Power transmission and distribution network coordinated planning method based on power distribution network equivalence

Through the coordinated planning method of transmission and distribution networks based on the distribution network equivalent value, dynamically adjusting the power supply range and building a feedback mechanism, the problem of lack of coordination in the transmission and distribution network planning in the existing technology is solved, and load balancing and grid stability are improved.

CN118982195APending Publication Date: 2024-11-19XUANCHENG POWER SUPPLY OF ANHUI ELECTRIC POWER CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411068958.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing transmission and distribution network planning methods lack effective coordination mechanisms, resulting in complex distribution network structure, many equipment and frequent load changes, making it difficult to achieve load balancing, and overload and light load phenomena are prone to occur, affecting the safety and economics of the power grid.

Method used

Adopt the coordinated planning method of transmission and distribution network based on distribution network equivalent values, through dynamic power supply range division strategy and difference identification and fine-tuning technology, combining load prediction and grid development needs, adjust the power supply range in real time, and build a feedback mechanism for transmission and distribution networks, iteratively Optimize planning results.

Benefits of technology

The balanced distribution of loads between adjacent substations is achieved, the operation efficiency and stability of the power grid is improved, the accuracy and practicality of the planning results are improved, and the reliability and economicality of the power grid is ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982195A_ABST
    Figure CN118982195A_ABST
Patent Text Reader

Abstract

The invention discloses a power transmission and distribution network coordinated planning method based on power distribution network equivalence, and relates to the technical field of power system planning, and the method comprises the following specific steps: S100, constructing a power distribution network equivalence model: constructing the equivalence model of a power distribution network, and simplifying the complex power distribution network into equivalent input parameters and random factors; s200, setting an initial power supply range: setting the initial power supply range by taking a newly built transformer substation as a center and comprehensively considering the capacity, expected load increase and landform factors of the transformer substation; according to the method, the equivalent model of the power distribution network is constructed, the capacity, expected load increase and landform factors of the transformer substations are comprehensively considered, the load coefficient of each transformer substation is updated in real time, the power supply range is dynamically adjusted, the load balance of the power grid is ensured, and the overall operation efficiency and stability of the power grid are improved; and by comparing load coefficients between adjacent transformer substations, areas with large differences are identified and optimized, and the reliability and economical efficiency of the power grid are further improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power system planning, and in particular to a transmission and distribution network coordination planning method based on distribution network equivalence. Background Art

[0002] With the continuous development and expansion of the power system, the planning and management of the transmission and distribution network are facing increasingly complex challenges. The reliable operation and efficient utilization of the power system are not only related to the stable development of the social economy, but also directly affect the electricity experience of the majority of users. In the current power system, the transmission network and the distribution network are two relatively independent subsystems, and their planning process often lacks an effective coordination mechanism, especially the distribution network. Due to its complex structure, numerous equipment and frequent load changes, the impact of its planning results on the transmission network cannot be ignored. Therefore, how to achieve coordinated planning between the transmission and distribution networks has become an urgent problem to be solved in the field of power system planning.

[0003] Traditional transmission and distribution network planning methods often focus on the independent planning of transmission networks or distribution networks, ignoring the close connection and mutual influence between the two. In terms of power supply scope division, traditional methods mostly adopt static or fixed methods, such as determining the power supply scope based on administrative regions, geographical locations or empirical rules. This method lacks flexibility and is difficult to adapt to the dynamic changes in grid load and adjustments to grid structure. In addition, traditional methods often ignore the differences in power supply capacity between different substations and the imbalance of load distribution, resulting in unreasonable power supply scope division, prone to overload and underload, affecting the safety and economy of the power grid.

[0004] In view of the above situation, it is necessary to optimize the existing transmission and distribution network coordination planning method and reverse optimization. By adopting a dynamic power supply range division strategy, the power supply range can be adjusted in real time according to load forecasts and power grid development needs, and the difference identification and fine-tuning technology can be used to achieve balanced distribution of loads between adjacent substations. Therefore, it is of great significance to develop a transmission and distribution network coordination planning method based on distribution network equivalence that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide a transmission and distribution network coordination planning method based on distribution network equivalence. It can adjust the power supply range in real time according to load forecasts and grid development needs by adopting a dynamic power supply range division strategy, and achieve balanced load distribution between adjacent substations through difference identification and fine-tuning technology. In addition, the present invention also constructs a feedback mechanism between transmission and distribution networks, and continuously improves the accuracy and practicality of planning results through iterative optimization.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a transmission and distribution network coordination planning method based on distribution network equivalence, the method comprising the following specific steps:

[0007] S100, Construction of distribution network equivalent model: Constructing an equivalent model of the distribution network and simplifying the complex distribution network into equivalent input parameters and random factors;

[0008] S200, initial power supply range setting: taking the newly built substation as the center, comprehensively considering the capacity of the substation, expected load growth and topographic factors, the initial power supply range is set;

[0009] S300, Dynamic Power Supply Range Adjustment: Based on load forecast and grid development needs, the power supply range is continuously expanded, and the load factor of each substation, i.e. the ratio of load within the power supply range to substation capacity, is updated in real time. By comparing the load factors between adjacent substations, the area with the largest difference is identified;

[0010] S400, transmission and distribution network coordination planning: Based on the distribution network equivalent model and the dynamically adjusted power supply range, the transmission network is planned and optimized, and the power grid is evaluated using the probabilistic power flow calculation method;

[0011] S500, feedback and optimization iteration: Feedback the transmission network planning results to the distribution network equivalent model, consider the impact of transmission network changes on the distribution network, and continuously adjust the distribution network equivalent model and power supply range division strategy through iterative optimization.

[0012] Furthermore, the step S100 includes:

[0013] S101, collecting detailed data of the distribution network, including but not limited to topology, load distribution, equipment parameters, historical data of renewable energy output and its predicted value;

[0014] S102, performing uncertainty analysis on the collected data;

[0015] S103, based on the above data and analysis results, using a power system modeling tool to construct an equivalent model of the distribution network.

[0016] Furthermore, the step S200 includes:

[0017] S201, determine the geographical location of the new substation according to the grid development plan and load distribution;

[0018] S202, with the newly built substation as the center, set the initial power supply range according to the preliminary planning goals and topographic factors.

[0019] Furthermore, the step S300 includes:

[0020] S301, using the ARIMA algorithm to build a load forecasting model to predict load changes in the future;

[0021] S302, calculating the load coefficient of each substation according to the current load distribution and substation capacity;

[0022] S303, gradually expanding the power supply range to cover the newly added load areas according to the load forecast results and the grid development needs;

[0023] S304, while expanding the power supply range, updating the load factor of each substation in real time to reflect the latest load distribution;

[0024] S305, regularly comparing the load coefficients between adjacent substations, identifying areas with large differences, and making the load coefficients between adjacent substations approach the same by fine-tuning the boundaries of the power supply range for the areas with large differences.

[0025] Furthermore, the step S301 collects historical load data, constructs a time series data set, fits the time series data set using the ARIMA model, and uses the fitted ARIMA model to predict the load changes in the future to obtain a predicted load series, the calculation formula of which is: in, is the predicted value at time t, μ is the mean, p is the autoregressive order, φ i is the autoregressive coefficient, y t-i is the actual value at time ti, q is the moving average order, θ j is the moving average coefficient, ∈ t-j is the error term at time tj.

[0026] Furthermore, the specific steps of calculating the load coefficient of each substation in step S302 are as follows:

[0027] (1) According to the current load distribution and substation capacity, the weight factor λ of each substation is set;

[0028] (2) The load coefficient of each substation is calculated using the load coefficient calculation formula k=λT+(-1λ)d, where T represents the load of the substation and d represents the power supply range;

[0029] (3) Analyze the load coefficient of each substation and compare the load differences between different substations;

[0030] (4) Dynamically adjust the power supply range based on the analysis results of the load coefficient.

[0031] Furthermore, the step S305 fine-tunes the boundary of the power supply range by using a gradient descent algorithm. Specifically, the initial power supply range boundary B is set. 0 , and define the loss function L(B) to evaluate the system performance under the current power supply range boundary and calculate the current boundary B t The gradient of the loss function under And according to the gradient descent formula Update the power supply range boundary, where η is the preset learning rate, repeat the iteration, and output the final optimized power supply range boundary B * .

[0032] Furthermore, the step S400 includes:

[0033] S401, based on the distribution network equivalent model and the dynamically adjusted power supply range, the transmission network is evaluated using a probabilistic power flow calculation method;

[0034] S402, formulating a transmission network planning scheme based on the probability power flow calculation results and the power grid planning objectives;

[0035] S403, conduct a comprehensive assessment of the developed planning scheme, including technical feasibility, economic feasibility and social benefits, and optimize and adjust the scheme based on the assessment results.

[0036] Furthermore, the specific steps of evaluating the transmission network using the probabilistic power flow calculation method in step S401 are as follows:

[0037] (1) According to the output characteristic curve of renewable energy on the distribution network side and the power demand curve of the load, the outage capacity and the corresponding probability distribution on the distribution network side are calculated to obtain the distribution network equivalent model;

[0038] (2) Monte Carlo simulation is used to evaluate the impact of different random factors on the power grid state. Specifically, for a vector W containing all random variables, each random variable W i has its corresponding probability distribution P(W i ), from each P(W i ) to form a sample vector W (k) ,Right now Where k is the sample index, for each sample vector W (k) , perform deterministic power flow calculation X (k) =f(W (k) ,Y), and get the corresponding state variable vector X (k) , where f is the power flow calculation function, Y is the system network parameter, and the probability distribution P(X) of the state variable X is obtained through the deterministic power flow calculation results of N samples, that is, P(X) = FitDistribution(X(1) ,X (2) ,…,X (N) );

[0039] (3) Based on the obtained probabilistic power flow calculation results, a series of transmission network planning evaluation indicators are calculated, including voltage over-limit probability, branch overload probability and system reliability index.

[0040] Furthermore, the step S500 uses an ant colony algorithm to iteratively optimize the distribution network equivalent model and the power supply range division strategy. Specifically, the ant colony algorithm parameters are initialized, including the number of ants m, the pheromone importance factor α, the heuristic function importance factor β, the pheromone volatility coefficient ρ, and the maximum number of iterations N, where each ant represents a potential optimization solution, and a fitness function F is defined. For each ant i, starting from the starting point, according to the state transition probability formula Select the next node where τ ij (t) is the amount of pheromone from node i to node j at time t, η ij (t) is the heuristic information, allowed k is the set of nodes that ant k can choose in the next step. After each ant completes a round of path selection, it calculates the quality of the path according to the fitness function F and updates the pheromone. The update rule is in It is the amount of pheromone released by ant k on the path from node i to node j. Repeat the iteration until the maximum number of iterations is reached and the optimization conditions are met, and then output the final optimized distribution network equivalent model and power supply range division strategy.

[0041] Compared with the prior art, the transmission and distribution network coordination planning method based on distribution network equivalence has the following beneficial effects:

[0042] 1. The present invention constructs an equivalent model of the distribution network, comprehensively considers the capacity of the substation, the expected load growth and topographic factors, updates the load coefficient of each substation in real time, dynamically adjusts the power supply range, ensures the load balance of the power grid, and improves the overall operation efficiency and stability of the power grid. In addition, by comparing the load coefficients between adjacent substations, the areas with large differences are identified and optimized, thereby further improving the reliability and economy of the power grid.

[0043] 2. The present invention introduces a probabilistic power flow calculation method to conduct a comprehensive evaluation of the power grid, fully considers the output characteristics of renewable energy on the distribution network side and the randomness of the load, and evaluates the impact of different random factors on the power grid state through Monte Carlo simulation to obtain more accurate and comprehensive power grid state evaluation results. Based on the evaluation results, a more reasonable and optimized transmission network planning scheme is formulated, and the planning scheme is further optimized and adjusted through comprehensive evaluations of technical feasibility, economic efficiency, social benefits and other aspects.

[0044] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 The present invention is a flow chart of a transmission and distribution network coordination planning method based on distribution network equivalence.

[0047] Figure 2 The figure is a flow chart of a transmission and distribution network coordination planning method based on distribution network equivalence. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Embodiment 1

[0050] This embodiment describes in detail the implementation process of a transmission and distribution network coordinated planning method based on distribution network equivalence.

[0051] In the distribution network equivalent model construction stage (S100), detailed data of the distribution network is comprehensively collected, including but not limited to: topological structure data: describing the connection relationship of various devices (such as transformers, lines, switches, etc.) in the distribution network, load distribution data: the load size and distribution of each node or area, equipment parameters: specifications, capacity, efficiency and other parameters of various equipment, historical data of renewable energy output and its predicted value: such as the power generation data of renewable energy power stations such as solar energy and wind energy and their prediction models, uncertainty analysis is performed on the collected data, and various uncertain factors affecting the operation of the distribution network are identified and quantified, such as load fluctuations, uncertainty in renewable energy power generation, etc. Based on the above data and analysis results, an equivalent model of the distribution network is constructed using power system modeling tools (such as MATLAB / Simulink, PSASP, etc.). The model should be able to reflect the main characteristics of the distribution network and simplify the complex actual system to facilitate subsequent analysis and planning.

[0052] In the initial power supply range setting stage (S200), according to the power grid development plan and load distribution, taking into account factors such as topography, traffic conditions, and construction costs, the geographical location of the new substation is determined. With the new substation as the center (or the starting point is set according to specific planning requirements), a reasonable power supply range is preliminarily set according to preliminary planning goals and topography factors. This range needs to cover the initial load demand of the substation and reserve a certain amount of expansion space.

[0053] In the dynamic power supply range adjustment stage (S300), the ARIMA algorithm is used to build a load forecasting model. A time series data set is constructed by collecting historical load data, and model fitting and prediction are performed. According to the current load distribution and substation capacity, the weight factor of each substation is set, and the load coefficient of each substation is calculated using the load coefficient calculation formula. The load coefficient reflects the relative relationship between the current load and capacity of the substation and is an important indicator for evaluating power supply capacity. According to the load forecast results and the development needs of the power grid, the power supply range is gradually expanded to cover the newly added load areas. At the same time, the load coefficient of each substation is updated in real time to reflect the latest load distribution. At the same time, the load coefficients between adjacent substations are compared regularly to identify areas with large differences. For these areas, the boundaries of the power supply range are fine-tuned to make the load coefficients between adjacent substations approach the same, so as to achieve the purpose of balanced power supply.

[0054] In the transmission and distribution network coordination planning stage (S400), based on the distribution network equivalent model and the dynamically adjusted power supply range, the transmission network is evaluated using the probabilistic power flow calculation method. Specifically, according to the output characteristic curve of renewable energy on the distribution network side and the power demand curve of the load, the outage capacity and the corresponding probability distribution on the distribution network side are calculated. Then, the Monte Carlo simulation is used to evaluate the impact of different random factors on the power grid state. Specifically, for the vector W containing all random variables, each random variable W i has its corresponding probability distribution P(W i ), from each P(W i ) to form a sample vector W (k) ,Right now Where k is the sample index, for each sample vector W (k) , perform deterministic power flow calculation X (k) =f(W (k) ,Y), and get the corresponding state variable vector X (k) , where f is the power flow calculation function, Y is the system network parameter, and the probability distribution P(X) of the state variable X is obtained through the deterministic power flow calculation results of N samples, that is, P(X) = FitDistribution(X (1) ,X (2) ,…,X (N) ), formulate a transmission network planning scheme based on the probabilistic flow calculation results and power grid planning objectives (such as reliability, economy, environmental friendliness, etc.). The scheme should take various factors into consideration to ensure the coordinated development of the transmission network and the distribution network. A comprehensive evaluation should be conducted on the formulated planning scheme, including technical feasibility, economy, and social benefits. The scheme should be optimized and adjusted according to the evaluation results to ensure the scientificity and rationality of the planning scheme.

[0055] In the feedback and optimization iteration stage (S500), the transmission network planning results are fed back to the distribution network equivalent model. Considering the impact of transmission network changes on the distribution network, the weighted Voronoi diagram method is used to iteratively optimize the distribution network equivalent model and the power supply range division strategy. By continuously adjusting the weights of substations and distributed power sources, reconstructing the weighted Voronoi diagram and evaluating the optimization results, the distribution network equivalent model and power supply range division strategy that meet the planning objectives are finally obtained.

[0056] Embodiment 2

[0057] Based on the first embodiment, this embodiment describes in detail the specific steps of the dynamic power supply range adjustment phase of a transmission and distribution network coordination planning method based on distribution network equivalence.

[0058] In the dynamic power supply range adjustment stage, the ARIMA algorithm is used to build a load forecasting model. By collecting historical load data to build a time series data set, and performing model fitting, the fitted ARIMA model is used to predict the load changes in the future period of time to obtain the predicted load sequence. The calculation formula is: in, is the predicted value at time t, μ is the mean, p is the autoregressive order, φ i is the autoregressive coefficient, y t-i is the actual value at time ti, q is the moving average order, θ j is the moving average coefficient, ∈ t-j is the error term at time tj.

[0059] According to the current load distribution and substation capacity, the load coefficient of each substation is calculated. The specific steps are as follows:

[0060] (1) According to the current load distribution and substation capacity, the weight factor λ of each substation is set;

[0061] (2) The load coefficient of each substation is calculated using the load coefficient calculation formula k=λT+(-1λ)d, where T represents the load of the substation and d represents the power supply range;

[0062] (3) Analyze the load coefficient of each substation and compare the load differences between different substations;

[0063] (4) Dynamically adjust the power supply range based on the analysis results of the load coefficient.

[0064] According to the load forecast results and the needs of grid development, the power supply range is gradually expanded to cover the newly added load areas, and the load coefficient of each substation is updated in real time to reflect the latest load distribution. At the same time, the load coefficients between adjacent substations are regularly compared to identify areas with large differences. For these areas, the boundaries of the power supply range are fine-tuned through the gradient descent algorithm. Specifically, the initial power supply range boundary B is set. 0 , and define the loss function L(B) to evaluate the system performance under the current power supply range boundary and calculate the current boundary B t The gradient of the loss function under And according to the gradient descent formula Update the power supply range boundary, where η is the preset learning rate, repeat the iteration, and output the final optimized power supply range boundary B * .

[0065] The transmission network planning results are fed back to the distribution network equivalent model. Considering the impact of transmission network changes on the distribution network, the ant colony algorithm is used to iteratively optimize the distribution network equivalent model and the power supply range division strategy. Specifically, the ant colony algorithm parameters are initialized, including the number of ants m, the pheromone importance factor α, the heuristic function importance factor β, the pheromone volatility coefficient ρ, and the maximum number of iterations N. Each ant represents a potential optimization solution. The fitness function F is defined. For each ant i, starting from the starting point, according to the state transition probability formula Select the next node where τ ij (t0 is the amount of pheromone from node i to node j at time t, η ij (t) is the heuristic information, allowed k is the set of nodes that ant k can choose in the next step. After each ant completes a round of path selection, it calculates the quality of the path according to the fitness function F and updates the pheromone. The update rule is in It is the amount of pheromone released by ant k on the path from node i to node j. Repeat the iteration until the maximum number of iterations is reached and the optimization conditions are met, and then output the final optimized distribution network equivalent model and power supply range division strategy.

[0066] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A transmission and distribution network coordination planning method based on distribution network equivalence, characterized in that: The method comprises the following specific steps: S100, Construction of distribution network equivalent model: Constructing an equivalent model of the distribution network and simplifying the complex distribution network into equivalent input parameters and random factors; S200, initial power supply range setting: taking the newly built substation as the center, comprehensively considering the capacity of the substation, expected load growth and topographic factors, the initial power supply range is set; S300, Dynamic Power Supply Range Adjustment: Based on load forecast and grid development needs, the power supply range is continuously expanded, and the load factor of each substation, i.e. the ratio of load within the power supply range to substation capacity, is updated in real time. By comparing the load factors between adjacent substations, the area with the largest difference is identified; S400, transmission and distribution network coordination planning: Based on the distribution network equivalent model and the dynamically adjusted power supply range, the transmission network is planned and optimized, and the power grid is evaluated using the probabilistic power flow calculation method; S500, feedback and optimization iteration: Feedback the transmission network planning results to the distribution network equivalent model, consider the impact of transmission network changes on the distribution network, and continuously adjust the distribution network equivalent model and power supply range division strategy through iterative optimization.

2. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 1, characterized in that: The step S100 includes: S101, collecting detailed data of the distribution network, including but not limited to topology, load distribution, equipment parameters, historical data of renewable energy output and its predicted value; S102, performing uncertainty analysis on the collected data; S103, based on the above data and analysis results, using a power system modeling tool to construct an equivalent model of the distribution network.

3. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 1, characterized in that: The step S200 includes: S201, determine the geographical location of the new substation according to the grid development plan and load distribution; S202, with the newly built substation as the center, set the initial power supply range according to the preliminary planning goals and topographic factors.

4. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 1, characterized in that: The step S300 includes: S301, using the ARIMA algorithm to build a load forecasting model to predict load changes in the future; S302, calculating the load coefficient of each substation according to the current load distribution and substation capacity; S303, gradually expanding the power supply range to cover the newly added load areas according to the load forecast results and the grid development needs; S304, while expanding the power supply range, updating the load factor of each substation in real time to reflect the latest load distribution; S305, regularly comparing the load coefficients between adjacent substations, identifying areas with large differences, and making the load coefficients between adjacent substations approach the same by fine-tuning the boundaries of the power supply range for the areas with large differences.

5. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 4, characterized in that: The step S301 collects historical load data, constructs a time series data set, fits the time series data set using the ARIMA model, and uses the fitted ARIMA model to predict the load changes in the future to obtain a predicted load sequence, the calculation formula of which is: in, is the predicted value at time t, μ is the mean, p is the autoregressive order, φ i is the autoregressive coefficient, y t-i is the actual value at time ti, q is the moving average order, θ j is the moving average coefficient, ∈ t-j is the error term at time tj.

6. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 4, characterized in that: The specific steps of calculating the load coefficient of each substation in step S302 are: (1) According to the current load distribution and substation capacity, the weight factor λ of each substation is set; (2) The load coefficient of each substation is calculated using the load coefficient calculation formula k=λT+(-1λ)d, where T represents the load of the substation and d represents the power supply range; (3) Analyze the load coefficient of each substation and compare the load differences between different substations; (4) Dynamically adjust the power supply range based on the analysis results of the load coefficient.

7. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 4, characterized in that: The step S305 fine-tunes the boundary of the power supply range by using a gradient descent algorithm. Specifically, the initial power supply range boundary B is set. 0 , and define the loss function L(B) to evaluate the system performance under the current power supply range boundary and calculate the current boundary B t The gradient of the loss function under And according to the gradient descent formula Update the power supply range boundary, where η is the preset learning rate, repeat the iteration, and output the final optimized power supply range boundary B * .

8. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 1, characterized in that: The step S400 includes: S401, based on the distribution network equivalent model and the dynamically adjusted power supply range, the transmission network is evaluated using a probabilistic power flow calculation method; S402, formulating a transmission network planning scheme based on the probability power flow calculation results and the power grid planning objectives; S403, conduct a comprehensive assessment of the developed planning scheme, including technical feasibility, economic feasibility and social benefits, and optimize and adjust the scheme based on the assessment results.

9. A transmission and distribution network coordination planning method based on distribution network equivalence according to claim 8, characterized in that: The specific steps of step S401 to evaluate the transmission network using the probabilistic power flow calculation method are as follows: (1) According to the output characteristic curve of renewable energy on the distribution network side and the power demand curve of the load, the outage capacity and the corresponding probability distribution on the distribution network side are calculated to obtain the distribution network equivalent model; (2) Monte Carlo simulation is used to evaluate the impact of different random factors on the power grid state. Specifically, for a vector W containing all random variables, each random variable W i has its corresponding probability distribution P(W i ), from each P(W i ) to form a sample vector W (k) ,Right now Where k is the sample index, for each sample vector W (k) , perform deterministic power flow calculation X (k) =f(W (k) ,Y), and get the corresponding state variable vector X (k) , where f is the power flow calculation function, Y is the system network parameter, and the probability distribution P(X) of the state variable X is obtained through the deterministic power flow calculation results of N samples, that is, P(X) = FitDistribution(X (1) ,X (2) ,…,X (N) ); (3) Based on the obtained probabilistic power flow calculation results, a series of transmission network planning evaluation indicators are calculated, including voltage over-limit probability, branch overload probability and system reliability index.

10. A transmission and distribution network coordinated planning method based on distribution network equivalence according to claim 1, characterized in that: The step S500 uses the ant colony algorithm to iteratively optimize the distribution network equivalent model and the power supply range division strategy. Specifically, the ant colony algorithm parameters are initialized, including the number of ants m, the pheromone importance factor α, the heuristic function importance factor β, the pheromone volatility coefficient ρ, and the maximum number of iterations N. Each ant represents a potential optimization solution, and a fitness function F is defined. For each ant i, starting from the starting point, according to the state transition probability formula Select the next node where τ ij (t) is the amount of pheromone from node i to node j at time t, η ij (t) is the heuristic information, allowed k is the set of nodes that ant k can choose in the next step. After each ant completes a round of path selection, it calculates the quality of the path according to the fitness function F and updates the pheromone. The update rule is in It is the amount of pheromone released by ant k on the path from node i to node j. Repeat the iteration until the maximum number of iterations is reached and the optimization conditions are met, and then output the final optimized distribution network equivalent model and power supply range division strategy.