Power data processing method and power dispatching method of renewable energy power generation system

Abstract

The invention relates to a power data processing method and a power dispatching method of a renewable energy power generation system. The power data processing method is applied to an edge control module of the renewable energy power generation system, operation data and environment data are used as input, a preset power dispatching model is called, and load demand change data and power generation capacity change data of the renewable energy power generation system are obtained through prediction, the power dispatching model is obtained by training a long-short-term memory model based on historical environment data and historical operation data of the renewable energy power generation system, a power dispatching strategy is further determined according to load demand change data and power generation capacity change data, and data support is provided for efficient power dispatching of a subsequent cloud server. The power dispatching method is applied to the cloud server of the renewable energy power generation system, power dispatching is carried out on the renewable energy power generation system according to the power dispatching strategy, and the dispatching efficiency of the renewable energy power generation system is improved.

Description

Technical Field

[0001] The present application relates to the field of electronic power technology, and in particular to a power data processing method for a renewable energy power generation system, a power dispatching method for a renewable energy power generation system, a renewable energy power generation system, a power data processing device for a renewable energy power generation system, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the rapid development of renewable energy, renewable energy power generation systems play an increasingly important role in energy management and power systems. However, due to the frequent fluctuations in renewable energy generation, the current renewable energy power generation system has the defects of low energy efficiency and low intelligence level.

[0003] In traditional solutions, cloud servers are usually deployed in renewable energy power generation systems. Operation data of the renewable energy power generation systems are received through remote cloud servers. Then, based on the operation data, the cloud servers remotely dispatch the renewable energy power generation systems to improve the energy efficiency and intelligence of the renewable energy power generation systems.

[0004] However, with the increasing complexity of renewable energy power generation systems, more and more operating data needs to be uploaded to the cloud server in traditional solutions, and the time spent on uploading the operating data is getting longer and longer. It also takes a lot of time for the cloud server to process so much operating data, which leads to a slower response speed of the renewable energy power generation system to emergencies and low scheduling efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide a power data processing method for a renewable energy power generation system that can improve scheduling efficiency, a power scheduling method for a renewable energy power generation system, a renewable energy power generation system, a power data processing device for a renewable energy power generation system, a computer device, a computer-readable storage medium and a computer program product in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a method for processing power data of a renewable energy power generation system, the system comprising an edge control module deployed on a power supply module side; the method is applied to the edge control module, comprising:

[0007] Acquiring environmental data and operation data of the renewable energy power generation system sent by the power supply module;

[0008] Taking the operation data and the environmental data as input, calling a preset power dispatch model, and predicting load demand change data and power generation change data of the renewable energy power generation system;

[0009] Determining a power dispatching strategy based on the load demand change data and the power generation change data;

[0010] The power dispatching model is obtained by training a long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system.

[0011] In one of the embodiments, the power data processing method further includes:

[0012] Taking the operation data as input, calling a preset operation state prediction model, and predicting the operation state of the renewable energy power generation system;

[0013] The operation status prediction model is obtained by training a long short-term memory model based on historical operation data and the historical operation status of the renewable energy power generation system.

[0014] In one embodiment, the method further comprises:

[0015] According to the operating status, the health status of the renewable energy power generation system is evaluated to obtain a health status evaluation result;

[0016] When the health status assessment result indicates that the renewable energy power generation system is operating abnormally, a preset alarm mechanism is triggered, an operating status adjustment instruction is generated, and the operating status adjustment instruction is sent to the power supply module in the renewable energy power generation system to adjust the operating status of the power supply module.

[0017] In one embodiment, the method further comprises:

[0018] Determining the power generation efficiency of the power supply module in the renewable energy power generation system according to the operating data;

[0019] When it is determined based on the power generation efficiency that the power supply module is in an abnormal operating state, a device maintenance message is pushed.

[0020] In a second aspect, the present application further provides a power data processing device for a renewable energy power generation system, the system comprising an edge control module deployed on the side of a power supply module; the device is applied to the edge control module. The device comprises:

[0021] A data acquisition module, used to acquire environmental data and operation data of the renewable energy power generation system sent by the power supply module;

[0022] A model prediction module, used to use the operation data and the environmental data as input, call a preset power dispatch model, and predict the load demand change data and power generation change data of the renewable energy power generation system;

[0023] A strategy determination module, used to determine a power dispatch strategy based on the load demand change data and the power generation change data;

[0024] The power dispatching model is obtained by training a long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in any one of the above-mentioned embodiments of the power data processing method for a renewable energy power generation system are implemented.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in any one of the above-mentioned embodiments of the method for processing power data of a renewable energy power generation system are implemented.

[0027] In a fifth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in any of the above-mentioned embodiments of the power data processing method for a renewable energy power generation system.

[0028] The power data processing method, device, computer equipment, computer-readable storage medium and computer program product of the above-mentioned renewable energy power generation system are different from the traditional solution in which the operation data of the renewable energy power generation system is directly uploaded to the cloud server. In this solution, an edge control module is deployed in the renewable energy power generation system, and the edge control module pre-stores a power dispatching model obtained by training the long short-term memory model based on historical environmental data and historical operation data. The environmental data and the operation data of the renewable energy power generation system are not directly uploaded to the cloud server, but the environmental data and the operation data are used as input data of the power dispatching model. The power dispatching model outputs the load demand change data and the power generation change data of the renewable energy power generation system. Then, the edge control module can determine the power dispatching strategy based on the load demand change data and the power generation change data. Since the long short-term memory model can capture complex time series dependencies, it can well handle the volatility of renewable energy power generation over time, thereby obtaining an accurate dispatching strategy. In this way, it is possible to avoid uploading a large amount of operation data to the cloud server, and the edge control module closer to the data source processes the operation data, and efficiently and accurately generates a dispatching strategy, which provides a basis for subsequent cloud servers to perform efficient system scheduling.

[0029] In a sixth aspect, the present application provides a power dispatching method for a renewable energy power generation system, the system comprising an edge control module and a cloud server connected to each other, the method being applied to the cloud server, comprising:

[0030] Receiving a power dispatching strategy sent by the edge control module, where the power dispatching strategy is obtained by the edge control module using the steps of any one of the above-mentioned power data processing method embodiments;

[0031] Based on the power dispatching strategy, the renewable energy power generation system is dispatched.

[0032] In one embodiment, there are multiple edge control modules, and receiving the power dispatching strategy sent by the edge control module includes:

[0033] Receiving multiple power dispatching strategies sent by multiple edge control modules;

[0034] The step of dispatching the renewable energy power generation system based on the power dispatching strategy includes:

[0035] Based on the plurality of power dispatch strategies, determining a global power dispatch strategy for the renewable energy power generation system;

[0036] Based on the global power dispatching strategy, generating a dispatching instruction;

[0037] The scheduling instruction is sent to a power supply module of the renewable energy power generation system so that the power supply module executes the global power scheduling strategy.

[0038] In one embodiment, the number of the edge control modules is multiple, and the power dispatching method further includes:

[0039] With the goal of maximizing resource utilization of the renewable energy power generation system, resources are allocated to the edge control module.

[0040] In one embodiment, the power dispatching method further includes:

[0041] Receiving operation data of the edge control module;

[0042] Based on the operating data, determining the operating state of the edge control module;

[0043] When the running state of the edge control module is abnormal, take over the running task of the edge control module.

[0044] In a seventh aspect, the present application further provides a power dispatching device for a renewable energy power generation system, the system comprising an edge control module and a cloud server connected to each other, the device being applied to the cloud server, comprising:

[0045] a strategy acquisition module, configured to receive a power dispatch strategy sent by the edge control module, wherein the power dispatch strategy is obtained by the edge control module using the steps in any one of the above-mentioned power data processing method embodiments;

[0046] A power dispatching module is used to dispatch the renewable energy power generation system based on the power dispatching strategy.

[0047] In an eighth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in any one of the above-mentioned embodiments of the power dispatching method for a renewable energy power generation system are implemented.

[0048] In a ninth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in any one of the above-mentioned power dispatching method embodiments of a renewable energy power generation system are implemented.

[0049] In a tenth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned power dispatching method embodiments of a renewable energy power generation system.

[0050] The power dispatching method, device, computer equipment, computer-readable storage medium and computer program product of the above-mentioned renewable energy power generation system are different from the traditional solution in which a large amount of data is directly received and processed by the cloud server. This solution transmits data between the edge control module and the cloud server. The edge control module acts as a transfer station between the cloud server and the renewable energy power generation system. The operating data is first processed by the edge control module, and only the necessary information is transmitted to the cloud server, which not only greatly reduces the data transmission time, but also reduces the burden on the cloud server. In addition, the power dispatching strategy generated by the edge control module can provide a dispatching basis for the cloud server. The cloud server can efficiently dispatch the renewable energy power generation system based on the power dispatching strategy.

[0051] In an eleventh aspect, the present application provides a renewable energy power generation system, the system comprising a power supply module, an edge control module deployed on the side of the power supply module, and a cloud server connected to the edge control module;

[0052] The power supply module is used to send the operating data of the renewable energy power generation system to the edge control module;

[0053] The edge control module is used to obtain environmental data and operating data of the renewable energy power generation system sent by the power supply module, and to call a preset power dispatching model with the operating data and the environmental data as input to predict load demand change data and power generation change data of the renewable energy power generation system, and to determine a power dispatching strategy based on the load demand change data and the power generation change data, wherein the power dispatching model is obtained by training a long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system;

[0054] The cloud server is used to receive the power dispatching strategy and dispatch the renewable energy power generation system based on the power dispatching strategy.

[0055] The above-mentioned renewable energy power generation system is different from the traditional power system in that a cloud server is used to analyze and process various power data in the power system. In the renewable energy power generation system in this scheme, an edge control module close to the power supply module is deployed, and the edge control module pre-stores a power dispatching model obtained by training the long short-term memory model based on historical environmental data and historical operating data. The environmental data and operating data are used as input data for the power dispatching model. The power dispatching model outputs the load demand change data and power generation change data of the renewable energy power generation system. Then, the edge control module can determine the power dispatching strategy, and the cloud server dispatches the renewable energy power generation system based on the power dispatching strategy. In this way, it is unnecessary to upload a large amount of data to the cloud server. Instead, the edge control module closer to the data source processes the operating data, generates the dispatching strategy efficiently and accurately, reduces the data transmission time, and thus improves the response speed of the renewable energy power generation system to emergencies and improves the dispatching efficiency of the renewable energy power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 An application environment diagram of a power data processing method or a power dispatching method for a renewable energy power generation system in one embodiment;

[0058] Figure 2 is a flow chart of a power data processing method in one embodiment;

[0059] Figure 3 A schematic diagram of a flow chart of a power data processing method in a detailed embodiment;

[0060] Figure 4 A schematic diagram of a flow chart of a power dispatching method in one embodiment;

[0061] Figure 5 is a flow chart of a power dispatching method in another embodiment;

[0062] Figure 6 A schematic diagram of a flow chart of a power dispatching method in a detailed embodiment;

[0063] Figure 7 is a structural block diagram of a renewable energy power generation system in one embodiment;

[0064] Figure 8 is a structural block diagram of a power data processing device in one embodiment;

[0065] Fig. 9 is a structural block diagram of a power dispatching device in one embodiment;

[0066] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] The power data processing method and power dispatching method of the renewable energy power generation system provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown in the figure, the power supply module 102 communicates with the edge control module 104 and the cloud server 106 through the network. The data storage system can store the data that the edge control module 104 and the cloud server 106 need to process. The data storage system can be integrated on the edge control module 104 and the cloud server 106, or it can be placed on the cloud or other network servers.

[0069] Specifically, the power supply module 102 includes but is not limited to power generation modules, energy storage modules, etc. The sensors in the power supply module 102 can collect the operating data of the power generation module, energy storage module, etc. in real time, that is, the operating data of the renewable energy power generation system, and send the operating data to the edge control module 104. In addition, the edge control module 104 can obtain environmental data from the meteorological station in real time or regularly or irregularly, including but not limited to temperature, light intensity, humidity, wind speed, etc. Further, the edge control module 104 uses the operating data and environmental data as input, calls the pre-stored power dispatch model, predicts the load demand change data and power generation change data of the renewable energy power generation system, and then determines the power dispatch strategy based on the load demand change data and power generation change data, wherein the power dispatch model is obtained by training the long short-term memory model based on the historical environmental data and the historical operating data of the renewable energy power generation system, and can be pre-stored in the data storage system.

[0070] Then, the edge control module 104 sends the power dispatching strategy obtained through analysis to the cloud server 106 , and the cloud server 106 dispatches the renewable energy power generation system.

[0071] In an exemplary embodiment, Figure 2As shown, a method for processing power data of a renewable energy power generation system is provided, and the method is applied to Figure 1 Taking the edge control module 104 in FIG. 1 as an example, the following steps are included:

[0072] S110, acquiring environmental data and operation data of the renewable energy power generation system sent by the power supply module.

[0073] Among them, environmental data is the external environmental factors that affect the efficiency of renewable energy power generation, including but not limited to temperature, humidity, wind speed, wind direction, and solar radiation intensity. Environmental data is one of the important factors affecting the power generation of renewable energy power generation systems and can be obtained from meteorological stations. The power supply module is a system module responsible for controlling and distributing the output power of the renewable energy power generation system, including but not limited to the power generation module, energy storage module, etc. It has a large number of sensors deployed inside, and can upload operating data to the edge control module. Operating data includes but is not limited to the power generation power, power output fluctuation, charging and discharging data, etc. of the renewable energy power generation system.

[0074] Taking the photovoltaic power generation system as an example, the edge control module includes but is not limited to the photovoltaic inverter (used to convert the direct current generated by the photovoltaic panels into alternating current, which can monitor the output voltage, current and power data of the photovoltaic panels in real time, and predict the power generation power of the photovoltaic panels through the internally deployed power scheduling model), the energy management module (used to manage and control the energy storage module, which can monitor the charging and discharging status, temperature and health status of the battery, and analyze the charging and discharging behavior of the energy storage module through the internally deployed power scheduling model), the edge computing gateway (which can collect data from the photovoltaic inverter, energy management module and environmental sensors, and generate power scheduling strategies through the internally deployed power scheduling model), etc.

[0075] The renewable energy power generation system also includes a communication module for realizing communication between various modules. In order to improve data transmission efficiency, in this embodiment, the communication between the power supply module and the edge control module, and between the edge control module and the cloud server, all use low-latency, high-bandwidth communication protocols.

[0076] S120, using the operation data and the environmental data as input, calling a preset power dispatching model, and predicting the load demand change data and the power generation change data of the renewable energy power generation system.

[0077] Among them, the power dispatch model is trained based on the long short-term memory model based on historical environmental data and historical operating data of renewable energy power generation systems. The long short-term memory model is a recursive neural network suitable for time series data. It can effectively capture the long-term and short-term dependencies in the time series and can handle the volatility of renewable energy power generation well. The load demand change data represents the change of power demand on the user side over time. It is affected by various factors such as seasonality, climate, and power consumption patterns. The power generation change data represents the change of power generation capacity of renewable energy power generation systems in the future.

[0078] Taking the renewable energy power generation system as a photovoltaic power generation system, the training process of the power dispatching model can be: first collect the historical environmental data of the renewable energy power generation system (including but not limited to the output voltage and current of the photovoltaic panel, the battery power of the energy storage module, and the charging and discharging status), historical operation data (including but not limited to the ambient temperature, humidity, and light intensity), and the timestamps of the historical environmental data and historical operation data, and then perform preliminary processing such as data cleaning, processing missing values, removing abnormal data, and denoising on the collected original data, and then perform feature engineering processing on the data after preliminary processing to extract key features, such as the average light intensity in the past 24 hours, the voltage change rate and current change rate of the photovoltaic panel in the past 1 hour, the ambient temperature, etc., remove redundant or irrelevant features, and normalize or standardize the extracted features to make them in the same dimension, such as scaling the voltage data and current data to the range of [0, 1] to obtain processed data.

[0079] Then, the processed data is divided into a training set, a validation set, and a test set, for example, 70% training set, 20% validation set, and 10% test set. The data in the training set is used to train the long short-term memory model, and the model parameters are adjusted so that it performs well on the validation set. The early stopping strategy can be used during the training process to reduce the risk of model overfitting. The model performance is evaluated using the data in the validation set, and hyperparameters such as learning rate and batch size are adjusted to optimize the model performance. The generalization ability of the model is evaluated using the data in the test set, and evaluation indicators such as mean square error (MSE) and root mean square error (RMSE) are calculated to obtain the trained power dispatch model, which is converted into a format suitable for edge device operation, and then the converted power dispatch model is deployed to the edge control device.

[0080] It should be noted that transfer learning algorithms can be introduced in the model training process, for example, a deep learning model that has been trained on a similar photovoltaic power generation system is used and migrated to a new environment for adjustment and application. In this way, even if the amount of data is limited in the new environment, power generation forecasts and load demand forecasts can be quickly performed. For example, in a newly deployed photovoltaic power station, the model trained on other power stations is directly used for power generation forecasts, and then fine-tuned through local data, thereby accelerating the adaptation speed of the model and improving the accuracy of the forecast. In addition, photovoltaic power generation systems are often greatly affected by geographical location and climatic conditions, but there may be commonalities between different regions. Using transfer learning, photovoltaic power generation data from different regions can be integrated to train a more universal power dispatch model. Then, in the new region, only a small amount of localized data fine-tuning is required to obtain better forecast results. For example, a model that has been trained in an area with similar climatic conditions is applied to a photovoltaic power station in a new area to forecast power generation and load demand. Through transfer learning, the training cost of the new model can be effectively reduced.

[0081] In this embodiment, before calling the trained power dispatch model, the edge control module can first perform a series of pre-processing operations such as data clarity, denoising, feature engineering, etc. on the received raw data, and can also integrate data from multiple sensors or different data sources to form multi-modal environmental data and multi-modal operating data as input data for the power dispatch model, thereby outputting more accurate load demand change data and power generation change data of the renewable energy power generation system. In addition, in actual operation, the environment of the renewable energy power generation system will change over time, such as seasonal changes, equipment aging, etc. At this time, the power dispatch model can be continuously fine-tuned and optimized using the real-time collected data through the online update mechanism of transfer learning to improve the accuracy and adaptability of the power dispatch model. Specifically, the power dispatch model continues to learn from new environmental data and operating data in the process of performing real-time prediction tasks, and continuously optimizes the model performance. For example, the edge control module can periodically send new environmental data and operating data to the cloud server, and the cloud server uses these environmental data and operating data to continuously update the power dispatch model, and then sends the updated power dispatch model to the edge control module.

[0082] S130, determining a power dispatching strategy based on the load demand change data and the power generation change data.

[0083] Among them, the power dispatching strategy refers to an optimization strategy that dynamically adjusts the operating mode of the renewable energy power generation system according to the current load demand change data and power generation change data of the renewable energy power generation system to meet the power demand. The optimization goals of the power dispatching strategy generally include but are not limited to minimizing power fluctuations, improving power generation efficiency, reducing energy waste, and ensuring supply and demand balance.

[0084] In a photovoltaic power generation system, the power dispatching strategy includes, but is not limited to, an optimization strategy for photovoltaic power generation modules and an optimization strategy for energy storage modules. For example, the optimization strategy for photovoltaic power generation modules may be to adjust the working point of the photovoltaic array through maximum power point tracking to maximize the power generation, or to adjust the power generation plan of the photovoltaic power generation module according to the power generation change data; the optimization strategy for the energy storage module may be to adjust the charging and discharging plan according to the load demand change data, the power generation change data, the battery status data of the energy storage module, etc. For example, during the peak period of power demand, discharge from the energy storage module is given priority to meet the demand, and during the trough period of power demand, the excess power generation of the power generation module is used to charge the battery of the energy storage module.

[0085] Exemplarily, the edge scheduling module can determine the optimal power generation, charging and discharging timing, etc. of the renewable energy power generation system based on the load demand change data and the power generation change data through optimization algorithms, including but not limited to linear programming, genetic algorithms, particle swarm optimization algorithms, etc., and generate a power scheduling strategy. Taking the photovoltaic power generation system as an example, for example, the maximum power point tracking algorithm is adopted so that the photovoltaic panel can achieve maximum power output under various lighting conditions. In addition to determining the power scheduling strategy based on the load demand change data and the power generation change data, the edge control module can also adjust the power scheduling strategy according to the health status, remaining life, grid load, and electricity price changes of the battery of the energy storage module. For example, when the battery health status is relatively poor, the charging voltage and charging current are reduced to reduce battery loss; during the peak period of grid electricity price, the energy storage module is controlled to discharge, and the energy storage module is charged during the low electricity price period.

[0086] The power data processing method of the above-mentioned renewable energy power generation system is different from the traditional solution in which the operation data of the renewable energy power generation system is directly uploaded to the cloud server. In this solution, an edge control module is deployed in the renewable energy power generation system, and the edge control module pre-stores a power dispatching model obtained by training the long short-term memory model based on historical environmental data and historical operation data. The environmental data and the operation data of the renewable energy power generation system are not directly uploaded to the cloud server, but the environmental data and the operation data are used as input data of the power dispatching model. The power dispatching model outputs the load demand change data and the power generation change data of the renewable energy power generation system. Then, the edge control module can determine the power dispatching strategy based on the load demand change data and the power generation change data. Since the long short-term memory model can capture complex time series dependencies, it can well handle the volatility of renewable energy power generation over time, thereby obtaining an accurate dispatching strategy. In this way, it is possible to avoid uploading a large amount of operation data to the cloud server, and the edge control module closer to the data source processes the operation data, and efficiently and accurately generates a dispatching strategy, which reduces the data transmission time, thereby improving the response speed of the renewable energy power generation system to emergencies, and can support improving the dispatching efficiency of the renewable energy power generation system.

[0087] In an exemplary embodiment, Figure 3 As shown, the power data processing method also includes:

[0088] S140, using the operation data as input, calling a preset operation status prediction model to predict the operation status of the renewable energy power generation system.

[0089] The operation status prediction model is obtained by training the long short-term memory model based on the historical operation data and the historical operation status of the renewable energy power generation system. The operation status prediction model can predict the future operation status of the renewable energy power generation system based on the input operation data. The model can be used to predict possible failures of the power supply module in the renewable energy power generation system, changes in power generation efficiency, etc. The operation status of renewable energy includes but is not limited to normal operation status, low power output status, fault status, maintenance status, start or stop status, etc.

[0090] Exemplarily, the operation data is input into the operation state prediction model, and the operation state prediction model will predict the operation state of the renewable energy power generation system in the future period of time based on the rules learned during training, including but not limited to the operation state of each power device in the renewable energy power generation system. In addition, the edge control module can make adaptive adjustments to each power device based on the operation state, for example, adjust the blade angle of the wind turbine and the angle of the photovoltaic panel according to the predicted operation state.

[0091] It should be noted that in the training process of the operation status prediction model, a transfer learning algorithm can also be used. For example, the operation status prediction model trained on other renewable energy power generation systems can be migrated, and fine-tuned with a small amount of local data to obtain a trained operation status prediction model.

[0092] In this embodiment, by deploying an operating status prediction model on the edge control module, the future operating status of the renewable energy power generation system can be evaluated based on the operating data sent by the power supply module, and because the edge control module is relatively close to the power supply module, when the future operating status of the renewable energy power generation system is abnormal, countermeasures can be taken quickly and efficiently to improve the stability of the renewable energy power generation system.

[0093] In an exemplary embodiment, Figure 3 As shown, the power data processing method also includes:

[0094] S150, evaluating the health status of the renewable energy power generation system according to the operating status, and obtaining a health status evaluation result.

[0095] S160, when the health status assessment result indicates that the renewable energy power generation system is operating abnormally, trigger a preset alarm mechanism, generate an operating status adjustment instruction, and send the operating status adjustment instruction to the power supply module in the renewable energy power generation system to adjust the operating status of the power supply module.

[0096] Among them, health status assessment refers to judging whether the health status or working status of the renewable energy power generation system is within the normal range, whether there are potential faults and performance degradations, by analyzing the operating status and other data of the renewable energy power generation system. The health status assessment results can characterize whether the renewable energy power generation system is in a normal, sub-healthy or abnormal state. The health status assessment results may include but are not limited to quantitative indicators or status descriptions of each power equipment in the renewable energy power generation system, such as health score, fault probability, remaining service life, etc.

[0097] Exemplarily, taking the photovoltaic power generation system as an example, the abnormal operation conditions include but are not limited to: abnormal power generation module, abnormal energy storage module, abnormal communication module, etc. Specifically, the abnormal condition of the power generation module may be abnormally low power generation (which may be caused by the photovoltaic components being blocked by accumulated dust or leaves, photovoltaic component failure, or inverter failure). The edge control module can identify the cause of abnormally low power generation based on the operating data of the power generation module and send a maintenance notification to the maintenance personnel. If it is caused by the photovoltaic components being blocked, the maintenance personnel will be arranged to conduct on-site inspection and cleaning. If it is an equipment failure, the maintenance personnel will be arranged to arrange the faulty parts. It can also be that the voltage or current of the power generation module has abnormal fluctuations. At this time, the edge control module alarms (sound and light alarms, sends alarm messages to the cloud server, etc.), and sends operating status adjustment instructions to the power generation module to reduce the photovoltaic power generation output power. The maintenance personnel can also be notified to inspect the power generation module.

[0098] The abnormal situation of the energy storage module can be battery overcharge or over discharge (may be caused by charging controller failure or battery management system abnormality). The edge control module sends an operation status adjustment instruction to the energy storage module to cut off the charging or discharging circuit to protect the battery. The abnormal situation of the energy storage module can also be that the battery temperature is too high (may be caused by internal battery short circuit, high ambient temperature or cooling system failure). The edge control module sends an operation status adjustment instruction to the energy storage module to start the backup cooling system or reduce the battery discharge rate to lower the battery temperature. If the temperature cannot be effectively reduced, the edge control module immediately controls the energy storage module to stop the battery charging and discharging operation and notifies the technician to check.

[0099] Abnormal conditions of the communication module may be data transmission interruption (possibly caused by communication module failure or network connection problem), data transmission error (possibly caused by signal interference or module failure), etc. The edge control module sends an operation status adjustment instruction to the communication module to switch to the backup communication channel or try to switch the network, and alarms to remind technicians to check the data transmission path, transmission equipment, etc.

[0100] In addition, it is also possible that the grid status of the public power grid connected to the photovoltaic power generation system is abnormal, such as the grid voltage is too high or too low (which may be caused by grid instability, sudden changes in system load, etc.), the grid frequency is abnormal (caused by grid failure, unstable inverter output, etc.), etc. The edge control module sends an operation status adjustment instruction to the power generation module and the energy storage module to adjust the output power of the power generation module and the charging and discharging power of the energy storage module to help stabilize the grid voltage. If the grid frequency exceeds the safe range, the edge control module controls the power generation module and the energy storage module to disconnect from the grid, and reconnect after the grid returns to normal, and check the working status of the power equipment in the photovoltaic power generation system. If the above method still cannot solve the abnormal grid status, the edge control module sends an alarm message to the cloud server, and the cloud server notifies the grid operator and takes further measures, such as the edge control module controlling the photovoltaic power generation system to operate off-grid, or starting the backup power supply, etc.

[0101] Following the above embodiment, the edge control module evaluates the health status of the renewable energy power generation system according to the predicted operating status. If the health status evaluation result indicates that the health of the renewable energy power generation system is in an abnormal state, such as the remaining service life of some power equipment is short and the possibility of failure in the future is high, the edge control module will trigger a preset alarm mechanism, such as sound and light alarm, send an alarm message to the cloud server, and remind relevant maintenance personnel through the cloud server. In addition, the edge control module will also generate an operating status adjustment instruction. For example, if the remaining service life of a generator A is less than three months, the operating status adjustment instruction can be "turn off generator A", and send an alarm message to the cloud server to replace generator A, and the cloud server will forward the alarm message to the terminal of the relevant maintenance personnel.

[0102] In this embodiment, by predicting the operating status of the renewable energy power generation system, the health status of the renewable energy power generation system is evaluated, and the edge control module can automatically generate and execute operating status adjustment instructions and take action quickly without having to process through the cloud server, thereby improving the response speed and stability of the renewable energy power generation system.

[0103] In an exemplary embodiment, Figure 3 As shown, the power data processing method also includes:

[0104] S170, determining the power generation efficiency of the power supply module in the renewable energy power generation system according to the operation data.

[0105] S180: When it is determined based on the power generation efficiency that the power supply module is in an abnormal working state, a device maintenance message is pushed.

[0106] Among them, power generation efficiency refers to the ratio between the electrical energy that a power generation module can convert under specific conditions and the energy it consumes, which can be expressed as a percentage. The higher the power generation efficiency, the higher the energy conversion rate of the power generation module.

[0107] Exemplarily, sensors are deployed in the power supply module to collect the operating data of the power generation module. Taking the power generation module in the photovoltaic power generation system as an example, the sensors on the power generation module can collect environmental data such as solar radiation intensity, and the environmental data can reflect the solar power absorbed by the photovoltaic panel. In addition, the operating data also includes the power generation power of the power generation module. The edge control module can determine the power generation efficiency of the power supply module based on the solar power absorbed by the power generation module and the power generation power.

[0108] Furthermore, when the power generation efficiency of the power supply module is significantly lower than the normal range, it can be considered that the power supply module is in an abnormal working state, indicating that the power supply module may have a fault, performance degradation or maintenance requirements. It should be noted that the normal range of the power generation efficiency of the power supply module can be dynamically adjusted, for example, according to different seasons, weather, and equipment usage time. In order to improve the response speed, the edge control module can push equipment maintenance messages to maintenance personnel directly or indirectly through the cloud server, wherein the equipment maintenance messages include but are not limited to the operating status, abnormal level, maintenance measures, etc. of the power supply module. In addition, the edge control module also includes a storage unit, which can store the operating data, environmental data, etc. obtained by the edge control module, as well as the operating status, power dispatching strategy, health status, maintenance records of the renewable energy power generation system obtained based on the analysis of the operating data and environmental data, and the communication records between the edge control module and the cloud server.

[0109] In this embodiment, based on the operating data of the renewable energy power generation system, the power generation efficiency of the power supply module in the renewable energy power generation system can be quickly determined, and when the power supply module is in an abnormal working state, the edge control module can automatically push equipment maintenance messages, which significantly improves the response speed of the renewable energy power generation system and can reduce the failure probability of the renewable energy power generation system.

[0110] In order to explain the power data processing method of the renewable energy power generation system proposed in this scheme more clearly, the following will be combined with the attached Figure 3 and one A specific embodiment is explained in detail, and the specific embodiment includes the following steps:

[0111] S110, acquiring environmental data and operation data of the renewable energy power generation system sent by the power supply module.

[0112] S120, using the operation data and the environmental data as input, calling a preset power dispatching model, and predicting the load demand change data and the power generation change data of the renewable energy power generation system.

[0113] S130, determining a power dispatching strategy based on the load demand change data and the power generation change data.

[0114] S140, using the operation data as input, calling a preset operation status prediction model to predict the operation status of the renewable energy power generation system.

[0115] S150, evaluating the health status of the renewable energy power generation system according to the operating status, and obtaining a health status evaluation result.

[0116] S160, when the health status assessment result indicates that the renewable energy power generation system is operating abnormally, trigger the preset alarm mechanism, generate an operation status adjustment instruction, and send the operation status adjustment instruction to the power supply module in the renewable energy power generation system S170, determine the power generation efficiency of the power supply module in the renewable energy power generation system based on the operating data.

[0117] S180: When it is determined based on the power generation efficiency that the power supply module is in an abnormal working state, a device maintenance message is pushed.

[0118] In one embodiment, a power dispatching method for a renewable energy power generation system is provided. The system includes an edge control module and a cloud server connected to each other. The method is applied to the cloud server, such as Figure 4 As shown, the method comprises the following steps:

[0119] S210, receiving a power dispatching strategy sent by an edge control module.

[0120] S220, dispatching the renewable energy power generation system based on the power dispatching strategy.

[0121] The power dispatching strategy is obtained by the edge control module using the steps in any of the above-mentioned power data processing method embodiments of the renewable energy power generation system. The cloud server is a central computing unit that processes and stores a large amount of data. It can uniformly manage the power dispatching strategy and other data uploaded by the edge control module, and is responsible for global dispatching optimization and strategy execution.

[0122] Specifically, the power dispatching strategy generated by the above power data method includes but is not limited to: adjusting the speed of wind turbines, or adjusting the inclination of solar panels, coordinating the output plans of different power generation equipment, formulating the charging and discharging plan of energy storage modules, etc. The edge control module and the cloud server can communicate through the network. In order to improve timeliness, the communication protocol can choose lightweight and efficient protocols as much as possible, such as Wi-Fi, BLE (Bluetooth Low Energy), Zigbee (Zigbee protocol), LoRa (Long Range, long-range radio), etc.

[0123] Furthermore, the cloud server is equivalent to a management and control center, responsible for the overall coordination, remote monitoring and management of the system. After receiving the power dispatch strategy, the cloud server can further adjust the power dispatch strategy appropriately, such as optimizing and updating the power dispatch strategy in real time based on the real-time changes in environmental data (such as wind speed changes, solar radiation intensity changes, etc.) combined with deep learning technology. Then, the cloud server generates a series of dispatch instructions based on the optimized power dispatch strategy and sends them to the various power equipment in the renewable energy power generation system, thereby coordinating the operating status of different power equipment to meet the current system's power demand.

[0124] In this embodiment, through the data transmission between the edge control module and the cloud server, the edge control module acts as a transfer station between the cloud server and the renewable energy power generation system. The operation data is first processed by the edge control module, and only the necessary information is transmitted to the cloud server, which reduces the burden on the cloud server. In addition, the power dispatching strategy generated by the edge control module can provide a dispatching basis for the cloud server. This method can reduce the transmission of data in the network, thereby saving bandwidth and network congestion, and can also reduce the risk of data leakage.

[0125] In an exemplary embodiment, there are multiple edge control modules, such as Figure 5 As shown, S210 includes:

[0126] S211, receiving multiple power scheduling strategies sent by multiple edge control modules.

[0127] S220 includes:

[0128] S221, determining a global power dispatching strategy for the renewable energy power generation system based on multiple power dispatching strategies.

[0129] S222, generating a dispatch instruction based on the global power dispatch strategy.

[0130] S223, sending a scheduling instruction to the power supply module of the renewable energy power generation system, so that the power supply module executes the global power scheduling strategy.

[0131] In a complex renewable energy power generation system, there may be multiple distributed edge control modules, which are deployed in different geographical areas or different types of power generation equipment (such as wind power generation, photovoltaic power generation, etc.) to collect and process local environmental data and operating data. Each edge control module determines different power dispatch strategies based on local environmental data and operating data. The dispatch instruction is a specific execution command generated by the cloud server based on the global dispatch strategy, which is used to instruct each power supply module in the renewable energy power generation system to adjust the operating status or output power, etc.

[0132] For example, when the area covered by the renewable energy power generation system is large, it may include multiple energy sources (wind energy, solar energy, etc.). In order to achieve global scheduling of the renewable energy power generation system, it is necessary to deploy independent edge control modules on each distributed power station or subsystem. Each edge control module generates a local power scheduling strategy based on local environmental data and operation data, and different edge control modules maintain communication connection with the cloud server. It should be noted that in addition to each edge control module communicating with the cloud server separately, different edge control modules can also communicate and share data appropriately, so as to adjust the local power scheduling strategy based on the data of other edge control modules, and realize coordinated optimization of the renewable energy power generation system.

[0133] The cloud server receives multiple power dispatching strategies from multiple edge control modules, and then summarizes and optimizes these strategies, for example, while considering the power generation status and power generation efficiency of each power station or subsystem, it optimizes the power generation efficiency, resource utilization rate, etc. of the entire renewable energy power generation system. For example, since different power dispatching strategies may have different optimization goals, for example, some tend to optimize power generation efficiency, and some tend to optimize the service life of power equipment, after the cloud server receives multiple power dispatching strategies, it first performs a fusion analysis on the multiple power dispatching strategies, and assigns weights to each power dispatching strategy based on the overall power supply and demand of the renewable energy power generation system, so as to determine the final global dispatching strategy. For example, in the renewable energy power generation system, the load demand in some areas is relatively high, and the local power generation capacity is insufficient. The cloud server can use the dispatching strategy to allocate the surplus power in other areas to the high-load area. It should be noted that the global dispatching strategy is not immutable. The cloud server can directly obtain some high-priority operation data from the power supply module of each power station or subsystem, and dynamically adjust the global dispatching strategy based on these operation data and real-time environmental data.

[0134] Finally, the cloud server generates dispatch instructions based on the global dispatch strategy and sends them to each power supply module. Dispatching instructions include global dispatch instructions and local dispatch instructions. Global dispatch instructions involve the power generation optimization of the entire renewable energy power generation system, and its goal is to achieve global load balance and optimal resource allocation, such as power coordination between different power stations or subsystems to cope with global load fluctuations. Local dispatch instructions are for the power supply module of each power station or subsystem, and their goal is to improve the power generation efficiency of a single power station or subsystem, such as fine-tuning the working parameters of the power supply module.

[0135] After receiving the dispatch instruction, the power supply module will adjust its working state according to the dispatch instruction. For example, the photovoltaic inverter adjusts the output power according to the dispatch instruction, and the wind turbine adjusts the speed according to the dispatch instruction. In addition, the edge control module can monitor the execution of the instructions of each power supply module in real time, and when there is a deviation in the execution of the instruction or other abnormal conditions, the edge control module will send an alarm message to the cloud server in time.

[0136] In this embodiment, considering that there may be multiple edge control modules and the computing resources of edge control modules are prioritized, usually only local optimization problems are focused on. The cloud server has a broader perspective and can make more complex optimization decisions based on the global state of the renewable energy power generation system, such as scheduling and allocating resources between multiple substations to improve the overall power generation efficiency and resource utilization of the renewable energy power generation system.

[0137] In one embodiment, there are multiple edge control modules, such as Figure 5 As shown, the power dispatching method further includes:

[0138] S230, allocating resources to the edge control module with the goal of maximizing resource utilization of the renewable energy power generation system.

[0139] Among them, resource utilization refers to the degree to which the resources of each device in the renewable energy power generation system (such as storage resources, computing resources, communication resources, etc.) are utilized in actual operation. Maximizing resource utilization means optimizing resource allocation so that each component of the renewable energy power generation system can work efficiently and reduce resource waste.

[0140] For example, in a renewable energy power generation system, each edge control module is responsible for processing local power data processing tasks. In order to maximize resource utilization, the renewable energy power generation system can dynamically adjust the allocation of resources according to the load conditions of different edge control modules, including but not limited to storage resources, computing resources, communication resources, etc. For example, edge control modules with higher loads can allocate more computing resources so that they can complete data processing tasks in a timely manner, while edge control modules with lower loads can allocate fewer resources to save the consumption of total resources of the renewable energy power generation system.

[0141] In addition, storage resources, computing resources, communication resources, etc. can be allocated to edge control modules according to the type and operation status of power supply modules near the edge control modules. For example, wind power generation and photovoltaic power generation require faster response and scheduling due to climate factors, so the edge control modules corresponding to wind turbines and photovoltaic generators will be allocated more computing resources, storage resources, and communication resources.

[0142] In addition, adaptive algorithms can be introduced into the cloud server to realize resource allocation. For example, by combining deep learning algorithms, resources can be adaptively allocated to edge control modules according to the operating status of the edge control modules, thereby continuously optimizing the resource allocation plan and maximizing resource utilization.

[0143] In this embodiment, by allocating resources to different edge control modules, the efficiency of the edge control modules in completing data processing tasks can be improved, thereby improving the operating efficiency of the entire renewable energy power generation system. In particular, when the system load is unbalanced, the waste of the system's overall computing resources, storage resources, communication resources, etc. can be effectively reduced.

[0144] In an exemplary embodiment, Figure 6 As shown, the power dispatching method further includes:

[0145] S240, receiving operation data of the edge control module.

[0146] S250, determining the operating state of the edge control module based on the operating data.

[0147] S260: When the running state of the edge control module is abnormal, take over the running task of the edge control module.

[0148] Exemplarily, the cloud server in the renewable energy power generation system can receive the operating data of the edge control module in real time, and judge the operating status of the edge control module based on the operating data, such as judging whether indicators such as the device temperature and response time of the edge control module exceed the normal range. If it is identified that the device temperature of the edge control module is too high or the response time is too long, the edge control module is judged to be in an abnormal operating state.

[0149] When the cloud server identifies that the operating status of an edge control module is abnormal, the cloud server immediately takes over the operating tasks of the edge control module and can also start backup computing resources, so that the cloud server can quickly replace the edge control module and improve the stability of the renewable energy power generation system. In addition, during the period when the cloud server takes over the operating tasks, the cloud server can also send maintenance messages to relevant maintenance personnel, including but not limited to the abnormal edge control module identification, abnormal time, potential abnormal reasons, etc. When the edge control module returns to normal, the cloud server can reassign operating tasks to the edge control module.

[0150] In this embodiment, by introducing an automatic takeover mechanism, the cloud server can respond quickly when an abnormality occurs in the edge control module, so that the renewable energy power generation system has better fault tolerance and improves the stability and reliability of the renewable energy power generation system.

[0151] In order to explain the power dispatching method of renewable energy power generation system proposed in this scheme more clearly, the following will be combined with the attached Figure 6 and one A specific embodiment is explained in detail, and the specific embodiment includes the following steps:

[0152] S211, receiving multiple power scheduling strategies sent by multiple edge control modules.

[0153] S221, determining a global power dispatching strategy for the renewable energy power generation system based on multiple power dispatching strategies.

[0154] S222, generating a dispatch instruction based on the global power dispatch strategy.

[0155] S223, sending a scheduling instruction to the power supply module of the renewable energy power generation system, so that the power supply module executes the global power scheduling strategy.

[0156] S230, allocating resources to the edge control module with the goal of maximizing resource utilization of the renewable energy power generation system.

[0157] S240, receiving operation data of the edge control module.

[0158] S250, determining the operating state of the edge control module based on the operating data.

[0159] S260: When the running state of the edge control module is abnormal, take over the running task of the edge control module.

[0160] In an exemplary embodiment, a renewable energy power generation system 700 is provided, including a power supply module 710 , an edge control module 720 deployed on a side of the power supply module 710 , and a cloud server 730 connected to the edge control module 720 .

[0161] The power supply module 710 is used to send the operating data of the renewable energy power generation system to the edge control module.

[0162] The edge control module 720 is used to obtain environmental data and operating data of the renewable energy power generation system sent by the power supply module 710, and uses the operating data and environmental data as input to call a preset power dispatching model to predict the load demand change data and power generation change data of the renewable energy power generation system, and determine the power dispatching strategy based on the load demand change data and the power generation change data, wherein the power dispatching model is obtained by training the long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system.

[0163] The cloud server 730 is used to receive the power dispatching strategy and dispatch the renewable energy power generation system based on the power dispatching strategy.

[0164] It should be noted that the power supply module 710, the edge control module 720, and the cloud server 730 in the system embodiment have been described in detail in the above method embodiments and will not be repeated here.

[0165] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0166] Based on the same inventive concept, the embodiment of the present application also provides a power data processing device or power dispatching device for a renewable energy power generation system for implementing the power data processing method or power dispatching method of the renewable energy power generation system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the power data processing device or power dispatching device for one or more renewable energy power generation systems provided below can refer to the limitations of the power data processing method or power dispatching method for the renewable energy power generation system above, and will not be repeated here.

[0167] In an exemplary embodiment, Figure 8 As shown, a power data processing device 800 (hereinafter referred to as the power data processing device 800) of a renewable energy power generation system is provided. The system includes an edge control module deployed on the power supply module side; the device is applied to the edge control module. The device includes: a data acquisition module 810, a model prediction module 820 and a strategy determination module 830, wherein:

[0168] The data acquisition module 810 is used to acquire environmental data and operation data of the renewable energy power generation system sent by the power supply module.

[0169] The model prediction module 820 is used to use the operation data and environmental data as inputs, call the preset power dispatch model, and predict the load demand change data and power generation change data of the renewable energy power generation system.

[0170] The strategy determination module 830 is used to determine the power dispatch strategy based on the load demand change data and the power generation change data.

[0171] Among them, the power dispatching model is obtained by training the long short-term memory model based on historical environmental data and historical operation data of renewable energy power generation systems.

[0172] In an exemplary embodiment, the power data processing device 800 is also used to call a preset operating status prediction model with operating data as input to predict the operating status of the renewable energy power generation system, wherein the operating status prediction model is obtained by training a long short-term memory model based on historical operating data and the historical operating status of the renewable energy power generation system.

[0173] In an exemplary embodiment, the power data processing device 800 is also used to evaluate the health status of the renewable energy power generation system according to the operating status to obtain a health status assessment result. When the health status assessment result indicates that the renewable energy power generation system is operating abnormally, a preset alarm mechanism is triggered to generate an operating status adjustment instruction, and the operating status adjustment instruction is sent to the power supply module in the renewable energy power generation system to adjust the operating status of the power supply module.

[0174] In an exemplary embodiment, the power data processing device 800 is also used to determine the power generation efficiency of the power supply module in the renewable energy power generation system based on the operating data, and push a device maintenance message when it is determined that the power supply module is in an abnormal working state based on the power generation efficiency.

[0175] In an exemplary embodiment, Fig. 9 As shown, a power dispatching device 900 (hereinafter referred to as the power dispatching device 900) of a renewable energy power generation system is provided, the system includes an edge control module deployed on the power supply module side; the device is applied to the edge control module. The device includes: a strategy acquisition module 910 and a power dispatching module 920, wherein:

[0176] The strategy acquisition module 910 is used to receive the power dispatching strategy sent by the edge control module. The power dispatching strategy is obtained by the edge control module using the steps in any one of the above power data processing method embodiments.

[0177] The power dispatching module 920 is used to dispatch the renewable energy power generation system based on the power dispatching strategy.

[0178] In an exemplary embodiment, there are multiple edge control modules, and the power dispatching device 900 is also used to receive multiple power dispatching strategies sent by the multiple edge control modules, determine the global power dispatching strategy of the renewable energy power generation system based on the multiple power dispatching strategies, generate dispatching instructions based on the global power dispatching strategy, and send the dispatching instructions to the power supply module of the renewable energy power generation system so that the power supply module executes the global power dispatching strategy.

[0179] In an exemplary embodiment, there are multiple edge control modules, and the power dispatching device 900 is further configured to allocate resources to the edge control modules with the goal of maximizing resource utilization of the renewable energy power generation system.

[0180] In an exemplary embodiment, the power dispatching device 900 is also used to receive operating data of the edge control module, determine the operating status of the edge control module based on the operating data, and take over the operating tasks of the edge control module when the operating status of the edge control module is abnormal.

[0181] Each module in the above-mentioned power data processing device or power dispatching device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0182] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as environmental data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power data processing method or a power dispatching method is implemented.

[0183] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0184] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in any one of the above-mentioned embodiments of the method for processing power data of a renewable energy power generation system are implemented.

[0185] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above-mentioned power data processing method embodiments of a renewable energy power generation system are implemented.

[0186] In an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned power data processing method embodiments of a renewable energy power generation system.

[0187] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in any one of the above-mentioned power dispatching method embodiments of a renewable energy power generation system are implemented.

[0188] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in any one of the above-mentioned power dispatching method embodiments of a renewable energy power generation system are implemented.

[0189] In an exemplary embodiment, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the steps in any of the above-mentioned power dispatching method embodiments of a renewable energy power generation system.

[0190] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0191] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0192] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0193] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing power data of a renewable energy power generation system, characterized in that: The system includes an edge control module deployed on the power supply module side; The method is applied to the edge control module, comprising: Acquiring environmental data and operation data of the renewable energy power generation system sent by the power supply module; Taking the operation data and the environmental data as input, calling a preset power dispatch model, and predicting load demand change data and power generation change data of the renewable energy power generation system; Determining a power dispatching strategy based on the load demand change data and the power generation change data; The power dispatching model is obtained by training a long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system.

2. The method according to claim 1, characterized in that The power data processing method further includes: Taking the operation data as input, calling a preset operation state prediction model, and predicting the operation state of the renewable energy power generation system; The operation status prediction model is obtained by training a long short-term memory model based on historical operation data and the historical operation status of the renewable energy power generation system.

3. The method according to claim 2, characterized in that The method further comprises: According to the operating status, the health status of the renewable energy power generation system is evaluated to obtain a health status evaluation result; When the health status assessment result indicates that the renewable energy power generation system is operating abnormally, a preset alarm mechanism is triggered, an operating status adjustment instruction is generated, and the operating status adjustment instruction is sent to the power supply module in the renewable energy power generation system to adjust the operating status of the power supply module.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Determining the power generation efficiency of the power supply module in the renewable energy power generation system according to the operating data; When it is determined based on the power generation efficiency that the power supply module is in an abnormal operating state, a device maintenance message is pushed.

5. A method for dispatching power of a renewable energy power generation system, characterized in that: The system includes an edge control module and a cloud server connected to each other, and the method is applied to the cloud server, including: receiving a power dispatching strategy sent by the edge control module, wherein the power dispatching strategy is obtained by the edge control module using the power data processing method according to any one of claims 1 to 4 above; Based on the power dispatching strategy, the renewable energy power generation system is dispatched.

6. The power dispatching method according to claim 5, characterized in that: There are multiple edge control modules, and receiving the power dispatching strategy sent by the edge control module includes: Receiving multiple power dispatching strategies sent by multiple edge control modules; The step of dispatching the renewable energy power generation system based on the power dispatching strategy includes: Based on the plurality of power dispatch strategies, determining a global power dispatch strategy for the renewable energy power generation system; Based on the global power dispatching strategy, generating a dispatching instruction; The scheduling instruction is sent to a power supply module of the renewable energy power generation system so that the power supply module executes the global power scheduling strategy.

7. The power dispatching method according to claim 5, characterized in that: The number of the edge control modules is multiple, and the power dispatching method further includes: With the goal of maximizing resource utilization of the renewable energy power generation system, resources are allocated to the edge control module.

8. The power dispatching method according to any one of claims 5 to 7, characterized in that: The power dispatching method further includes: Receiving operation data of the edge control module; Based on the operating data, determining the operating state of the edge control module; When the running state of the edge control module is abnormal, take over the running task of the edge control module.

9. A renewable energy power generation system, characterized in that: The system includes a power supply module, an edge control module deployed on the side of the power supply module, and a cloud server connected to the edge control module; The power supply module is used to send the operating data of the renewable energy power generation system to the edge control module; The edge control module is used to obtain environmental data and operating data of the renewable energy power generation system sent by the power supply module, and to call a preset power dispatching model with the operating data and the environmental data as input to predict load demand change data and power generation change data of the renewable energy power generation system, and to determine a power dispatching strategy based on the load demand change data and the power generation change data, wherein the power dispatching model is obtained by training a long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system; The cloud server is used to receive the power dispatching strategy and dispatch the renewable energy power generation system based on the power dispatching strategy.

10. A power data processing device for a renewable energy power generation system, characterized in that: The system includes an edge control module deployed on the power supply module side; The device is applied to the edge control module, and the device includes: A data acquisition module, used to acquire environmental data and operation data of the renewable energy power generation system sent by the power supply module; A model prediction module, used to use the operation data and the environmental data as input, call a preset power dispatch model, and predict the load demand change data and power generation change data of the renewable energy power generation system; A strategy determination module, used to determine a power dispatch strategy based on the load demand change data and the power generation change data; The power dispatching model is obtained by training a long short-term memory model based on historical environmental data and historical operating data of the renewable energy power generation system.

Images