CN120256244B - Distributed energy data monitoring method, device, equipment and medium based on cloud platform - Google Patents
Distributed energy data monitoring method, device, equipment and medium based on cloud platformInfo
- Publication number
- CN120256244B CN120256244B CN202510343926.9A CN202510343926A CN120256244B CN 120256244 B CN120256244 B CN 120256244B CN 202510343926 A CN202510343926 A CN 202510343926A CN 120256244 B CN120256244 B CN 120256244B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- state evaluation
- evaluation value
- energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a cloud platform-based distributed energy data monitoring method, a device, equipment and a medium, which belong to the technical field of cloud computing, and comprise the steps of collecting monitoring operation data of energy node monitoring equipment in real time to obtain an operation data set; the method comprises the steps of obtaining an operation state evaluation value of monitoring equipment according to an operation data set, judging the magnitude of the operation state evaluation value and a preset threshold value, selecting a real-time monitoring mode, a mixed monitoring mode and a predictive monitoring mode according to a judgment result, and outputting monitoring data by utilizing the selected modes. The invention realizes real-time, accurate and efficient monitoring of the running state of the energy equipment through the optimization of the multi-mode monitoring and prediction model.
Description
Technical Field
The invention relates to the technical field of cloud computing, in particular to a distributed energy data monitoring method, device, equipment and medium based on a cloud platform.
Background
With the increasing demand for energy and the increasing prominence of environmental problems, distributed energy systems have been rapidly developed. The distributed energy system has the characteristics of dispersibility, diversity, dynamic property and the like, and has higher requirements on the data monitoring technology.
The monitoring technology of the distributed energy system mainly depends on the traditional real-time data acquisition and analysis method, a large amount of data are acquired in real time, resource waste and bandwidth pressure exist, redundancy exists in real-time monitoring for equipment with stable running states, the response speed of real-time monitoring is possibly insufficient when the monitoring equipment is abnormal, problems cannot be found and processed in time, potential risks are accumulated, and finally, the traditional monitoring system lacks an intelligent operation and maintenance strategy, and is difficult to flexibly adjust a monitoring mode according to the running states of the equipment, so that the monitoring efficiency is low.
Disclosure of Invention
In order to solve the problems, the invention provides a distributed energy data monitoring method, a device, equipment and a medium based on a cloud platform, and the real-time, accurate and efficient monitoring of the running state of energy equipment is realized through the optimization of a multi-mode monitoring and prediction model.
The above object can be achieved by the following scheme:
The distributed energy data monitoring method based on the cloud platform comprises the steps of collecting monitoring operation data of energy node monitoring equipment in real time to obtain an operation data set, calculating an operation state evaluation value of the monitoring equipment according to the operation data set, judging the size of the operation state evaluation value and a preset threshold value, selecting a real-time monitoring mode, a hybrid monitoring mode and a predictive monitoring mode according to a judging result, and outputting the monitoring data by utilizing the selected modes.
Further, the calculation of the operation state evaluation value of the monitoring equipment according to the operation data set comprises the steps of obtaining historical monitoring operation data and historical operation state evaluation values of the monitoring equipment from a preset database to obtain a historical data set, establishing an operation state evaluation function for representing the operation state evaluation values, optimizing parameters of the operation state evaluation function by using the historical data set to obtain a final operation state evaluation function, inputting the operation data set into the final operation state evaluation function to obtain an operation state evaluation value, and obtaining an operation state evaluation value S for the operation state evaluation value:
Wherein a i is a weight coefficient of the ith monitoring operation data in the operation data set, B i is the ith monitoring operation data in the operation data set, C is an error coefficient, and n is an integer greater than 0.
Further, the judging of the operation state evaluation value and the preset threshold value comprises judging whether the operation state evaluation value is larger than a preset first threshold value, selecting a real-time monitoring mode to monitor energy data and output monitoring data if the operation state evaluation value is larger than the first threshold value, judging whether the operation state evaluation value is larger than a preset second threshold value if the operation state evaluation value is smaller than or equal to the first threshold value, selecting a hybrid monitoring mode to monitor energy data and output monitoring data if the operation state evaluation value is larger than the second threshold value, and selecting a predictive monitoring mode to monitor energy data and output monitoring data if the operation state evaluation value is smaller than or equal to the second threshold value.
Further, the selecting of the real-time monitoring mode for monitoring the energy data and outputting the monitoring data comprises the steps of collecting the data of the energy nodes in real time, extracting the characteristics of the collected data to obtain the monitoring data, and outputting the monitoring data.
The method comprises the steps of selecting a predictive monitoring mode, monitoring energy data and outputting monitoring data, collecting historical monitoring data of energy nodes to obtain a training data set, taking monitoring data at the previous moment as input and monitoring data at the current moment as output, constructing and training a neural network model by using the training data set to obtain a monitoring data predictive model, obtaining the monitoring data at the previous moment and inputting the monitoring data predictive model to obtain current monitoring predictive data, and outputting the current monitoring predictive data.
The hybrid monitoring mode is used for monitoring energy data and outputting monitoring data, wherein the monitoring mode comprises the steps of collecting data of energy nodes in real time and judging whether the collected data are abnormal, extracting characteristics of the collected data to obtain current monitoring data and outputting the current monitoring data if the collected data are not abnormal, and inputting the monitoring data at the previous moment into the monitoring data prediction model to obtain current monitoring prediction data and outputting the current monitoring prediction data if the collected data are abnormal.
The method further comprises the steps of collecting data of the energy nodes in real time and extracting features to obtain actual monitoring data, outputting the actual monitoring data and sending early warning information when errors of the actual monitoring data and current monitoring prediction data are larger than preset conditions, checking monitoring equipment according to the early warning information and feeding back checking results, if the checking results are abnormal, optimizing a monitoring data prediction model is not needed, and if the checking results are abnormal, optimizing the monitoring data prediction model according to the actual monitoring data.
Based on the same inventive concept, the invention also provides a distributed energy data monitoring device based on the cloud platform, which comprises a data acquisition module, an evaluation value calculation module, an evaluation value analysis module and a monitoring mode selection module, wherein the data acquisition module is used for acquiring monitoring operation data of energy node monitoring equipment in real time to obtain an operation data set, the evaluation value calculation module is used for calculating an operation state evaluation value of the monitoring equipment according to the operation data set, the evaluation value analysis module is used for judging the operation state evaluation value and the size of a preset threshold value, and the monitoring mode selection module is used for selecting a real-time monitoring mode, a mixed monitoring mode and a predicted monitoring mode according to a judgment result and outputting the monitoring data by utilizing the selected mode.
Based on the same inventive concept, the present invention also provides a computer storage medium storing one or more programs, which when executed, implement any of the methods described above.
Based on the same inventive concept, the invention also provides a device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus, and the processor is used for executing the program stored in the computer readable storage medium.
Compared with the prior art, the invention has the following advantages:
1. the intelligent monitoring mode selection mechanism can be adjusted according to the actual running state of the monitoring equipment, so that the monitoring efficiency is improved, and the problems of resource waste and monitoring blind areas are avoided;
2. When the operation state of the monitoring equipment is common, the invention realizes the efficient and accurate monitoring of the energy data by combining the advantages of the real-time data acquisition and the prediction model, effectively avoids the monitoring interruption or the error data output caused by the data abnormality, and improves the stability and the reliability of the monitoring system;
3. According to the invention, when the running state of the monitoring equipment is poor, the dependence on real-time monitoring can be reduced by predicting the current monitoring data, so that the response speed of the system when the running state of the monitoring equipment is poor is improved, the rapid taking of measures when the equipment fails is ensured, the influence of the failure on the system is reduced, and the stability and reliability of the system are improved;
4. The invention also comprises a real-time data verification and model optimization flow, and errors are found and corrected in time by comparing actual monitoring data with predicted data, so that the accuracy of the data is ensured;
5. the technical scheme of the invention is based on the cloud platform and has the advantages of easy deployment and maintenance. The operation and maintenance cost of the system is reduced, and the expandability and flexibility of the system are improved, so that the system can be better suitable for distributed energy systems with different scales and requirements.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a distributed energy data monitoring method based on a cloud platform according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating an implementation of a distributed energy data monitoring method based on a cloud platform according to an embodiment of the present invention.
FIG. 3 is a flow chart illustrating the execution of the real-time monitoring mode according to an embodiment of the present invention.
FIG. 4 is a flow chart of the execution of the predictive monitoring mode in accordance with an embodiment of the invention.
Fig. 5 is a flowchart of the execution of the hybrid monitoring mode according to the embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a distributed energy data monitoring device based on a cloud platform according to an embodiment of the present invention.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the invention provides a distributed energy data monitoring method based on a cloud platform, and real-time, accurate and efficient monitoring of an operating state of energy equipment is realized through multi-mode monitoring and optimization of a prediction model.
The method of the embodiment specifically comprises the following steps:
monitoring operation data of the energy node monitoring equipment are collected in real time, and an operation data set is obtained;
In particular, operation data are obtained in real time from monitoring devices of various energy nodes (such as solar panels, wind turbines, energy storage devices and the like) of the distributed energy system, and the data may include various parameters such as current, voltage, power, temperature, humidity and the like, depending on the type of the monitoring devices and the type of the monitored energy.
According to the operation data set, calculating to obtain an operation state evaluation value of the monitoring equipment;
In particular, the operating state of the monitoring device is evaluated using an operating data set, which typically requires an evaluation function or model that can calculate an operating state evaluation value for the device based on real-time operating data, which can reflect the health, performance level, or potential risk of failure of the device.
Judging the sizes of the running state evaluation value and a preset threshold value;
and selecting a real-time monitoring mode, a hybrid monitoring mode and a predictive monitoring mode according to the judging result, and outputting monitoring data by using the selected modes.
The method comprises the steps of selecting a proper monitoring mode to output monitoring data according to a comparison result of an operation state evaluation value and a preset threshold value, wherein the real-time monitoring mode is used for collecting and outputting the data in real time, the characteristics of real-time monitoring and predictive monitoring are combined by the mixed monitoring mode, the predictive monitoring mode is mainly used for outputting the data depending on a predictive model, and the operation state of energy equipment can be monitored accurately and efficiently in real time, so that the stability and reliability of a system are improved.
Further, according to the operation data set, calculating an operation state evaluation value of the monitoring device includes:
Acquiring historical monitoring operation data and a historical operation state evaluation value of monitoring equipment from a preset database to obtain a historical data set;
The method comprises the steps of extracting historical monitoring operation data of the same or similar equipment as the current monitoring equipment and a corresponding historical operation state evaluation value thereof from a preset database, wherein the data are used for training or optimizing an operation state evaluation function so as to improve accuracy and reliability of the operation state evaluation function, and a historical data set contains data in various operation states so as to comprehensively reflect performance characteristics of the equipment.
Establishing an operation state evaluation function for representing the operation state evaluation value;
Specifically, a function capable of representing the running state evaluation value is established according to the characteristics and the monitoring requirements of the monitoring equipment, the function can be a mathematical formula, a machine learning model, a deep learning network or the like, the specific form depends on the characteristics of data and the complexity of problems, and the purpose of the function is to calculate the running state evaluation value of the equipment according to real-time running data.
Optimizing parameters of the running state evaluation function by using the historical data set to obtain a final running state evaluation function;
specifically, for the running state evaluation function based on multiple linear regression, an optimization algorithm such as a gradient descent method or a least square method can be used for adjusting the weight coefficients, an optimal set of weight coefficients can be found through iterative calculation, so that the error between the predicted health index and the actual value is minimum, and the set of weight coefficients is used for the final running state evaluation function.
Inputting the operation data set into a final operation state evaluation function to obtain an operation state evaluation value, wherein the operation state evaluation value S comprises:
Wherein a i is a weight coefficient of the ith monitoring operation data in the operation data set, B i is the ith monitoring operation data in the operation data set, C is an error coefficient, and n is an integer greater than 0.
By way of example, it is assumed that a final operating state evaluation function has been obtained and a set of monitored operating data (which may be, for example, a wind speed of 12m/s, a power output of 2MW and a temperature of 20 ℃) has been acquired in real time, these data are input into the operating state evaluation function and calculated to obtain an operating state evaluation value of the device. According to the running state evaluation value, whether the running state of the equipment is good can be judged, and a proper monitoring mode is selected to output monitoring data.
Further, as shown in fig. 2, determining the magnitude of the running state evaluation value and the preset threshold includes:
Judging whether the running state evaluation value is larger than a preset first threshold value or not;
If the running state evaluation value is greater than the first threshold value, selecting a real-time monitoring mode, monitoring energy data and outputting monitoring data;
If the running state evaluation value is smaller than or equal to the first threshold value, judging whether the running state evaluation value is larger than a preset second threshold value or not;
If the running state evaluation value is greater than the second threshold value, selecting a hybrid monitoring mode, monitoring energy data and outputting monitoring data;
And if the running state evaluation value is smaller than or equal to the second threshold value, selecting a prediction monitoring mode, monitoring the energy data and outputting monitoring data.
The monitoring method comprises the steps of providing a monitoring device, calculating an operation state evaluation value of the monitoring device through an operation state evaluation function to obtain the operation state evaluation value of the monitoring device to be 80, providing a first threshold value of 70 and a second threshold value of 40, selecting a real-time monitoring mode to monitor energy data and output monitoring data because the operation state evaluation value 80 is larger than the first threshold value 70, and flexibly adjusting a monitoring strategy according to the actual operation state of the device by the aid of the judging process and the monitoring mode selection mechanism to realize efficient and accurate monitoring.
Further, as shown in fig. 3, selecting the real-time monitoring mode, performing energy data monitoring and outputting monitoring data includes:
Collecting data of energy nodes in real time;
specifically, in the real-time monitoring mode, data is continuously and uninterruptedly collected from the energy source node, the collected data may include various parameters such as voltage, current, power, frequency, temperature, humidity and the like, depending on the type of equipment and monitoring requirements, and the collection process is usually realized through equipment such as a sensor, a data collector and the like, and the equipment converts analog signals into digital signals for subsequent processing and analysis.
Extracting characteristics of the collected data to obtain monitoring data;
specifically, feature extraction is one of key steps of data processing, in a real-time monitoring mode, collected original data is processed and analyzed, features which are significant for monitoring are extracted, the feature extraction possibly comprises operations such as data cleaning, denoising, normalization, transformation and the like, statistics calculation, trend analysis, anomaly detection and the like, and the extracted features are used as monitoring data for subsequent judgment, decision making and output.
And outputting the monitoring data.
Specifically, outputting monitoring data is one of the final purposes of the monitoring system, in a real-time monitoring mode, the extracted monitoring data is visually presented to a user or transmitted to other systems through an interface, and the output data may include information such as a real-time curve, a report, an alarm and the like, so that the user can know the running state and the performance of the equipment in time.
Further, as shown in fig. 4, selecting the predictive monitoring mode, performing energy data monitoring and outputting monitoring data further includes:
collecting historical monitoring data of energy nodes to obtain a training data set;
Taking the monitoring data at the previous moment as input, taking the monitoring data at the current moment as output, and constructing and training a neural network model by utilizing a training data set to obtain a monitoring data prediction model;
Specifically, in a predictive monitoring mode, historical monitoring data of an energy node is required to be collected firstly and used as a training data set for training a neural network model, the historical monitoring data comprises data in a plurality of time periods so that the model can learn the change rule and trend of the data, the data collection process is usually realized through a data collector, a database and the like, the accuracy and the integrity of the data are ensured, after the training data set is collected, the neural network model is required to be constructed and trained by utilizing the data, the input of the model is monitoring data at the previous moment, the output of the model is monitoring data at the current moment, the training process usually comprises the steps of data preprocessing, model construction, parameter optimization and the like, the aim of accurately predicting the future monitoring data by the model, and the common neural network model comprises a feedforward neural network, a convolutional neural network, a cyclic neural network and the like, and the specific selection depends on the characteristics and the prediction requirements of the data.
The method comprises the steps of providing a photovoltaic power generation system, collecting historical monitoring data such as power generation capacity, illumination intensity and temperature of the past year, extracting the historical monitoring data from a data acquisition system of the photovoltaic power station, storing the historical monitoring data into a database to serve as a training data set, selecting a feedforward neural network as a prediction model for the photovoltaic power generation system, enabling the model to input monitoring data such as power generation capacity, illumination intensity and temperature of the previous moment and output power generation capacity predicted values of the current moment, training the model through the training data set, and adjusting parameters such as weight and bias of the model to enable the model to accurately predict future power generation capacity.
Acquiring the previous monitoring data and inputting the monitoring data prediction model to obtain the current monitoring prediction data;
And outputting the current monitoring prediction data.
Specifically, after a monitoring data prediction model is trained, the monitoring data at the previous moment is required to be acquired and input into the model for prediction, the model calculates current monitoring prediction data according to the input data, after the current monitoring prediction data is obtained, the current monitoring prediction data is required to be output into a user interface or other systems so that a user can know the running state and performance of the equipment in time, and the output data can comprise information such as a predicted value, a predicted interval, a predicted confidence coefficient and the like so that the user can make decisions and judgment.
Further, as shown in fig. 5, in the hybrid monitoring mode, performing energy data monitoring and outputting monitoring data includes:
collecting data of the energy nodes in real time, and judging whether the collected data are abnormal or not;
specifically, in the hybrid monitoring mode, data of the energy nodes are collected in real time, wherein the data may include key parameters such as voltage, current, power and temperature, the data are analyzed immediately after being collected to judge whether the data are in a normal range, namely whether abnormality exists, and the abnormality judgment may be based on a preset threshold value, statistical rules of historical data or a machine learning algorithm.
If the collected data is not abnormal, extracting the characteristics of the collected data to obtain current monitoring data and outputting the current monitoring data;
Specifically, if the data collected in real time are not abnormal, the data are subjected to feature extraction, such as calculation of average value, maximum value, minimum value, fluctuation rate and the like, so as to obtain current monitoring data, and the extracted monitoring data are output to a user interface or other systems, so that a user can know the running state of the equipment in time.
If the collected data is abnormal, the monitoring data at the previous moment is input into a monitoring data prediction model, the current monitoring prediction data is obtained and output.
Specifically, if the data collected in real time are abnormal, the abnormal data are not directly output, but are predicted by using a previously trained monitoring data prediction model, the monitoring data at the previous moment are input into the prediction model, the model predicts the current monitoring data according to historical data and learned rules, and the predicted monitoring data are output into a user interface or other systems to replace the abnormal real-time data, so that the monitoring continuity and accuracy are ensured.
The method comprises the steps of providing a wind power generation system, acquiring data such as wind speed, rotor rotating speed and generator temperature in real time, judging that the data are abnormal if the wind speed suddenly drops to a value far lower than a normal range or the generator temperature suddenly rises, calculating average value and fluctuation rate of the data as current monitoring data output if the data such as the wind speed, rotor rotating speed and generator temperature which are acquired in real time are all in the normal range for the wind power generation system, inputting the data such as the wind speed, rotor rotating speed and generator temperature at the previous moment into a prediction model if the data acquired in real time suddenly drops, predicting the current wind speed value according to the historical data and learned wind speed change rule by the model, outputting the current wind speed value as monitoring data, and combining the advantages of real-time monitoring and predictive monitoring by acquiring the data in real time and judging abnormality of the data, so that the current state of the device can be known in time, accurate predictive data can be provided when the data are abnormal, and the continuity and accuracy of monitoring can be ensured.
Further, as shown in fig. 4, the method further includes:
collecting data of energy nodes in real time and extracting features to obtain actual monitoring data;
Specifically, data of the energy nodes are continuously collected in real time, the data may include key parameters such as electric quantity, voltage, current, temperature and pressure, and the collected data are subjected to feature extraction processing, such as average value calculation, peak value calculation, fluctuation rate calculation and the like, so that actual monitoring data are obtained.
When the error between the actual monitoring data and the current monitoring prediction data is larger than a preset condition, outputting the actual monitoring data and sending early warning information;
Specifically, the actual monitoring data is compared with the prediction data output by the monitoring data prediction model, if the error exceeds a preset threshold or condition, the prediction model is considered to be possibly inaccurate, and then the actual monitoring data is output and early warning information is sent to operation and maintenance personnel.
Checking the monitoring equipment according to the early warning information and feeding back a checking result;
specifically, after receiving the early warning information, the operation and maintenance personnel can check the related monitoring equipment to determine whether the abnormality exists, and the check result can be fed back to the system for subsequent judgment and decision.
If the checking result is abnormal, the monitoring data prediction model is not required to be optimized;
Specifically, if the inspection result shows that the monitoring device itself is abnormal, the error of the prediction model may be caused by the device fault, not the problem of the model itself, in which case, the monitoring data prediction model is not required to be optimized, but the faulty device should be repaired or replaced.
And if the checking result is that the checking result is abnormal, optimizing the monitoring data prediction model according to the actual monitoring data.
Specifically, as shown in fig. 5, if the inspection result shows that the monitoring device works normally, the error of the prediction model may be caused by inaccuracy or outdated model itself, and in this case, the prediction model of the monitoring data may be optimized according to the actual monitoring data, so as to improve the accuracy and reliability of the model.
The method comprises the steps of collecting data such as voltage, current and power factor of a transformer substation in real time in a smart grid system, calculating average value and fluctuation rate of the data to serve as actual monitoring data, outputting the actual voltage value and sending early warning information to prompt operation and maintenance personnel to check voltage monitoring equipment or a prediction model if errors of the actual voltage value and the prediction voltage value exceed +/-5%, sending early warning information to the transformer substation to check the voltage monitoring equipment after the operation and maintenance personnel receive early warning information of voltage abnormality, confirming whether the equipment works normally or not, damaging or failing, feeding back check results (such as equipment is normal, equipment is damaged and the like) to the system, and if the operation and maintenance personnel find that the voltage monitoring equipment is damaged, repairing or replacing the voltage prediction model is not optimized, and training and optimizing the voltage prediction model by using the actual voltage data to improve the prediction accuracy of the model if the operation and maintenance personnel confirm that the voltage monitoring equipment works normally. The method has important application value in a distributed energy data monitoring system.
Based on the same inventive concept, as shown in fig. 6, the invention further provides a distributed energy data monitoring device based on a cloud platform, which comprises:
the data acquisition module is used for acquiring monitoring operation data of the energy node monitoring equipment in real time to obtain an operation data set;
the evaluation value calculation module is used for calculating and obtaining an operation state evaluation value of the monitoring equipment according to the operation data set;
the evaluation value analysis module is used for judging the sizes of the running state evaluation value and a preset threshold value;
And the monitoring mode selection module is used for selecting a real-time monitoring mode, a hybrid monitoring mode and a predictive monitoring mode according to the judging result and outputting monitoring data by utilizing the selected modes.
Based on the above disclosure, the invention correspondingly provides an electronic device. As shown in fig. 7, the electronic device according to the embodiment of the present invention includes at least one processor and at least one storage medium electrically connected to the processor, where the storage medium stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method as described above.
Based on the same inventive concept, the present invention also provides a storage medium storing instructions executable by at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as above.
The electrical connection between the above units does not necessarily mean a direct connection or an indirect connection of lines, and the present invention may be applied to an embodiment of the present invention as long as the object of the present invention is achieved. The above are merely exemplary embodiments of the present invention, and the scope of the present invention should not be limited thereto.
That is, equivalent changes and modifications are contemplated by the teachings of the present application, which fall within the scope of the present application. Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.
Claims (7)
1. The distributed energy data monitoring method based on the cloud platform is characterized by comprising the steps of collecting monitoring operation data of energy node monitoring equipment in real time to obtain an operation data set;
According to the operation data set, calculating to obtain an operation state evaluation value of the monitoring equipment;
judging the sizes of the running state evaluation value and a preset threshold value;
Selecting a real-time monitoring mode, a hybrid monitoring mode and a predictive monitoring mode according to the judging result, and outputting monitoring data by using the selected modes;
The step of judging the magnitude of the running state evaluation value and a preset threshold value comprises judging whether the running state evaluation value is larger than a preset first threshold value or not;
if the running state evaluation value is larger than the first threshold value, selecting a real-time monitoring mode, monitoring energy data and outputting monitoring data;
if the running state evaluation value is smaller than or equal to the first threshold value, judging whether the running state evaluation value is larger than a preset second threshold value or not;
If the running state evaluation value is larger than the second threshold value, a hybrid monitoring mode is selected, energy data monitoring is conducted, and monitoring data are output;
if the running state evaluation value is smaller than or equal to the second threshold value, selecting a prediction monitoring mode, monitoring energy data and outputting monitoring data;
the selecting the prediction monitoring mode, monitoring the energy data and outputting the monitoring data further comprises the steps of collecting the history monitoring data of the energy nodes to obtain a training data set;
Taking monitoring data at the previous moment as input, taking monitoring data at the current moment as output, and constructing and training a neural network model by utilizing the training data set to obtain a monitoring data prediction model;
Acquiring the previous monitoring data and inputting the monitoring data prediction model to obtain the current monitoring prediction data;
Outputting current monitoring prediction data;
The hybrid monitoring mode is used for monitoring energy data and outputting monitoring data and comprises the steps of collecting the data of energy nodes in real time and judging whether the collected data is abnormal or not;
if the collected data is not abnormal, extracting the characteristics of the collected data to obtain current monitoring data and outputting the current monitoring data;
If the collected data is abnormal, the monitoring data at the previous moment is input into the monitoring data prediction model, the current monitoring prediction data is obtained and output.
2. The cloud platform-based distributed energy data monitoring method according to claim 1, wherein the calculating the operation state evaluation value of the monitoring device according to the operation data set comprises obtaining historical monitoring operation data and historical operation state evaluation values of the monitoring device from a preset database to obtain a historical data set;
establishing an operation state evaluation function for representing the operation state evaluation value;
Optimizing parameters of the running state evaluation function by using the historical data set to obtain a final running state evaluation function;
Inputting the operation data set into a final operation state evaluation function to obtain an operation state evaluation value, wherein the operation state evaluation value S comprises:
,
wherein ai is the weight coefficient of the ith monitoring operation data in the operation data set, bi is the ith monitoring operation data in the operation data set, C is the error coefficient, and n is an integer greater than 0.
3. The cloud platform-based distributed energy data monitoring method of claim 1, wherein selecting a real-time monitoring mode, performing energy data monitoring and outputting monitoring data comprises collecting data of energy nodes in real time;
Extracting characteristics of the collected data to obtain monitoring data;
and outputting the monitoring data.
4. The cloud platform-based distributed energy data monitoring method according to claim 3, further comprising the steps of collecting data of energy nodes in real time and extracting features to obtain actual monitoring data;
outputting the actual monitoring data and sending early warning information when the error between the actual monitoring data and the current monitoring prediction data is larger than a preset condition;
checking the monitoring equipment according to the early warning information and feeding back a checking result;
if the checking result is abnormal, the monitoring data prediction model is not required to be optimized;
and if the checking result is that the monitored data is abnormal, optimizing the monitored data prediction model according to the actual monitored data.
5. The cloud platform-based distributed energy data monitoring device is used for realizing the cloud platform-based distributed energy data monitoring method according to any one of claims 1-4, and is characterized by comprising a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring monitoring operation data of energy node monitoring equipment in real time to obtain an operation data set;
The evaluation value calculation module is used for calculating and obtaining an operation state evaluation value of the monitoring equipment according to the operation data set;
The evaluation value analysis module is used for judging the sizes of the running state evaluation value and a preset threshold value;
And the monitoring mode selection module is used for selecting a real-time monitoring mode, a hybrid monitoring mode and a predictive monitoring mode according to the judging result and outputting monitoring data by utilizing the selected modes.
6. A computer storage medium, wherein one or more programs are stored, and when the one or more programs are executed, the cloud platform-based distributed energy data monitoring method of any of claims 1-4 can be implemented.
7. An apparatus comprising a processor, a communication interface, a memory and a communication bus, the memory storing at least one program capable of being loaded by the processor and executed on a computer storage medium as in claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510343926.9A CN120256244B (en) | 2025-03-22 | Distributed energy data monitoring method, device, equipment and medium based on cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510343926.9A CN120256244B (en) | 2025-03-22 | Distributed energy data monitoring method, device, equipment and medium based on cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120256244A CN120256244A (en) | 2025-07-04 |
| CN120256244B true CN120256244B (en) | 2026-02-06 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118885356A (en) * | 2024-08-23 | 2024-11-01 | 睿和聚能(深圳)科技有限公司 | A server failure remote monitoring system and method |
| CN119004303A (en) * | 2024-07-03 | 2024-11-22 | 华能济南黄台发电有限公司 | Power plant equipment fault diagnosis method and system based on artificial intelligence and automation |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119004303A (en) * | 2024-07-03 | 2024-11-22 | 华能济南黄台发电有限公司 | Power plant equipment fault diagnosis method and system based on artificial intelligence and automation |
| CN118885356A (en) * | 2024-08-23 | 2024-11-01 | 睿和聚能(深圳)科技有限公司 | A server failure remote monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117408162B (en) | Power grid fault control method based on digital twin | |
| CN111555716B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
| CN119312250A (en) | Substation main equipment self-test system based on multi-source heterogeneous data fusion technology | |
| CN118313812A (en) | A method for collecting and processing power big data based on machine learning | |
| CN119151160B (en) | Intelligent management method and system for operation of new energy station | |
| CN117989074A (en) | Intelligent monitoring method for offshore wind turbine based on sensing calculation coordination | |
| CN119674932B (en) | New energy storage and digestion capacity index prediction method | |
| CN113169708A (en) | Solar power generation balance control system and method | |
| CN113169709A (en) | Solar power generation control system and method based on machine learning | |
| CN117951633B (en) | Photovoltaic power generation equipment fault diagnosis method and system | |
| CN117674249A (en) | A fault self-healing control and evaluation method for distribution network containing distributed photovoltaics | |
| CN116308304A (en) | New energy smart operation and maintenance method and system based on meta-learning concept drift detection | |
| CN120106354B (en) | A method, system, equipment and medium for early warning of faults in wind farm collector lines. | |
| CN118311352A (en) | Bus duct fault diagnosis method and system for photovoltaic energy storage system | |
| CN119944624A (en) | Power quality monitoring system and method for distributed photovoltaic grid-connected distribution network | |
| CN120011715A (en) | Distribution system fault prediction system and prediction method based on big data analysis | |
| CN120341874A (en) | A photovoltaic storage AC/DC hybrid microgrid system and method | |
| CN116591911B (en) | Intelligent detection operation and maintenance system and method facing to offshore wind turbine generator set | |
| CN120256244B (en) | Distributed energy data monitoring method, device, equipment and medium based on cloud platform | |
| CN118246695B (en) | A photovoltaic new energy operation and maintenance dispatching system | |
| CN119944940A (en) | A distributed photovoltaic operation and maintenance data intelligent processing method and system | |
| CN119782390A (en) | A method and system for generating substation inspection report | |
| Xiong et al. | Research on health condition assessment method for spacecraft power control system based on SVM and cloud model | |
| CN118364627A (en) | Low-efficiency positioning method and system based on string analysis | |
| CN119149991A (en) | Rapid early warning system and method for degradation state trend of water energy storage unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |