electric energy meter data interaction method provided by the embodiment of the present invention or the non-intrusive load identification method provided by the embodiment of the present invention.

The specific details of the above computer equipment can be understood by referring to the corresponding descriptions and effects in the embodiments shown in FIGS. 1-6 , and details are not repeated here.

Those skilled in the art can understand that the realization of all or part of the processes in the methods of the above embodiments is a program that can be completed by instructing relevant hardware through a computer program and can be stored in a computer-readable storage medium. When the program is executed , which may include the processes of the above-mentioned method embodiments. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive) , abbreviation: HDD) or solid-state hard disk (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memories.

Obviously, the above-mentioned embodiments are only examples for clear description, and are not intended to limit the implementation manner. For those of ordinary skill in the art, changes or modifications in other different forms can also be made on the basis of the above description. There is no need and cannot be exhaustive of all implementations here. However, the obvious changes or changes derived from this are still within the protection scope of the present invention.

Claims (10)

1. A method for non-intrusive load identification, comprising:

acquiring first power operation data of an object to be identified in a target monitoring area during action;

extracting a current standard load and a voltage compensation mode and standard load characteristics corresponding to the current standard load from a preset load characteristic fingerprint database corresponding to the target monitoring area;

compensating the first electric power operation data according to the voltage compensation mode;

and extracting current load characteristics from the compensated electric power operation data, comparing the current load characteristics with the standard load characteristics, and determining a load identification result of the object to be identified.

2. The non-invasive load identification method according to claim 1, wherein before obtaining the first power operation data of the object to be identified in the target monitoring area during the action, the non-invasive load identification method further comprises:

monitoring second electrical operating data of the target monitoring area, the second electrical operating data including at least: active power;

determining whether an object to be identified acts or not according to the variable quantity of the active power;

when the object to be identified acts, first power operation data of the object to be identified in the target monitoring area during the action period are acquired.

3. The method according to claim 1, wherein when the voltage compensation mode is uncompensated, the compensating the first electrical operating data according to the voltage compensation mode comprises: the first electrical operating data is not compensated.

4. The non-intrusive load identification method of claim 1, wherein the first electrical operating data comprises at least: the current voltage value of the object to be identified after the action;

when the voltage compensation mode is compensated, compensating the first electric power operation data according to the voltage compensation mode, including:

acquiring a standard voltage corresponding to the current standard load;

determining a compensation parameter according to the standard voltage and the current voltage;

compensating the first electrical operating data according to the compensation parameter.

5. The non-intrusive load identification method of claim 4, wherein the first electrical operating data further comprises: the active power variation and the reactive power variation before and after the action of the object to be identified;

the compensating the first electrical operating data according to the compensation parameter includes:

and respectively compensating the active power variation and the reactive power variation according to the compensation parameters to obtain the compensated active power variation and reactive power variation.

6. The non-intrusive load identification method as claimed in claim 5, wherein the extracting current load characteristics from the compensated power operation data and comparing the current load characteristics with the standard load characteristics to determine the load identification result of the object to be identified comprises:

judging whether the current load characteristic belongs to a preset range of the standard load characteristic or not;

and when the current conforming characteristic belongs to the preset range of the standard load characteristic, judging that the object to be identified is the current standard load.

7. The method of non-intrusive load identification as defined in claim 6, further comprising:

and when the current conforming characteristic does not belong to the preset range of the standard load characteristic, re-extracting the current standard load and the corresponding voltage compensation mode and standard load characteristic thereof from the preset load characteristic fingerprint database.

8. A non-intrusive load identification system, comprising:

the device comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring first power operation data of an object to be identified in a target monitoring area during action;

the extraction module is used for extracting the current standard load and a voltage compensation mode and standard load characteristics corresponding to the current standard load from a preset load characteristic fingerprint database corresponding to the target monitoring area;

the processing module is used for compensating the first electric power operation data according to the voltage compensation mode;

and the matching module is used for extracting current load characteristics from the compensated electric power operation data and comparing the current load characteristics with the standard load characteristics to determine a load identification result of the object to be identified.

9. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the method of non-intrusive load identification as defined in any of claims 1 to 7.

10. A computer device, comprising: a memory and a processor, the memory and the processor being communicatively coupled to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method of non-invasive load identification according to any of claims 1-7.

Images