Power system distributed self-healing recovery method and system considering uncertainty of new energy output

Abstract

The invention discloses an electric power system distributed self-healing recovery method and system considering new energy output uncertainty, and relates to the technical field of electric power systems.Output fluctuation events are classified by defining output fluctuation quantity and output fluctuation rate and setting trigger conditions of the output fluctuation events; collecting meteorological data and operation data of a new energy unit, training a short-term prediction model, predicting new energy output in future time, judging whether a trigger condition of an output fluctuation event is reached or not, and if yes, evaluating severity; establishing a self-healing control strategy, designing the state, action and reward function of the intelligent agent, and optimizing the self-healing control strategy by adopting a reinforcement learning algorithm; when an output fluctuation event is triggered, the optimized self-healing control strategy is issued to a power system control unit, and the optimized self-healing control strategy is executed; and obtaining an effect evaluation value of self-healing control of the output fluctuation event, and feeding back the effect evaluation value to the reinforcement learning algorithm to guide the next round of control strategy optimization.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a distributed self-healing recovery method and system for power systems that take into account the uncertainty of new energy output. Background Art

[0002] Distributed self-healing and restoration of power systems refers to the automatic detection and isolation of faults in a distributed manner after a power system failure or disturbance, and the restoration of power supply as soon as possible, so that the system returns to normal or near-normal operating conditions, improving the reliability and recovery capabilities of the system. This is one of the important aspects of building a smart grid.

[0003] The Chinese patent with publication number CN114465236A discloses a self-healing method for a distribution network to cope with ground faults and a distribution network. The self-healing method includes fault detection, fault location, fault isolation and network self-healing; fault detection includes: the protection module of the circuit breaker control device collects the current data of the corresponding power supply line; the current input signal En of the real-time cycle is calculated according to the current data; the current change difference ΔFn is obtained according to the current input signal En of several cycles; the current change difference ΔFn of different power supply lines in the same time period is compared to determine whether the corresponding power supply line has a fault, and if so, enter the fault location; the distribution network can execute the above self-healing method. The method of the invention is applicable to the global communication intelligent distributed power distribution system, and takes corresponding self-healing measures when a small current ground fault is detected in the distribution system.

[0004] Existing power system self-healing and restoration methods do not adequately consider the complexity and uncertainty of renewable energy access scenarios, and lack flexibility and adaptability. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present application is to propose a distributed self-healing recovery method and system for a power system considering the uncertainty of new energy output, thereby improving the adaptability of distributed self-healing recovery of the power system.

[0006] One aspect of the present application provides a distributed self-healing restoration method for a power system considering the uncertainty of renewable energy output, including:

[0007] Step S100: define the new energy output fluctuation amount and the new energy output fluctuation rate, set the triggering conditions of the new energy output fluctuation event, and classify the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction;

[0008] Step S200: collecting meteorological data and operation data of new energy units, training a short-term prediction model for predicting new energy output, using the short-term prediction model to predict new energy output in the future, judging whether the triggering condition of the new energy output fluctuation event is met, and if so, evaluating the severity of the new energy output fluctuation event;

[0009] Step S300: Establish a self-healing control strategy for new energy output fluctuation events, design the state, action and reward function of the intelligent agent, and use a reinforcement learning algorithm to optimize the self-healing control strategy;

[0010] Step S400: Each control unit of the power system monitors the new energy output fluctuation event in real time. When the new energy output fluctuation event is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy;

[0011] Step S500: obtaining an effect evaluation value of the self-healing control of the new energy output fluctuation event, and feeding the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy;

[0012] The specific method of defining the new energy output fluctuation amount and the new energy output fluctuation rate, setting the triggering conditions of the new energy output fluctuation event, and classifying the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction is as follows:

[0013] Step S110: Preset a time window mt, define the change in the new energy output within the time window as the new energy output fluctuation Δp, and define the ratio of the new energy output fluctuation to the new energy installed capacity as the new energy output fluctuation rate Ra;

[0014] Step S120: Setting a first volatility threshold R th1 , when the new energy output fluctuation rate is greater than or equal to the first fluctuation rate threshold, it is considered that a new energy output fluctuation event is triggered;

[0015] Step S130: According to the magnitude of the fluctuation rate of the new energy output, the fluctuation amplitude is divided into three levels: small fluctuation, medium fluctuation, and large fluctuation. The range of the fluctuation rate of the new energy output with small fluctuation is [R th1 ,R th2 ), the range of the fluctuation rate of the new energy output is [R th2 ,R th3 ), the range of the large fluctuation of new energy output fluctuation rate is [R th3 ,+∞), where R th1 , R th2 , R th3 They are respectively a preset first volatility threshold, a second volatility threshold, and a third volatility threshold;

[0016] Step S140: According to the duration T of the new energy output fluctuation event dur It is divided into short-term fluctuations and long-term fluctuations. The duration of the short-term fluctuations ranges from (0, T th ), the duration of the long-term fluctuation is in the range of [T th ,+∞), where T th is a preset time threshold;

[0017] Step S150: according to the positive or negative value of the new energy output fluctuation amount Δp, the fluctuation direction is divided into an upward fluctuation and a downward fluctuation;

[0018] The specific method of collecting meteorological data and operation data of new energy units, training a short-term prediction model for predicting new energy output, using the short-term prediction model to predict new energy output in the future, and judging whether the triggering conditions of the new energy output fluctuation event are met is:

[0019] Step S210: configuring meteorological sensors and electrical sensors at the new energy station to collect meteorological data and operating data of the new energy unit, wherein the meteorological data includes historical meteorological data and weather forecast data, and the operating data includes inverter output power and total station output;

[0020] Step S220: Selecting a long short-term memory network as the initial network of the short-term prediction model, presetting the sliding window length nt and the sliding step length, and generating a time series from the historical meteorological data, the operating data, and the weather forecast data in chronological order;

[0021] Step S230: The historical meteorological data and operation data of nt moments before the t-th moment and the weather forecast data of nt moments after the t-th moment are used as input data of the short-term prediction model, and the future new energy output is used as output data. The sliding window moves backward in the time series in sequence according to the sliding step size, and a training sample is generated in the time series in the form of a sliding window;

[0022] Step S240: define mean square error as the loss function for training the long short-term memory network, use training samples to train the long short-term memory network, optimize model parameters by minimizing the value of the loss function, and obtain a trained short-term prediction model when the loss function reaches convergence;

[0023] Step S250: every time window mt, input the historical meteorological data and operation data of nt moments before the current moment and the weather forecast data of nt moments after the current moment into the short-term prediction model, predict the future new energy output, and calculate the new energy output fluctuation amount Δp and the new energy output fluctuation rate Ra according to the predicted new energy output;

[0024] Step S260: Compare the new - energy output volatility with the first volatility threshold R th1 If the new - energy output volatility is greater than or equal to the first volatility threshold, trigger a new - energy output fluctuation event;

[0025] The specific method for evaluating the severity of the new - energy output fluctuation event is as follows:

[0026] Step S270: Judge the severity of the fluctuation amplitude, duration, and fluctuation direction of the new - energy output fluctuation event;

[0027] The judgment method for the fluctuation amplitude is: Define the severity of the fluctuation amplitude as 1, 2, and 3 for small fluctuations, medium fluctuations, and large fluctuations respectively. According to the magnitude of the new - energy output volatility, judge the value of the severity Rs of the fluctuation amplitude, where Rs = {1, 2, 3};

[0028] The judgment method for the duration is: Obtain the new - energy output sequence based on n - time predictions of the new - energy output. Judge the moment t1 when the new - energy output volatility Ra is first greater than or equal to the first volatility threshold R th1 as the starting moment of the new - energy output fluctuation event; Starting from moment t1, judge the moment t2 when the new - energy output volatility Ra is first less than the first volatility threshold R th1 as the ending moment of the new - energy output fluctuation event. Obtain the duration according to the difference between moment t1 and moment t2; Define the severity of the duration as 1 and 2 for short - term fluctuations and long - term fluctuations respectively. According to the magnitude of the duration, judge the value of the severity RT of the duration, where RT = {1, 2};

[0029] The judgment method for the fluctuation direction is: Define the severity of the fluctuation direction as 1 and 2 for upward fluctuations and downward fluctuations respectively. According to the positive or negative of the new - energy output fluctuation amount, judge the value of the severity Rd of the fluctuation direction, where Rd = {1, 2};

[0030] Step S280: Calculate the severity S of the new - energy output fluctuation event according to the severity of the fluctuation amplitude, duration, and fluctuation direction;

[0031] Step S290: Set severity thresholds S1 and S2, and classify the severity of the new - energy output fluctuation event into mild fluctuations, moderate fluctuations, and severe fluctuations; Among them, the range of the severity of mild fluctuations is: 1 ≤ S < S1, the range of the severity of moderate fluctuations is: S1 ≤ S < S2, and the range of the severity of severe fluctuations is: S2 ≤ S < 3;

[0032] The specific method for designing the state, action, and reward function of the intelligent agent and optimizing the self - healing control strategy using the reinforcement learning algorithm is as follows:

[0033] Step S310: define the state space of the agent, the state s includes the new energy output fluctuation rate Ra, the grid frequency deviation Δf, the energy storage system charge state SOC, the controllable load state, the severity S of the new energy output fluctuation event, define the action space of the agent, the action a includes the new energy output limit instruction P cur , Energy storage charging and discharging power instruction P ess and controllable load control command P load ;

[0034] Step S320: Based on the grid frequency deviation Δf and the new energy output limit |P cur |、Energy storage system charge change |ΔSOC|、Controllable load control quantity |P load | and the effect evaluation value of historical actions define the agent’s reward function;

[0035] Step S330: Using the reinforcement learning algorithm, initialize the current Q network parameters, and in the current state s t Next, randomly select an action with probability ε, or select the action with the largest Q value with probability 1-ε, and execute the selected action a t , get the next moment state s t+1 and the reward function value r t ;

[0036] Step S340: t ,a t ,r t ,s t+1 ) is stored in the experience replay cache, and a batch of samples (s j ,a j ,r j ,s j+1 ), calculate the target value of the current Q network;

[0037] Step S350: define the loss function L(θ) of the current Q network, update the current Q network parameter θ by gradient descent method, minimize the value of the loss function, and regularly update the target Q network parameter θ - Update to the current Q network parameter θ;

[0038] Step S360: The agent selects the optimal action according to the current state. When selecting an action, if an action outside the constraint range is selected, the agent reselects until an action within the constraint range is selected, thereby obtaining an optimized self-healing control strategy.

[0039] The specific method of establishing the self-healing control strategy for the new energy output fluctuation event is:

[0040] According to the severity of the new energy output fluctuation event, a self-healing control strategy is set as the new energy output limit instruction P in the action space. cur , Energy storage charging and discharging power instruction P ess and controllable load control command P load The constraint range of the new energy output limit instruction during mild fluctuations is P cur ∈[0.9P0, P0], the constraint range of energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.95P l , 1.05P l ]; The constraint range of the new energy output limit command during moderate fluctuation is P cur ∈[0.8P0, 0.9P0), the constraint range of the energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.9P l , 1.1P l ]; The constraint range of the new energy output limit command during severe fluctuations is P cur ∈[0.7P0, 0.8P0), the constraint range of the energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.85P l , 1.15P l ], where P0 is the initial output of new energy, is the rated power of the energy storage system, P l is the initial power of the controllable load;

[0041] Each control unit of the power system monitors the new energy output fluctuation event in real time. When the new energy output fluctuation event is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system. The specific method of executing the optimized self-healing control strategy is:

[0042] Step S410: Each control unit of the power system is equipped with monitoring equipment and communication equipment to monitor the fluctuation event of the output of new energy in real time. When the control unit detects that the fluctuation event of the output of new energy is triggered within its jurisdiction, the optimized self-healing control strategy is sent to each control unit of the power system, and each control unit is adjusted to execute the corresponding instruction according to the output limit instruction of new energy, the charge and discharge power instruction of energy storage and the controllable load control instruction;

[0043] The specific method of obtaining the effect evaluation value of the self-healing control of the new energy output fluctuation event, feeding the effect evaluation value back to the reinforcement learning algorithm, and guiding the optimization of the next round of self-healing control strategy is:

[0044] Step S510: After executing the optimized self-healing control strategy, obtain the effect evaluation index of the self-healing control, the effect evaluation index includes: the power grid frequency recovery time T fr , Energy storage cycle life loss L ess and controllable load adjustment cost C load ;

[0045] Step S520: calculating the effect evaluation value of the self-healing control of the new energy output fluctuation event according to the effect evaluation index;

[0046] Step S530: Feedback the effect evaluation value obtained by currently executing the self-healing control strategy to the reinforcement learning algorithm to guide the optimization of the next self-healing control strategy.

[0047] One aspect of the present application provides a distributed self-healing restoration system for a power system taking into account the uncertainty of new energy output, including:

[0048] The fluctuation event classification module is used to define the fluctuation amount and fluctuation rate of new energy output, set the trigger conditions of new energy output fluctuation events, and classify new energy output fluctuation events according to fluctuation amplitude, duration and fluctuation direction;

[0049] The severity calculation module is used to collect meteorological data and operation data of new energy units, train a short-term prediction model for predicting new energy output, use the short-term prediction model to predict new energy output in the future, and determine whether the triggering conditions of the new energy output fluctuation event are met. If so, the severity of the new energy output fluctuation event is evaluated;

[0050] The self-healing strategy optimization module is used to establish the self-healing control strategy for the new energy output fluctuation event, design the state, action and reward function of the intelligent agent, and use the reinforcement learning algorithm to optimize the self-healing control strategy;

[0051] The self-healing strategy execution module is used for each control unit of the power system to monitor the fluctuation events of renewable energy output in real time. When the fluctuation event of renewable energy output is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy;

[0052] The effect evaluation feedback module is used to obtain the effect evaluation value of the self-healing control of the new energy output fluctuation event, and feed the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy.

[0053] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a distributed self-healing restoration method for an electric power system that takes into account the uncertainty of output of renewable energy are implemented.

[0054] One aspect of the present application provides a readable storage medium storing a computer program suitable for loading by a processor to execute steps in a distributed self-healing restoration method for a power system taking into account the uncertainty of new energy output.

[0055] The distributed self-healing recovery method and system for power systems considering the uncertainty of renewable energy output proposed in this application have the following advantages over the prior art:

[0056] This application clearly defines indicators such as the fluctuation amount and volatility of new energy output, and comprehensively defines and quantifies new energy output fluctuation events from multiple dimensions such as fluctuation amplitude, duration, and direction.

[0057] This application uses deep learning methods such as LSTM, combined with meteorological data and operation data to train short-term prediction models, which can predict the fluctuation trend of new energy output in advance and buy time for taking countermeasures in advance.

[0058] This application considers the fluctuation amplitude, duration, direction and other factors to construct a quantitative index of the severity of fluctuation events. This helps to formulate differentiated self-healing control strategies according to the severity of fluctuations and improve the pertinence of measures.

[0059] This application models the self-healing control problem as a Markov decision process, and uses a reinforcement learning algorithm to solve the optimal control strategy by designing the agent state, action, and reward function. The control process can adapt to fluctuations of different severity, reflecting the autonomous decision-making ability based on artificial intelligence.

[0060] This application feeds back the actual control effect evaluation results to the reinforcement learning algorithm to guide the optimization of the next round of control strategy. Through the closed loop of "prediction-evaluation-optimization control-effect feedback-re-optimization", the effect of self-healing control can be continuously improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A method flow chart of a distributed self-healing restoration method for a power system considering the uncertainty of new energy output provided in this application;

[0062] Figure 2 A flow chart of the classification method of renewable energy output fluctuation events provided for this application;

[0063] Figure 3 A flow chart of the method for triggering a new energy output fluctuation event provided for this application;

[0064] Figure 4 Functional module diagram of a distributed self-healing restoration system for a power system considering the uncertainty of renewable energy output provided in this application. DETAILED DESCRIPTION

[0065] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0066] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0067] It should also be understood that expressions such as "including", "comprising", "having", "containing" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0068] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0069] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0070] Example 1

[0071] like Figure 1As shown, the distributed self-healing recovery method of the power system considering the uncertainty of the output of new energy provided by this application includes:

[0072] Step S100: define the new energy output fluctuation amount and the new energy output fluctuation rate, set the triggering conditions of the new energy output fluctuation event, and classify the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction;

[0073] The specific method of defining the new energy output fluctuation amount and the new energy output fluctuation rate, setting the triggering conditions of the new energy output fluctuation event, and classifying the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction is as follows:

[0074] Step S110: Preset a time window mt, define the change in the new energy output within the time window as the new energy output fluctuation Δp, and define the ratio of the new energy output fluctuation to the new energy installed capacity as the new energy output fluctuation rate Ra;

[0075] The new energy output fluctuation amount represents the change amount of the new energy output within the time window mt;

[0076] The new energy output fluctuation rate represents the fluctuation amount of new energy output Δp and the new energy installed capacity p cap The ratio of

[0077] Step S120: Setting a first volatility threshold R th1 , when the new energy output fluctuation rate is greater than or equal to the first fluctuation rate threshold, it is considered that a new energy output fluctuation event is triggered;

[0078] Step S130: According to the magnitude of the fluctuation rate of the new energy output, the fluctuation amplitude is divided into three levels: small fluctuation, medium fluctuation, and large fluctuation. The range of the fluctuation rate of the new energy output with small fluctuation is [R th1 ,R th2 ), the range of the fluctuation rate of the new energy output is [R th2 ,R th3 ), the range of the large fluctuation of new energy output fluctuation rate is [R th3 ,+∞), where R th1 , R th2 , R th3 They are respectively a preset first volatility threshold, a second volatility threshold, and a third volatility threshold;

[0079] Step S140: According to the duration T of the new energy output fluctuation event dur It is divided into short-term fluctuations and long-term fluctuations. The duration of the short-term fluctuations ranges from (0, T th ), the duration of the long-term fluctuation is in the range of [Tth ,+∞), where T th is a preset time threshold;

[0080] Step S150: according to the positive or negative value of the new energy output fluctuation amount Δp, the fluctuation direction is divided into an upward fluctuation and a downward fluctuation;

[0081] Figure 2 A flow chart of the classification method of renewable energy output fluctuation events provided for this application;

[0082] Step S200: collecting meteorological data and operation data of new energy units, training a short-term prediction model for predicting new energy output, using the short-term prediction model to predict new energy output in the future, judging whether the triggering condition of the new energy output fluctuation event is met, and if so, evaluating the severity of the new energy output fluctuation event;

[0083] The specific method of collecting meteorological data and operation data of new energy units, training a short-term prediction model for predicting new energy output, using the short-term prediction model to predict new energy output in the future, and judging whether the triggering conditions of the new energy output fluctuation event are met is:

[0084] Step S210: configuring meteorological sensors and electrical sensors at the new energy station to collect meteorological data and operating data of the new energy unit, wherein the meteorological data includes historical meteorological data and weather forecast data, and the operating data includes inverter output power and total station output;

[0085] The historical meteorological data include wind speed, radiation intensity, and temperature at historical times;

[0086] The weather forecast data includes wind speed, radiation intensity and temperature at a future time predicted by the meteorological station;

[0087] Step S220: Selecting a long short-term memory network as the initial network of the short-term prediction model, presetting the sliding window length nt and the sliding step length, and generating a time series from the historical meteorological data, the operating data, and the weather forecast data in chronological order;

[0088] The values ​​of the sliding window length nt and the sliding step length are preset by those skilled in the art based on experience;

[0089] Step S230: The historical meteorological data and operation data of nt moments before the t-th moment and the weather forecast data of nt moments after the t-th moment are used as input data of the short-term prediction model, and the future new energy output is used as output data. The sliding window moves backward in the time series in sequence according to the sliding step size, and a training sample is generated in the time series in the form of a sliding window;

[0090] Step S240: define mean square error as the loss function for training the long short-term memory network, use training samples to train the long short-term memory network, optimize model parameters by minimizing the value of the loss function, and obtain a trained short-term prediction model when the loss function reaches convergence;

[0091] The calculation formula of the loss function is: Among them, N yb is the total number of training samples, P n To contribute to the real new energy in the nth training sample, Contribute to the predicted new energy;

[0092] Step S250: every time window mt, input the historical meteorological data and operation data of nt moments before the current moment and the weather forecast data of nt moments after the current moment into the short-term prediction model, predict the future new energy output, and calculate the new energy output fluctuation amount Δp and the new energy output fluctuation rate Ra according to the predicted new energy output;

[0093] The calculation formula of the new energy output fluctuation is: Δp = P t -P t-mt , where P t represents the new energy output at the current time t, P t-mt represents the new energy output at time t-mt before a time window, and Δp is the fluctuation of the new energy output between two moments;

[0094] Step S260: Compare the new energy output fluctuation rate with the first fluctuation rate threshold R th1 Comparing, if the new energy output fluctuation rate is greater than or equal to the first fluctuation rate threshold, a new energy output fluctuation event is triggered;

[0095] The duration is determined based on the predicted new energy output;

[0096] Figure 3 A flow chart of the method for triggering a new energy output fluctuation event provided for this application;

[0097] The specific method for evaluating the severity of the new energy output fluctuation event is as follows:

[0098] Step S270: determining the severity of the fluctuation amplitude, duration and fluctuation direction of the new energy output fluctuation event;

[0099] The method for determining the fluctuation amplitude is as follows: the severity of the fluctuation amplitude is defined as 1, 2, and 3 according to small fluctuation, medium fluctuation, and large fluctuation, respectively, and the value of the severity of the fluctuation amplitude Rs is determined according to the magnitude of the fluctuation rate of the new energy output, where Rs = {1, 2, 3};

[0100] The method for judging the duration is as follows: obtain the new energy output sequence based on the new energy output predicted n times, and judge the moment t1 when the new energy output volatility Ra is greater than or equal to the first volatility threshold R for the first time as the starting moment of the new energy output fluctuation event; starting from the moment t1, judge the moment t2 when the new energy output volatility Ra is less than the first volatility threshold R for the first time thereafter as the ending moment of the new energy output fluctuation event, and obtain the duration according to the difference between the moment t1 and the moment t2; define the severity of the duration as 1 and 2 for short-term fluctuation and long-term fluctuation respectively, and judge the value of the severity RT of the duration according to the size of the duration, where RT = {1, 2}; th1 The calculation formula for the duration is: T th1 = t2 - t1;

[0101] The method for judging the fluctuation direction is as follows: define the severity of the fluctuation direction as 1 and 2 for upward fluctuation and downward fluctuation respectively, and judge the value of the severity Rd of the fluctuation direction according to the positive and negative of the new energy output fluctuation amount, where Rd = {1, 2}; dur

[0102]

[0103] Step S280: Calculate the severity S of the new energy output fluctuation event according to the severities of the fluctuation amplitude, duration and fluctuation direction;

[0104] The calculation formula for the severity of the new energy output fluctuation event is: S = ws × Rs + wT × RT + wd × Rd, where ws, wT, and wd are the weight coefficients of the severities of the fluctuation amplitude, duration and fluctuation direction respectively, and are set by those skilled in the art according to experience;

[0105] Step S290: Set the severity thresholds S1 and S2, and classify the severities of the new energy output fluctuation events into mild fluctuation, moderate fluctuation and severe fluctuation; among them, the range of the severity of mild fluctuation is: 1 ≤ S < S1, the range of the severity of moderate fluctuation is: S1 ≤ S < S2, and the range of the severity of severe fluctuation is: S2 ≤ S < 3;

[0106] Step S300: Establish a self-healing control strategy for the new energy output fluctuation event, design the state, action and reward functions of the intelligent agent, and optimize the self-healing control strategy by using the reinforcement learning algorithm;

[0107] The specific method for establishing the self-healing control strategy for the new energy output fluctuation event, designing the state, action and reward functions of the intelligent agent, and optimizing the self-healing control strategy by using the reinforcement learning algorithm is as follows:

[0108] ​​Step S310: define the state space of the agent, the state s includes the new energy output fluctuation rate Ra, the grid frequency deviation Δf, the energy storage system charge state SOC, the controllable load state, the severity S of the new energy output fluctuation event, define the action space of the agent, the action a includes the new energy output limit instruction P cur , Energy storage charging and discharging power instruction P ess and controllable load control command P load ;

[0109] The grid frequency deviation reflects the degree to which the grid frequency deviates from the rated value and is an indicator for measuring grid stability. The grid frequency is measured in real time and its deviation degree is calculated by using wide-area measurement devices deployed at key nodes of the grid.

[0110] The energy storage system charge state indicates the ratio of the current available capacity of the energy storage system to the rated capacity, which affects the regulation capability of the energy storage system and is obtained through real-time monitoring of the energy storage battery management system;

[0111] The controllable load state refers to the access power level of the controllable load, which affects the regulation capability of the load-side resources. The real-time power of the controllable load is monitored by the load management system, and the percentage of the real-time power of the controllable load to the rated power of the controllable load is calculated according to the rated power of the controllable load.

[0112] The new energy output limit instruction refers to adjusting the output limit of the new energy station when the new energy output is unstable, thereby reducing the fluctuation range of the new energy output and alleviating the frequency fluctuation of the power grid;

[0113] The energy storage charging and discharging power instruction refers to adjusting the charging and discharging power of the energy storage system, smoothing the fluctuation of new energy output, and maintaining the stability of the grid frequency;

[0114] The controllable load control instruction refers to adjusting the access power of the controllable load, smoothing the fluctuation of the output of new energy, and maintaining the stability of the grid frequency;

[0115] Step S320: Based on the grid frequency deviation Δf and the new energy output limit |P cur |、Energy storage system charge change |ΔSOC|、Controllable load control quantity |P load | and the effect evaluation value of historical actions define the agent’s reward function;

[0116] The calculation formula of the reward function is: r = -ω1×|Δf|-ω2×|P cur |-ω3×ΔSOC|-ω4×|P load |+ω5×R zb , where R zbis the effect evaluation value, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of the effect evaluation value of the grid frequency deviation, the output limit of new energy, the charge change of the energy storage system, the controllable load control amount, and the historical action respectively;

[0117] The weight coefficients of the grid frequency deviation, the new energy output limit, the energy storage system charge change, the controllable load control amount and the historical action effect evaluation value are set by those skilled in the art based on experience;

[0118] The new energy output limit refers to the difference between the new energy output before and after the current action is executed during the new energy output fluctuation process;

[0119] The energy storage system charge change refers to the absolute value of the change in the energy storage system charge state SOC before and after the current action is performed during the new energy output fluctuation process;

[0120] The controllable load control amount represents the absolute value of the control amplitude of the controllable load control instruction before and after the current action is executed during the fluctuation of the output of the new energy source;

[0121] Step S330: Using the reinforcement learning algorithm, initialize the current Q network parameters, and in the current state s t Next, randomly select an action with probability ε, or select the action with the largest Q value with probability 1-ε, and execute the selected action a t , get the next moment state s t+1 and the reward function value r t ;

[0122] Preferably, the reinforcement learning algorithm selects a DQN algorithm;

[0123] The value of probability ε is set by those skilled in the art based on experience;

[0124] The DQN algorithm includes two Q networks with the same structure but different parameters: the current Q network and the target Q network. The current Q network is used for action selection and parameter update, and the target Q network is used to calculate the target value. Its parameters θ - Copied from the current Q network every certain number of steps.

[0125] Step S340: t ,a t ,r t ,s t+1 ) is stored in the experience replay cache, and a batch of samples (s j ,a j ,r j ,s j+1 ), calculate the target value of the current Q network;

[0126] The calculation formula of the target value of the current Q network is: Where γ is the discount factor, θ - is the parameter of the target Q network, a' represents the state s j+1 The action selected next, Q(s j+1 ,a';θ - ) represents the action value function calculated by the target Q network, which is used to estimate the state s j+1 The Q value when taking action a', max a’ It means to select the action that can obtain the maximum value among all actions a';

[0127] Step S350: define the loss function L(θ) of the current Q network, update the current Q network parameter θ by gradient descent method, minimize the value of the loss function, and regularly update the target Q network parameter θ - Update to the current Q network parameter θ;

[0128] The calculation formula of the loss function of the current Q network is: in, It means to find the expected value, Q(s j ,a j ; θ) represents the predicted value of the current Q network, and the loss function L(θ) of the current Q network represents the mean square error between the predicted value of the current Q network and the target value;

[0129] Step S360: Setting a self-healing control strategy according to the severity of the new energy output fluctuation event as the new energy output limit instruction P in the action space cur , Energy storage charging and discharging power instruction P ess and controllable load control command P load The constraint range of the new energy output limit instruction during mild fluctuations is P cur ∈[0.9P0, P0], the constraint range of energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.95P l , 1.05P l ]; The constraint range of the new energy output limit command during moderate fluctuation is P cur ∈[0.8P0,0.9P0) and the constraint range of the energy storage charging and discharging power instruction is P ess The constraint range of the controllable load control command is P load ∈[0.9P l , 1.1P l ]; The constraint range of the new energy output limit command during severe fluctuations is P cur∈[0.7P0, 0.8P0), the constraint range of the energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.85P l , 1.15P l ], where P0 is the initial output of new energy, is the rated power of the energy storage system, P l is the initial power of the controllable load;

[0130] Step S370: The agent selects the optimal action according to the current state. When selecting an action, if an action outside the constraint range is selected, the agent reselects until an action within the constraint range is selected, thereby obtaining an optimized self-healing control strategy.

[0131] Step S400: Each control unit of the power system monitors the new energy output fluctuation event in real time. When the new energy output fluctuation event is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy;

[0132] Each control unit of the power system monitors the new energy output fluctuation event in real time. When the new energy output fluctuation event is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system. The specific method of executing the optimized self-healing control strategy is:

[0133] Step S410: Each control unit of the power system is equipped with monitoring equipment and communication equipment to monitor the fluctuation event of the output of new energy in real time. When the control unit detects that the fluctuation event of the output of new energy is triggered within its jurisdiction, the optimized self-healing control strategy is sent to each control unit of the power system, and each control unit is adjusted to execute the corresponding instruction according to the output limit instruction of new energy, the charge and discharge power instruction of energy storage and the controllable load control instruction;

[0134] Step S500: obtaining an effect evaluation value of the self-healing control of the new energy output fluctuation event, and feeding the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy;

[0135] The specific method of obtaining the effect evaluation value of the self-healing control of the new energy output fluctuation event, feeding the effect evaluation value back to the reinforcement learning algorithm, and guiding the optimization of the next round of self-healing control strategy is:

[0136] Step S510: After executing the optimized self-healing control strategy, obtain the effect evaluation index of the self-healing control, the effect evaluation index includes: the power grid frequency recovery time T fr , Energy storage cycle life loss L ess and controllable load adjustment cost C load ;

[0137] The grid frequency recovery time refers to the time taken for the grid frequency deviation Δf to recover to the normal range after the fluctuation occurs. The frequency data is recorded in real time by the grid frequency monitoring equipment, and the recovery time is determined according to the normal range; the normal range is determined according to the grid frequency standard and the actual operation requirements, and preferably, it can be set to ±0.05Hz of the rated frequency;

[0138] The energy storage cycle life loss refers to the ratio of the number of energy storage charge and discharge cycles to the rated cycle life. The number of charge and discharge cycles is recorded according to the SOC change of the energy storage system, and the energy storage cycle life loss is calculated in combination with the rated cycle life. The rated cycle life is determined according to the type of energy storage battery and the data provided by the manufacturer;

[0139] The controllable load regulation cost refers to the user utility loss and compensation cost caused by the controllable load regulation. The regulation cost is calculated based on the type and regulation power of the controllable load, combined with the utility function and the compensation cost;

[0140] The calculation formula of the controllable load adjustment cost is: Among them, K is the total number of controllable loads, U k (·) is the utility function of the kth controllable load, are the controllable load power before and after adjustment, is the compensation cost of the kth controllable load;

[0141] The functional expression of the utility function of the controllable load is: Among them, U k (P k ) represents the kth controllable load at the controllable load power P k The user utility value under α and β are parameters of the utility function, which represent the user's preference for electric energy and are set by technicians in this field based on experience, α>0, β>0;

[0142] Step S520: calculating the effect evaluation value of the self-healing control of the new energy output fluctuation event according to the effect evaluation index;

[0143] The calculation formula for the effect evaluation value of the self-healing control of the new energy output fluctuation event is: R zb =-ω fr ×T fr -ω ess ×L ess -ω load ×C load , where ω fr ,ω ess ,ω loadare the weight coefficients of grid frequency recovery time, energy storage cycle life loss and controllable load regulation cost respectively;

[0144] The weight coefficients of the grid frequency recovery time, energy storage cycle life loss and controllable load adjustment cost are set by technicians in this field according to actual needs, and the sum of the weight coefficients is 1;

[0145] Step S530: Feedback the effect evaluation value obtained by currently executing the self-healing control strategy to the reinforcement learning algorithm to guide the optimization of the next self-healing control strategy.

[0146] Example 2

[0147] like Figure 4 As shown, the distributed self-healing recovery system for the power system considering the uncertainty of the output of new energy provided by this application includes:

[0148] The fluctuation event classification module is used to define the fluctuation amount and fluctuation rate of new energy output, set the trigger conditions of new energy output fluctuation events, and classify new energy output fluctuation events according to fluctuation amplitude, duration and fluctuation direction;

[0149] The severity calculation module is used to collect meteorological data and operation data of new energy units, train a short-term prediction model for predicting new energy output, use the short-term prediction model to predict new energy output in the future, and determine whether the triggering conditions of the new energy output fluctuation event are met. If so, the severity of the new energy output fluctuation event is evaluated;

[0150] The self-healing strategy optimization module is used to establish the self-healing control strategy for the new energy output fluctuation event, design the state, action and reward function of the intelligent agent, and use the reinforcement learning algorithm to optimize the self-healing control strategy;

[0151] The self-healing strategy execution module is used for each control unit of the power system to monitor the fluctuation events of renewable energy output in real time. When the fluctuation event of renewable energy output is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy;

[0152] The effect evaluation feedback module is used to obtain the effect evaluation value of the self-healing control of the new energy output fluctuation event, and feed the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy.

[0153] Example 3

[0154] According to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, the distributed self-healing recovery method of the power system considering the uncertainty of the output of new energy as described above may be executed.

[0155] The method or system according to the embodiment of the present application can also be implemented with the help of the architecture of the following electronic device. The electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store the distributed self-healing recovery method of the power system considering the uncertainty of the output of new energy provided in the present application. The distributed self-healing recovery method of the power system considering the uncertainty of the new energy output may include, for example: defining the new energy output fluctuation amount and the new energy output fluctuation rate, setting the triggering conditions of the new energy output fluctuation event, and classifying the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction; collecting meteorological data and the operation data of the new energy unit, training the short-term prediction model for predicting the new energy output, using the short-term prediction model to predict the new energy output in the future, judging whether the triggering conditions of the new energy output fluctuation event are met, and if so, evaluating the severity of the new energy output fluctuation event; establishing a self-healing control strategy for the new energy output fluctuation event, designing the state, action and reward function of the intelligent body, and optimizing the self-healing control strategy using a reinforcement learning algorithm; each control unit of the power system monitors the new energy output fluctuation event in real time, and when the new energy output fluctuation event is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy; obtaining the effect evaluation value of the self-healing control of the new energy output fluctuation event, and feeding the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy. Further, the electronic device may also include a user interface. Of course, the above architecture is only exemplary, and when implementing different devices, one or more components in the above electronic device may be omitted according to actual needs.

[0156] Example 4

[0157] A readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the distributed self-healing recovery method of the power system considering the uncertainty of the output of new energy according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0158] In addition, according to the implementation mode of the present application, the process described in the above reference flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present application, such as: defining the new energy output fluctuation amount and the new energy output fluctuation rate, setting the triggering conditions of the new energy output fluctuation event, and classifying the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction; collecting meteorological data and the operation data of the new energy unit, training a short-term prediction model for predicting the new energy output, using the short-term prediction model to predict the new energy output in the future, and judging whether it has reached The triggering conditions of the new energy output fluctuation event, if met, evaluate the severity of the new energy output fluctuation event; establish a self-healing control strategy for the new energy output fluctuation event, design the state, action and reward function of the intelligent body, and use the reinforcement learning algorithm to optimize the self-healing control strategy; each control unit of the power system monitors the new energy output fluctuation event in real time, and when the new energy output fluctuation event is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy; obtain the effect evaluation value of the self-healing control of the new energy output fluctuation event, and feed the effect evaluation value back to the reinforcement learning algorithm to guide the next round of self-healing control strategy optimization. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of this application are executed.

[0159] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0160] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0161] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A distributed self-healing restoration method for power systems considering the uncertainty of renewable energy output, characterized in that: include: Define the fluctuation amount and fluctuation rate of new energy output, set the trigger conditions of new energy output fluctuation events, and classify new energy output fluctuation events according to fluctuation amplitude, duration and fluctuation direction; Collect meteorological data and operation data of new energy units, train a short-term prediction model for predicting new energy output, use the short-term prediction model to predict new energy output in the future, and determine whether the triggering conditions of new energy output fluctuation events are met. If so, evaluate the severity of the new energy output fluctuation events; Establish a self-healing control strategy for renewable energy output fluctuation events, design the state, action and reward functions of the intelligent agent, and use reinforcement learning algorithms to optimize the self-healing control strategy; Each control unit of the power system monitors the output fluctuation events of renewable energy in real time. When a fluctuation event of renewable energy is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy. Obtain the effect evaluation value of the self-healing control of renewable energy output fluctuation events, and feed the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy.

2. The distributed self-healing restoration method for a power system considering the uncertainty of new energy output as claimed in claim 1, characterized in that: The specific method of defining the new energy output fluctuation amount and the new energy output fluctuation rate, setting the triggering conditions of the new energy output fluctuation event, and classifying the new energy output fluctuation event according to the fluctuation amplitude, duration and fluctuation direction is as follows: A time window mt is preset, and the change in the output of new energy within the time window is defined as the output fluctuation of new energy Δp, and the ratio of the output fluctuation of new energy to the installed capacity of new energy is defined as the output fluctuation rate of new energy Ra; Set the first volatility threshold R th1 , when the new energy output fluctuation rate is greater than or equal to the first fluctuation rate threshold, it is considered that a new energy output fluctuation event is triggered; According to the magnitude of the fluctuation rate of the new energy output, the fluctuation range is divided into three levels: small fluctuation, medium fluctuation and large fluctuation. The range of the fluctuation rate of the new energy output with small fluctuation is [R th1 ,R th2 ), the range of the fluctuation rate of the new energy output is [R th2 ,R th3 ), the range of the large fluctuation of new energy output fluctuation rate is [R th3 ,+∞), where R th1 , R th2 , R th3 They are respectively a preset first volatility threshold, a second volatility threshold, and a third volatility threshold; According to the duration T of the renewable energy output fluctuation event dur It is divided into short-term fluctuations and long-term fluctuations. The duration of the short-term fluctuations ranges from (0, T th ), the duration of the long-term fluctuation is in the range of [T th ,+∞), where T th is a preset time threshold; According to the positive or negative value of the new energy output fluctuation Δp, the fluctuation direction is divided into upward fluctuation and downward fluctuation.

3. The distributed self-healing restoration method for power system considering the uncertainty of new energy output as claimed in claim 2, characterized in that: The specific method of collecting meteorological data and operation data of new energy units, training a short-term prediction model for predicting new energy output, using the short-term prediction model to predict new energy output in the future, and judging whether the triggering conditions of the new energy output fluctuation event are met is: Meteorological sensors and electrical sensors are configured at new energy stations to collect meteorological data and operating data of new energy units. The meteorological data includes historical meteorological data and weather forecast data, and the operating data includes inverter output power and total station output; The long short-term memory network is selected as the initial network of the short-term prediction model, the sliding window length nt and the sliding step length are preset, and the historical meteorological data, operation data and weather forecast data are generated into a time series in chronological order; The historical meteorological data and operation data of nt moments before the tth moment and the weather forecast data of nt moments after the tth moment are used as the input data of the short-term prediction model, and the future new energy output is used as the output data. The sliding window moves backward in the time series according to the sliding step size, and the training samples are generated in the time series in the form of a sliding window. Define mean square error as the loss function for training the long short-term memory network, use training samples to train the long short-term memory network, optimize model parameters by minimizing the value of the loss function, and obtain a trained short-term prediction model when the loss function reaches convergence; Every time window \(m_t\), the historical meteorological data and operation data of the \(n_t\) moments before the current moment and the weather forecast data of the \(n_t\) moments after are input into the short-term prediction model to predict the future new energy output. According to the predicted new energy output, calculate the new energy output fluctuation amount \(\Delta p\) and the new energy output volatility \(R_a\). The new energy output volatility and the first volatility threshold R th1 By comparison, if the new energy output fluctuation rate is greater than or equal to the first fluctuation rate threshold, a new energy output fluctuation event is triggered.

4. The distributed self-healing restoration method for a power system considering the uncertainty of the output of new energy sources as claimed in claim 3 is characterized in that: The specific method for evaluating the severity of the new energy output fluctuation event is as follows: Judge the severity of the fluctuation amplitude, duration, and fluctuation direction of the new energy output fluctuation event. Among them, the judgment method for the fluctuation amplitude is: Define the severity of the fluctuation amplitude as 1, 2, and 3 for small fluctuations, medium fluctuations, and large fluctuations respectively. According to the magnitude of the new energy output volatility, judge the value of the severity \(R_s\) of the fluctuation amplitude, where \(R_s=\{1, 2, 3\}\). The duration is determined by: obtaining a new energy output sequence based on the n predicted new energy outputs, and determining that the new energy output volatility Ra is greater than or equal to the first volatility threshold R for the first time th1 The time t1 is taken as the starting time of the new energy output fluctuation event; Starting from time t1, it is determined that the new energy output fluctuation rate Ra is less than the first fluctuation rate threshold R for the first time. th1 The time t2 is taken as the end time of the new energy output fluctuation event, and the duration is obtained according to the difference between the time t1 and the time t2; Define the severity of the duration as 1 and 2 for short-term fluctuations and long-term fluctuations respectively. According to the magnitude of the duration, judge the value of the severity \(R_T\) of the duration, where \(R_T = \{1, 2\}\). Among them, the judgment method for the fluctuation direction is: Define the severity of the fluctuation direction as 1 and 2 for upward fluctuations and downward fluctuations respectively. According to the positive and negative of the new energy output fluctuation amount, judge the value of the severity \(R_d\) of the fluctuation direction, where \(R_d=\{1, 2\}\). According to the severity of the fluctuation amplitude, duration, and fluctuation direction, calculate the severity \(S\) of the new energy output fluctuation event. Set severity thresholds \(S_1\) and \(S_2\), and classify the severity of the new energy output fluctuation event into mild fluctuations, moderate fluctuations, and severe fluctuations. Among them, the range of the severity of mild fluctuations is: \(1\leq S < S_1\), the range of the severity of moderate fluctuations is: \(S_1\leq S < S_2\), and the range of the severity of severe fluctuations is: \(S_2\leq S < 3\).

5. The distributed self-healing restoration method for a power system considering the uncertainty of the output of new energy sources as claimed in claim 4 is characterized in that: The specific method for designing the state, action, and reward function of the intelligent agent and optimizing the self-healing control strategy using the reinforcement learning algorithm is as follows: Define the state space of the agent, where the state s includes the new energy output fluctuation rate Ra, the grid frequency deviation Δf, the energy storage system charge state SOC, the controllable load state, and the severity S of the new energy output fluctuation event; define the action space of the agent, where the action a includes the new energy output limit instruction P cur , Energy storage charging and discharging power instruction P ess and controllable load control command P load ; Based on the grid frequency deviation Δf, the new energy output limit |P cur |、Energy storage system charge change |ΔSOC|、Controllable load control quantity |P load | and the effect evaluation value of historical actions define the agent’s reward function; Using the reinforcement learning algorithm, initialize the current Q network parameters, and at the current state s t Next, randomly select an action with probability ε, or select the action with the largest Q value with probability 1-ε, and execute the selected action a t , get the next moment state s t+1 and the reward function value r t ; Will (s t ,a t ,r t ,s t+1 ) is stored in the experience replay cache, and a batch of samples (s j ,a j ,r j ,s j+1 ), calculate the target value of the current Q network; Define the loss function L(θ) of the current Q network, update the current Q network parameter θ by gradient descent method, minimize the value of the loss function, and regularly update the target Q network parameter θ - Update to the current Q network parameter θ; The intelligent agent selects the optimal action according to the current state. When selecting an action, if an action outside the constraint range is selected, reselect until an action within the constraint range is selected, and obtain the optimized self-healing control strategy.

6. The distributed self-healing restoration method for a power system considering the uncertainty of the output of new energy sources as claimed in claim 5, characterized in that: The specific method for establishing the self-healing control strategy for the new energy output fluctuation event is as follows: According to the severity of the new energy output fluctuation event, a self-healing control strategy is set as the new energy output limit instruction P in the action space. cur , Energy storage charging and discharging power instruction P ess and controllable load control command P load The constraint range of the new energy output limit instruction during mild fluctuations is P cur ∈[0.9P0, P0], the constraint range of energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.95P l , 1.05P l ]; The constraint range of the new energy output limit command during moderate fluctuation is P cur ∈[0.8P0, 0.9P0), the constraint range of the energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.9P l , 1.1P l ]; The constraint range of the new energy output limit command during severe fluctuations is P cur ∈[0.7P0, 0.8P0), the constraint range of the energy storage charging and discharging power instruction is The constraint range of the controllable load control command is P load ∈[0.85P l , 1.15P l ], where P0 is the initial output of new energy, is the rated power of the energy storage system, P l is the initial power of the controllable load.

7. The distributed self-healing restoration method for a power system considering the uncertainty of the output of new energy sources as claimed in claim 6, characterized in that: The specific method for obtaining the effect evaluation value of the self-healing control of the new energy output fluctuation event and feeding the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy is as follows: After executing the optimized self-healing control strategy, the effect evaluation index of the self-healing control is obtained, and the effect evaluation index includes: the power grid frequency recovery time T fr , Energy storage cycle life loss L ess and controllable load adjustment cost C load ; Calculate the effect evaluation value of the self-healing control of the new energy output fluctuation event according to the effect evaluation index. Feed the effect evaluation value obtained by executing the current self-healing control strategy back to the reinforcement learning algorithm to guide the optimization of the next self-healing control strategy.

8. A distributed self-healing restoration system for a power system considering the uncertainty of the output of new energy sources, which is implemented based on a distributed self-healing restoration method for a power system considering the uncertainty of the output of new energy sources as described in any one of claims 1 to 7, characterized in that: Including: A fluctuation event classification module, which is used to define the new energy output fluctuation amount and the new energy output volatility, set the trigger condition of the new energy output fluctuation event, and classify the new energy output fluctuation event according to the fluctuation amplitude, duration, and fluctuation direction. The severity calculation module is used to collect meteorological data and operation data of new energy units, train a short-term prediction model for predicting new energy output, use the short-term prediction model to predict new energy output in the future, and determine whether the triggering conditions of the new energy output fluctuation event are met. If so, the severity of the new energy output fluctuation event is evaluated; The self-healing strategy optimization module is used to establish the self-healing control strategy for the new energy output fluctuation event, design the state, action and reward function of the intelligent agent, and use the reinforcement learning algorithm to optimize the self-healing control strategy; The self-healing strategy execution module is used for each control unit of the power system to monitor the fluctuation events of renewable energy output in real time. When the fluctuation event of renewable energy output is triggered, the optimized self-healing control strategy is sent to the distributed control unit of the power system to execute the optimized self-healing control strategy; The effect evaluation feedback module is used to obtain the effect evaluation value of the self-healing control of the new energy output fluctuation event, and feed the effect evaluation value back to the reinforcement learning algorithm to guide the optimization of the next round of self-healing control strategy.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the distributed self-healing restoration method of the power system considering the uncertainty of the output of new energy sources as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in the distributed self-healing restoration method of the power system considering the uncertainty of the output of new energy as described in any one of claims 1-7.

Images