Digitized power grid area operation optimization method, system, equipment, medium and product

Abstract

The invention relates to the technical field of power systems, and discloses a digital power grid area operation optimization method, system, device, medium and product, and the method comprises the steps: obtaining the operation data of a plurality of preset monitoring nodes in a power grid area, and carrying out the deep mining of the data; and performing clustering analysis on the operation characteristic data, dividing the power grid region into a plurality of sub-regions, and inputting the operation data corresponding to each sub-region into a digital twinborn model of the power grid region for real-time simulation. Based on real-time simulation data, a plurality of operation scenes are generated, electric energy loss minimization, load imbalance minimization, new energy consumption maximization, electric power cost minimization and power grid reliability maximization of a power grid area are taken as multi-optimization targets, an optimal operation scene is determined through the targets, and then an optimal operation strategy of the power grid area is formulated. Operation optimization can be rapidly carried out, and the stability of power grid operation is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular, to a method, system, device, medium and product for optimizing the operation of a digital power grid area. Background Art

[0002] With the continuous growth of power demand and the expansion of the power grid scale, traditional power grid management methods are difficult to meet the requirements of high efficiency, safety and reliability. The optimization of the operation of the digital power grid area realizes the real-time monitoring, optimization and control of the power grid operation state through advanced technologies such as intelligent sensors, cloud computing, and big data analysis, improving the operation efficiency and stability of the power grid.

[0003] In the existing solutions, the linkage of data transmission in each area of the power grid is poor, resulting in data transmission and processing delays, low real-time performance, and difficulty in quickly performing operation optimization, affecting the stability of the power grid. Summary of the Invention

[0004] In view of this, the present invention provides a method, system, device, medium and product for optimizing the operation of a digital power grid area, which solves the technical problem that in the existing solutions, the linkage of data transmission in each area of the power grid is poor, resulting in data transmission and processing delays, low real-time performance, and difficulty in quickly performing operation optimization, affecting the stability of the power grid.

[0005] The first aspect of the present invention provides a method for optimizing the operation of a digital power grid area, including:

[0006] Obtaining the operation data of multiple preset monitoring nodes in the power grid area, and performing data mining on the operation data to obtain operation characteristic data;

[0007] Performing clustering processing on the operation characteristic data, and dividing the power grid area into multiple sub-areas according to the clustering result;

[0008] Inputting the operation data corresponding to each of the multiple sub-areas into the digital twin model of the power grid area for real-time simulation to obtain simulation operation data;

[0009] Performing random sampling on the simulation operation data through Monte Carlo simulation to generate multiple operation scenarios;

[0010] According to the optimization goal of the power grid area, constructing a multi-optimization objective function; the optimization goals include one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability;

[0011] Optimize and solve the multi - optimization objective function according to multiple said operation scenarios, determine the optimal operation scenario based on the optimal solution, and determine the optimal operation strategy for the power grid area according to the optimal operation scenario.

[0012] Preferably, the method further includes: pre - processing the operation data; the pre - processing includes data noise filtering, redundant data filtering, abnormal data cleaning, data standardization, and acquisition time series synchronization.

[0013] Preferably, data mining is performed on the operation data to obtain operation feature data, including:

[0014] Obtain operation change feature data by performing wavelet transform on the operation data;

[0015] Perform load forecasting based on the operation change feature data to obtain load forecasting data;

[0016] Determine power quality feature data according to the operation change feature data;

[0017] Perform fault forecasting based on the operation change feature data to obtain fault forecasting data;

[0018] Integrate the load forecasting data, the power quality feature data, and the fault forecasting data to obtain the operation feature data.

[0019] Preferably, the clustering process is performed on the operation feature data, and the power grid area is divided into multiple sub - areas according to the clustering result, including:

[0020] Perform clustering on the operation feature data according to the feature types of the operation feature data to obtain multiple clusters; wherein, the feature types include load forecasting type, power quality type, and fault forecasting type;

[0021] Divide the power grid area according to multiple said clusters to obtain multiple said sub - areas.

[0022] Preferably, the method further includes:

[0023] Perform data sharing among nodes through blockchain technology according to the operation data of multiple preset monitoring nodes in the power grid area, and generate initial block operation data corresponding to each of the preset monitoring nodes;

[0024] Verify the integrity of the initial block operation data;

[0025] Use the initial block operation data that passes the integrity verification as the operation data.

[0026] Preferably, the method further includes:

[0027] Send the optimal operation strategy of the power grid area to the power grid area, operate according to the optimal operation strategy of the power grid area, and perform power flow optimization adjustment on the power grid area according to the operation results.

[0028] In a second aspect, the present invention also provides a digital power grid area operation optimization system, including:

[0029] A data mining module, configured to obtain operation data of multiple preset monitoring nodes in the power grid area, and perform data mining on the operation data to obtain operation characteristic data;

[0030] A power grid area module, configured to perform clustering processing on the operation characteristic data, and divide the power grid area into multiple sub-areas according to the clustering result;

[0031] A data simulation module, configured to input the operation data corresponding to multiple sub-areas into the digital twin model of the power grid area for real-time simulation to obtain simulation operation data;

[0032] A random sampling module, configured to perform random sampling on the simulation operation data through Monte Carlo simulation to generate multiple operation scenarios;

[0033] An optimization target module, configured to construct a multi-optimization target function according to the optimization target of the power grid area; the optimization target includes one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability;

[0034] An operation optimization module, configured to perform optimization solution on the multi-optimization target function according to multiple operation scenarios, determine the optimal operation scenario according to the optimal solution, and determine the optimal operation strategy of the power grid area according to the optimal operation scenario.

[0035] In a third aspect, the present invention also provides an electronic device, the electronic device includes a memory and a processor, a computer program is stored in the memory, and when the computer program is executed by the processor, the processor is caused to execute the steps of the digital power grid area operation optimization method as described in the first aspect.

[0036] In a fourth aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps of the digital power grid area operation optimization method as described in the first aspect are implemented.

[0037] Fifth aspect, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer is caused to execute the steps of the digital power grid area operation optimization method as described in the first aspect.

[0038] As can be seen from the above technical solutions, the present invention obtains the operation data of multiple preset monitoring nodes in the power grid area and deeply mines this data. By performing clustering analysis on the operation characteristic data, the power grid area is divided into several sub-areas, and the operation data corresponding to each sub-area is input into the digital twin model of the power grid area for real-time simulation. Based on the real-time simulation data, multiple operation scenarios are generated, and with the minimization of power loss in the power grid area, the minimization of load imbalance, the maximization of new energy consumption, the minimization of power cost, and the maximization of power grid reliability as multiple optimization objectives, the optimal operation scenario is determined through these objectives, and then the optimal operation strategy for the power grid area is formulated. By dividing sub-areas and combining digital twin simulation in the embodiments of the present application, real-time linkage of data transmission in each area of the power grid is achieved, significantly improving the real-time performance of data transmission, and being able to quickly perform operation optimization, effectively improving the stability of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is an application environment diagram of a digital power grid area operation optimization method provided by an embodiment of the present invention;

[0041] Figure 2 It is a flowchart of a digital power grid area operation optimization method provided by an embodiment of the present invention;

[0042] Figure 3 It is a schematic structural diagram of deploying self-organizing network technology and multi-agent system provided by an embodiment of the present invention;

[0043] Figure 4 It is a schematic structural diagram of a digital power grid area operation optimization system provided by an embodiment of the present invention;

[0044] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0046] The digital power grid area operation optimization method provided by the embodiments of this application can be applied to, for example Figure 1 the application environment shown. Among them, the terminal 101 communicates with the server 102 through the network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or placed in the cloud or other network servers. The terminal 101 or the server 102 obtains the operation data of multiple preset monitoring nodes in the power grid area, and performs data mining on the operation data to obtain operation feature data; performs clustering processing on the operation feature data, and divides the power grid area into multiple sub-areas according to the clustering result; inputs the operation data corresponding to the multiple sub-areas into the digital twin model of the power grid area for real-time simulation to obtain simulation operation data; performs random sampling on the simulation operation data through Monte Carlo simulation to generate multiple operation scenarios; constructs a multi-optimization objective function according to the optimization objectives of the power grid area; the optimization objectives include one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability; performs optimization solution on the multi-optimization objective function according to the multiple operation scenarios, determines the optimal operation scenario according to the optimal solution, and determines the optimal operation strategy of the power grid area according to the optimal operation scenario.

[0047] The terminal 101 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, etc.

[0048] The server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0049] As Figure 2 shown, the embodiments of this application provide a digital power grid area operation optimization method. Taking the method applied to Figure 1 the terminal 101 or the server 102 in as an example, it includes the following steps S1 to S6. Among them:

[0050] Step S1: Obtain the operation data of multiple preset monitoring nodes in the power grid area, and perform data mining on the operation data to obtain operation feature data.

[0051] Among them, the pre-set monitoring nodes can be the key nodes of the power grid area. The key nodes and areas of the power grid refer to the places and equipment positions that have a greater impact on the power grid operation and are crucial for power dispatching and operation status. They include substations, distribution stations, transmission lines and switch stations, load centers, power quality monitoring nodes, etc.

[0052] Deploying high-precision intelligent sensors at the key nodes and areas of the power grid can achieve the acquisition of parameters such as current, voltage, and temperature, and generate initial monitoring data. The deployment of high-precision intelligent sensors is the basis of the present invention, and they can accurately capture the subtle changes in the power system. Intelligent sensors such as fiber optic sensors and microelectromechanical systems (MEMS) sensors have high sensitivity and high precision, and can work stably in harsh environments. Fiber optic sensors use the change in the refractive index of light to monitor temperature and pressure, while MEMS sensors monitor current and voltage through micro-mechanical structures. These sensors generate initial monitoring data in real time to ensure the comprehensive monitoring of the power grid operation status.

[0053] Among them, for the operation data of substations, it includes current, voltage, temperature, transformer load rate, short-circuit fault current, etc. For example: In a 220 kV main substation, high-precision sensors are deployed to monitor the operating temperature and current load status of the main transformer to prevent equipment damage caused by overload. In a 110 kV regional substation, the load conditions of each feeder are monitored to optimize load dispatching and avoid overloading of the regional power grid.

[0054] For the operation data of distribution stations, it includes: voltage, current, frequency, switch status, transformer load rate, etc. of distribution equipment. For example: In urban distribution stations, the load conditions of distribution transformers are monitored to optimize the low-voltage distribution network and prevent overload tripping. In rural distribution stations, the voltage stability of low-voltage lines is detected to prevent excessive voltage deviation from affecting user equipment.

[0055] The operation data of transmission lines and switch stations includes: conductor temperature, current load, external environment influence (wind speed, ice and snow load), insulator pollution degree, etc. For example: On high-voltage transmission lines (500 kV level), conductor temperature monitoring sensors are deployed to detect the risk of line overheating and give early warnings of grounding hazards caused by conductor expansion. In urban underground cable tunnels, humidity and temperature sensors are deployed to prevent cable insulation aging caused by high-temperature and humid environments.

[0056] The operation data of load centers includes: real-time power demand, voltage fluctuation, load prediction data, fault prediction. For example: In large industrial parks, the operation status of high-power equipment is monitored to prevent local power grid instability caused by power surges. In commercial centers, the distribution strategy is adjusted through load monitoring to optimize the power consumption peak dispatching.

[0057] The operation data of the power quality monitoring node includes: harmonics, voltage sag, voltage flicker, frequency deviation, etc. For example: In the high-speed rail power supply system, power quality monitoring equipment is deployed to prevent harmonic pollution caused by high-power inverters. At the power input point of the data center, voltage stability is detected to ensure stable power supply to the server.

[0058] Among them, the operation data is preprocessed.

[0059] Exemplarily, data preprocessing is performed through edge computing nodes, including data noise filtering, redundant data filtering, abnormal data cleaning, data standardization, and acquisition time series synchronization.

[0060] Among them, data noise filtering adopts a low-pass filtering algorithm. The low-pass filter allows low-frequency signals to pass through while blocking high-frequency noise, thereby smoothing the signal and enhancing the accuracy of the data.

[0061] Redundant data filtering uses a data compression algorithm, which reduces data redundancy, reduces data volume, and improves the efficiency of data transmission and storage.

[0062] Abnormal data cleaning is to eliminate invalid data using rule-based methods (such as setting thresholds to detect abnormal current and voltage) or statistical methods (such as standard deviation to remove outliers).

[0063] Data standardization is the process of normalizing or standardizing different types of data (such as temperature, current, voltage) with different numerical ranges to unify the data into the same scale range.

[0064] The synchronization of acquisition time series is due to the fact that the data sources include different sensors, edge computing nodes, etc., and the timestamps may be inconsistent, so time alignment is required.

[0065] It can be understood that preliminary processing through edge computing nodes has multiple effects. First, it reduces the amount of data transmitted to the cloud computing platform, reduces the burden of cloud computing, and improves the response speed of the entire system. Second, the data after preliminary processing is more accurate and reliable, providing a solid foundation for subsequent in-depth data analysis. In addition, the distributed processing capabilities of edge computing nodes ensure the robustness and flexibility of the system, allowing power grid management to respond and adjust in a timely manner.

[0066] In a specific embodiment, a high-precision optical fiber sensor deployed in a substation acquires the temperature of a transformer. When the temperature data exceeds a set threshold, the sensor generates initial monitoring data and sends it to an edge computing node. The edge computing node first uses a low-pass filtering algorithm to remove high-frequency noise to ensure the smoothness and accuracy of the temperature data, then applies a data compression algorithm to reduce the data volume, and finally generates preliminary processed data and quickly transmits it to a cloud computing platform for further analysis. This acquisition and processing mechanism can effectively prevent faults caused by transformer overheating and improve the stability and security of the power system.

[0067] In summary, by deploying high-precision intelligent sensors at key nodes and regions of the power grid and using edge computing nodes to preliminarily process the initial monitoring data, the present invention realizes real-time and accurate monitoring and data processing of the operating state of the power grid. The application of technical means such as noise filtering and redundant data removal ensures the high quality and transmission efficiency of the data, thus greatly improving the intelligent level and reliability of power grid management.

[0068] Among them, data mining technology can extract hidden, undiscovered but valuable information and knowledge for decision-making from a large amount of data. In the present invention, data mining is mainly used to reveal the core characteristics of power grid operation, and feature selection is to select the most representative features from the original data, and these features can accurately reflect the main conditions of power grid operation.

[0069] For example, in load forecasting, data mining can reveal the periodic laws, seasonal trends of load changes, and the impacts of emergencies. In power quality analysis, data mining can identify the occurrence frequencies and durations of power quality problems such as harmonics, voltage sags, and voltage flickers. In fault prediction, data mining can correlate the operating data before a fault and the fault type to construct a fault warning model.

[0070] Step S2: Perform clustering processing on the operation feature data, and divide the power grid area into multiple sub-areas according to the clustering results.

[0071] Among them, the clustering algorithm is used to divide the power grid area into different sub-areas. The clustering algorithm can group regions with similar characteristics into one category according to the operation feature data, which is convenient for customized management and optimization for different regions. The sub-area analysis data includes load forecasting, fault prediction, and operating status of each sub-area, providing detailed information for further optimization and decision-making.

[0072] Step S3: Input the operation data corresponding to multiple sub-areas into the digital twin model of the power grid area for real-time simulation to obtain simulation operation data.

[0073] Among them, the digital twin model of the power grid area is a highly refined virtual model, which is constructed based on the actual power grid structure and operation parameters and can reflect the operation status of the power grid in real time. This model integrates a large number of physical, electrical, and control parameters, as well as the topological structure and equipment characteristics of the power grid, making the simulation results highly consistent with the actual operation of the power grid. By inputting the operation data of the sub-region into the digital twin model, the performance of the power grid under different operation strategies can be simulated, and then the effectiveness and feasibility of various strategies can be evaluated.

[0074] Step S4: Randomly sample the simulation operation data through Monte Carlo simulation to generate multiple operation scenarios.

[0075] Among them, Monte Carlo simulation is a stochastic simulation method based on probability statistics. It randomly samples the simulation operation data to generate multiple possible operation scenarios. These scenarios cover the operation conditions of the power grid under different conditions, providing a rich data basis for subsequent optimization and solution. Through Monte Carlo simulation, various uncertainties and fluctuations in the power grid operation can be considered, making the optimization results closer to the actual situation and improving the reliability and practicality of the optimization strategy.

[0076] Step S5: Construct a multi-objective optimization function according to the optimization objectives of the power grid area; the optimization objectives include one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability.

[0077] Among them, the multi-objective optimization algorithm is an optimization technology that can handle multiple conflicting objective functions. In power grid management, the main optimization objectives include meeting power demand, efficient allocation of resources, and stability of power grid operation. The multi-objective optimization algorithm constructs a multi-objective optimization model, comprehensively considers the weights and priorities of each objective, and finds a global optimal solution. Commonly used multi-objective optimization algorithms include genetic algorithms, multi-objective particle swarm optimization algorithms, etc.

[0078] In the embodiments of this application, aiming at minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing grid reliability in the power grid area, by integrating these objective functions into a comprehensive optimization model, the balance and coordination among multiple objectives are achieved. The objective of minimizing power loss aims to reduce the energy loss during the power grid transmission process and improve the energy utilization efficiency. The objective of minimizing load imbalance focuses on the load distribution in different areas of the power grid, ensuring the balance of power supply, and avoiding local overloading or underloading phenomena. The objective of maximizing new energy consumption encourages the power grid to absorb more renewable energy, reduce the dependence on traditional energy, and promote green and sustainable development. The objective of minimizing power cost aims to reduce the cost of power production and transmission by optimizing the power grid operation strategy and improve the economic benefits. The objective of maximizing grid reliability emphasizes ensuring that the power grid can operate stably under various operating conditions and improving the reliability and safety of power supply.

[0079] When constructing the multi-objective function, it is necessary to consider the trade-offs and compromises among various objectives. For example, minimizing power loss and minimizing power cost may conflict with maximizing new energy consumption to a certain extent because the access of new energy may require additional power grid equipment and operation and maintenance costs. Similarly, minimizing load imbalance may have a certain contradiction with the objective of maximizing grid reliability because sometimes in order to ensure reliability, a certain degree of load balance needs to be sacrificed. Therefore, when constructing the multi-objective function, it is necessary to comprehensively consider the priorities and weights of various objectives, and through reasonable algorithms and model solutions, find an operation strategy that can meet the requirements of multiple objectives and achieve the overall optimum.

[0080] Among them, the multi-objective function can be expressed as:

[0081]

[0082] In the formula, F represents the function value, 、 、 、 、 are all weights, is the total power loss, is the load balance value, is the new energy consumption, is the power cost, is the reliable operation coefficient.

[0083] Among them,

[0084]

[0085] =

[0086]

[0087]

[0088]

[0089] In the formula, is the total line resistance of sub-region i, N is the number of sub-regions, is the current passing through sub-region , is the load demand of sub-region , is the power supply response of sub-region , is the wind power output of sub-region , is the PV power output of sub-region , is the power generation cost of sub-region , is the transmission loss cost of sub-region , is the average fault repair time of sub-region ; is the average failure-free operation time of sub-region ;

[0090] Among them, =

[0091] =

[0092] In the formula, is the power generation power, is the power generation price, is the transmission power, is the transmission price.

[0093]

[0094] In the formula, , , are all empirical coefficients, reflects the influence degree of the power flow change on the repair time, reflects the effect of the equipment complexity on the repair time, is a basic time constant, representing some fixed maintenance operation times, etc., is the maximum power value that appears on a certain key line or equipment in the power flow after the fault occurs, is the active power value of sub-region i under normal operating conditions. is the equipment complexity factor, which is a dimensionless number with a value ranging from 1 to 2.

[0095] Step S6: Optimize and solve the multi-objective function according to multiple operating scenarios, determine the optimal operating scenario based on the optimal solution, and determine the optimal operating strategy for the power grid area according to the optimal operating scenario.

[0096] Among them, the method of optimizing and solving the multi-objective function can adopt genetic algorithm or particle swarm optimization algorithm, or can also adopt reinforcement learning algorithm. The parameters of the optimal operating scenario include the line power flow parameters (current, voltage), load demand, power supply response, wind power output, photovoltaic power output, power generation power, transmission power of each sub-region, and the active power value of each sub-region under normal operating conditions.

[0097] By combining the multi-objective optimization algorithm and the reinforcement learning algorithm, the digital power grid area management method can achieve global optimization of power demand, resource allocation, and operating status. The multi-objective optimization algorithm provides a globally optimal power distribution strategy to ensure the efficient operation of the power grid and the rational utilization of resources.

[0098] It should be noted that in the embodiments of this application, the operation data of multiple preset monitoring nodes in the power grid area are obtained and deeply mined. Through cluster analysis of the operation characteristic data, the power grid area is divided into several sub-regions, and the operation data corresponding to each sub-region are input into the digital twin model of the power grid area for real-time simulation. Based on the real-time simulation data, multiple operating scenarios are generated, and the minimum power loss, minimum load imbalance, maximum new energy consumption, minimum power cost, and maximum power grid reliability of the power grid area are used as multi-objective optimization goals. The optimal operating scenario is determined through these goals, and then the optimal operating strategy for the power grid area is formulated. In the embodiments of this application, by dividing sub-regions and combining digital twin simulation, the real-time linkage of data transmission in each area of the power grid is realized, the real-time performance of data transmission is significantly improved, and operation optimization can be quickly carried out, effectively improving the stability of power grid operation.

[0099] In some embodiments, data mining is performed on the operation data to obtain operation characteristic data, including:

[0100] Step S201: Obtain operation change characteristic data by performing wavelet transform on the operation data;

[0101] Among them, by performing wavelet transform on the operation data, the local change characteristics in the data can be effectively extracted. Wavelet transform can decompose a signal into wavelet coefficients with different frequencies and positions, thereby revealing the changes in the signal at different time scales. In the present invention, by performing wavelet transform on the power grid operation data, key features such as load changes and fault precursors can be extracted, providing strong support for subsequent clustering processing and operation optimization. The operation change feature data can reflect the dynamic characteristics of the power grid under different operation states and is the basis for achieving precise monitoring and optimized management.

[0102] Step S202: Perform load forecasting based on the operation change feature data to obtain load forecasting data.

[0103] Among them, a time series forecasting model (such as the Autoregressive Integrated Moving Average Model (ARIMA), Long Short-Term Memory (LSTM)) can be used to forecast the future electricity load. Specifically, based on the historical load data and operation change feature data, a load forecasting model is constructed. The load forecasting model can learn the law of the power grid load changing over time and take into account the impact of special events or weather conditions on the load. By inputting the current and recent operation change feature data, the load forecasting model can output the load forecasting data for a period of time in the future.

[0104] Step S203: Determine the power quality feature data based on the operation change feature data.

[0105] Among them, determining the power quality feature data based on the operation change feature data includes power quality, power factor, and load distribution. Through in-depth analysis of the operation data, the features related to power quality are extracted. Power quality is an important indicator for measuring the operation state of the power grid and directly reflects the stability and reliability of power supply. The power factor reflects the proportional relationship between the useful power and the total power in the power grid and is a key factor for evaluating the power grid efficiency. The load distribution describes the power demand situation in different regions of the power grid and is of great significance for optimizing power distribution and reducing line losses. The equipment health reflects the operation state and lifespan of the power grid equipment and is an important basis for formulating equipment maintenance and replacement plans.

[0106] Step S204: Perform fault forecasting based on the operation change feature data to obtain fault forecasting data.

[0107] Among them, a supervised learning model is used to perform fault prediction using operation change feature data. By deeply analyzing and learning past fault records and the corresponding operation data, this model can effectively identify potential patterns and regularities of fault occurrence. Utilizing this learning ability, when the model monitors and analyzes the current operation data in real time, it can predict and alert potential fault areas in advance. For example, when the model detects that the operation parameters of a certain substation exhibit characteristics similar to those during past faults, it will immediately issue an alarm signal. Such a warning mechanism enables relevant maintenance personnel to promptly inspect and perform necessary maintenance on this substation, thereby effectively preventing possible faults and ensuring the stable operation of the system.

[0108] Step S205: Integrate the load prediction data, power quality feature data, and fault prediction data to obtain operation feature data.

[0109] In some embodiments, the operation feature data is subjected to clustering processing, and the power grid area is divided into multiple sub-areas according to the clustering results, including:

[0110] Step S301: Perform clustering processing on the operation feature data according to the feature types of the operation feature data to obtain multiple clusters; among them, the feature types include load prediction type, power quality type, and fault prediction type;

[0111] Step S302: Divide the power grid area according to the multiple clusters to obtain multiple sub-areas.

[0112] Exemplarily, perform clustering processing on the operation feature data according to the load prediction type, and divide the power grid area to obtain multiple sub-areas, including:

[0113] Industrial load areas (such as manufacturing industries, chemical industrial parks): High power demand and periodic fluctuations.

[0114] Residential load areas (such as residential areas): Obvious difference in load between day and night, with obvious morning and evening peaks.

[0115] Commercial load areas (such as shopping malls, office buildings): High load during the day on weekdays and low load at night.

[0116] New energy consumption capacity:

[0117] High new energy access areas (wind farms, photovoltaic power stations): Grid dispatching needs to consider the volatility of renewable energy.

[0118] Conventional power supply areas (main grid power supply areas): Mainly rely on traditional thermal power or hydropower, with relatively stable load.

[0119] Cluster the operation characteristic data according to the power quality type, and divide the power grid area to obtain multiple sub-areas, including:

[0120] High-quality power supply area: Such as the core power grid in the city, with small voltage fluctuations, a power factor close to 1, and low harmonic content. Areas with poor power quality: Such as high-speed rail power supply, wind power grid connection, etc., where voltage instability and serious harmonic pollution are caused by large power load fluctuations, power feedback, etc.

[0121] Cluster the operation characteristic data according to the fault prediction type, and divide the power grid area to obtain multiple sub-areas, including:

[0122] High fault frequency area:

[0123] Areas where substations and distribution lines have experienced multiple short circuits, overloads, switch tripping and other accidents.

[0124] For example: In old power grid areas, due to equipment aging, the failure rate is relatively high.

[0125] Low fault area:

[0126] Areas that have been operating stably in recent years and have not experienced large-scale faults, such as newly built power grid areas.

[0127] In some embodiments, the method further includes:

[0128] Step S21: Share the data between each node through blockchain technology according to the operation data of multiple preset monitoring nodes in the power grid area, and generate initial block operation data corresponding to each preset monitoring node;

[0129] Step S22: Verify the integrity of the initial block operation data;

[0130] Step S23: Use the initial block operation data that passes the integrity verification as the operation data.

[0131] Blockchain technology ensures the security and credibility of power grid data. Each power grid node records and shares data through blockchain technology, generates initial block data, and verifies and stores it through the blockchain network, thus generating verified block data. The application of blockchain technology can ensure the authenticity and integrity of data, and prevent data from being tampered with and lost.

[0132] Blockchain realizes the secure storage and transmission of data through encryption algorithms and consensus mechanisms. Each power grid node can generate and record data, and these data are packaged into blocks and verified through the blockchain network. Consensus mechanisms (such as proof of work and proof of stake) ensure that each node in the blockchain network reaches a consensus on the consistency of the data, thus ensuring the authenticity and immutability of the data.

[0133] In power grid management, the initial block data generated by each power grid node is verified and stored through the blockchain network to generate verified block data. This data includes operating parameters such as current, voltage, and temperature, as well as load management and fault handling information. Blockchain technology ensures the security and integrity of this data during transmission and storage.

[0134] In digital power grid management, blockchain technology is used to ensure the security, integrity, and traceability of power grid data. The blockchain network consists of multiple power grid nodes, and each node stores, verifies, and shares power grid operation data to ensure that the data cannot be tampered with.

[0135] Verification of block data. When a power grid node generates initial block operation data (including current, voltage, temperature, load management, fault handling information, etc.), the blockchain network will execute the following verification process:

[0136] Data integrity verification. Use a hash function (SHA-256) to calculate the hash value of each block of data and link it to the hash value of the previous block to ensure that the data has not been tampered with. For example, for current and voltage data, the hash value of the block data is calculated as follows:

[0137]

[0138] where is the hash value of the current block; is the hash value of the previous block; is the power grid data stored in the current block.

[0139] Adopt a hybrid consensus mechanism of Proof of Work (PoW) and Proof of Stake (PoS):

[0140] PoW (Proof of Work): Ensure the computational security of block data and prevent tampering.

[0141] PoS (Proof of Stake): Based on the historical data contributions of each power grid node for verification, improve efficiency.

[0142] Adopt the Practical Byzantine Fault Tolerance (PBFT) mechanism. Through multiple power grid nodes to reach a consensus on the same data, avoid single point of failure. If the data of a certain power grid node is abnormal (such as voltage and current exceeding the standard), multiple nodes will compare historical data and eliminate the abnormal values.

[0143] Once the block data passes the verification of the blockchain network, the cloud computing platform will collect all the verified block data and perform data aggregation, cleaning, and analysis:

[0144] Data aggregation, classify data from different power grid regions, and perform time series alignment, for example: load management data (sampled every 15 minutes), fault handling data (recorded during anomalies).

[0145] Data cleaning: Filter out abnormal data points (such as sensor false alarms), use Kalman filtering to smooth current and voltage curves, and reduce errors.

[0146] Data analysis, pattern recognition: Detect the operating state of the power grid, such as load patterns, fault trends; Anomaly detection: Identify problems such as load overload, equipment overheating, and line short circuits; Trend prediction: Use LSTM (Long Short-Term Memory Network) to predict future load changes; Use XGBoost to predict the probability of faults occurring.

[0147] In some embodiments, the method further includes:

[0148] Send the optimal operation strategy of the power grid region to the power grid region, operate according to the optimal operation strategy of the power grid region, and perform power flow optimization adjustment on the power grid region according to the operation results.

[0149] Among them, use AC power flow calculation (Alternating Current Optimal Power Flow, AC-OPF), when the load of the transmission line is close to the upper limit, adjust the power flow direction to avoid overload:

[0150]

[0151] Among them, is the injected power, , is the node voltage; , is the line admittance; is the phase angle difference.

[0152] Among them, through continuous cycling and iteration of the feedback data of the optimal operation strategy of the power grid region, continuous optimization of power grid management is achieved. The power grid nodes make real-time adjustments according to the optimized feedback data, forming a dynamic feedback and optimization loop. This loop process ensures that the power grid management system can quickly respond to environmental changes and fluctuations in the operating state, thereby maintaining an efficient and stable operating state.

[0153] In an exemplary embodiment, in order to more clearly clarify a digital power grid region operation optimization method provided by the embodiments of the present application, the following uses a specific embodiment to specifically illustrate the digital power grid region operation optimization method.

[0154] Deploy high-precision intelligent sensors at key nodes and regions of the power grid to obtain current, voltage, and temperature parameters, generate initial monitoring data, and perform preliminary processing on the initial monitoring data through edge computing nodes to filter out noise and redundant data and generate preliminarily processed data.

[0155] The preliminarily processed data is subjected to noise filtering and redundant data removal through edge computing nodes, specifically including the processing of current data, voltage data, and temperature data. Low-pass filtering algorithm is used for noise filtering, and data compression algorithm is used for redundant data removal.

[0156] Transmit the preliminarily processed data to the cloud computing platform for data mining to generate mined feature data, and use clustering algorithms to divide the power grid area into different management sub-regions based on the mined feature data. Conduct customized analysis for each sub-region to generate sub-region analysis data, input the mined feature data and the mined feature data of the sub-region into a multi-layer digital twin model to construct the overall power grid model data and sub-region model data, and perform real-time simulation to generate simulation data.

[0157] Among them, data mining includes:

[0158] Analyze current and voltage signals through wavelet transform to extract short-term change features. Analyze harmonic components through Fourier transform to evaluate power quality. Use deep learning models (such as LSTM, Transformer) to extract time series features from historical data to predict load trends.

[0159] Load prediction model: Use time series prediction models (such as ARIMA, LSTM) to predict future electricity loads and adjust distribution strategies in advance.

[0160] Fault prediction model: Use supervised learning models (such as Support Vector Machine (SVM), random forest) to analyze potential fault risks based on historical fault data.

[0161] Voltage stability analysis: Evaluate the voltage stability of different regions based on modal analysis method to determine the regions prone to instability.

[0162] The final outputs of data mining include:

[0163] Load prediction data: Predict the power demands of each region in future time periods to optimize power supply scheduling.

[0164] Fault prediction data: Based on abnormal voltage and current fluctuations, predict possible short-term faults and give early warnings.

[0165] Operating status data: Include key parameters such as power quality, power factor, load distribution, and equipment health.

[0166] Through the above data mining, digital power grid regional management can achieve accurate prediction of future power grid loads, early warning of potential faults, and comprehensive assessment of the overall operating status. This not only improves the management efficiency and safety of the power grid but also provides a solid technical foundation for the intelligent operation of the power grid. Power grid managers can optimize the allocation of power resources according to the prediction and analysis results, promptly handle potential faults, and ensure the stability and reliability of power supply.

[0167] The cloud computing platform uses clustering algorithms to divide the entire power grid area into multiple management sub-areas. The clustering algorithm plays a key role in this invention. By analyzing and dividing the load characteristics, fault history, and operating parameters of each sub-area, it realizes the refined management of the power grid. The clustering algorithm is an unsupervised learning algorithm aimed at grouping data according to its inherent similarity, making the data within the same group highly similar and the data between different groups significantly different. In this invention, the clustering algorithm divides the power grid into multiple management sub-areas according to the specific parameters of each sub-area, and each sub-area has similar load characteristics, fault history, and operating parameters.

[0168] The principle of regional division by the clustering algorithm lies in the differences in load characteristics, fault occurrence frequencies, and operating parameters among different regions of the power grid. Load characteristics refer to the changes in power demand of the power grid at different times. The fault history records the types and frequencies of faults that occurred in each region in the past. Operating parameters include operating state data such as voltage, current, and temperature. The clustering algorithm comprehensively analyzes these parameters and groups regions with similar characteristics into the same category, making the management and optimization of each sub-area more accurate and effective.

[0169] The generated sub-area analysis data includes load prediction, fault prediction, and operating status. These data provide a basis for the further optimization and management of the power grid. The load prediction of the sub-area is based on the time series prediction model, the fault prediction is generated through the supervised learning model, and the operating status is determined through the pattern recognition algorithm. These analysis data enable managers to deeply understand the specific conditions of each sub-area and formulate targeted management strategies.

[0170] In a specific embodiment, assume that a certain power grid covers multiple urban areas, and there are significant differences in power demand and operating status in each area. Through the clustering algorithm, based on the load characteristics of each area (such as the power demand fluctuations during the day and night), fault history (such as the types of faults that frequently occurred in some area substations), and operating parameters (such as voltage stability and temperature fluctuations), the power grid is divided into several sub-areas.

[0171] By using a clustering algorithm, the power grid is divided into different management sub - regions, and detailed sub - region analysis data is generated. The digital power grid regional management method realizes the refinement and intelligence of power grid management. The sub - region analysis data includes load forecasting, fault forecasting, and operating status, providing in - depth insights and decision - making basis for managers. In this way, power grid managers can formulate targeted management strategies according to the specific conditions of different sub - regions, improve the efficiency and reliability of power grid operation, reduce the risk of faults, and ensure the stability and security of power supply.

[0172] In power grid simulation, Monte Carlo simulation generates a large number of operating scenarios by performing multiple random samplings and calculations to simulate the operating data of the power grid under different load and fault conditions.

[0173] The Monte Carlo simulation method is used to evaluate the fault risk in this region under high load. By performing multiple random samplings and calculations, different combinations of load changes and equipment failures are simulated to generate the risk assessment results for this region. The simulation results show that in some high - load situations, some equipment in the substation may overheat, leading to an increased risk of faults.

[0174] Based on the simulation results, the multi - layer digital twin system generates optimized operating strategies, suggesting enabling backup power supplies during high - load periods and performing preventive maintenance on key equipment. At the same time, the system generates detailed fault handling plans, listing possible fault situations and corresponding handling steps. In addition, the risk assessment results provide the occurrence probabilities of various faults and their possible impacts, providing comprehensive decision - making support for managers.

[0175] Through the application of the multi - layer digital twin model, a comprehensive simulation and optimization of the power grid can be achieved, enabling the simulation process to simultaneously evaluate the physical performance and operating risks of the power grid, and providing scientific operating strategies and fault handling plans. This not only improves the operating efficiency and security of the power grid but also provides a solid technical foundation for the intelligent management of the power grid. Managers can make scientific and reasonable management decisions based on the simulation - optimized data to ensure the stability and reliability of power supply.

[0176] As Figure 3 shown, self - organizing network technology and multi - agent systems are deployed at each power grid node. Each intelligent agent receives the simulation - optimized data and performs self - adjustment and optimization. Self - organizing network technology and multi - agent systems are important technical means for realizing digital power grid regional management. Self - organizing network technology allows power grid nodes to autonomously coordinate and manage without centralized control, making the power grid system highly flexible and self - adaptable. Each power grid node is equipped with an intelligent agent, which performs self - adjustment and optimization by receiving the simulation - optimized data. An intelligent agent is a distributed artificial intelligence system that can make independent decisions based on the received data and cooperate with other intelligent agents.

[0177] The simulation optimization data is generated by a multi-layer digital twin system. The intelligent agent self-adjusts based on this data to generate power distribution data, load management data, and fault handling data. The power distribution data is used to optimize the allocation of power resources to ensure that the power demands of each region are met. The load management data is used to balance the grid load and avoid overloading and underloading situations. The fault handling data provides preventive and response measures for faults to ensure the reliable operation of the grid.

[0178] Multi-objective optimization algorithms (such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO)) are used to coordinate the power demand, resource allocation, and operating status of the power grid to ensure the stable, efficient, and economic operation of the power grid. The optimization objectives include minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing grid reliability.

[0179] Through the genetic algorithm, the multi-objective optimization algorithm continuously optimizes the operating parameters of the power grid through selection, crossover, and mutation mechanisms to find the optimal operating scheme.

[0180] Based on the same inventive concept, the embodiment of the present application also provides a digital grid regional operation optimization system for implementing the digital grid regional operation optimization method involved above.

[0181] The implementation solution provided by this system to solve problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the digital grid regional operation optimization system provided below can refer to the limitations on the digital grid regional operation optimization method in the above text and will not be elaborated here.

[0182] As Figure 4 shown, the embodiment of the present application provides a digital grid regional operation optimization system, including:

[0183] A data mining module 100, configured to obtain the operation data of multiple preset monitoring nodes in the grid area and perform data mining on the operation data to obtain operation feature data;

[0184] A grid area module 200, configured to perform clustering processing on the operation feature data and divide the grid area into multiple sub-areas according to the clustering result;

[0185] A data simulation module 300, configured to input the operation data corresponding to each of the multiple sub-areas into the digital twin model of the grid area for real-time simulation to obtain simulation operation data;

[0186] A random sampling module 400, configured to perform random sampling on simulation operation data through Monte Carlo simulation to generate multiple operation scenarios;

[0187] An optimization objective module 500, configured to construct a multi-optimization objective function according to the optimization objectives of the power grid area; the optimization objectives include one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability;

[0188] An operation optimization module 600, configured to perform optimization solution on the multi-optimization objective function according to multiple operation scenarios, determine the optimal operation scenario according to the optimal solution, and determine the optimal operation strategy of the power grid area according to the optimal operation scenario.

[0189] In some embodiments, the system includes: a preprocessing module, configured to preprocess the operation data; the preprocessing includes data noise filtering, redundant data filtering, abnormal data cleaning, data standardization, and acquisition time series synchronization.

[0190] In some embodiments, a data mining module 100, configured to:

[0191] Obtain operation change feature data by performing wavelet transform on the operation data;

[0192] Perform load forecasting according to the operation change feature data to obtain load forecasting data;

[0193] Determine power quality feature data according to the operation change feature data;

[0194] Perform fault forecasting according to the operation change feature data to obtain fault forecasting data;

[0195] Integrate the load forecasting data, power quality feature data, and fault forecasting data to obtain operation feature data.

[0196] In some embodiments, a power grid area module 200, configured to:

[0197] Perform clustering processing on the operation feature data according to the feature types of the operation feature data to obtain multiple clusters; wherein, the feature types include load forecasting type, power quality type, and fault forecasting type;

[0198] Divide the power grid area according to the multiple clusters to obtain multiple sub-areas.

[0199] In some embodiments, the system further includes: a data sharing module, configured to:

[0200] Perform data sharing among the nodes according to the operation data of multiple preset monitoring nodes in the power grid area through blockchain technology to generate initial block operation data respectively corresponding to the preset monitoring nodes;

[0201] Perform integrity verification on the initial block operation data;

[0202] Use the initial block operation data that passes the integrity verification as the operation data.

[0203] In some embodiments, the system further includes: an optimization and adjustment module, configured to send the optimal operation strategy of the power grid area to the power grid area, operate according to the optimal operation strategy of the power grid area, and perform power flow optimization and adjustment on the power grid area according to the operation results.

[0204] As Figure 5 shown, an embodiment of the present application provides an electronic device. The electronic device 10 includes a memory 20 and a processor 30. A computer program is stored in the memory 20. When the computer program is executed by the processor 30, the processor 30 is caused to execute the steps of the digital power grid area operation optimization method in the above embodiments.

[0205] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the steps of the digital power grid area operation optimization method in the above embodiments are implemented.

[0206] An embodiment of the present application provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. Wherein, when the program instructions are executed by a computer, the computer is caused to execute the steps of the digital power grid area operation optimization method in the above embodiments

[0207] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, electronic device, computer storage medium, and computer program product can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0208] It should be noted that the terms "including" and "having" in the specification and claims of the present invention and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0209] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, 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. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0210] In several embodiments provided by the present invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0211] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0212] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0213] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in various embodiments of the present invention through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (English full name: Read-Only Memory, English abbreviation: ROM), random access memories (English full name: Random Access Memory, English abbreviation: RAM), magnetic disks, or optical discs.

[0214] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A digital power grid regional operation optimization method, characterized in that, Including: Obtain the operation data of multiple preset monitoring nodes in the power grid area, and perform data mining on the operation data to obtain operation characteristic data; Perform clustering processing on the operation characteristic data, and divide the power grid area into multiple sub-areas according to the clustering result; Input the operation data corresponding to multiple sub-areas into the digital twin model of the power grid area for real-time simulation to obtain simulation operation data; Perform random sampling on the simulation operation data through Monte Carlo simulation to generate multiple operation scenarios; According to the optimization objectives of the power grid area, construct a multi-optimization objective function; the optimization objectives include one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability; Perform optimization solution on the multi-optimization objective function according to multiple operation scenarios, determine the optimal operation scenario according to the optimal solution, and determine the optimal operation strategy of the power grid area according to the optimal operation scenario.

2. The digital power grid regional operation optimization method according to claim 1, characterized in that It also includes: Preprocess the operation data; the preprocessing includes data noise filtering, redundant data filtering, abnormal data cleaning, data standardization, and acquisition time series synchronization.

3. The digital power grid regional operation optimization method according to claim 1, wherein Perform data mining on the operation data to obtain operation characteristic data, including: Obtain operation change characteristic data by performing wavelet transform on the operation data; Perform load forecasting according to the operation change characteristic data to obtain load forecasting data; Determine power quality characteristic data according to the operation change characteristic data; Perform fault forecasting according to the operation change characteristic data to obtain fault forecasting data; Integrate the load forecasting data, the power quality characteristic data, and the fault forecasting data to obtain the operation characteristic data.

4. The digital power grid regional operation optimization method according to claim 3, characterized in that The clustering processing of the operation characteristic data and dividing the power grid area into multiple sub-areas according to the clustering result includes: Perform clustering processing on the operation characteristic data according to the characteristic types of the operation characteristic data to obtain multiple clusters; wherein, the characteristic types include load forecasting type, power quality type, and fault forecasting type; Divide the power grid area according to multiple clusters to obtain multiple sub-areas.

5. The digital power grid regional operation optimization method according to claim 1, characterized in that It also includes: Perform data sharing between nodes through blockchain technology according to the operation data of multiple preset monitoring nodes in the power grid area to generate initial block operation data corresponding to each preset monitoring node; Verify the integrity of the initial block operation data; Use the initial block operation data that passes the integrity verification as the operation data.

6. The digital power grid regional operation optimization method according to claim 1, characterized in that It also includes: Send the optimal operation strategy of the power grid area to the power grid area, operate according to the optimal operation strategy of the power grid area, and perform power flow optimization adjustment on the power grid area according to the operation result.

7. A digital power grid regional operation optimization system, characterized in that Including: A data mining module for obtaining the operation data of multiple preset monitoring nodes in the power grid area and performing data mining on the operation data to obtain operation characteristic data; A power grid area module for performing clustering processing on the operation characteristic data and dividing the power grid area into multiple sub-areas according to the clustering result; A data simulation module, configured to input the operation data respectively corresponding to multiple said sub-regions into the digital twin model of the power grid region for real-time simulation, so as to obtain simulated operation data; A random sampling module, configured to perform random sampling on the simulated operation data through Monte Carlo simulation to generate multiple operation scenarios; An optimization objective module, configured to construct a multi-optimization objective function according to the optimization objective of the power grid region; the optimization objective includes one or more of minimizing power loss, minimizing load imbalance, maximizing new energy consumption, minimizing power cost, and maximizing power grid reliability; An operation optimization module, configured to perform optimization solution on the multi-optimization objective function according to multiple said operation scenarios, determine the optimal operation scenario according to the optimal solution, and determine the optimal operation strategy of the power grid region according to the optimal operation scenario.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, and a computer program is stored in the memory. When the computer program is executed by the processor, the processor is caused to execute the steps of the digital power grid region operation optimization method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, the steps of the digital power grid region operation optimization method according to any one of claims 1-6 are implemented.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. Wherein, when the program instructions are executed by a computer, the computer is caused to execute the steps of the digital power grid region operation optimization method according to any one of claims 1-6.

Images