Distributed wind power acceptance capability assessment method, system, equipment and medium

Abstract

The invention discloses a distributed wind power acceptance capability assessment method, system and device and a medium, and relates to the technical field of rural power grid distributed wind power acceptance capability assessment, and the method comprises the steps: constructing a probability model of distributed wind power output power and power grid load; constructing a distributed wind power access capacity optimization model based on the target function, and calculating the distributed wind power access capacity by adopting a reinforcement learning algorithm; and constructing a distributed wind power acceptance capability evaluation system, and obtaining a distributed wind power acceptance capability evaluation result by comparing examples. According to the method, the uncertainty of the wind power output power and the randomness of the load are accurately described through the established probability simulation model; by adopting the improved SAC algorithm, the high-dimensional continuous action space is efficiently processed, wind power is received as much as possible, and the utilization rate of renewable energy sources is increased; by constructing a distributed wind power acceptance capability assessment system, the reliability and flexibility of wind power access to the power grid are comprehensively assessed, and the operation of the power grid is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed wind power acceptance capacity assessment for rural power grids, and in particular to a distributed wind power acceptance capacity assessment method, system, equipment and medium. Background Art

[0002] As the global energy structure transitions toward a low-carbon one, distributed wind power has become an important energy supplement for rural power grids due to its cleanliness, flexibility, and local consumption advantages. Rural power grids typically have low load density, weak grid structure, and limited peak-shaving capacity. The access of distributed wind power can not only alleviate power supply pressure in remote areas, but also promote the consumption of renewable energy. However, the randomness, volatility, and anti-peaking characteristics of wind power pose severe challenges to the voltage stability, line capacity margin, and power balance of rural power grids.

[0003] Traditional wind power acceptance capacity assessment methods mainly include static assessment and dynamic assessment. Static assessment is based on the preset grid topology and typical operating conditions, and solves the maximum access capacity through linear programming or heuristic algorithms. However, it ignores the temporal and spatial volatility of wind power and has difficulty reflecting real-time operating constraints. Although dynamic assessment considers wind power output changes through time series simulation, it relies on precise physical models and a large amount of computing resources. When faced with complex scenarios with multiple nodes and multiple constraints in rural power grids, it suffers from the problem of dimensionality disaster and low convergence efficiency. In addition, traditional methods often use Monte Carlo simulation when dealing with probabilistic constraints, which has high computational costs and makes it difficult to achieve multi-objective collaborative optimization.

[0004] Reinforcement learning (RL) algorithms, with their data-driven and adaptive decision-making characteristics, offer a breakthrough path to addressing these challenges. For example, the improved Soft Actor-Critic (SAC) algorithm achieves efficient exploration and convergence in high-dimensional continuous action spaces by maximizing cumulative rewards and policy entropy. This algorithm is particularly well-suited for rural power grid scenarios involving uncertainty modeling, complex constraint processing, and multi-objective optimization. It can simultaneously optimize access capacity and operational risk, outperforming traditional single-objective optimization methods. Compared to traditional methods, the improved SAC algorithm demonstrates significant advantages in convergence speed, high-dimensional nonlinear problem handling, and real-time decision-making capabilities, providing efficient and intelligent technical support for the large-scale integration of distributed wind power into rural power grids. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: the existing distributed wind power acceptance capacity assessment method cannot take into account the uncertainty of wind power output, is difficult to handle probabilistic constraints, is difficult to achieve multi-objective collaborative optimization, and how to efficiently evaluate the distributed wind power acceptance capacity.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for evaluating distributed wind power acceptance capacity, comprising obtaining wind speed and wind turbine power characteristics and constructing a distributed wind power output power probability model, obtaining historical grid load parameters and constructing a grid load probability model; constructing a distributed wind power access capacity optimization model based on an objective function, and calculating the distributed wind power access capacity using a reinforcement learning algorithm; constructing a distributed wind power acceptance capacity evaluation system based on defined flexibility and reliability indicators, and obtaining distributed wind power acceptance capacity evaluation results through comparative examples.

[0009] As a preferred solution of the distributed wind power acceptance capacity assessment method described in the present invention, the construction of a distributed wind power output probability model includes determining a wind speed probability density function by acquiring historical wind speed data; defining a wind speed interval in combination with the segmented characteristics of the wind turbine output power, and deriving a wind power output power probability model based on the defined wind speed interval.

[0010] As a preferred solution of the distributed wind power acceptance capacity assessment method described in the present invention, the construction of the grid load probability model includes calculating the load power mean and variance by obtaining historical grid load data; based on the load obeying the normal distribution, simulating the randomness of the load, and obtaining the probability density function of the load.

[0011] As a preferred solution of the distributed wind power acceptance capacity assessment method described in the present invention, the construction of a distributed wind power access capacity optimization model includes defining an objective function based on the grid safety operation constraints and the uncertainty of wind power; the objective function is to maximize the total access capacity of the candidate node set.

[0012] As a preferred embodiment of the distributed wind power acceptance capacity assessment method described in the present invention, the method of calculating the distributed wind power access capacity using a reinforcement learning algorithm includes constructing a state space, an action space, and a reward function of the reinforcement learning algorithm; executing the reinforcement learning algorithm based on the reinforcement learning algorithm process, and outputting the optimal strategy and the maximum access capacity when the access capacity fluctuation for 10 consecutive iterations is less than 1%, thereby obtaining the distributed wind power access capacity.

[0013] As a preferred solution of the distributed wind power acceptance capacity assessment method described in the present invention, the construction of a distributed wind power acceptance capacity assessment system includes defining flexibility indicators and reliability indicators based on the flexibility and reliability of the power grid, and selecting key operating parameters of the power grid to form a distributed wind power carrying capacity assessment index system for the power grid.

[0014] As a preferred embodiment of the distributed wind power acceptance capacity assessment method described in the present invention, the method of obtaining the distributed wind power acceptance capacity assessment result by comparing calculation examples includes calculating the indicator difference between the baseline scenario and the optimization scenario through a comparison algorithm to obtain the distributed wind power acceptance capacity assessment result of the power grid.

[0015] Secondly, the present invention provides a distributed wind power acceptance capacity assessment system, which can construct a probabilistic simulation model of wind power output power and a grid load probability model by obtaining wind speed, wind turbine power characteristics and historical grid load parameters, and obtain a probability function, thereby solving the problem that the existing technology cannot effectively handle the uncertainty of wind power output and the randomness of load.

[0016] As a preferred solution of the distributed wind power acceptance capacity assessment system described in the present invention, it includes: a data acquisition module, an optimization output module, and a comparative evaluation module; the data acquisition module is used to obtain wind speed and wind turbine power characteristics and construct a distributed wind power output power probability model, obtain historical power grid load parameters and construct a power grid load probability model; the optimization output module is used to construct a distributed wind power access capacity optimization model based on the objective function, and use a reinforcement learning algorithm to calculate the distributed wind power access capacity; the comparative evaluation module is used to construct a distributed wind power acceptance capacity assessment system based on defined flexibility and reliability indicators, and obtain distributed wind power acceptance capacity assessment results through comparative calculation examples.

[0017] In a third aspect, the present invention provides an electronic device, comprising:

[0018] memory and processor;

[0019] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distributed wind power acceptance capacity assessment method are implemented.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the distributed wind power acceptance capacity assessment method.

[0021] Beneficial effects of the present invention: The distributed wind power acceptance capacity assessment method provided by the present invention can accurately describe the uncertainty of wind power output power and the randomness of load through the established probabilistic simulation model, thereby more realistically reflecting the operating status of the rural power grid and avoiding the limitations of traditional static assessment methods; by dynamically adjusting the allowed access range based on historical data and probability distribution, the assessment results can be made more in line with the actual situation; by adopting the improved SAC algorithm to output the optimal strategy, the maximum access capacity of distributed wind power is obtained, which can efficiently process high-dimensional continuous action space, avoid the dimensional disaster and low convergence efficiency problems of traditional dynamic assessment methods, and at the same time, the access capacity is used to evaluate the performance of the distributed wind power system. With the goal of maximizing the amount of wind power, it can accept as much wind power as possible under the premise of ensuring the safe operation of the power grid, thereby improving the utilization rate of renewable energy; by dynamically adjusting the ratio of capacity weight and safety weight in the reward function, a balance between economy and safety can be achieved, and an access plan that is more in line with the actual situation can be obtained; by constructing a distributed wind power acceptance capacity evaluation system and evaluating various indicators, the impact of wind power access on the reliability and flexibility of the power grid can be comprehensively evaluated, and a basis for optimizing the operation of the power grid can be provided; the present invention has achieved better results in describing the accuracy of wind power output power and load, evaluating wind power access capacity, and providing an access plan that takes into account both economy and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is an overall flow chart of a distributed wind power acceptance capacity assessment method provided by the first embodiment of the present invention.

[0024] Figure 2 A wind turbine power output curve diagram of a distributed wind power acceptance capacity assessment method provided in a second embodiment of the present invention.

[0025] Figure 3 This is a diagram showing wind power acceptance capacity assessment results of a distributed wind power acceptance capacity assessment method provided by the second embodiment of the present invention.

[0026] Figure 4 This is an overall flow chart of a distributed wind power acceptance capacity assessment system provided by the third embodiment of the present invention. DETAILED DESCRIPTION

[0027] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that 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 persons in this field without creative work should fall within the scope of protection of the present invention.

[0028] Example 1, reference Figure 1 , as one embodiment of the present invention, provides a method for evaluating distributed wind power acceptance capacity, comprising:

[0029] S1: Obtain wind speed and wind turbine power characteristics and build a distributed wind power output power probability model, obtain grid historical load parameters and build a grid load probability model.

[0030] S2: Based on the objective function, a distributed wind power access capacity optimization model is constructed, and the distributed wind power access capacity is calculated using the reinforcement learning algorithm.

[0031] S3: Based on the defined flexibility and reliability indicators, a distributed wind power acceptance capacity evaluation system is constructed, and the distributed wind power acceptance capacity evaluation results are obtained through comparative examples.

[0032] It should be noted that when distributed wind power is connected to the rural power grid, due to its randomness, volatility and anti-peak characteristics, the sudden change in wind power output may cause the node voltage to exceed the limit, increase the risk of line overload, and then cause a chain reaction failure. Therefore, scientifically evaluating the wind power acceptance capacity of the rural power grid is the core prerequisite for optimizing the wind power layout and ensuring the safe operation of the power grid.

[0033] Therefore, in order to address the node voltage over-limit problem caused by the inability to scientifically evaluate the wind power acceptance capacity of rural power grids, steps S1-S3 are used to construct a distributed wind power output power probability model to simulate the uncertainty of wind power output power, and a grid load probability model is constructed to simulate the reliability probability of rural power grid load, so as to achieve accurate derivation of wind power output power and rural power grid load; and based on the derivation of the probability model, a distributed wind power access capacity optimization model is constructed to calculate the maximum distributed wind power capacity that the rural power grid load can accept under a certain probability, and through the distributed wind power acceptance capacity evaluation system, it is evaluated whether the acceptance capacity meets the economic and safety standards, so as to achieve a scientific evaluation of the wind power acceptance capacity of rural power grids.

[0034] Example 2, reference Figure 1-Figure 3 , which is an embodiment of the present invention, provides a distributed wind power acceptance capacity evaluation method based on the above embodiment.

[0035] In the embodiment of the present application, constructing a distributed wind power output probability model in step S1 includes the following steps A1-A2:

[0036] A1: Determine the wind speed probability density function by obtaining historical wind speed data;

[0037] A2: Based on the segmented characteristics of wind turbine output power, define wind speed intervals and derive a wind power output power probability model based on the defined wind speed intervals.

[0038] Specifically, in A1, the annual average wind speed in most areas conforms to the Weibull distribution, so the specific expression of the wind speed probability density function is:

[0039]

[0040] Where v is the wind speed, k and c are the shape parameter and scale parameter of the Weibull distribution;

[0041] In A2, the output power of the wind turbine has an uncertain characteristic that varies with wind speed. Figure 2 The wind turbine power output curve is as follows:

[0042]

[0043] Where k1 = p r / (v r -v ci ), k2=-k1v ci , P r is the rated power of the wind turbine, v r is the rated wind speed, v ci is the cut-in wind speed, v co To cut out wind speed;

[0044] In practice, the wind speed is between the cut-in wind speed and the rated wind speed for most of the time, that is, the wind speed and output active power satisfy a linear relationship. The probability distribution of the distributed wind power output can be calculated and derived, which is expressed as:

[0045]

[0046] Among them, F(p w ) is the probability distribution of distributed wind power output power.

[0047] In an optional implementation, the NWP model can also be used to predict meteorological parameters such as wind speed and wind direction in the future, and combined with the power curve of the wind turbine generator set to calculate the probability distribution of future wind power output and construct a distributed wind power output power probability model.

[0048] In another optional embodiment, a model of a single wind turbine generator set can be established, the influence of factors such as rotor blade characteristics and control system on the wind turbine output can be considered, the wind turbine output at different wind speeds can be simulated, and the probability distribution of wind power output can be calculated.

[0049] In the embodiment of the present application, constructing the grid load probability model in step S1 includes the following steps B1-B2:

[0050] B1: Calculate the load power mean and variance by obtaining historical grid load data;

[0051] B2: Based on the load obeying normal distribution, simulate the randomness of the load and obtain the probability density function of the load.

[0052] Specifically, based on the fact that there is enough measured load data for rural power grids, the load power obeys the normal distribution. Based on the normal distribution to simulate the randomness of the load, the probability density function of the load is expressed as:

[0053]

[0054] Where y is the historical measured data of rural power grid load power, y=y i ,i=1,2,...,N,μ is the average load power of rural power grid,σ 2 is the rural power grid load power variance.

[0055] In the embodiment of the present application, in step S2, a distributed wind power access capacity optimization model is constructed, including defining an objective function based on grid safety operation constraints and wind power uncertainty.

[0056] Specifically, the objective function is defined as maximizing the total access capacity of the candidate node set Ω, which can be expressed as:

[0057]

[0058] Among them, Ω is the set of candidate wind power access nodes, P w,i is the wind power access capacity of node i;

[0059] Grid safety operation constraints include node voltage constraints, line capacity constraints, power balance constraints, wind power output fluctuation constraints, and radial topology constraints;

[0060] The node voltage constraint is expressed as:

[0061]

[0062] Among them, V i is the voltage amplitude of node i, N is the set of grid nodes, V min 、Vmax is the minimum and maximum value of the node voltage;

[0063] The line capacity constraint is expressed as:

[0064]

[0065] Among them, S ij is the apparent power of line i,j, is the apparent maximum power of line i, j, L is the line set;

[0066] The power balance constraint is expressed as:

[0067] ∑P w,i +P grid ΣP load +P loss

[0068] Among them, P grid Indicates the grid injected power, P load Indicates load power, P loss Indicates network loss;

[0069] Wind power output fluctuation constraint is expressed as:

[0070]

[0071] Among them, P w,i (t) represents the distributed wind power output active power at time t, They represent the minimum and maximum values ​​of the allowed access range that is dynamically adjusted based on the wind power output probability distribution generated based on historical data;

[0072] The radial topology constraint uses the improved DistFlow model to describe the radial characteristics of the rural power grid to ensure the solvability of the power flow equation. The radial topology constraint is expressed as:

[0073]

[0074] in, is the set of downstream nodes of node j, r ij 、x ij Represents line resistance and reactance, V i and V j are the voltages of nodes i and j, respectively, P ij , Q ij is the injected active power and reactive power of node i at time t, P jk , Q jk are respectively the active power flow and reactive power flow of branch jk, P load,j , Q load,j are the node active load and reactive load respectively.

[0075] In the embodiment of the present application, the calculation of the distributed wind power access capacity using the reinforcement learning algorithm in step S2 includes the following steps C1-C3:

[0076] C1: Construct the state space, action space, and reward function of the reinforcement learning algorithm;

[0077] C2: Execute reinforcement learning algorithm based on the reinforcement learning algorithm process;

[0078] C3: When the access capacity fluctuation is less than 1% for 10 consecutive iterations, the optimal strategy and maximum access capacity are output to obtain the distributed wind power access capacity.

[0079] It should be noted that the reinforcement learning algorithm used in C1 is the improved SAC algorithm, and the state space, action space and reward function of the SAC algorithm are improved according to the characteristics of rural power grids.

[0080] Specifically, in C1, the state space, action space and reward function of the improved SAC algorithm are constructed;

[0081] State space parameters include grid state parameters and environmental state parameters; among them, grid state parameters include node voltage V i , line power S ij and load demand P load ; Environmental status parameters include wind power forecast output and temporal characteristics;

[0082] Temporal features include but are not limited to seasons, time periods, and other features;

[0083] Action space, adjust the wind power access capacity of each node ΔP w,i , and normalized to -1,1;

[0084] Construct the reward function, which is expressed as:

[0085]

[0086] Among them, α and β are the capacity weight coefficient and safety weight coefficient of the reward function respectively, V ref Indicates an over-limit voltage.

[0087] It should be noted that by improving the reward function and dynamically adjusting the ratio of α / β, the economy and safety of wind power access capacity can be reasonably balanced.

[0088] In C2, the improved SAC algorithm process includes the following steps C21-C25:

[0089] C21: Constructs grid topology parameters, load time series data, and historical wind power output, initializes Actor and Critic network weights, initializes the experience replay pool capacity, and initializes the initial number of exploration steps;

[0090] C22: Selects an action based on the current strategy, calculates access capacity, verifies constraints, and returns the reward and next state.

[0091] C23: Store data into the experience pool and sort by priority;

[0092] C24: Update the Critic network based on minimizing the Bellman error, and update the Actor network based on maximizing the expected return and entropy;

[0093] C25: When the access capacity fluctuation is less than 1% for 10 consecutive iterations, the training is terminated and the optimal strategy is output. This means that the training termination condition is met, which is expressed as:

[0094]

[0095] In an optional embodiment, the reinforcement learning algorithm can also adopt an algorithm based on a value function, such as the Q-Learning algorithm, which selects actions that can maximize future cumulative rewards by learning the state-action value function, i.e., the Q function, iteratively trains, and outputs the optimal strategy.

[0096] In another optional implementation, in order to improve the efficiency and accuracy of distributed wind power access capacity calculation, a deep Q network algorithm combined with a proximal strategy optimization algorithm may be used to obtain the maximum capacity of distributed wind power access.

[0097] In the embodiment of the present application, constructing a distributed wind power acceptance capacity evaluation system in step S3 includes defining flexibility indicators and reliability indicators based on the flexibility and reliability of the power grid, and selecting key operating parameters of the power grid to form a distributed wind power carrying capacity evaluation index system for the power grid.

[0098] Specifically, grid flexibility refers to the ability of the grid to quickly respond to changes in distributed wind power and load uncertainty by adjusting the output of various types of equipment within a certain time scale;

[0099] In the implementation manner of this application, the flexibility indicators include the proportion of distributed wind power generation and the distributed wind power absorption rate;

[0100] Specifically, the proportion of distributed wind power generation is the ratio of distributed wind power generation power to the total load of all nodes, and the formal expression is:

[0101] F PW =P PW,t / P load,t

[0102] Among them, F PW is the proportion of distributed wind power generation, P PW,t is the distributed wind power generation power at time t, P load,t is the load power at time t;

[0103] The distributed wind power consumption rate is the ratio of distributed wind power generation power to distributed wind power forecast power, and its formal expression is:

[0104] F cons =P PW,t / P PW,f,t

[0105] Among them, F cons is the distributed wind power consumption rate, P PW,f,t Forecast the power generation of distributed wind power at time t;

[0106] Grid reliability refers to the ability of the grid to meet the electricity and power demands of users at acceptable standards and expected quantities;

[0107] In the embodiment of the present application, the reliability indicators include voltage qualification rate, voltage deviation rate and network loss rate;

[0108] Taking the rural power grid as an example, the voltage qualification rate is the ratio of the number of nodes whose voltage is within the qualified voltage range to the total number of nodes in the rural power grid. The formal expression is:

[0109] R sat =n sat,t / N node

[0110] Among them, R sat is the voltage qualification rate, n sat,t is the number of nodes that meet the voltage qualification standard at time t, N node is the total number of nodes;

[0111] The voltage deviation rate is the deviation ratio between the rural power grid node and the rated voltage, and its formal expression is:

[0112] R ΔU =|U N -U i,t | / U N

[0113] Among them, R ΔU is the voltage deviation rate, U N is the rated voltage, U i,t is the node voltage of the i-th node at time t;

[0114] The network loss rate is the ratio of the active power loss of the rural power grid line to the total load, and the formal expression is:

[0115]

[0116] Among them, R loss is the network loss rate, N line is the total number of lines, I i,t is the current of the i-th circuit at time t, R i is the resistance of the i-th circuit.

[0117] In the embodiment of the present application, in step S3, refer to Figure 3 ,Taking nodes 7, 10, and 18 as examples, the distributed wind power acceptance capacity evaluation results are obtained through comparative examples, including calculating the indicator differences between the benchmark scenario and the optimized scenario through the comparative algorithm, and obtaining the distributed wind power acceptance capacity evaluation results of the power grid.

[0118] Example 3, reference Figure 4 , which is the third embodiment of the present invention, provides a system for evaluating the distributed wind power acceptance capacity, including a data acquisition module, an optimization output module, and a comparison and evaluation module.

[0119] Among them, the data acquisition module is used to obtain wind speed and wind turbine power characteristics and construct a distributed wind power output power probability model, obtain the historical load parameters of the power grid and construct a power grid load probability model; the optimization output module is used to construct a distributed wind power access capacity optimization model based on the objective function, and use the reinforcement learning algorithm to calculate the distributed wind power access capacity; the comparative evaluation module is used to construct a distributed wind power acceptance capacity evaluation system based on the defined flexibility and reliability indicators, and obtain the distributed wind power acceptance capacity evaluation results through comparative examples.

[0120] This embodiment also provides an electronic device suitable for distributed wind power acceptance capacity assessment, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the distributed wind power acceptance capacity assessment method proposed in the above embodiment.

[0121] This embodiment further provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for evaluating the distributed wind power acceptance capacity proposed in the above embodiment is implemented.

[0122] The storage medium proposed in this embodiment and the method for implementing distributed wind power acceptance capacity assessment proposed in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0123] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0124] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating distributed wind power acceptance capacity, characterized in that: include: Obtain wind speed and wind turbine power characteristics and build a distributed wind power output power probability model; obtain historical grid load parameters and build a grid load probability model; Based on the objective function, a distributed wind power access capacity optimization model is constructed, and the distributed wind power access capacity is calculated using a reinforcement learning algorithm. Based on the defined flexibility and reliability indicators, a distributed wind power acceptance capacity evaluation system is constructed, and the distributed wind power acceptance capacity evaluation results are obtained through comparative examples.

2. The distributed wind power acceptance capacity assessment method according to claim 1, wherein: The constructing of the distributed wind power output probability model includes determining a wind speed probability density function by acquiring historical wind speed data; Combined with the segmented characteristics of wind turbine output power, wind speed intervals are defined, and based on the defined wind speed intervals, a wind power output power probability model is derived.

3. The distributed wind power acceptance capacity assessment method according to claim 2, wherein: The constructing of the grid load probability model includes calculating the load power mean and variance by acquiring the historical grid load data; Based on the load obeying normal distribution, the randomness of the load is simulated and the probability density function of the load is obtained.

4. The distributed wind power acceptance capacity assessment method according to claim 3, wherein: The construction of the distributed wind power access capacity optimization model includes defining an objective function based on grid safety operation constraints and wind power uncertainty; The objective function is to maximize the total access capacity of the candidate node set.

5. The distributed wind power acceptance capacity assessment method according to claim 4, wherein: The method of calculating the distributed wind power access capacity using a reinforcement learning algorithm includes constructing a state space, an action space, and a reward function of the reinforcement learning algorithm; Based on the reinforcement learning algorithm process, the reinforcement learning algorithm is executed. When the access capacity fluctuation of 10 consecutive iterations is less than 1%, the optimal strategy and maximum access capacity are output to obtain the distributed wind power access capacity.

6. The distributed wind power acceptance capacity assessment method according to claim 5, wherein: The construction of the distributed wind power acceptance capacity evaluation system includes defining flexibility indicators and reliability indicators based on the flexibility and reliability of the power grid, and selecting key power grid operating parameters to form a power grid distributed wind power carrying capacity evaluation index system.

7. The distributed wind power acceptance capacity assessment method according to claim 6, wherein: The obtaining of the distributed wind power acceptance capacity evaluation result by comparing calculation examples includes calculating the index difference between the baseline scenario and the optimization scenario by comparing algorithms to obtain the distributed wind power acceptance capacity evaluation result of the power grid.

8. A distributed wind power acceptance capacity assessment system, applying the method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, optimization output module, comparison and evaluation module; The data acquisition module is used to obtain wind speed and wind turbine power characteristics and build a distributed wind power output power probability model, obtain power grid historical load parameters and build a power grid load probability model; The optimization output module is used to construct a distributed wind power access capacity optimization model based on the objective function and calculate the distributed wind power access capacity using a reinforcement learning algorithm; The comparative evaluation module is used to construct a distributed wind power acceptance capacity evaluation system based on defined flexibility and reliability indicators, and obtain a distributed wind power acceptance capacity evaluation result through comparative calculation examples.

9. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distributed wind power acceptance capacity assessment method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the distributed wind power acceptance capacity assessment method according to any one of claims 1 to 7.

Images