Power system planning operation optimization method, system and device and storage medium

Abstract

The invention relates to the technical field of electric power energy storage system planning analysis, and discloses an electric power system planning operation optimization method, system and device and a storage medium. The method comprises the following steps: collecting electrical and equipment states and environmental parameters for feature extraction, and evaluating the health state of equipment; grouping the distributed energy sources based on health state evaluation and weather early warning information to form a virtual power plant resource pool; performing task decomposition according to the characteristics of the resource pool, and formulating a collaborative scheduling strategy; arranging a maintenance plan according to the equipment state and the scheduling strategy; and optimizing system operation parameters based on the scheduling strategy and the maintenance plan to obtain a balance control scheme. According to the invention, under the condition of considering the health state of the equipment and the influence of extreme weather, the dynamic balance of the minimization of the operation cost of the power distribution network and the maximization of renewable energy consumption is realized through the intelligent arrangement technology of the virtual power plant group.

Description

Technical Field

[0001] The present application relates to the technical field of power energy storage system planning and analysis, and in particular to a power system planning and operation optimization method, system, device and storage medium. Background Art

[0002] The planning and operation optimization of the power system is an important part of ensuring the safe and stable operation of the power grid. The existing power system planning and operation methods mainly carry out optimization from the aspects of equipment maintenance, load forecasting, power supply scheduling, etc., and optimize the system operation mode by establishing a mathematical model. At the same time, with the large-scale access of distributed energy, virtual power plant technology is gradually applied to the coordinated control of the power system, improving the system's control ability by integrating scattered distributed resources.

[0003] However, the existing technology has the following shortcomings: first, there is a lack of effective coordination mechanism between equipment health status assessment and scheduling optimization, which makes it difficult to coordinate maintenance plans with system operation requirements; second, there is a lack of quantitative assessment methods for the impact of extreme weather on power equipment, making it difficult to formulate targeted prevention and control strategies; third, the resource grouping method of the virtual power plant is relatively simple, and does not fully consider the equipment health status and weather factors, which reduces the system's operational reliability; finally, the multi-time scale collaborative optimization mechanism is imperfect, making it difficult to achieve global optimization of system operation. Summary of the invention

[0004] The present application provides a method, system, device and storage medium for optimizing power system planning and operation, which are used to achieve a dynamic balance between minimizing distribution network operating costs and maximizing renewable energy consumption through intelligent orchestration technology of virtual power plant groups while taking into account equipment health status and extreme weather impacts.

[0005] In the first aspect, the present application provides a method for optimizing the planning and operation of an electric power system, the method comprising: performing multi-dimensional collection and feature extraction of the operation data of the electric power system according to electrical parameters, equipment status parameters and environmental parameters to obtain equipment health status assessment data; performing resource grouping and priority division of distributed energy, controllable loads and energy storage systems based on the equipment health status assessment data and regional extreme weather warning information to form a virtual power plant resource pool; performing global task decomposition and target allocation according to the capacity distribution and operation characteristics of the virtual power plant resource pool to generate a collaborative scheduling strategy for a virtual power plant group; performing equipment status prediction and maintenance timing scheduling according to the equipment health status assessment data and the collaborative scheduling strategy for the virtual power plant group to obtain a maintenance plan for key equipment; performing multi-time scale optimization configuration of system operation parameters based on the collaborative scheduling strategy for the virtual power plant group and the maintenance plan for key equipment to obtain a balance control plan for the electric power system.

[0006] In a second aspect, the present application provides a power system planning and operation optimization system, the power system planning and operation optimization system comprising: The extraction module is used to collect and extract features of the power system operation data in multiple dimensions according to electrical parameters, equipment status parameters and environmental parameters to obtain equipment health status assessment data; A partitioning module is used to group and prioritize distributed energy, controllable loads, and energy storage systems based on the equipment health status assessment data and regional extreme weather warning information to form a virtual power plant resource pool; An allocation module, used to perform global task decomposition and target allocation according to the capacity distribution and operation characteristics of the virtual power plant resource pool, and generate a collaborative scheduling strategy for a virtual power plant group; A prediction module is used to predict the status of the equipment and schedule the maintenance schedule according to the equipment health status assessment data and the virtual power plant group collaborative scheduling strategy, and obtain a maintenance plan for key equipment; A configuration module is used to perform multi-time scale optimization configuration of system operating parameters based on the virtual power plant group collaborative dispatching strategy and the key equipment maintenance plan to obtain a power system balance control solution.

[0007] A third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned power system planning and operation optimization method.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned power system planning and operation optimization method.

[0009] In the technical solution provided in the present application, a comprehensive equipment health status assessment system is established through multi-dimensional collection and feature extraction of electrical parameters, equipment status parameters and environmental parameters, thereby improving the accuracy and timeliness of equipment status monitoring; by grouping and prioritizing resources based on equipment health status assessment data and regional extreme weather warning information, dynamic optimization configuration of virtual power plant resources is achieved, and the system's adaptability to extreme weather is enhanced; by performing global task decomposition and target allocation on the capacity distribution and operating characteristics of the virtual power plant resource pool, a scheduling strategy generation method based on multi-level collaboration is proposed, thereby improving the coordinated control effect of the system; based on the equipment health status assessment data and the collaborative scheduling strategy of the virtual power plant group, the equipment status is predicted and the maintenance schedule is scheduled, a preventive maintenance decision-making mechanism is constructed, and the risk of equipment failure is reduced; based on the collaborative scheduling strategy of the virtual power plant group and the maintenance plan of key equipment, the system operating parameters are optimized at multiple time scales, a dynamic balance control scheme is designed, and the system operating efficiency is improved. In terms of data processing, the present invention adopts a deep learning feature fusion model, which can effectively extract the key features of the equipment operating status, and dynamically weight different features through the attention mechanism, thereby improving the accuracy of state assessment; in terms of resource scheduling, a graph neural network algorithm is applied for dynamic grouping, which fully considers the topological relationship and operating characteristics between resources, and improves the collaborative control effect of the virtual power plant; in terms of optimization decision-making, a multi-agent reinforcement learning method is introduced to realize the adaptive optimization control of the system, thereby enhancing the practicability and generalizability of the solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0011] Figure 1 A schematic diagram of an embodiment of a method for optimizing power system planning and operation in an embodiment of the present application; Figure 2 A schematic diagram of a process for performing multi-time scale optimization configuration of system operating parameters in an embodiment of the present application; Figure 3 A schematic diagram of an embodiment of a power system planning and operation optimization system in an embodiment of the present application; Figure 4 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a method, system, device and storage medium for optimizing the planning and operation of a power system. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the power system planning and operation optimization method in the embodiment of the present application includes: Step S101: Perform multi-dimensional collection and feature extraction of power system operation data according to electrical parameters, equipment status parameters and environmental parameters to obtain equipment health status assessment data; Step S102: grouping and prioritizing distributed energy, controllable loads, and energy storage systems based on equipment health status assessment data and regional extreme weather warning information to form a virtual power plant resource pool; Step S103: performing global task decomposition and target allocation according to the capacity distribution and operation characteristics of the virtual power plant resource pool, and generating a collaborative scheduling strategy for the virtual power plant group; Step S104: Predict the status of the equipment and schedule maintenance according to the equipment health status assessment data and the collaborative dispatching strategy of the virtual power plant group, and obtain a maintenance plan for key equipment; Step S105: Based on the collaborative dispatching strategy of the virtual power plant group and the maintenance plan of key equipment, the system operating parameters are optimized at multiple time scales to obtain a power system balance control solution.

[0014] It is understandable that the execution subject of the present application may be a power system planning and operation optimization system, or a terminal or a server, which is not specifically limited here. The present application embodiment is described by taking a server as the execution subject as an example.

[0015] Specifically, multi-dimensional data collection and feature extraction are performed. Electrical parameters include voltage, current, active power and reactive power, equipment status parameters include temperature, vibration, noise and partial discharge data, and environmental parameters include temperature, humidity, wind speed and rainfall data. The electrical parameter data is standardized, and the voltage, current and other parameters are normalized to a unified dimension to form an electrical feature vector. The equipment status parameters are analyzed in the time and frequency domains, and the spectrum characteristics and time domain statistical characteristics of the vibration signal are extracted by wavelet transform. The temperature, noise and other data are normalized to construct the equipment status feature vector. The environmental parameter data is normalized to form an environmental feature vector. The three types of feature vectors are fused to construct the equipment operation feature matrix. The dynamic data in the feature matrix is ​​analyzed for time series correlation to obtain the dynamic health index, and the static data is evaluated for life cycle to obtain the static health index. The equipment health status assessment data is obtained by weighted fusion. Based on the equipment health status assessment data, the health risk coefficient is extracted for each device to form an equipment vulnerability assessment matrix. At the same time, the types and intensity levels of weather disasters are identified and divided according to the regional extreme weather warning information to obtain a set of weather impact factors. The equipment vulnerability assessment matrix is ​​correlated with the weather impact factor set to construct an equipment-weather sensitivity table to reflect the degree of impact of different types of equipment under various extreme weather conditions. Distributed energy, controllable loads, and energy storage systems are regionally clustered according to the equipment-weather sensitivity table to obtain preliminary resource groupings. Available capacity assessment and response capability analysis are performed on various types of resources to generate resource regulation priority indicators. Finally, resource groupings and priority indicators are integrated and mapped to form a virtual power plant resource pool.

[0016] Based on the virtual power plant resource pool, the capacity distribution data is statistically analyzed to form a resource capacity basic matrix, and the volatility and stability are evaluated to obtain a capacity availability evaluation table. The operating characteristics of various resources such as output characteristics, response time and regulation capacity are analyzed to construct operating characteristic evaluation indicators. The capacity availability evaluation table and the operating characteristic evaluation indicators are subjected to multi-objective correlation analysis to obtain a resource-task fitness matrix. The matrix is ​​hierarchically decomposed and the boundaries are identified to generate a task partition table and a cross-region mutual assistance plan. Based on these results, resource allocation and load distribution are carried out to obtain the initial scheduling instruction set. Finally, the collaborative scheduling strategy of the virtual power plant group is generated through the collaborative optimization of time series and spatial regions.

[0017] Based on the equipment health status assessment data, the historical trends are analyzed and the fault characteristics are extracted to generate the equipment health decay curve. The curve is correlated with the equipment scheduling load in the virtual power plant group collaborative scheduling strategy to obtain the equipment operation pressure index. Based on the index, the remaining life prediction and risk rating are carried out to build the equipment status warning table. The equipment is classified and sorted according to the importance and operation risk to generate the maintenance priority matrix. The maintenance time window is divided in combination with the virtual power plant group collaborative scheduling strategy to obtain the maintenance schedule. Finally, the maintenance resource allocation and process planning are carried out to obtain the key equipment maintenance plan. The virtual power plant group collaborative scheduling strategy is decomposed according to different time scales to obtain the hierarchical scheduling strategy matrix. The scheduling data of each time scale in the matrix is ​​analyzed in time series to generate the scheduling strategy time series feature table. The key equipment maintenance plan is mapped in time dimension to generate the equipment available capacity time series table, and the capacity balance analysis is performed according to the time node to obtain the equipment operation availability curve. The resource matching degree is calculated according to the scheduling strategy time series feature table and the equipment operation availability curve to build the resource allocation constraint matrix. The matrix is ​​subjected to multi-dimensional constraint analysis to form the system operation boundary condition set. The boundary condition set is evaluated for regional coordination of spatial distribution to obtain a regional mutual aid constraint table. Finally, boundary condition integration and constraint mapping are performed to generate a system operation constraint boundary set, and multi-time scale optimization configuration is performed based on this to obtain a power system balance control solution.

[0018] For example, when planning and optimizing the operation of a regional distribution network, multi-dimensional data such as voltage, current, temperature, and vibration of the main transformer are collected. Through data standardization and feature extraction, it is found that the harmonic content of phase A current is high and the temperature fluctuation is obvious. Combined with the weather forecast, it shows that there is strong convective weather in the area. The equipment-weather sensitivity analysis shows that the transformer has a high risk of failure under strong convective weather. Therefore, when grouping resources, the distributed photovoltaic, energy storage system, and controllable air-conditioning load in the area where the transformer is located are prioritized to form a virtual power plant unit. By analyzing the capacity characteristics and response capabilities of the unit, a time-divided scheduling strategy is formulated. At the same time, according to the equipment health status assessment results, the transformer is included in the maintenance plan priority sequence and is selected for maintenance during the photovoltaic power generation off-peak period. Finally, through multi-time scale optimization configuration, a system balance control scheme including maintenance arrangement, load regulation, and energy storage scheduling is formed.

[0019] In an embodiment of the present application, an equipment health status assessment system is established by multi-dimensionally collecting and extracting features of electrical parameters, equipment status parameters and environmental parameters, thereby improving the accuracy and timeliness of equipment status monitoring; by grouping and prioritizing resources based on equipment health status assessment data and regional extreme weather warning information, dynamic optimization configuration of virtual power plant resources is achieved, and the system's adaptability to extreme weather is enhanced; by performing global task decomposition and target allocation on the capacity distribution and operating characteristics of the virtual power plant resource pool, a scheduling strategy generation method based on multi-level collaboration is proposed, thereby improving the coordinated control effect of the system; based on equipment health status assessment data and the collaborative scheduling strategy of the virtual power plant group, the equipment status is predicted and the maintenance schedule is scheduled, a preventive maintenance decision-making mechanism is constructed, and the risk of equipment failure is reduced; based on the collaborative scheduling strategy of the virtual power plant group and the maintenance plan of key equipment, the system operating parameters are optimized at multiple time scales, a dynamic balance control scheme is designed, and the system operating efficiency is improved. In terms of data processing, the present invention adopts a deep learning feature fusion model, which can effectively extract the key features of the equipment operating status, and dynamically weight different features through the attention mechanism, thereby improving the accuracy of state assessment; in terms of resource scheduling, a graph neural network algorithm is applied for dynamic grouping, which fully considers the topological relationship and operating characteristics between resources, and improves the collaborative control effect of the virtual power plant; in terms of optimization decision-making, a multi-agent reinforcement learning method is introduced to realize the adaptive optimization control of the system, thereby enhancing the practicability and generalizability of the solution.

[0020] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Collecting voltage, current, active power and reactive power data from electrical parameters, standardizing the collected data and obtaining electrical feature vectors; (2) Collect the equipment temperature, vibration, noise and partial discharge data in the equipment status parameters, perform time-frequency domain analysis on the collected data through wavelet transform, and obtain the equipment status feature vector; (3) Collect temperature, humidity, wind speed, and rainfall data from environmental parameters, normalize the collected data, and obtain the environmental feature vector; (4) Fusing the electrical feature vector, equipment state feature vector, and environmental feature vector to construct the equipment operation feature matrix; (5) Perform time series correlation analysis on the dynamic data in the equipment operation characteristic matrix to obtain the equipment dynamic health index; (6) Perform life cycle assessment on the static data in the equipment operation characteristic matrix to obtain the equipment static health index; (7) The equipment dynamic health index and the equipment static health index are weighted and integrated to obtain the equipment health status assessment data.

[0021] Specifically, during the electrical parameter collection process, voltage, current, active power and reactive power data are acquired in real time from substations, transmission lines and distribution network nodes through intelligent sensor networks. These raw data have inconsistent dimensions and large differences in numerical ranges, so they need to be standardized. The standardization process uses the Z-score standardization method to convert each parameter into a standard distribution with a mean of 0 and a standard deviation of 1, so that electrical parameters of different dimensions can be effectively compared and integrated. For example, the voltage data of a transformer fluctuates between 110kV and 115kV, and the current data varies between 90A and 110A. After standardization, these data are mapped to the same numerical interval to form an electrical feature vector. In the equipment status parameter collection stage, the focus is on monitoring equipment temperature, vibration, noise and partial discharge data. The equipment temperature is obtained by infrared thermal imagers and temperature sensors, the vibration data is measured by acceleration sensors, the noise data is collected by acoustic sensors, and the partial discharge data is obtained by special discharge detection instruments. These equipment status data often contain rich time-frequency characteristics. Time-frequency domain analysis through wavelet transform can extract the key features of the equipment operation status. Wavelet transform decomposes the signal into wavelet coefficients of different frequencies and time scales, which can effectively capture the non-stationary characteristics and transient characteristics in the equipment status data. By selecting appropriate wavelet basis functions, such as Daubechies wavelet or Morlet wavelet, the vibration signal is decomposed at multiple scales to extract key features such as energy distribution, spectral characteristics and singular points to form the equipment status feature vector. The environmental parameter collection link focuses on temperature, humidity, wind speed and rainfall data, which directly affect the equipment operating environment. Environmental data is obtained by meteorological stations and environmental monitoring equipment distributed at key nodes of the power system. Due to the large difference in the numerical range of environmental parameters, normalization processing is required to map each parameter value to the [0,1] interval for subsequent fusion analysis. The normalization process uses the maximum and minimum value normalization method to calculate the normalized value of each environmental parameter to form an environmental feature vector.

[0022] The electrical feature vector, equipment status feature vector and environmental feature vector are fused to construct the equipment operation feature matrix. The feature fusion adopts a multi-level fusion strategy. First, the weight of each feature vector is configured, and the weight coefficient is assigned according to the degree of influence of each parameter on the health status of the equipment. Then, the three types of feature vectors are fused into a unified feature representation by weighted summation. The equipment operation feature matrix contains both the dynamic features of the current operation status of the equipment and the static features of the historical operation and basic properties of the equipment. The dynamic data in the equipment operation feature matrix is ​​analyzed for time series correlation. The autoregressive sliding average model is used to process the time series data, extract the trend, periodicity and randomness characteristics of the time series, calculate the time series correlation coefficient matrix between parameters, and identify the key parameter combination and its change mode. By setting a threshold, it is judged whether there is an abnormality in the equipment operation status, and the risk level of the abnormality is evaluated in combination with the expert knowledge base, and finally the dynamic health index of the equipment is obtained. The static data in the equipment operation feature matrix is ​​evaluated for life cycle. Based on the static information such as the equipment model, operating years, cumulative operating time, historical maintenance records, etc., the theoretical life consumption rate of the equipment is calculated in combination with the equipment aging curve model. Taking into account factors such as the importance of the equipment, the availability of spare parts, and the difficulty of maintenance, a comprehensive assessment is made to obtain the static health index of the equipment.

[0023] The dynamic health index of the equipment is weighted and fused with the static health index of the equipment to obtain comprehensive equipment health status assessment data. The weighted fusion process takes into account the characteristics of different types of equipment and assigns different weights to the dynamic index and static index. For example, for large static equipment such as transformers, the static health index weight may be higher, while for frequently operated equipment such as circuit breakers, the dynamic health index weight may be larger.

[0024] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Analyze the equipment health status assessment data, extract the health risk factor of each equipment, and generate the equipment vulnerability assessment matrix; (2) Based on the regional extreme weather warning information, the weather disaster types are identified and the intensity levels are classified to obtain a set of weather impact factors. The equipment vulnerability assessment matrix is ​​then correlated with the weather impact factor set to construct an equipment-weather sensitivity table. (3) Based on the equipment-weather sensitivity table, distributed energy, controllable loads and energy storage systems are regionally clustered to obtain a resource grouping sequence. The available capacity and response capability of each type of resource in the resource grouping sequence are evaluated and analyzed to generate a resource regulation priority index. (4) Performing geographical location correlation analysis on each resource group in the resource grouping sequence to generate a resource spatial distribution matrix; (5) Cross-map the resource spatial distribution matrix with the resource regulation priority index to obtain the initial resource combination table; (6) Conduct energy complementarity analysis on the resources in the initial resource combination table, construct a resource complementarity matrix, and optimize and reorganize the initial resource combination table based on the resource complementarity matrix to obtain the resource synergy index; (7) The resource synergy index and the resource regulation priority index are weighted and integrated to form a virtual power plant resource pool.

[0025] Specifically, risk analysis is performed on the equipment health status data. For each equipment, the risk factor is calculated based on its health status assessment data: ； in, is the equipment risk factor (dimensionless, range 0-1); is the weight of the i-th health status indicator; is the deviation value of the indicator; is the number of evaluation indicators. These risk factors constitute the equipment vulnerability assessment matrix.

[0026] Analyze extreme weather warning information and construct weather impact factors: ; in, is the weather influencing factor; For the Type coefficient of weather-like disasters; is the strength grade coefficient; is the duration impact index; is the number of weather disaster types. The weather impact factor is associated with the equipment vulnerability to obtain the sensitivity calculation formula: ; in, is the sensitivity of the i-th device to the j-th weather type; is the coupling coefficient. This forms the equipment-weather sensitivity table.

[0027] Resource clustering analysis based on sensitivity table: ; in, For the Characteristic values ​​of class resource groups; is the resource capacity; For each type of resource, evaluate its available capacity and response characteristics: ; in, It is a priority indicator for resource regulation; is the available capacity factor; is the response time coefficient; is the adjustment error coefficient.

[0028] Conduct geographic location association analysis and construct a spatial distribution matrix: ; in, is the spatial distance between resources (km); , )and( , ) are the longitude and latitude coordinates of the two resource points.

[0029] Energy complementarity analysis of resources: ; in, is the complementarity coefficient; and is the output of the two types of resources at time t; T is the length of the evaluation period.

[0030] The final resource pool construction adopts weighted fusion: ； in, It is a comprehensive evaluation indicator for the resource pool; and is the weight coefficient and + = 1. This indicator comprehensively considers the regulation priority and complementary characteristics of resources, and provides a basis for the optimal allocation of resources in virtual power plants. Taking photovoltaic power stations, wind farms and energy storage power stations in a certain area as an example, the above evaluation system can identify the sensitivity of various resources to extreme weather, reasonably allocate resource combinations, and improve the operational reliability and economy of virtual power plants. The evaluation system systematically integrates multi-dimensional factors such as equipment status, weather impact, geographical distribution and energy characteristics to form a resource pool construction method.

[0031] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Perform hierarchical statistics on the capacity distribution data in the virtual power plant resource pool according to energy type and capacity size, extract spatiotemporal distribution characteristics, and generate a resource capacity basic matrix; (2) Perform volatility analysis and stability assessment on the data in the resource capacity basic matrix and compare it with historical operation data to obtain a capacity availability assessment table; (3) Based on the output characteristics, response time, and regulation capabilities of various resources in the virtual power plant resource pool, multi-dimensional parameter extraction and feature mapping are performed to construct operating characteristic evaluation indicators; (4) Perform multi-objective correlation analysis on the capacity availability evaluation table and the operation characteristic evaluation index to obtain the resource-task fit matrix; (5) Perform hierarchical decomposition and boundary identification on the resource-task fit matrix to generate a task partition table and cross-region mutual assistance plan; (6) Based on the task partition table and the cross-region mutual assistance plan, resource allocation and load distribution are carried out to obtain the initial scheduling instruction set; (7) The initial scheduling instruction set is collaboratively optimized and conflict resolved according to time series and spatial regions to generate a collaborative scheduling strategy for the virtual power plant group.

[0032] Specifically, when performing hierarchical statistics on the capacity distribution data in the virtual power plant resource pool, it is necessary to classify and summarize various types of distributed energy, controllable loads and energy storage devices according to energy types (such as photovoltaic, wind power, energy storage, adjustable loads, etc.) and capacity sizes (such as large, medium, and small). Hierarchical statistics use a tree structure to classify resources at multiple levels according to primary energy types, secondary capacity levels, and tertiary geographical locations to form structured data. The extraction of spatiotemporal distribution features is to conduct statistical analysis on the geographical location and time availability of various resources, including the density distribution of resources in different regions, seasonal variation characteristics, and intraday fluctuation patterns. By matrixing these feature data, a resource capacity basic matrix is ​​formed. The rows of the matrix represent different resource types, the columns represent different spatiotemporal feature dimensions, and the matrix element values ​​represent the available capacity values ​​of the corresponding type of resources under specific spatiotemporal conditions. When performing volatility analysis on the data in the resource capacity basic matrix, the coefficient of variation method is used to calculate the volatility index of the capacity of various types of resources. The larger the coefficient of variation, the stronger the output volatility of this type of resource. At the same time, the stability of resource capacity is evaluated through statistical methods such as standard deviation analysis and entropy method, and the stability scores of various resources are obtained. The results of volatility analysis and stability evaluation are compared with historical operation data. The sliding time window method is used to compare the performance differences between the current resource status and the historical performance under the same period and weather conditions, and the similarity index is calculated. Based on these analysis results, a capacity availability evaluation table is generated, which contains the actual available capacity ratio and reliability level of various resources in different time periods and different weather conditions.

[0033] When extracting multidimensional parameters based on the output characteristics, response time and regulation capabilities of various resources in the virtual power plant resource pool, it is necessary to model and quantify the dynamic response characteristics of each type of resource. Output characteristics include parameters such as maximum output, minimum output, ramp rate and duration; response time refers to the time delay from receiving the dispatch instruction to the actual response; regulation capability reflects the execution accuracy and stability of the resource to the dispatch instruction. By normalizing and weighting these parameters, using multidimensional feature mapping methods such as radar charts, a resource operation characteristic evaluation index system is constructed to form a capacity portrait of various resources in different operation scenarios. When the capacity availability evaluation table and the operation characteristic evaluation index are analyzed for multi-objective correlation, the fuzzy comprehensive evaluation method is used to cross-match the two sets of index systems. First, a task type library is set, including different task types such as peak load regulation, frequency regulation, standby, and demand response. Then, for each task type, the specific demand characteristics are matched with the operation characteristics of the resource to generate a resource-task adaptation matrix. The rows of the matrix represent different resources, the columns represent different task types, and the matrix element values ​​represent the degree of adaptation of a specific resource to perform a specific task.

[0034] When the resource-task fitness matrix is ​​hierarchically decomposed, the cluster analysis method is used to group resources and tasks with similar fitness characteristics to form resource-task sub-blocks. Boundary identification is to identify the boundary resources and tasks of each sub-block by setting the fitness threshold, and clarify the task boundaries of each resource group and the resource boundaries of each task type. The results of hierarchical decomposition and boundary identification are used to generate a task partition table to clarify the task allocation plan for different regions and different time periods. The cross-region mutual assistance plan is based on the boundary identification results, and the complementarity analysis of the resources and tasks in the boundary area is carried out to formulate a cross-regional resource allocation strategy under extreme conditions. When resource allocation and load distribution are performed based on the task partition table and the cross-region mutual assistance plan, the linear programming method is used to solve the optimal resource allocation plan. With minimizing the dispatching cost and maximizing the renewable energy consumption rate as the objective function, and with power balance constraints, line capacity constraints and equipment operation constraints as constraints, the optimal output plan of each type of resource and the response plan of each type of load are calculated to form an initial dispatch instruction set.

[0035] When the initial dispatch instruction set is optimized and conflict resolved according to time series and spatial regions, the rolling time domain decomposition method is used to handle the continuity of instructions in the time dimension to ensure smooth transition of dispatch instructions in each time period; the regional coordination mechanism is used to handle resource allocation conflicts in the spatial dimension to ensure cross-regional power balance and safety constraints. Through iterative optimization, the time and space conflicts between dispatch instructions are eliminated, and finally a collaborative dispatch strategy for virtual power plant groups is generated.

[0036] Take a regional power grid as an example. The region includes photovoltaic power stations (total capacity of 50MW), wind farms (total capacity of 30MW), industrial controllable loads (total capacity of 20MW) and energy storage systems (capacity of 15MW / 60MWh). First, these resources are hierarchically counted by type and capacity, and combined with geographical distribution and time characteristics to form a resource capacity basic matrix. By analyzing the historical output data of photovoltaic and wind power, it is calculated that the capacity variation coefficient of photovoltaic power stations on sunny days is 0.3, which rises to 0.6 in cloudy weather; the variation coefficient of wind farms under stable meteorological conditions is 0.2, which rises to 0.5 when the weather changes drastically. Combined with weather forecast data and historical performance over the same period, a capacity availability assessment table for each time period of the next day is generated. Analyze the operating characteristics of various resources, such as photovoltaic response time is short but cannot be adjusted upward, wind power has a certain adjustment margin, industrial load response time is long but the adjustment range is large, energy storage responds quickly and has strong two-way adjustment capabilities, and construct operating characteristic evaluation indicators. Through multi-objective correlation analysis, it is clear that photovoltaic and wind power are suitable for basic output tasks, energy storage is suitable for fast frequency regulation and peak-valley filling tasks, and industrial load is suitable for demand response and standby tasks, forming a resource-task adaptation matrix. According to the adaptation matrix, the resources are divided into three functional areas: basic power supply area, fast regulation area and emergency response area, and a mutual assistance strategy between regions is formulated. Based on the functional area division and load forecast, the optimal resource allocation plan for each time period is calculated. For example, the morning load climbing period mainly relies on energy storage discharge and wind power peak regulation, and the noon photovoltaic output peak period guides industrial load to increase consumption. Finally, through smoothing processing in the time dimension and conflict resolution in the space dimension, a virtual power plant group collaborative dispatching strategy covering the entire region is formed 24 hours a day to achieve economical and efficient operation of the power system.

[0037] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Perform historical trend analysis and fault feature extraction on equipment health status assessment data to generate equipment health decline curve; (2) Correlate the equipment health decay curve with the equipment dispatch load in the virtual power plant group collaborative dispatch strategy to obtain the equipment operation pressure index; (3) Based on the equipment operation pressure index, the remaining life of the equipment is predicted and the risk rating is performed, and an equipment status early warning table is constructed; (4) Classify and sort each device in the equipment status warning table according to its importance and operation risk, and generate a maintenance priority matrix; (5) Divide the maintenance time window according to the maintenance priority matrix and the virtual power plant group collaborative scheduling strategy to obtain the maintenance schedule; (6) Allocate maintenance resources and plan maintenance procedures based on the maintenance schedule to obtain a maintenance plan for key equipment.

[0038] Specifically, by deeply analyzing the equipment health status assessment data, the key features of the equipment operation process are extracted. The historical data is analyzed in time series, including the change trend of the equipment's electrical parameters, temperature change rules, vibration characteristics, etc. Each characteristic parameter has its own unique change pattern. For example, the winding temperature of the transformer shows periodic changes during normal operation, and when an abnormality occurs, it will show obvious mutation characteristics. By extracting and analyzing these features, a health decay curve reflecting the change of the equipment health status over time is drawn. After obtaining the equipment health decay curve, it is necessary to correlate it with the load data in the virtual power plant group collaborative scheduling strategy. The scheduling load data contains the equipment's operating condition information, such as load rate, start and stop frequency, load change rate, etc. By analyzing the relationship between the equipment health status and the operating condition, the equipment operation pressure index is calculated. This index comprehensively reflects the degree of match between the equipment's health status and the operating load.

[0039] Based on the equipment operation stress index, the remaining life of the equipment is predicted. The historical operation data, current health status and expected future operating conditions of the equipment are taken into account in the prediction process. At the same time, the risk rating of the equipment is carried out according to the prediction results. The rating criteria include multiple dimensions such as equipment importance, failure probability, and failure impact range. Through these analyses, an equipment status warning table containing various risk indicators is constructed. The equipment status warning table contains a large amount of risk assessment information for equipment. This information is analyzed and sorted, focusing on the two dimensions of the importance of the equipment in the power grid and the operation risk. The importance of the equipment is determined by its location in the power grid, the functions it undertakes, the scope of impact, and other factors. The operation risk is based on the previous health status assessment and the remaining life prediction results. Through the comprehensive analysis of these factors, a maintenance priority matrix is ​​generated.

[0040] According to the sorting results of the maintenance priority matrix, combined with the collaborative dispatching strategy of the virtual power plant group, the equipment maintenance time is reasonably arranged. The dispatching strategy provides load forecasting and resource allocation information for different time periods. By analyzing this information, the appropriate maintenance time window is selected. The selection of the time window needs to balance the urgency of maintenance and the impact of system operation, and the maintenance schedule is obtained. The maintenance schedule is further refined to configure the required maintenance resources, including personnel, materials, equipment, etc. At the same time, specific maintenance procedures are planned, including pre-maintenance preparation, maintenance process control, and post-maintenance acceptance. Through these detailed plans, a complete maintenance plan for key equipment is finally formed.

[0041] Take the maintenance plan of the main transformer of a certain substation as an example: through the analysis of the operation data of the transformer in the past year, it was found that its temperature data showed a gradual upward trend, the vibration amplitude of the core increased, and the dissolved gas content in the oil was abnormal. The health decay curve drawn in combination with the data shows that the health status of the equipment is accelerating. At the same time, the transformer undertakes important industrial load power supply tasks, with an average load rate of 85%, and frequent load adjustments. The operating pressure index obtained through correlation analysis is high, and the predicted remaining life is lower than expected, which is classified as a high-risk level. Considering the important position of the transformer in the power grid and its current health status, it is listed at the forefront of the maintenance priority. Combined with the load forecast, it was found that the industrial load dropped significantly during the Spring Festival. This time window was selected for maintenance, and a detailed maintenance plan including winding inspection, oil quality treatment, and core tightening was formulated.

[0042] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) The collaborative dispatch strategy of the virtual power plant group is decomposed into four time scales: annual, monthly, day-ahead, and real-time, to obtain a hierarchical dispatch strategy matrix; (2) Map the time dimension of the maintenance plan for key equipment and generate a time series table of available equipment capacity; (3) Analyze the matching between the hierarchical scheduling strategy matrix and the equipment available capacity schedule to construct the system operation constraint boundary set; (4) According to the system operation constraint boundary set, the operation parameters are configured in different time periods and divided into intervals to obtain a parameter adjustment range table; (5) Perform timing coupling analysis and mutual feedback impact assessment on each parameter in the parameter adjustment range table to generate a parameter coordination control sequence; (6) The parameter coordination control sequence is integrated and optimized at multiple time scales to obtain the power system balance control scheme.

[0043] Specifically, Figure 2As shown, it is a flow chart of multi-time scale optimization configuration of system operation parameters in the embodiment of the present application. The decomposition of the collaborative scheduling strategy of the virtual power plant group starts from the annual scale. The annual scheduling mainly focuses on the equipment maintenance cycle, seasonal load characteristics and renewable energy output law. Monthly scheduling focuses on the load change trend and equipment maintenance arrangement within the month. Day-ahead scheduling focuses on load forecasting and resource allocation within 24 hours. Real-time scheduling adjusts the power balance at the minute level. Through this hierarchical decomposition, a hierarchical scheduling strategy matrix containing scheduling requirements at different time scales is obtained. When mapping the time dimension of the maintenance plan for key equipment, it is necessary to consider the impact of the maintenance work on the available capacity of the equipment. The maintenance process of the equipment usually includes two methods: full stop maintenance and load maintenance, and the corresponding capacity impact is also different. By analyzing the maintenance process and duration, the maintenance plan is converted into time series data of the available capacity of the equipment, and a time series table of the available capacity of the equipment is generated.

[0044] When performing a matching analysis between the hierarchical scheduling strategy matrix and the equipment available capacity time series table, it is necessary to identify the relationship between capacity constraints and scheduling requirements at each time scale. On the annual scale, the main consideration is the matching of maintenance plans with seasonal loads. On the monthly and day-ahead scales, the focus is on the impact of maintenance activities on scheduling resources. On the real-time scale, it is necessary to consider temporary constraints during equipment maintenance. Through these analyses, a complete set of system operation constraint boundaries is constructed. Based on the system operation constraint boundary set, the system operation parameters are configured and divided into time periods. The operating parameters include key indicators such as voltage, frequency, and power, and each parameter has its reasonable operating range. By analyzing the load characteristics and network status of different time periods, the adjustment range of each parameter is determined to form a parameter adjustment range table.

[0045] Perform time-series coupling analysis on each parameter in the parameter adjustment range table, focusing on the mutual influence relationship between parameters. For example, power adjustment will affect the voltage level, and frequency changes will affect the operating status of the equipment. By analyzing these coupling relationships, evaluate the mutual feedback impact of parameter adjustment, and generate a parameter coordination control sequence. Integrate and optimize the parameter coordination control sequence at different time scales. The annual level optimization mainly considers the coordination of equipment maintenance and seasonal loads. The monthly level focuses on optimizing the coordination of maintenance plans and monthly scheduling. The day-ahead level focuses on the response strategy for intraday load fluctuations. The real-time level mainly solves the problem of instantaneous power balance. Through the coordinated optimization of multiple time scales, a complete power system balance control solution is finally formed. Take a distribution network area as an example, which contains multiple distributed power sources and controllable loads. Annual dispatch analysis shows that the load is higher in summer and lower in winter, while distributed photovoltaic power generation presents the opposite seasonal characteristics. Monthly analysis finds that the industrial load is larger in the middle of each month, and relatively smaller at the beginning and end of the month. Day-ahead analysis shows that there are obvious load peaks in the morning and evening on weekdays. Real-time data shows that the fluctuation of distributed photovoltaic power generation has a great impact on system stability. Based on these characteristics, a hierarchical dispatch strategy is formulated: at the annual level, large equipment maintenance is arranged during the low load period in winter, and at the monthly level, routine maintenance is arranged at the beginning or end of the month. Day-ahead dispatch makes full use of the energy storage system to cope with the morning and evening peaks, and real-time dispatch uses fast-response energy storage devices to smooth photovoltaic fluctuations. At the same time, by analyzing the constraints of each time scale, the adjustment range of operating parameters such as voltage qualification rate and power factor is determined. The final balance control scheme not only meets the operation requirements of different time scales, but also ensures the safe and stable operation of the system.

[0046] In a specific embodiment, the process of performing the step of performing a matching analysis between the hierarchical scheduling strategy matrix and the device available capacity time sequence table may specifically include the following steps: (1) Perform time series analysis on the scheduling data of each time scale in the hierarchical scheduling strategy matrix to generate a scheduling strategy time series feature table; (2) Perform capacity balance analysis on the equipment available capacity time series table according to time nodes to obtain the equipment operation availability curve; (3) Calculate resource matching degree based on the scheduling strategy timing characteristic table and equipment operation availability curve, and construct a resource allocation constraint matrix; (4) Analyze the voltage constraint, power constraint, and capacity constraint of the resource allocation constraint matrix to form a set of system operation boundary conditions; (5) Evaluate the regional coordination of the system operation boundary condition set according to its spatial distribution to obtain a regional mutual assistance constraint table; (6) Integrate the boundary conditions and perform constraint mapping on the regional mutual assistance constraint table to generate the system operation constraint boundary set.

[0047] Specifically, the hierarchical scheduling strategy matrix contains scheduling data at four time scales: annual, monthly, day-ahead, and real-time. The time series analysis process first unifies the scheduling data at each time scale, decomposes the annual data by month, the monthly data by day, the day-ahead data by hour, and the real-time data by minute, to form a scheduling strategy time series with a unified time granularity. Time series analysis uses time series decomposition technology to decompose the scheduling data at each time scale into three components: trend items, period items, and random items, and extracts key time series features, such as peak values, valley values, ramp rates, duration, and other time series characteristic parameters, to finally form a scheduling strategy time series feature table. This feature table uses time as rows and feature indicators as columns, clearly showing the scheduling characteristics of each time node. When the equipment available capacity time series table is used for capacity balance analysis according to time nodes, it is necessary to aggregate and balance the available capacity of various types of power generation equipment, energy storage equipment, and adjustable loads in the time dimension. First, the equipment is grouped by type, and the total available capacity of various types of equipment at different time nodes is calculated. Then, according to the power balance principle, the supply and demand balance state of the system at each time node is calculated. The capacity balance analysis adopts the sliding time window method, taking a specific time window (such as 30 minutes, 1 hour) as the basic unit, calculates the capacity balance index within the window, and forms a continuous equipment operation availability curve. This curve intuitively shows the changes in the capacity availability status of the system on the time axis, making it easier to identify periods of capacity shortage and periods of surplus.

[0048] When calculating resource matching according to the scheduling strategy timing characteristic table and the equipment operation availability curve, the time-space matching algorithm is used to analyze the scheduling requirements and resource capabilities. For each time node, the demand characteristics of the scheduling strategy (such as frequency regulation requirements, standby requirements, peak regulation requirements, etc.) are matched with the available capacity of the equipment at the corresponding time to calculate the degree of adaptation of various resources to meet various scheduling requirements. The matching calculation takes into account multi-dimensional factors such as resource response time, adjustment rate, and continuous capacity. The weighted scoring method is used to comprehensively evaluate the adaptability of resources to specific scheduling requirements and construct a resource allocation constraint matrix. The matrix has resource types as rows and time nodes as columns. The matrix element values ​​represent the allocation constraints of specific resources at specific times, such as the maximum dispatchable capacity and the minimum required reserved capacity.

[0049] When analyzing the voltage constraint, power constraint and capacity constraint of the resource allocation constraint matrix, the physical characteristics and safe operation restrictions of the power system need to be considered comprehensively. The voltage constraint analysis extracts the allowable voltage variation range of each node based on the power flow calculation results to form a voltage constraint set; the power constraint analysis extracts the power transmission limit of each transmission line and equipment based on the equipment rated parameters and system stability requirements to form a power constraint set; the capacity constraint analysis extracts the capacity dispatch limit of various resources based on the equipment reliability and dispatch flexibility requirements to form a capacity constraint set. By integrating these three types of constraint sets, a complete set of system operation boundary conditions is formed, which describes the various constraints for safe and stable operation of the system in a standardized format. When the system operation boundary condition set is evaluated for regional coordination according to spatial distribution, the power transmission capacity, resource complementarity and emergency mutual assistance capacity between regions are comprehensively evaluated based on the geographical division of the power system. The regional coordination evaluation adopts the regional coupling degree analysis method to calculate the power flow capacity and resource complementarity between regions, identify key interconnection channels and regional cooperation bottlenecks, and form a regional mutual assistance constraint table. This constraint table clearly shows the mutual assistance capacity boundaries between regions, including key indicators such as the maximum transmission capacity between regions, the minimum reserved capacity and the emergency mutual assistance response time.

[0050] When integrating boundary conditions and mapping constraints of the regional mutual aid constraint table, the mutual aid constraints at the regional level are integrated with the operation constraints at the equipment level to form a multi-level, full-dimensional constraint system. The boundary condition integration adopts the constraint fusion algorithm to unify the constraint conditions of different levels and dimensions, eliminate redundant constraints, strengthen key constraints, and form a concise and comprehensive constraint set. Constraint mapping maps abstract constraint conditions to specific control parameters and dispatch variables, clarifies the control objectives and restriction ranges corresponding to each constraint condition, and finally generates a system operation constraint boundary set, which provides a clear operation boundary for the subsequent power system balance control scheme.

[0051] Take a regional power grid as an example. The grid includes multiple power generation resources such as thermal power, hydropower, wind power and photovoltaic power, as well as flexible adjustment resources such as pumped storage and battery energy storage. First, the hierarchical scheduling strategy matrix is ​​analyzed in time series. The plan for seasonal regulation of hydropower in the annual scheduling strategy is decomposed into monthly granularity, the unit maintenance arrangement in the monthly scheduling strategy is decomposed into daily granularity, and the unit start and stop in the day-ahead scheduling strategy is decomposed into hourly granularity, forming a time series feature table containing the scheduling characteristics of each time node. The table shows that during the peak heating load period in winter, the scheduling strategy requires the thermal power units to operate at full capacity, while the spring flood season requires hydropower to generate power first. Then, according to the maintenance plan of key equipment, the equipment available capacity time series table is generated. Through the sliding time window analysis, it is found that in the third week of a certain month, due to the simultaneous maintenance of two large thermal power units, the system reserved capacity dropped below the warning line, forming a "trough" in the equipment operation availability curve. Based on the scheduling strategy time series characteristic table and equipment operation availability curve, the matching degree of various resources is calculated. For example, gas units and battery storage with fast response time have a high matching degree in real-time frequency regulation, while pumped storage with a large adjustment range has a high matching degree in intraday peak regulation. A resource allocation constraint matrix containing time and space dimension constraint information is constructed. A multi-dimensional constraint analysis is performed on the matrix to determine the power flow limit of each transmission channel, the voltage qualified range of each bus, and the scheduling capacity limit of various resources to form a set of system operation boundary conditions. According to the regional division of the system, the coordination between regions is evaluated. For example, area A has abundant wind power resources but limited absorption capacity, and forms a mutual assistance relationship with area B where the power load is concentrated, but is limited by the capacity of the interconnection line, and the mutual assistance capacity has an upper limit. A detailed regional mutual assistance constraint table is generated. Finally, the constraints at the equipment level and the regional level are integrated, and the control targets corresponding to each constraint are clarified, such as the power flow of the interconnection line not exceeding 80% of the rated capacity, the voltage deviation of each bus not exceeding ±5% of the rated value, and the minimum rotating reserve capacity of each region not less than 50% of the maximum unit capacity. This forms a system operation constraint boundary set, which provides clear boundary conditions for the formulation of power system balance control plans.

[0052] The above describes the power system planning and operation optimization method in the embodiment of the present application. The following describes the power system planning and operation optimization system in the embodiment of the present application. Figure 3 In the embodiment of the present application, an embodiment of the power system planning and operation optimization system includes: Through the collaborative cooperation of the above-mentioned components, a comprehensive equipment health status assessment system was established through multi-dimensional collection and feature extraction of electrical parameters, equipment status parameters and environmental parameters, thereby improving the accuracy and timeliness of equipment status monitoring; by grouping and prioritizing resources based on equipment health status assessment data and regional extreme weather warning information, dynamic optimization of virtual power plant resources was achieved, enhancing the system's adaptability to extreme weather; by globally decomposing tasks and allocating goals to the capacity distribution and operating characteristics of the virtual power plant resource pool, a scheduling strategy generation method based on multi-level collaboration was proposed, thereby improving the coordinated control effect of the system; based on equipment health status assessment data and the collaborative scheduling strategy of the virtual power plant group, the equipment status was predicted and the maintenance schedule was scheduled, a preventive maintenance decision-making mechanism was established, and the risk of equipment failure was reduced; based on the collaborative scheduling strategy of the virtual power plant group and the maintenance plan of key equipment, the system operating parameters were optimized at multiple time scales, a dynamic balance control scheme was designed, and the system operating efficiency was improved. In terms of data processing, the present invention adopts a deep learning feature fusion model, which can effectively extract the key features of the equipment operating status, and dynamically weight different features through the attention mechanism, thereby improving the accuracy of state assessment; in terms of resource scheduling, a graph neural network algorithm is applied for dynamic grouping, which fully considers the topological relationship and operating characteristics between resources, and improves the collaborative control effect of the virtual power plant; in terms of optimization decision-making, a multi-agent reinforcement learning method is introduced to realize the adaptive optimization control of the system, thereby enhancing the practicability and generalizability of the solution.

[0053] Reference Figure 4 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0054] Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0055] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0056] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0057] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0058] 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 this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole 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, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0059] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing power system planning and operation, characterized in that: The power system planning and operation optimization method comprises: Perform multi-dimensional collection and feature extraction of power system operation data based on electrical parameters, equipment status parameters, and environmental parameters to obtain equipment health status assessment data; Based on the equipment health status assessment data and regional extreme weather warning information, distributed energy, controllable loads and energy storage systems are grouped and prioritized to form a virtual power plant resource pool; Performing global task decomposition and target allocation according to the capacity distribution and operation characteristics of the virtual power plant resource pool, and generating a collaborative scheduling strategy for a virtual power plant group; According to the equipment health status assessment data and the virtual power plant group collaborative scheduling strategy, equipment status prediction and maintenance schedule are arranged to obtain a key equipment maintenance plan; Based on the virtual power plant group collaborative dispatching strategy and the key equipment maintenance plan, the system operating parameters are optimized and configured at multiple time scales to obtain a power system balance control solution.

2. The power system planning and operation optimization method according to claim 1, characterized in that: The multi-dimensional collection and feature extraction of the power system operation data according to the electrical parameters, equipment status parameters and environmental parameters to obtain equipment health status assessment data includes: Collecting voltage, current, active power and reactive power data from the electrical parameters, and performing standardization processing on the collected data to obtain an electrical characteristic vector; Collecting the equipment temperature, vibration, noise and partial discharge data from the equipment status parameters, and performing time-frequency domain analysis on the collected data by wavelet transform to obtain the equipment status feature vector; Collecting the temperature, humidity, wind speed, and rainfall data from the environmental parameters, and normalizing the collected data to obtain an environmental feature vector; Performing feature fusion on the electrical feature vector, the device state feature vector and the environment feature vector to construct a device operation feature matrix; Performing time series correlation analysis on the dynamic data in the equipment operation characteristic matrix to obtain a dynamic health index of the equipment; Performing life cycle assessment on the static data in the equipment operation characteristic matrix to obtain a static health index of the equipment; The device dynamic health index and the device static health index are weighted and fused to obtain the device health status assessment data.

3. The power system planning and operation optimization method according to claim 1, characterized in that: The resource grouping and priority division of distributed energy, controllable loads and energy storage systems based on the equipment health status assessment data and regional extreme weather warning information to form a virtual power plant resource pool includes: Analyze the equipment health status assessment data, extract the health risk coefficient of each equipment, and generate an equipment vulnerability assessment matrix; Identify the type of weather disaster and classify its intensity level according to the regional extreme weather warning information to obtain a set of weather impact factors, and perform correlation analysis between the equipment vulnerability assessment matrix and the set of weather impact factors to construct an equipment-weather sensitivity table; Based on the equipment-weather sensitivity table, distributed energy, controllable loads and energy storage systems are regionally clustered to obtain a resource grouping sequence, and available capacity evaluation and response capability analysis are performed on various types of resources in the resource grouping sequence to generate a resource regulation priority index; Performing geographical location correlation analysis on each group of resources in the resource grouping sequence to generate a resource spatial distribution matrix; Cross-mapping the resource space distribution matrix with the resource regulation priority index to obtain an initial resource combination table; Performing energy complementarity analysis on the resources in the initial resource combination table, constructing a resource complementarity matrix, and optimizing and reorganizing the initial resource combination table according to the resource complementarity matrix to obtain a resource synergy index; The resource synergy index is weighted and integrated with the resource regulation priority index to form the virtual power plant resource pool.

4. The method for optimizing power system planning and operation according to claim 1, characterized in that: The step of performing global task decomposition and target allocation according to the capacity distribution and operation characteristics of the virtual power plant resource pool and generating a collaborative scheduling strategy for a virtual power plant group includes: Performing hierarchical statistics on the capacity distribution data in the virtual power plant resource pool according to energy type and capacity size, extracting spatiotemporal distribution characteristics, and generating a resource capacity basic matrix; Performing volatility analysis and stability evaluation on the data in the resource capacity basic matrix, and comparing it with historical operation data to obtain a capacity availability evaluation table; According to the output characteristics, response time and regulation capability of various resources in the virtual power plant resource pool, multi-dimensional parameter extraction and feature mapping are performed to construct an operation characteristic evaluation index; Performing a multi-objective correlation analysis on the capacity availability evaluation table and the operation characteristic evaluation index to obtain a resource-task adaptation matrix; Performing hierarchical decomposition and boundary identification on the resource-task adaptability matrix to generate a task partition table and a cross-region mutual assistance plan; Perform resource allocation and load distribution based on the task partition table and the cross-region mutual assistance plan to obtain an initial scheduling instruction set; The initial scheduling instruction set is collaboratively optimized and conflict-resolved according to time series and spatial regions to generate the collaborative scheduling strategy for the virtual power plant group.

5. The method for optimizing power system planning and operation according to claim 1, characterized in that: The device health status assessment data and the virtual power plant group collaborative scheduling strategy are used to predict the status of the device and schedule the maintenance schedule to obtain a key equipment maintenance plan, including: Performing historical trend analysis and fault feature extraction on the equipment health status assessment data to generate an equipment health decay curve; Correlation analysis is performed on the equipment health decay curve and the equipment dispatching load in the virtual power plant group collaborative dispatching strategy to obtain an equipment operation pressure index; Based on the equipment operation pressure index, the remaining life of the equipment is predicted and the risk rating is performed, and an equipment status early warning table is constructed; Classify and sort each device in the equipment status warning table according to importance and operation risk, and generate a maintenance priority matrix; Divide the maintenance time window according to the maintenance priority matrix and the virtual power plant group collaborative scheduling strategy to obtain a maintenance time schedule; Maintenance resources are allocated and maintenance procedures are planned for the maintenance time schedule to obtain the maintenance plan for the key equipment.

6. The method for optimizing power system planning and operation according to claim 1, characterized in that: The multi-time scale optimization configuration of system operation parameters based on the virtual power plant group collaborative dispatching strategy and the key equipment maintenance plan to obtain a power system balance control solution includes: Decomposing the virtual power plant group collaborative dispatching strategy according to four time scales: annual, monthly, day-ahead and real-time, to obtain a hierarchical dispatching strategy matrix; Mapping the key equipment maintenance plan in time dimension to generate a time series table of available capacity of the equipment; Perform matching analysis on the hierarchical scheduling strategy matrix and the equipment available capacity time series table to construct a system operation constraint boundary set; According to the system operation constraint boundary set, the operation parameters are configured in different time periods and divided into intervals to obtain a parameter adjustment range table; Performing timing coupling analysis and mutual feedback impact assessment on each parameter in the parameter adjustment range table to generate a parameter coordination control sequence; The parameter coordination control sequence is integrated and optimized at multiple time scales to obtain the power system balance control scheme.

7. The method for optimizing power system planning and operation according to claim 6, characterized in that: The matching analysis of the hierarchical scheduling strategy matrix and the equipment available capacity time series table is performed to construct a system operation constraint boundary set, including: Performing time series analysis on the scheduling data of each time scale in the hierarchical scheduling strategy matrix to generate a scheduling strategy time series feature table; Performing capacity balance analysis on the equipment available capacity time series table according to time nodes to obtain an equipment operation availability curve; Calculate resource matching degree according to the scheduling strategy timing characteristic table and the equipment operation availability curve, and construct a resource allocation constraint matrix; Performing voltage constraint, power constraint and capacity constraint analysis on the resource allocation constraint matrix to form a system operation boundary condition set; Performing regional coordination evaluation on the system operation boundary condition set according to spatial distribution to obtain a regional mutual aid constraint table; The boundary conditions of the regional mutual assistance constraint table are integrated and the constraint mapping is performed to generate the system operation constraint boundary set.

8. A power system planning and operation optimization system, used to implement the power system planning and operation optimization method according to any one of claims 1 to 7, characterized in that: The power system planning and operation optimization system comprises: The extraction module is used to collect and extract features of the power system operation data in multiple dimensions according to electrical parameters, equipment status parameters and environmental parameters to obtain equipment health status assessment data; A partitioning module is used to group and prioritize distributed energy, controllable loads, and energy storage systems based on the equipment health status assessment data and regional extreme weather warning information to form a virtual power plant resource pool; An allocation module, used to perform global task decomposition and target allocation according to the capacity distribution and operation characteristics of the virtual power plant resource pool, and generate a collaborative scheduling strategy for a virtual power plant group; A prediction module is used to predict the status of the equipment and schedule the maintenance schedule according to the equipment health status assessment data and the virtual power plant group collaborative scheduling strategy, and obtain a maintenance plan for key equipment; A configuration module is used to perform multi-time scale optimization configuration of system operating parameters based on the virtual power plant group collaborative dispatching strategy and the key equipment maintenance plan to obtain a power system balance control solution.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and is characterized in that when the processor executes the computer program, the power system planning and operation optimization method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is enabled to execute the power system planning and operation optimization method according to any one of claims 1 to 7.

Images