Light storage and charging integrated smart power grid control method and system

Abstract

The invention provides an optical storage and charging integrated smart power grid control method and system, and the method comprises the steps: obtaining operation data of an optical storage and charging integrated smart power grid, carrying out the feature extraction, and obtaining a feature vector of the optical storage and charging integrated smart power grid; inputting the feature vectors into a pre-constructed prediction model, and predicting predicted power data of the photovoltaic power station, predicted state data of the energy storage device and predicted state data of the electric vehicle; under a preset constraint condition, solving a pre-constructed power grid dispatching model by utilizing the obtained prediction data, and determining a dispatching strategy of the photovoltaic, storage and charging integrated smart power grid; based on a scheduling strategy, a power adjusting instruction is sent to a photovoltaic power station, a charging and discharging instruction is sent to an energy storage device, a charging instruction is sent to an electric vehicle, the operation state of the light storage and charging integrated intelligent power grid is displayed through a visual interface, and the energy management, real-time response capability and operation stability of the intelligent power grid are improved.

Description

Technical Field

[0001] This invention relates to the field of wind power equipment condition monitoring technology, and in particular to a smart grid control method and system integrating photovoltaic, energy storage and charging. Background Technology

[0002] With the widespread application of renewable energy and the popularization of electric vehicles, integrated photovoltaic, energy storage and charging smart grids have become an important infrastructure for achieving efficient energy utilization and green transportation.

[0003] However, with the increasing number of electric vehicles and the large-scale construction of photovoltaic power plants, the disorderly charging behavior of electric vehicles and the uncertainty of renewable energy output caused by environmental and other factors have brought many hidden dangers to the operation and safety of the power grid.

[0004] Therefore, how to effectively schedule the integrated photovoltaic, energy storage, and charging smart grid, and improve the energy management, real-time response capability, and operational stability of the smart grid, is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This invention provides a photovoltaic-storage-charging integrated smart grid control method and system to address the shortcomings of existing smart grids, such as low energy management efficiency, poor real-time response capability, and poor operational stability.

[0006] On one hand, the present invention provides a smart grid control method integrating photovoltaic, energy storage, and charging, which includes: Acquire operational data of the integrated photovoltaic, energy storage, and charging smart grid; Feature extraction is performed on the operational data to obtain the feature vector of the integrated photovoltaic, energy storage and charging smart grid; The feature vector of the integrated photovoltaic, energy storage and charging smart grid is input into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device and the predicted state data of the electric vehicle. Under preset constraints, the pre-constructed power grid dispatching model is solved using the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle, to determine the dispatching strategy of the integrated photovoltaic-storage-charging smart grid; wherein, the power grid dispatching model is a multi-objective optimization model that minimizes power grid operating costs, maximizes electric vehicle user benefits, and maximizes power grid stability. Based on the scheduling strategy, power adjustment commands are sent to the photovoltaic power station, charging and discharging commands are sent to the energy storage device, and charging commands are sent to the electric vehicle. The operation status of the integrated photovoltaic-storage-charging smart grid is displayed through a visual interface.

[0007] According to the present invention, a photovoltaic-storage-charging integrated smart grid control method further includes: Acquire the actual power generation of photovoltaic power plants, the actual status data of energy storage devices, and the actual charging status data of electric vehicles; Determine the first difference between the actual power generation of the photovoltaic power station and the predicted power data of the photovoltaic power station; Determine a second difference between the actual state data of the energy storage device and the predicted state data of the energy storage device; Determine the third difference between the actual charging state data of the electric vehicle and the predicted state data of the electric vehicle; Based on the first difference, the second difference, and the third difference, the parameters of the power grid dispatching model and / or the parameters of the prediction model are dynamically adjusted.

[0008] According to the present invention, a photovoltaic-storage-charging integrated smart grid control method further includes: Construct a knowledge graph for the integrated photovoltaic, energy storage, and charging smart grid; wherein the knowledge graph includes nodes for scheduling strategies; Based on the knowledge graph, the policy relevance of the i-th candidate feature in the feature vector is determined; where i = 1, 2, ..., N, and N is the total number of candidate features in the feature vector; the policy relevance is the sum of the relevances of the i-th candidate feature to all nodes of the scheduling policy. By traversing all candidate features and nodes of all scheduling policies in the feature vector, the policy relevance of each candidate feature in the feature vector is obtained; Candidate features with a policy relevance greater than a preset relevance are retained to obtain multiple target features.

[0009] According to the integrated photovoltaic, energy storage, and charging smart grid control method provided by the present invention, determining the strategy relevance of the i-th candidate feature in the feature vector includes: Based on the knowledge graph, determine the structural relevance of the i-th candidate feature to the j-th scheduling strategy, the semantic relevance of the i-th candidate feature to the j-th scheduling strategy, and the importance of the i-th candidate feature; j = 1, 2, ..., M, where M is the total number of nodes in the scheduling strategy; Calculate the reciprocal of the average of the reciprocals of the structural relevance, the semantic relevance, and the importance, and determine the relevance of the i-th candidate feature to the j-th scheduling strategy; Sum all the relevance scores to obtain the strategy relevance score of the i-th candidate feature.

[0010] According to the integrated photovoltaic, energy storage, and charging smart grid control method provided by the present invention, determining the structural correlation between the i-th candidate feature and the j-th scheduling strategy includes: Based on the knowledge graph, determine the length of the shortest path from the node of the i-th candidate feature to the node of the j-th scheduling strategy and the total edge weight of the shortest path; The total edge weights and the length are input into a preset structural relevance calculation formula to obtain the structural relevance of the i-th candidate feature to the j-th scheduling strategy.

[0011] According to a photovoltaic-storage-charging integrated smart grid control method provided by the present invention, determining the semantic relevance of the i-th candidate feature to the j-th scheduling strategy includes: The i-th candidate feature is converted into feature text, and the j-th scheduling policy is converted into policy text; The semantic similarity between the feature text and the policy text is determined as the semantic relevance of the i-th candidate feature to the j-th scheduling policy.

[0012] According to a photovoltaic-storage-charging integrated smart grid control method provided by the present invention, determining the semantic similarity between the feature text and the strategy text includes: Multiple similarity algorithms are used to calculate multiple initial similarities between the feature text and the strategy text; The initial similarity is weighted and summed to obtain the comprehensive similarity between the feature text and the strategy text, which is then used as the semantic similarity.

[0013] According to the integrated photovoltaic, energy storage, and charging smart grid control method provided by the present invention, the process of setting the weight of each similarity algorithm includes: Obtain the feature retention contribution of each similarity algorithm over a past time period; Based on the pre-defined correlation between contribution and weight adjustment coefficient, the weight adjustment coefficient for each similarity algorithm is determined. The product of the original weight of each similarity algorithm and the weight adjustment coefficient is used as the adjusted weight.

[0014] According to the integrated photovoltaic, energy storage, and charging smart grid control method provided by the present invention, determining the importance of the i-th candidate feature includes: Determine the strategy coverage breadth, information hub value, and business importance of the i-th candidate feature; The importance of the i-th candidate feature is obtained by weighted summation of the strategy coverage breadth, the information hub value, and the business importance.

[0015] On the other hand, the present invention also provides an integrated photovoltaic, energy storage, and charging smart grid control system, which includes: The acquisition module is used to acquire operational data of the integrated photovoltaic, energy storage, and charging smart grid. The extraction module is used to extract features from the operating data to obtain the feature vector of the integrated photovoltaic, energy storage and charging smart grid; The prediction module is used to input the feature vector of the integrated photovoltaic, energy storage and charging smart grid into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted status data of the energy storage device and the predicted status data of the electric vehicle. The strategy generation module, under preset constraints, uses the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle to solve the pre-constructed power grid dispatch model and determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid; wherein, the power grid dispatch model is a multi-objective optimization model that minimizes power grid operating costs, maximizes electric vehicle user benefits, and maximizes power grid stability. The control module is used to send power adjustment commands to the photovoltaic power station, charge and discharge commands to the energy storage device, and charging commands to the electric vehicle based on the scheduling strategy, and to display the operating status of the integrated photovoltaic-storage-charging smart grid through a visual interface.

[0016] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the integrated photovoltaic, energy storage, and charging smart grid control method as described above.

[0017] On the other hand, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the integrated photovoltaic, energy storage and charging smart grid control method as described above.

[0018] On the other hand, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the integrated photovoltaic, energy storage and charging smart grid control method as described above.

[0019] The present invention provides a photovoltaic-storage-charging integrated smart grid control method and system. This method acquires operational data of the integrated photovoltaic-storage-charging smart grid; extracts features from the operational data to obtain a feature vector of the integrated photovoltaic-storage-charging smart grid; inputs the feature vector of the integrated photovoltaic-storage-charging smart grid into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle; under preset constraints, the pre-built grid dispatch model is solved using the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle to determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid; based on the dispatch strategy, power adjustment commands are sent to the photovoltaic power station, charging and discharging commands are sent to the energy storage device, and charging commands are sent to the electric vehicle; and the operational status of the integrated photovoltaic-storage-charging smart grid is displayed through a visual interface, thereby improving the energy management, real-time response capability, and operational stability of the smart grid. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the integrated photovoltaic, energy storage, and charging smart grid control method provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the integrated photovoltaic, energy storage and charging smart grid control system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0023] Figure 1 This is a flowchart illustrating the integrated photovoltaic, energy storage, and charging smart grid control method provided in this embodiment of the invention.

[0024] like Figure 1As shown, the execution subject of the integrated photovoltaic, energy storage, and charging smart grid control method provided in this embodiment of the invention can be an electronic device, and the method mainly includes the following steps: 101. Obtain operational data of the integrated photovoltaic, energy storage, and charging smart grid; In a specific implementation process, data acquisition devices such as sensors and image acquisition equipment deployed on the electric vehicle side and the power grid side can be used to obtain the operation data of the integrated photovoltaic, energy storage and charging smart grid. This data can include real-time power data of photovoltaic power plants, status data of energy storage devices (such as state of charge, charging and discharging power), charging status data of electric vehicles (such as charging power, charging time, and remaining battery capacity), and grid operating environment data (such as electricity price information, load demand, and weather data).

[0025] 102. Extract features from the operational data to obtain the feature vector of the integrated photovoltaic, energy storage, and charging smart grid; In a specific implementation process, the operation data of the photovoltaic-storage-charging integrated smart grid can be cleaned and normalized to remove noise data. The feature vector of the photovoltaic-storage-charging integrated smart grid can be obtained through statistical analysis, frequency domain transformation or machine learning feature extraction algorithms (such as principal component analysis and feature selection algorithms). The feature vector contains key parameters that reflect the system's operating status.

[0026] 103. Input the feature vector of the integrated photovoltaic, energy storage and charging smart grid into the pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device and the predicted state data of the electric vehicle. In a specific implementation process, a predictive model can be constructed using historical data and machine learning models (such as neural networks and random forests) or deep learning models (such as LSTM and Transformer). This predictive model can include a photovoltaic power prediction sub-model, an energy storage state prediction sub-model, and an electric vehicle charging state prediction sub-model.

[0027] The feature vectors of the integrated photovoltaic, energy storage, and charging smart grid can be input into a pre-built prediction model to predict the predicted power data of photovoltaic power plants, the predicted state data of energy storage devices, and the predicted state data of electric vehicles.

[0028] 104. Under preset constraints, the pre-constructed power grid dispatch model is solved using the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle, so as to determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid. In a specific implementation process, a multi-objective optimization model can be constructed as the grid dispatch model with the objectives of minimizing grid operating costs, maximizing electric vehicle user benefits, and maximizing grid stability. Under constraints such as grid safety operation constraints, energy storage device capacity constraints, and electric vehicle charging power limitations, the pre-constructed grid dispatch model is solved using the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle, based on antagonistic algorithms, to determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid.

[0029] 105. Based on the scheduling strategy, send power adjustment commands to the photovoltaic power station, charge and discharge commands to the energy storage device, and charging commands to the electric vehicle, and display the operating status of the integrated photovoltaic-storage-charging smart grid through a visual interface.

[0030] In a specific implementation, based on the scheduling strategy of the integrated photovoltaic-storage-charging smart grid, power regulation commands for photovoltaic power plants, charging and discharging commands for energy storage devices, and charging commands for electric vehicles can be generated and sent to the corresponding targets. This enables coordinated control of photovoltaic power plants, energy storage devices, and electric vehicles, thereby achieving peak shaving and valley filling, reducing load power demand, smoothing load curves, and lowering the electricity costs of electric vehicles. Furthermore, the operating status of the integrated photovoltaic-storage-charging smart grid can be displayed through a visual interface, facilitating monitoring of the grid.

[0031] This embodiment of the integrated photovoltaic-storage-charging smart grid control method acquires the operational data of the integrated photovoltaic-storage-charging smart grid; extracts features from the operational data to obtain the feature vector of the integrated photovoltaic-storage-charging smart grid; inputs the feature vector of the integrated photovoltaic-storage-charging smart grid into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle; under preset constraints, the pre-built grid dispatch model is solved using the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle to determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid; based on the dispatch strategy, power adjustment commands are sent to the photovoltaic power station, charging and discharging commands are sent to the energy storage device, and charging commands are sent to the electric vehicle; and the operational status of the integrated photovoltaic-storage-charging smart grid is displayed through a visual interface, thereby improving the energy management, real-time response capability, and operational stability of the smart grid.

[0032] In a specific implementation process, the actual power generation of the photovoltaic power station, the actual status data of the energy storage device, and the actual charging status data of the electric vehicle can also be obtained. The first difference, second difference, and third difference between the actual data and the predicted data are calculated respectively. An error feedback mechanism is constructed based on the differences, and adaptive algorithms (such as gradient descent and Kalman filtering) are used to dynamically adjust the parameters of the power grid dispatching model (such as objective function weights and constraint thresholds) and / or the parameters of the prediction model (such as model training hyperparameters and network weights) to achieve online optimization of the model and improve the prediction accuracy and adaptability of the system dispatching strategy.

[0033] In a specific implementation process, a knowledge graph of the integrated photovoltaic-storage-charging smart grid can be constructed. This knowledge graph represents system entities (such as equipment, scheduling strategies, and features) and their relationships in a graph structure, including nodes for scheduling strategies (such as "photovoltaic power upscaling strategy" and "energy storage discharge strategy"). Based on this knowledge graph, multiple candidate features in the feature vector can be analyzed to determine the strategy relevance of each candidate feature, that is, the relevance of each candidate feature to determining the scheduling strategy. Thus, multiple target features can be obtained by filtering based on the strategy relevance of each candidate feature.

[0034] Specifically, this can be achieved as follows: (1) Based on the knowledge graph, determine the policy relevance of the i-th candidate feature in the feature vector; Where i = 1, 2, ..., N, and N is the total number of candidate features in the feature vector; the policy relevance is the sum of the relevance of the i-th candidate feature to all nodes of the scheduling policy.

[0035] Specifically, this can be achieved in the following way (1): a1. Based on the knowledge graph, determine the structural relevance of the i-th candidate feature to the j-th scheduling strategy, the semantic relevance of the i-th candidate feature to the j-th scheduling strategy, and the importance of the i-th candidate feature; Where j = 1, 2, ..., M, and M is the total number of nodes in the scheduling strategy.

[0036] In a specific implementation, the structural relevance of the i-th candidate feature to the j-th scheduling strategy can be determined as follows: S1. Based on the knowledge graph, determine the length of the shortest path from the node of the i-th candidate feature to the node of the j-th scheduling strategy and the total edge weight of the shortest path; In a specific implementation, the edge between any node of a candidate feature and any node of a scheduling strategy reflects the direct correlation between the two nodes. Therefore, based on the knowledge graph, the length of the shortest path from the node of the i-th candidate feature to the node of the j-th scheduling strategy can be obtained. Each edge in the knowledge graph has a corresponding business attribute (such as relationship confidence), which can be used as the weight of each edge. Thus, the weights of all edges in the shortest path can be summed to obtain the total edge weight of the shortest path.

[0037] S2. The total edge weight and the length are input into a preset structural correlation calculation formula to obtain the structural correlation between the i-th candidate feature and the j-th scheduling strategy.

[0038] In a specific implementation process, the preset formula for calculating structural relevance is as follows:

[0039] in, This represents the structural relevance of the i-th candidate feature to the j-th scheduling strategy. Let represent the total edge weight of the shortest path between the node with the i-th candidate feature and the node with the j-th scheduling strategy. Let represent the length of the shortest path between the node with the i-th candidate feature and the node with the j-th scheduling policy. This represents the attenuation factor, which controls the intensity of the penalty for path length. The value can range from 0.1 to 1. The larger the value, the more severe the penalty for long-distance connections, and the smaller the value, the more tolerant long-distance connections are.

[0040] In a specific implementation, the semantic relevance of the i-th candidate feature to the j-th scheduling strategy can be determined as follows: S11. Convert the i-th candidate feature into feature text, and convert the j-th scheduling policy into policy text; In a specific implementation, semantic recognition technology can be used to convert the i-th candidate feature into feature text, and the j-th scheduling policy into policy text.

[0041] S12. Determine the semantic similarity between the feature text and the policy text as the semantic relevance of the i-th candidate feature to the j-th scheduling policy.

[0042] In a specific implementation, multiple similarity algorithms can be set, and corresponding weights can be assigned to each similarity algorithm. In this way, multiple similarity algorithms can be used to calculate multiple initial similarities between feature text and policy text, and each initial similarity can be weighted and summed to obtain the similarity between the i-th candidate feature and the j-th scheduling policy as the semantic relevance of the i-th candidate feature to the j-th scheduling policy.

[0043] In a specific implementation, the weight of each similarity algorithm can be dynamically adjusted as follows: The first step is to obtain the feature retention contribution of each similarity algorithm over a past time period; In a specific implementation process, the impact of the weight changes of each similarity algorithm on the final feature retention can be directly analyzed to obtain the feature retention contribution of each similarity algorithm over a past period.

[0044] Specifically, assuming K matches were performed within a past period, the similarity obtained from the k-th match can be compared with the adjusted similarity obtained after adjusting the p-th similarity algorithm. This yields the feature retention contribution of the p-th similarity algorithm at the k-th match. The K feature retention contributions of the p-th similarity algorithm are then summed and averaged to obtain the feature retention contribution of the p-th similarity algorithm over the past period. By iterating through each similarity algorithm, the feature retention contribution of each algorithm over the past period can be obtained.

[0045] The second step is to determine the weight adjustment coefficient for each similarity algorithm based on the preset correlation between contribution and weight adjustment coefficient. In a specific implementation process, different correlations between contribution and adjustment coefficients can be pre-set. In this way, after obtaining the feature retention contribution of each similarity algorithm, the weight adjustment coefficient of each similarity algorithm can be obtained.

[0046] It should be noted that a contribution threshold can be set. If the feature retention contribution is greater than this threshold, the weight adjustment coefficient is an amplification coefficient, and the larger the feature retention contribution, the larger the weight adjustment coefficient. If the feature retention contribution is less than or equal to the threshold, the weight adjustment coefficient is a reduction coefficient, and the smaller the feature retention contribution, the larger the reduction coefficient.

[0047] The third step is to multiply the original weight of each similarity algorithm by the weight adjustment coefficient as the adjusted weight.

[0048] In a specific implementation, the importance of the i-th candidate feature can be determined as follows: S21. Determine the strategy coverage breadth, information hub value, and business importance of the i-th candidate feature; In a specific implementation process, the "position" of a running feature node in a knowledge graph determines its inherent importance in policy generation, and its specific importance can be measured by the breadth of policy coverage and the value of information hubs.

[0049] Specifically, the number of nodes directly connected to the scheduling strategy for the i-th candidate feature can be determined; the ratio of this number of nodes to the total number of nodes for all scheduling strategies is used as the strategy coverage breadth. In other words, the more nodes directly connected to the scheduling strategy for the i-th candidate feature, the more scheduling strategies are available for that i-th candidate feature, and the greater its strategy coverage breadth.

[0050] All nodes of the scheduling strategies can be paired to obtain multiple scheduling strategy node pairs. The shortest path between the nodes of the two scheduling strategies in each pair is determined, and the number of paths passing through the i-th candidate feature among all shortest paths is counted. The ratio of this number of paths to the total number of shortest paths is used as the information hub value. In other words, when the shortest path of any scheduling strategy node pair passes through a node of the i-th candidate feature, that i-th candidate feature node is a "key bridge" between the two scheduling strategies. A larger number of paths passing through the i-th candidate feature among all shortest paths indicates that the transmission and evolution of many scheduling strategies require it, representing a deep correlation indicator for strategy generation. The ratio of the number of paths passing through the i-th candidate feature among all shortest paths to the total number of shortest paths is used as the information hub value.

[0051] When constructing a knowledge graph, the business importance of the i-th candidate feature can be recorded through methods such as expert scoring.

[0052] S22. The importance of the i-th candidate feature is obtained by weighted summation of the strategy coverage breadth, the information hub value, and the business importance.

[0053] In a specific implementation, the weights of strategy coverage breadth, information hub value, and business importance can be set according to actual needs. Then, the weighted sum of the strategy coverage breadth, information hub value, and business importance is obtained to determine the importance of the i-th candidate feature. Weights are then assigned to the i-th candidate feature to obtain a weighted feature. The higher the importance of the i-th candidate feature, the greater its assigned weight; conversely, the lower the importance of the i-th candidate feature, the smaller its assigned weight.

[0054] b1. Calculate the reciprocal of the average of the reciprocals of the structural relevance, the semantic relevance, and the importance, and determine the relevance of the i-th candidate feature to the j-th scheduling strategy; Specifically, we can calculate the reciprocal of each of the structural contribution, semantic relevance, and importance, then calculate the average, and then calculate the reciprocal of the average. This way, we can be more sensitive to lower values ​​and avoid being dominated by a single indicator.

[0055] c1. Sum all the relevance scores to obtain the strategy relevance score of the i-th candidate feature.

[0056] Specifically, the i-th candidate running feature has a contribution to each scheduling policy, and the sum of all the contributions can be used as the policy relevance of the i-th candidate running feature.

[0057] (2) Traverse all candidate features and all scheduling policy nodes in the feature vector to obtain the policy relevance of each candidate feature in the feature vector; (3) Retain candidate features whose policy relevance is greater than the preset relevance to obtain multiple target features.

[0058] In this embodiment, candidate features with a policy relevance greater than a preset relevance can be retained to obtain the multiple target features. In this way, the multiple candidate operating features of the extracted power equipment can be dimensionality reduced, and only the target operating features with a high relevance to the generated scheduling strategy can be retained, which makes the subsequent determination of the scheduling strategy of the photovoltaic-storage-charging integrated smart grid more efficient.

[0059] Based on the same general inventive concept, this invention also protects an integrated photovoltaic, energy storage and charging smart grid control system. The integrated photovoltaic, energy storage and charging smart grid control system provided by this invention will be described below. The integrated photovoltaic, energy storage and charging smart grid control system described below can be referred to in correspondence with the integrated photovoltaic, energy storage and charging smart grid control method described above.

[0060] Figure 2 This is a schematic diagram of the structure of the integrated photovoltaic, energy storage, and charging smart grid control system provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the integrated photovoltaic, energy storage and charging smart grid control system of this embodiment includes an acquisition module 21, an extraction module 22, a prediction module 23, a strategy generation module 24 and a control module 25.

[0061] Among them, the acquisition module 21 is used to acquire the operation data of the integrated photovoltaic, energy storage and charging smart grid; Extraction module 22 is used to extract features from the operating data to obtain the feature vector of the integrated photovoltaic, energy storage and charging smart grid; Prediction module 23 is used to input the feature vector of the integrated photovoltaic, energy storage and charging smart grid into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted status data of the energy storage device and the predicted status data of the electric vehicle. The strategy generation module 24, under preset constraints, uses the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle to solve the pre-constructed power grid dispatch model and determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid; wherein, the power grid dispatch model is a multi-objective optimization model that minimizes power grid operating costs, maximizes electric vehicle user benefits, and maximizes power grid stability.

[0062] The control module 25 is used to send power adjustment commands to the photovoltaic power station, charge and discharge commands to the energy storage device, and charging commands to the electric vehicle based on the scheduling strategy, and to display the operating status of the integrated photovoltaic-storage-charging smart grid through a visual interface.

[0063] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions stored in the memory 330 to execute the integrated photovoltaic-storage-charging smart grid control method.

[0064] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0065] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the integrated photovoltaic, energy storage and charging smart grid control method provided by the above methods.

[0066] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the integrated photovoltaic, energy storage, and charging smart grid control method provided by the above methods.

[0067] It should be noted that all relevant information that may be involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and is information that users actively provide or that is generated as a result of using the product / service, as well as information that is obtained with the user's authorization.

[0068] The information processed in this application may vary depending on the specific product / service scenario and should be based on the specific scenario in which the user uses the product / service. It may involve the user's account information, device information, or other related information. This application will treat the relevant information and its processing with the utmost diligence.

[0069] This application attaches great importance to the security of relevant information and has taken reasonable and feasible security protection measures that comply with industry standards to protect the relevant information and prevent it from being accessed, disclosed, used, modified, damaged or lost without authorization.

[0070] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0071] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart grid control method integrating photovoltaic, energy storage, and charging, characterized in that, include: Acquire operational data of the integrated photovoltaic, energy storage, and charging smart grid; Feature extraction is performed on the operational data to obtain the feature vector of the integrated photovoltaic, energy storage and charging smart grid; The feature vector of the integrated photovoltaic, energy storage and charging smart grid is input into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device and the predicted state data of the electric vehicle. Under preset constraints, the pre-constructed power grid dispatching model is solved using the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle, to determine the dispatching strategy of the integrated photovoltaic-storage-charging smart grid; wherein, the power grid dispatching model is a multi-objective optimization model that minimizes power grid operating costs, maximizes electric vehicle user benefits, and maximizes power grid stability. Based on the scheduling strategy, power adjustment commands are sent to the photovoltaic power station, charging and discharging commands are sent to the energy storage device, and charging commands are sent to the electric vehicle. The operation status of the integrated photovoltaic-storage-charging smart grid is displayed through a visual interface.

2. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 1, characterized in that, Also includes: Acquire the actual power generation of photovoltaic power plants, the actual status data of energy storage devices, and the actual charging status data of electric vehicles; Determine the first difference between the actual power generation of the photovoltaic power station and the predicted power data of the photovoltaic power station; Determine a second difference between the actual state data of the energy storage device and the predicted state data of the energy storage device; Determine the third difference between the actual charging state data of the electric vehicle and the predicted state data of the electric vehicle; Based on the first difference, the second difference, and the third difference, the parameters of the power grid dispatching model and / or the parameters of the prediction model are dynamically adjusted.

3. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 1, characterized in that, Also includes: Construct a knowledge graph for the integrated photovoltaic, energy storage, and charging smart grid; wherein the knowledge graph includes nodes for scheduling strategies; Based on the knowledge graph, the policy relevance of the i-th candidate feature in the feature vector is determined; where i = 1, 2, ..., N, and N is the total number of candidate features in the feature vector; the policy relevance is the sum of the relevances of the i-th candidate feature to all nodes of the scheduling policy. By traversing all candidate features and nodes of all scheduling policies in the feature vector, the policy relevance of each candidate feature in the feature vector is obtained; Candidate features with a policy relevance greater than a preset relevance are retained to obtain multiple target features.

4. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 3, characterized in that, Determining the policy relevance of the i-th candidate feature in the feature vector includes: Based on the knowledge graph, determine the structural relevance of the i-th candidate feature to the j-th scheduling strategy, the semantic relevance of the i-th candidate feature to the j-th scheduling strategy, and the importance of the i-th candidate feature; j = 1, 2, ..., M, where M is the total number of nodes in the scheduling strategy; Calculate the reciprocal of the average of the reciprocals of the structural relevance, the semantic relevance, and the importance, and determine the relevance of the i-th candidate feature to the j-th scheduling strategy; Sum all the relevance scores to obtain the strategy relevance score of the i-th candidate feature.

5. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 4, characterized in that, Determine the structural relevance of the i-th candidate feature to the j-th scheduling strategy, including: Based on the knowledge graph, determine the length of the shortest path from the node of the i-th candidate feature to the node of the j-th scheduling strategy and the total edge weight of the shortest path; The total edge weights and the length are input into a preset structural relevance calculation formula to obtain the structural relevance of the i-th candidate feature to the j-th scheduling strategy.

6. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 4, characterized in that, Determining the semantic relevance of the i-th candidate feature to the j-th scheduling strategy includes: The i-th candidate feature is converted into feature text, and the j-th scheduling policy is converted into policy text; The semantic similarity between the feature text and the policy text is determined as the semantic relevance of the i-th candidate feature to the j-th scheduling policy.

7. The integrated photovoltaic-storage-charging smart grid control method according to claim 6, characterized in that, Determining the semantic similarity between the feature text and the policy text includes: Multiple similarity algorithms are used to calculate multiple initial similarities between the feature text and the strategy text; The initial similarity is weighted and summed to obtain the comprehensive similarity between the feature text and the strategy text, which is then used as the semantic similarity.

8. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 7, characterized in that, The process of setting the weights for each similarity algorithm includes: Obtain the feature retention contribution of each similarity algorithm over a past time period; Based on the pre-defined correlation between contribution and weight adjustment coefficient, the weight adjustment coefficient for each similarity algorithm is determined. The product of the original weight of each similarity algorithm and the weight adjustment coefficient is used as the adjusted weight.

9. The integrated photovoltaic, energy storage, and charging smart grid control method according to claim 4, characterized in that, Determining the importance of the i-th candidate feature includes: Determine the strategy coverage breadth, information hub value, and business importance of the i-th candidate feature; The importance of the i-th candidate feature is obtained by weighted summation of the strategy coverage breadth, the information hub value, and the business importance.

10. A smart grid control system integrating photovoltaic, energy storage, and charging, characterized in that, include: The acquisition module is used to acquire operational data of the integrated photovoltaic, energy storage, and charging smart grid. The extraction module is used to extract features from the operating data to obtain the feature vector of the integrated photovoltaic, energy storage and charging smart grid; The prediction module is used to input the feature vector of the integrated photovoltaic, energy storage and charging smart grid into a pre-built prediction model to predict the predicted power data of the photovoltaic power station, the predicted status data of the energy storage device and the predicted status data of the electric vehicle. The strategy generation module, under preset constraints, uses the predicted power data of the photovoltaic power station, the predicted state data of the energy storage device, and the predicted state data of the electric vehicle to solve the pre-constructed power grid dispatch model and determine the dispatch strategy of the integrated photovoltaic-storage-charging smart grid; wherein, the power grid dispatch model is a multi-objective optimization model that minimizes power grid operating costs, maximizes electric vehicle user benefits, and maximizes power grid stability. The control module is used to send power adjustment commands to the photovoltaic power station, charge and discharge commands to the energy storage device, and charging commands to the electric vehicle based on the scheduling strategy, and to display the operating status of the integrated photovoltaic-storage-charging smart grid through a visual interface.

Images