Rural power grid distributed wind power acceptance capability assessment method based on improved SAC algorithm

Abstract

The invention relates to the technical field of rural power grid distributed wind power acceptance capability evaluation, and discloses a rural power grid distributed wind power acceptance capability evaluation method and system based on an improved SAC algorithm, and the method comprises the steps: considering the uncertainty of wind power output, and building a probability simulation model of distributed wind power output power; establishing a rural power grid load probability model by considering the random characteristic of the load; establishing a rural power grid distributed wind power acceptance capability evaluation model, constructing an objective function, and determining constraint conditions; providing an accepting ability evaluation model solving method based on an improved flexible action-evaluation (SAC) algorithm, constructing an algorithm framework, and executing an algorithm solving model; constructing a rural power grid distributed wind power acceptance capability evaluation index system for evaluating an evaluation result; and verifying the feasibility and effectiveness of the proposed method by comparing examples to obtain a rural power grid distributed wind power acceptance capability assessment result.

Description

Technical Field

[0001] The present invention relates to the technical field of assessing the acceptance capacity of decentralized wind power in rural power grids, and particularly to a method for assessing the acceptance capacity of decentralized wind power in rural power grids based on an improved SAC algorithm. Background Art

[0002] With the transformation of the global energy structure towards low-carbonization, decentralized wind power has become an important direction for energy supplementation in rural power grids due to its cleanliness, flexibility, and advantages of nearby consumption. Rural power grids usually have characteristics such as low load density, weak grid structure, and limited peak shaving capacity. The access of decentralized wind power can not only relieve the power supply pressure in remote areas but also promote the consumption of renewable energy. However, the randomness, volatility, and reverse peak shaving characteristics of wind power pose severe challenges to the voltage stability, line capacity margin, and power balance of rural power grids. For example, sudden changes in wind power output may lead to node voltage over-limit, an increase in the risk of line overload, and even trigger cascading failures. Therefore, scientifically evaluating the wind power acceptance capacity of rural power grids is the core prerequisite for optimizing the wind power layout and ensuring the safe operation of the power grid.

[0003] Traditional methods for assessing wind power acceptance capacity mainly include two categories: static assessment and dynamic assessment. Static assessment is based on a preset grid topology and typical operating conditions, and solves for the maximum access capacity through linear programming or heuristic algorithms. However, it ignores the spatio-temporal volatility of wind power and is difficult to reflect real-time operating constraints. Although dynamic assessment considers the change in wind power output through time-series simulation, it relies on accurate physical models and a large amount of computing resources. In the face of the complex scenarios of multi-node and multi-constraint in rural power grids, there are problems of dimensionality disaster and low convergence efficiency. In addition, traditional methods mostly use Monte Carlo simulation when dealing with probabilistic constraints, with high computational costs and difficulty in achieving the coordinated optimization of multiple objectives.

[0004] Reinforcement Learning (RL) algorithms, due to their data-driven and adaptive decision-making characteristics, provide a breakthrough path for the above problems. Taking the improved Soft Actor-Critic (SAC) algorithm as an example, it realizes efficient exploration and convergence in a high-dimensional continuous action space by maximizing the cumulative reward and policy entropy value, and is particularly suitable for the following scenarios in rural power grids: uncertainty modeling, complex constraint handling, and multi-objective optimization. It can simultaneously optimize the access capacity and operation risk, and is superior to traditional single-objective optimization methods. Compared with traditional methods, the improved SAC algorithm shows significant advantages in convergence speed, handling high-dimensional non-linear problems, and real-time decision-making ability, providing efficient and intelligent technical support for the large-scale access of decentralized wind power in rural power grids. Summary of the Invention

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

[0006] Therefore, the present invention provides a method for evaluating the decentralized wind power accommodation capacity of rural power grids based on an improved SAC algorithm, which can comprehensively analyze and evaluate the decentralized wind power accommodation capacity of rural power grids, solve important problems such as the uncertainty of wind power access, load fluctuations, and grid stability, and provide a scientific basis for the effective utilization of renewable energy.

[0007] To solve the above technical problems, the present invention provides the following technical solutions. The method for evaluating the decentralized wind power accommodation capacity of rural power grids based on an improved SAC algorithm includes: considering the uncertainty of wind power output, establishing a probability simulation model for the output power of decentralized wind power; considering the stochastic characteristics of the load, establishing a load probability model for rural power grids; establishing an evaluation model for the decentralized wind power accommodation capacity of rural power grids, constructing an objective function, and determining the constraint conditions; proposing a solution method for the accommodation capacity evaluation model based on an improved flexible actor-critic SAC algorithm, constructing an algorithm framework, and executing the algorithm to solve the model; constructing an evaluation index system for the decentralized wind power accommodation capacity of rural power grids to evaluate the evaluation results; and obtaining the evaluation results of the decentralized wind power accommodation capacity of rural power grids through comparative examples.

[0008] As a preferred embodiment of the method for evaluating the decentralized wind power accommodation capacity of rural power grids based on an improved SAC algorithm of the present invention, wherein: the establishment of the probability simulation model for the output power of decentralized wind power includes constructing a wind speed probability density function based on the Weibull distribution;

[0009] According to the linear relationship between wind speed and the output power of wind turbines, deriving the probability distribution of the active power output of wind power;

[0010] Combining the cut-in wind speed, rated wind speed, and cut-out wind speed to determine the dynamic range of the wind power output.

[0011] As a preferred embodiment of the method for evaluating the decentralized wind power accommodation capacity of rural power grids based on an improved SAC algorithm of the present invention, wherein: the establishment of the load probability model for rural power grids includes calculating the mean and variance based on historical load data; and simulating the stochastic fluctuation characteristics of the load power using the normal distribution.

[0012] As a preferred embodiment of the method for evaluating the decentralized wind power accommodation capacity of rural power grids based on an improved SAC algorithm of the present invention, wherein: the construction of the objective function includes defining it as maximizing the sum of the wind power access capacities of each candidate node;

[0013] The constraint conditions include node voltage magnitude constraints, line apparent power capacity constraints, power balance constraints, wind power output fluctuation range constraints, and radial grid topology constraints.

[0014] As a preferred solution of the rural power grid decentralized wind power acceptance capacity evaluation method based on the improved SAC algorithm according to the present invention, wherein: the improved flexible action-evaluation SAC algorithm includes defining a state space including grid states and environmental states, and defining a continuous action space to adjust the wind power access capacity of each node;

[0015] A reward function with dynamically adjusted weights, integrating capacity maximization and safety penalty terms, and optimizing the strategy through an experience replay pool and a network update mechanism until the convergence condition is met.

[0016] As a preferred solution of the rural power grid decentralized wind power acceptance capacity evaluation method based on the improved SAC algorithm according to the present invention, wherein: the evaluation index system includes calculating the real-time ratio of the decentralized wind power generation power to the total grid load to obtain the proportion of decentralized wind power generation;

[0017] Determining the decentralized wind power consumption rate through the ratio of the actual decentralized wind power generation power to the predicted power generation power;

[0018] Counting the proportion of qualified voltage nodes in the total number of nodes and defining the voltage qualification rate;

[0019] Calculating the voltage deviation rate based on the deviation ratio of the node voltage to the rated voltage;

[0020] Quantifying the line loss rate according to the ratio of the line active power loss to the total load.

[0021] As a preferred solution of the rural power grid decentralized wind power acceptance capacity evaluation method based on the improved SAC algorithm according to the present invention, wherein: the comparative example includes inputting grid topology parameters, load time series data, and historical wind power output; executing the improved SAC algorithm to solve the optimal wind power access capacity; and verifying the effectiveness of the model through quantitative analysis results of the evaluation index system.

[0022] As a preferred solution of the rural power grid decentralized wind power acceptance capacity evaluation system based on the improved SAC algorithm according to the present invention, wherein: it includes a data acquisition module, a probability simulation module, an evaluation model construction module, an algorithm solution module, and an evaluation index calculation module;

[0023] The data acquisition module collects real-time wind speed, load, and historical power generation data information to provide data support for subsequent models;

[0024] The probability simulation module constructs a wind speed probability density function and simulates the load power based on the Weibull distribution, analyzes the randomness of wind power output and load, and generates a corresponding probability model;

[0025] The evaluation model construction module constructs an evaluation model for the acceptance capacity of decentralized wind power in rural power grids, sets the objective function and constraints, and provides an optimization objective for the algorithm.

[0026] The algorithm solving module improves the SAC algorithm, dynamically adjusts the wind power access capacity of each node, and optimizes the wind power access plan through experience replay and network update until convergence.

[0027] The evaluation index calculation module calculates various evaluation indexes based on the algorithm solving results to evaluate the acceptance capacity of the power grid for decentralized wind power.

[0028] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm are implemented.

[0029] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm are implemented.

[0030] The beneficial effects of the present invention are as follows: By establishing a model that comprehensively considers the uncertainty of wind power output and the random characteristics of load, the acceptance capacity of rural power grids for decentralized wind power can be evaluated more accurately; The improved SAC algorithm is adopted, enabling the evaluation process to dynamically adjust the wind power access capacity, maximizing the wind power utilization efficiency while taking into account the grid security, and enhancing the flexibility and stability of the grid; A set of systematic evaluation indexes are constructed to comprehensively reflect the acceptance capacity and operation status of rural power grids, and are adjusted and optimized according to the wind power resources and load characteristics of different regions. Description of the Drawings

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 It is a schematic flow chart of the method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm provided by an embodiment of the present invention.

[0033] Figure 2 It is the power output curve of the wind turbine provided by an embodiment of the method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm of the present invention.

[0034] Figure 3The flowchart of the SAC algorithm for the assessment method of the decentralized wind power acceptance capacity of rural power grids based on the improved SAC algorithm provided by an embodiment of the present invention.

[0035] Figure 4 The assessment result of the wind power acceptance capacity for the assessment method of the decentralized wind power acceptance capacity of rural power grids based on the improved SAC algorithm provided by an embodiment of the present invention.

[0036] Figure 5 The schematic diagram of the working modules of the assessment system for the decentralized wind power acceptance capacity of rural power grids based on the improved SAC algorithm provided by an embodiment of the present invention. Specific implementation manners

[0037] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific implementation manners of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0039] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0040] The present invention is described in detail in conjunction with the schematic diagrams. When detailing the embodiments of the present invention, for the sake of convenience of explanation, the cross-sectional views showing the device structures will be enlarged locally out of the general scale, and the schematic diagrams are only examples and should not limit the protection scope of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0041] Meanwhile, in the description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper, lower, inner, and outer" is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0042] Unless otherwise clearly defined and limited in the present invention, the terms "installed, connected, and coupled" shall be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can also be a mechanical connection, an electrical connection, or a direct connection, and can also be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] Example 1, referring to Figure 1 - Figure 4 , which is the first embodiment of the present invention. This embodiment provides a method for evaluating the decentralized wind power accommodation capacity of rural power grids based on an improved SAC algorithm, including:

[0044] S1: Considering the uncertainty of wind power output, establish a probability simulation model for the output power of decentralized wind power.

[0045] Furthermore, a large number of measured wind speed data shows that the annual average wind speed distribution in most regions conforms to the Weibull distribution. Then, the probability density function of the wind speed can be described by the following formula:

[0046]

[0047] where v is the wind speed; k and c are two parameters of the Weibull distribution, where k is the shape parameter and c is the scale parameter.

[0048] Figure 2 As shown, it is the power output curve of the wind turbine, which describes the characteristics of the wind turbine's output power changing with the wind speed. According to Figure 2 , the wind turbine output power expression is:

[0049]

[0050] 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; vci is the cut-in wind speed; v co is the cut-out wind speed.

[0051] In practice, the wind speed is between the cut-in wind speed v ci and the rated wind speed v r most of the time. That is, the wind speed and the output active power satisfy a linear relationship, and the probability distribution of the output active power of distributed wind power can be obtained:

[0052]

[0053] S2: Considering the stochastic characteristics of the load, establish a load probability model for the rural power grid.

[0054] [[ID=I19]]Furthermore, when there are enough measured load data in the rural power grid, the load power follows a normal distribution. Based on the normal distribution to simulate the randomness of the load, its probability density function is expressed as:

[0055]

[0056] where y is the historical measured data of the rural power grid load power, y = {y i , i = 1, 2,..., N}; μ and σ 2 are the mean and variance of the measured load data of the rural power grid respectively, and their calculation formulas are as follows:

[0057]

[0058] S3: Establish an evaluation model for the acceptance capacity of distributed wind power in the rural power grid, construct an objective function, and determine the constraint conditions.

[0059] Furthermore, for an optimization model with the maximization of the access capacity of distributed wind power in the rural power grid as the goal, considering the constraints of grid safe operation and wind power uncertainty, the objective function is as follows:

[0060]

[0061] where Ω is the set of candidate wind power access nodes; P w,i is the wind power access capacity of node i.

[0062] It should be noted that the node voltage constraint is: [[ID=I51]]

[0063]

[0064] where V i is the voltage amplitude of node i; N is the set of grid nodes.

[0065] Line capacity constraint:

[0066]

[0067] Among them, S ij is the apparent power of line (i, j); L is the set of lines.

[0068] Power balance constraint:

[0069] P w,i + P grid = P load + P loss

[0070] In the formula, P grid represents the grid injection power; P load represents the load power; P loss represents the power loss.

[0071] Wind power output fluctuation constraint:

[0072]

[0073] Among them, P w,i (t) represents the active power output of distributed wind power at time t; respectively represent the minimum value and the maximum value corresponding to the allowable access range dynamically adjusted based on the probability distribution of wind power output generated from historical data.

[0074] Furthermore, an improved DistFlow model is adopted to describe the radial characteristics of rural power grids, ensuring the solvability of the power flow equation.

[0075]

[0076] In the formula, is the set of downstream nodes of node j; r ij , x ij represent the line resistance and reactance; V i and V j are the voltages of node i and node j respectively; P ij , Q ij are the active power injection and reactive power injection of node i at time t; P jk , Q jk are the active power flow and reactive power flow of branch jk respectively; P load,j , Q load,j are the active power load and reactive power load of the node respectively.

[0077] S4: Propose a solution method for the acceptance capacity evaluation model based on the improved flexible actor-critic SAC algorithm, construct an algorithm framework, and execute the algorithm to solve the model.

[0078] Furthermore, the SoftActor-Critic (SAC) reinforcement learning algorithm is adopted to achieve efficient exploration in the high-dimensional continuous action space by maximizing the cumulative reward and the policy entropy value. The improvement for the rural power grid characteristics is as follows:

[0079] The state space includes the power grid state and the environmental state, where the power grid state includes the node voltage V i , the line power S ij , and the load demand P load ; the environmental state includes the predicted wind power output time series characteristics (such as season, time period).

[0080] The action space (ActionSpace) includes continuous actions, that is, the adjustment amount ΔP of the wind power access capacity of each node w,i , which is normalized to [-1, 1].

[0081] Set the reward function:

[0082]

[0083] The first term encourages maximizing the wind power access capacity, and the coefficient α is the capacity weight; the second term penalizes voltage over-limit and line overload, and the coefficient β is the safety weight. An improvement is made here to dynamically adjust the α / β ratio to balance economy and safety.

[0084] Furthermore, construct a power grid simulation environment with power grid topology parameters (r ij , x ij , ), load time series data, and historical wind power output. Initialize the weights of the Actor and Critic networks (the number of neural network layers and the number of nodes in each layer), the capacity of the experience replay pool, and the initial exploration steps.

[0085] The agent selects an action according to the current policy (σ decays with training); the simulation environment calculates the access capacity and verifies the constraints, and returns the reward r t and the next state s t+1 . Store (s t , a t , r t , s t+1 ) in the experience pool and sort them by priority.

[0086] Update the Critic network to minimize the Bellman error:

[0087]

[0088] Update the Actor network to maximize the expected return and the entropy value:

[0089]

[0090] Terminate the training when the access capacity fluctuation for 10 consecutive iterations is less than 1%, and output the optimal strategy. That is, terminate the training when the following conditions are met:

[0091]

[0092] Output the optimal strategy π * With the maximum access capacity The flow chart of the evaluation method for the decentralized wind power accommodation capacity of rural power grids based on the improved SAC algorithm is as Figure 3 shown.

[0093] S5: Construct an evaluation index system for the decentralized wind power accommodation capacity of rural power grids to evaluate the evaluation results. Through comparison with case studies, obtain the evaluation results of the decentralized wind power accommodation capacity of rural power grids.

[0094] Furthermore, to evaluate the accommodation capacity of rural power grids for decentralized wind power, this section follows the principles of scientificity, systematicness, and quantifiability, selects various key operating parameters of rural power grids, and forms an evaluation index system for the decentralized wind power bearing capacity of rural power grids. Considering the flexibility and reliability of rural power grids, the corresponding indicators are established as follows.

[0095] The flexibility of the rural power grid refers to the ability of the rural power grid to quickly respond to the uncertainties of decentralized wind power and load changes by adjusting the output of various equipment within a certain time scale.

[0096] Calculate the ratio of the decentralized wind power generation power to the total load of all nodes:

[0097] F PW = P PW,t / P load,t

[0098] In the formula: F PW is the proportion of decentralized wind power generation; P PW,t is the decentralized wind power generation power at time t; P load,t is the load power at time t.

[0099] Calculate the ratio of the decentralized wind power generation power to the predicted decentralized wind power generation power:

[0100] F cons = P FW,t / P FW,f,t

[0101] In the formula: F cons is the decentralized wind power consumption rate; P PW,f,t is the predicted decentralized wind power generation power at time t.

[0102] The reliability of the rural power grid refers to the ability of the rural power grid to meet the power and electricity demands of users according to acceptable standards and expected quantities.

[0103] Calculate the ratio of the number of nodes with the rural power grid voltage magnitude within the qualified voltage range to the total number of nodes:

[0104] R sat = n sat,t / N node

[0105] In the formula: R sat is the voltage qualification rate; n sat,t is the number of nodes meeting the voltage qualification standard at time t; N node is the total number of nodes.

[0106] Calculate the deviation ratio of the node voltage of the rural power grid to the rated voltage:

[0107] R ΔU = |U N - U i,t | / U N

[0108] In the formula: 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.

[0109] Calculate the ratio of the active power loss of the rural power grid lines to the total load:

[0110]

[0111] In the formula: 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 line at time t; R i is the resistance of the i-th line.

[0112] Example 2, the second example of the present invention, which is different from the previous example in that:

[0113] If the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., all of which can store program codes.

[0114] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0115] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROMs). Additionally, a computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0116] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0117] Example 4, referring to Figure 5 , which is an embodiment of the present invention, provides a rural power grid decentralized wind power acceptance capacity evaluation system based on an improved SAC algorithm, including a data acquisition module, a probability simulation module, an evaluation model construction module, an algorithm solving module, and an evaluation index calculation module;

[0118] The data acquisition module collects real-time wind speed, load, and historical power generation data information to provide data support for subsequent models;

[0119] The probability simulation module constructs a wind speed probability density function based on the Weibull distribution and simulates the load power, analyzes the randomness of wind power output and load, and generates a corresponding probability model;

[0120] The evaluation model construction module constructs an evaluation model for the rural power grid decentralized wind power acceptance capacity, sets the objective function and constraints, and provides an optimization goal for the algorithm;

[0121] The algorithm solving module improves the SAC algorithm, dynamically adjusts the wind power access capacity of each node, and optimizes the wind power access scheme through experience replay and network update until convergence;

[0122] The evaluation index calculation module calculates various evaluation indexes based on the algorithm solving results to evaluate the acceptance capacity of the power grid for decentralized wind power.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An evaluation method for the acceptance capacity of decentralized wind power in rural power grids based on an improved SAC algorithm, characterized in that: including Considering the uncertainty of wind power output, establish a probability simulation model for the output power of decentralized wind power; Considering the stochastic characteristics of the load, establish a load probability model for rural power grids; Establish an evaluation model for the acceptance capacity of decentralized wind power in rural power grids, construct an objective function, and determine the constraint conditions; Propose a solution method for the acceptance capacity evaluation model based on the improved flexible actor-critic soft actor-critic (SAC) algorithm, construct an algorithm framework, and execute the algorithm to solve the model; Construct an evaluation index system for the acceptance capacity of decentralized wind power in rural power grids to evaluate the evaluation results; Through comparative examples, obtain the evaluation results of the acceptance capacity of decentralized wind power in rural power grids.

2. The method for evaluating the decentralized wind power accommodation capacity of rural power grids based on the improved SAC algorithm according to claim 1, wherein: The establishment of the probability simulation model for the output power of decentralized wind power includes constructing a wind speed probability density function based on the Weibull distribution; According to the linear relationship between wind speed and the output power of wind turbines, deduce the probability distribution of the active power output of wind power; Combined with the cut-in wind speed, rated wind speed, and cut-out wind speed, determine the dynamic range of the wind power output.

3. The method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm according to claim 2, characterized in that: The establishment of the rural power grid load probability model includes calculating the mean and variance based on historical load data; Use the normal distribution to simulate the stochastic fluctuation characteristics of the load power.

4. The method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm according to claim 3, wherein: The construction of the objective function includes defining it as the maximization of the sum of the wind power access capacities of each candidate node; The constraint conditions include node voltage magnitude constraints, line apparent power capacity constraints, power balance constraints, wind power output fluctuation range constraints, and radial power grid topology constraints.

5. The method for evaluating the acceptance capacity of decentralized wind power in rural power grids based on the improved SAC algorithm according to claim 4, wherein: The improved flexible actor-critic SAC algorithm includes defining a state space that includes the power grid state and the environmental state, and defining a continuous action space to adjust the wind power access capacity of each node; A reward function with dynamically adjusted weights, integrating capacity maximization and safety penalty terms, optimizes the strategy through an experience replay pool and a network update mechanism until the convergence condition is met.

6. The method for evaluating the decentralized wind power accommodation capacity of rural power grids based on the improved SAC algorithm according to claim 5, characterized in that: The evaluation index system includes calculating the real-time ratio of the decentralized wind power generation power to the total load of the power grid to obtain the proportion of decentralized wind power generation; Determine the decentralized wind power consumption rate through the ratio of the actual wind power generation power to the predicted wind power generation power; Count the proportion of the number of qualified voltage nodes in the total number of nodes and define the voltage qualification rate; Calculate the voltage deviation rate based on the deviation ratio of the node voltage to the rated voltage; Quantify the network loss rate according to the ratio of the active power loss of the line to the total load.

7. The method for evaluating the decentralized wind power accommodation capacity of rural power grids based on the improved SAC algorithm according to claim 6, wherein: The comparative examples include inputting the power grid topology parameters, load time series data, and historical wind power output; executing the improved SAC algorithm to solve the optimal wind power access capacity; quantitatively analyzing the results through the evaluation index system to verify the effectiveness of the model.

8. A system adopting the method for evaluating the decentralized wind power acceptance capacity of rural power grids based on the improved SAC algorithm as described in any one of claims 1 to 7, characterized in that: Including a data acquisition module, a probability simulation module, an evaluation model construction module, an algorithm solution module, and an evaluation index calculation module; The data acquisition module collects real-time information on wind speed, load, and historical power generation data to provide data support for subsequent models; The probability simulation module constructs a wind speed probability density function based on the Weibull distribution and the simulation of load power, analyzes the randomness of wind power output and load, and generates corresponding probability models; The evaluation model construction module constructs an evaluation model for the acceptance capacity of decentralized wind power in rural power grids, sets the objective function and constraint conditions, and provides an optimization goal for the algorithm; The algorithm solving module improves the SAC algorithm, dynamically adjusts the wind power access capacity of each node, optimizes the wind power access scheme through experience replay and network update until convergence; The evaluation index calculation module calculates various evaluation indexes based on the algorithm solving result to evaluate the acceptance capacity of the power grid for decentralized wind power.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images