Quality-effect evaluation method, device and equipment for participation of energy storage power station in electric power spot market, and medium

Abstract

The invention discloses a quality-effect evaluation method, device and equipment for an energy storage power station participating in an electric power spot market, and a medium, and relates to the field of power distribution network energy storage optimization, and the method comprises the steps: determining a state space and a reward function according to operation data; inputting the state space and the reward function into the energy storage optimization regulation and control model to obtain an optimal energy storage regulation and control strategy; according to the addressing and sizing information, a Newton-Raphson power distribution network load flow calculation method and a multi-target genetic algorithm are adopted to carry out multiple iterations with minimum line loss and voltage fluctuation as targets, and an optimal addressing and sizing scheme is determined; and applying the optimal energy storage regulation and control strategy and the optimal locating and sizing scheme to a simulation scene in which the energy storage power station participates in the electric power spot market, comparing a quality-effect index of an actual scene in which the energy storage power station participates in the electric power spot market with a quality-effect index of the simulation scene, and determining a quality-effect evaluation result of the actual scene. The method can accurately and comprehensively realize the quality-effect evaluation of the energy storage power station participating in the electricity market.

Description

Technical Field

[0001] The present application relates to the field of distribution network energy storage optimization, and in particular to a method, device, equipment and medium for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market. Background Art

[0002] With the gradual opening of the power market and the large-scale access of renewable energy, the power spot market, as an important part of the distribution network system, has become increasingly important. As an important flexibility resource in the power system, the participation of energy storage power stations in the distribution network has a significant effect on alleviating the contradiction between peak and valley of the power grid, improving the regulation capacity of the system, and promoting the consumption of renewable energy. However, how to scientifically and comprehensively evaluate the quality and efficiency of energy storage power stations participating in the distribution network has become an urgent problem to be solved in the current research and practice of the distribution network.

[0003] Most of the related methods for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market focus on single-dimensional evaluation, such as economic benefits and technical performance, and lack comprehensive consideration of distribution network operation effects, grid regulation effects, etc. In addition, the evaluation process often lacks the support of big data analysis and intelligent algorithms, resulting in inaccurate and incomplete evaluation results, which in turn affects the operation efficiency of the distribution network and the optimization of resource allocation. Summary of the invention

[0004] The purpose of this application is to provide a method, device, equipment and medium for evaluating the quality and efficiency of distribution networks participating in the electricity spot market, which can accurately and comprehensively realize the quality and efficiency evaluation of energy storage power stations participating in the electricity spot market, thereby improving the operating efficiency of the distribution network and optimizing resource allocation.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] First, this application provides a quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market, including:

[0007] Obtain the current operating data and site selection and capacity information of the distribution network in which the energy storage power station participates;

[0008] Determine the state space and reward function at the current moment according to the operating data at the current moment; the state space includes: the power generation of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current moment; the reward function is determined according to the power generation of the energy storage power station, the load of the distribution network and the stored energy of the energy storage power station at the current moment;

[0009] The state space and reward function at the current moment are input into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; the energy storage optimization control model is constructed based on a deep reinforcement learning network and a neural network; the deep reinforcement learning network is used to output an action space based on the state space and the reward function; the action space includes: insufficient power generation action and excess power generation action; the neural network is used to obtain an action value function based on the action space output by the deep reinforcement learning network; the optimal energy storage control strategy is the energy storage control strategy corresponding to the maximum action value function; the energy storage control strategy includes: the power generation power of the energy storage power station and the load of the distribution network;

[0010] According to the current site selection and capacity determination information, the Newton-Raphson distribution network power flow calculation method and multi-objective genetic algorithm are used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and capacity determination plan at the current moment;

[0011] For the simulation scenario of energy storage power stations participating in the electricity spot market, the optimal energy storage control strategy and the optimal location and capacity determination scheme are used to operate and determine the quality and efficiency indicators of the simulation scenario; the quality and efficiency indicators include: market member benefits, market operation effects and grid regulation effects;

[0012] For the actual scenario of energy storage power stations participating in the electricity spot market, determine the quality and efficiency indicators of the actual scenario;

[0013] The quality and efficiency indicators of the actual scenario are compared with those of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario in which the energy storage power station participates in the electricity spot market.

[0014] In the second aspect, the present application provides a quality and efficiency evaluation device for energy storage power stations participating in the electricity spot market, including:

[0015] The data acquisition module is used to obtain the current operating data and site selection and capacity information of the distribution network in which the energy storage power station participates;

[0016] A parameter determination module is used to determine the state space and reward function at the current moment according to the operating data at the current moment; the state space includes: the power generation of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current moment; the reward function is determined according to the power generation of the energy storage power station, the load of the distribution network and the stored energy of the energy storage power station at the current moment;

[0017] The energy storage control strategy optimization module is used to input the current state space and reward function into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; the energy storage optimization control model is constructed based on a deep reinforcement learning network and a neural network; the deep reinforcement learning network is used to output an action space based on the state space and the reward function; the action space includes: insufficient power generation action and excess power generation action; the neural network is used to obtain an action value function based on the action space output by the deep reinforcement learning network; the optimal energy storage control strategy is the energy storage control strategy corresponding to the maximum action value function; the energy storage control strategy includes: energy storage power station power generation and distribution network load;

[0018] The site selection and sizing optimization module is used to determine the optimal site selection and sizing scheme at the current moment based on the site selection and sizing information, using the Newton-Raphson distribution network power flow calculation method and the multi-objective genetic algorithm to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation;

[0019] A simulation scenario quality and efficiency index determination module is used to determine the quality and efficiency indicators of the simulation scenario in which the energy storage power station participates in the electricity spot market, using the optimal energy storage control strategy and the optimal location and capacity determination plan to operate, and determine the quality and efficiency indicators of the simulation scenario; the quality and efficiency indicators include: market member benefits, market operation effects, and grid regulation effects;

[0020] The actual scenario quality and efficiency indicator determination module is used to determine the actual scenario quality and efficiency indicators for the actual scenario of energy storage power stations participating in the electricity spot market;

[0021] The quality and efficiency evaluation module is used to compare the quality and efficiency indicators of the actual scenario with those of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario in which the energy storage power station participates in the electricity spot market.

[0022] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned methods for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market.

[0024] According to the specific embodiments provided in this application, this application has the following technical effects:

[0025] The present application provides a method, device, equipment and medium for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market. The method uses an energy storage optimization and control model constructed based on a deep reinforcement learning network and a neural network to determine the optimal energy storage control strategy. The Newton-Raphson distribution network power flow calculation method and a multi-objective genetic algorithm are used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal location and sizing plan. The optimal energy storage control strategy and the optimal location and sizing plan are applied to a simulated scenario of the energy storage power station participating in the electricity spot market. The quality and efficiency indicators of the actual scenario of the energy storage power station participating in the electricity spot market are compared with the quality and efficiency indicators of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario. The present application accurately and comprehensively realizes the quality and efficiency evaluation of the energy storage power station participating in the electricity spot market from multiple dimensions such as market member benefits, market operation effects and grid regulation effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 This is an application environment diagram of a quality and efficiency evaluation method for an energy storage power station participating in the electricity spot market in one embodiment of the present application;

[0028] Figure 2 A flow chart of a method for evaluating the quality and efficiency of an energy storage power station participating in the electricity spot market provided in one embodiment of the present application;

[0029] Figure 3 A schematic diagram of a deep reinforcement learning process provided by an embodiment of the present application;

[0030] Figure 4 A schematic diagram of the construction process of an energy storage control optimization model based on deep reinforcement learning provided in one embodiment of the present application;

[0031] Figure 5 A flowchart of determining the optimal location and capacity solution based on a multi-objective genetic algorithm provided in one embodiment of the present application;

[0032] Figure 6 A schematic diagram of a network of site selection and capacity determination nodes provided in an embodiment of the present application;

[0033] Figure 7 A schematic diagram of an overall process of a quality and efficiency evaluation method for an energy storage power station participating in a spot electricity market provided in an embodiment of the present application;

[0034] Figure 8A schematic diagram of functional modules of a quality and efficiency evaluation device for energy storage power stations participating in the electricity spot market provided by another embodiment of the present application;

[0035] Fig. 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] The quality and efficiency evaluation method of energy storage power stations participating in the electricity spot market provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the current operating data and site selection and sizing information of the distribution network in which the energy storage power station participates to the server 104. After receiving the current operating data and site selection and sizing information of the distribution network in which the energy storage power station participates, the server 104 determines the state space and reward function at the current moment according to the current operating data of the distribution network in which the energy storage power station participates; inputs the current state space and reward function into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; according to the site selection and sizing information at the current moment, the Newton-Raphson distribution network flow calculation method and the multi-objective genetic algorithm are used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and sizing scheme at the current moment; under the optimal energy storage control strategy and the optimal site selection and sizing scheme, the line loss, voltage fluctuation and capacity of the distribution network in which the energy storage power station participates and the capacity of the energy storage power station are evaluated at the current moment to obtain a quality and efficiency evaluation result.

[0039] The server 104 can feed back the obtained quality and efficiency evaluation results to the terminal 102. In addition, in some embodiments, the quality and efficiency evaluation method of the energy storage power station participating in the electricity spot market can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly process the operation data and site selection and capacity information of the distribution network in which the energy storage power station participates at the current moment, or the server 104 can obtain the operation data and site selection and capacity information of the distribution network in which the energy storage power station participates at the current moment from the data storage system, and process the operation data and site selection and capacity information of the distribution network in which the energy storage power station participates at the current moment.

[0040] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0041] In an exemplary embodiment, Figure 2 As shown, a method for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 201 to 207. Among them:

[0042] Step 201, obtaining the current operating data and site selection and capacity determination information of the distribution network in which the energy storage power station participates.

[0043] Step 202, determining the state space and reward function at the current moment according to the operating data at the current moment.

[0044] The state space includes: the power generation of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current time; the reward function is determined according to the power generation of the energy storage power station, the load of the distribution network and the storage energy of the energy storage power station at the current time;

[0045] Step 203, input the current state space and reward function into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; the energy storage optimization control model is constructed based on a deep reinforcement learning network and a neural network.

[0046] The deep reinforcement learning network is used to output an action space according to the state space and the reward function; the action space includes: insufficient power generation action and excess power generation action; the neural network is used to obtain an action value function according to the action space output by the deep reinforcement learning network; the optimal energy storage control strategy is the energy storage control strategy corresponding to the maximum action value function; the energy storage control strategy includes: the power generation power of the energy storage power station and the load of the distribution network.

[0047] Step 204, based on the current site selection and sizing information, the Newton-Raphson distribution network power flow calculation method and the multi-objective genetic algorithm are used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and sizing solution at the current moment.

[0048] Step 205, for the simulation scenario of the energy storage power station participating in the electricity spot market, the optimal energy storage control strategy and the optimal site selection and sizing scheme are used to operate and determine the quality and efficiency indicators of the simulation scenario; the quality and efficiency indicators include: market member benefits, market operation effects and grid regulation effects.

[0049] The quality and efficiency indicators of the simulation scenario are determined under the optimal energy storage control strategy and the optimal site selection and sizing scheme. Therefore, the quality and efficiency indicators of the simulation scenario are the best quality and efficiency indicators.

[0050] Step 206, for the actual scenario of the energy storage power station participating in the electricity spot market, determine the quality and efficiency indicators of the actual scenario.

[0051] The actual scenario operates with the actual energy storage control strategy and the actual site selection and sizing plan. The operating conditions may not be the optimal operating conditions. The pros and cons of the operating conditions can be evaluated through quality and efficiency indicators.

[0052] Step 207, comparing the quality and efficiency indicators of the actual scenario with the quality and efficiency indicators of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario of the energy storage power station participating in the electricity spot market.

[0053] Specifically, the closer the quality and efficiency indicators of the actual scenario are to those of the simulation scenario, the better the quality and efficiency evaluation results are, that is, the more reasonable the actual scenario of the energy storage power station participating in the electricity spot market is.

[0054] The above-mentioned embodiment will compare the grid regulation effect, market operation effect, and market member benefits obtained after adopting the optimal energy storage control strategy and the optimal site selection and sizing scheme with the existing corresponding data of energy storage power stations participating in the electricity spot market without adopting the best optimization strategy, to achieve quality and efficiency evaluation, so as to determine the shortcomings of the existing energy storage power stations. The implementation of the above-mentioned steps 201 to 207 can accurately and comprehensively realize the quality and efficiency evaluation of energy storage power stations participating in the electricity spot market. The present application covers the quality and efficiency evaluation of energy storage power stations participating in the electricity spot market in many aspects, such as distribution network voltage stability, line loss, and capacity of energy storage power stations, which is of great significance for improving the operating efficiency of the distribution network and optimizing resource allocation.

[0055] In another exemplary embodiment of the present application, in step 203, the deep reinforcement learning network adopts a deep Q-learning network (Deep Q-Leaning Network, DQN); the deep Q-learning network is implemented based on a Markov decision process (Markov Decision Process, MDP). The neural network adopts a long short-term memory network (Long Short Term Memory Network, LSTM).

[0056] This embodiment uses a deep reinforcement learning algorithm to establish an intelligent agent after statistics, analysis, and organization of the historical data obtained, so as to realize the optimal control strategy of the intelligent agent through interaction and learning with the environment. In this application, the deep reinforcement learning algorithm is specifically implemented through a Markov decision process, in which the state, action, reward, transition probability, and discount factor of the intelligent agent are represented by S, A, R, P, and γ, respectively. The purpose of this reinforcement learning is to strengthen the random strategy π, which is defined as the probability of selecting a specific action in a given state:

[0057] π(a|s)=p[At=a|St=s];

[0058] In the formula, s is the given state; a is the selected action; t is the time node. According to the strategy π, the cumulative discounted reward G is calculated t , the specific form is as follows:

[0059]

[0060] In the formula, t is the time node; R is the reward function; γ is the discount factor; D is the terminal state time node. When the agent executes the strategy π, the expected value in state s is the state value function, which is as follows:

[0061]

[0062] Accordingly, the expected value under action a is the action value function, which is as follows:

[0063]

[0064] Reinforcement learning is committed to finding the optimal strategy π* to maximize the total return value, while the Bellman optimal equation is a calculation method for solving the optimal state value and the optimal action value. Its form is as follows:

[0065]

[0066]

[0067] In the formula, v*(s) is the optimal state value function of state s, q*(s,a) is the optimal action value function of action a under state s, s' is the next state of state s, and P is the transition probability function. After that, the agent can start to explore the optimal strategy π from the initial state S0 * , and the optimal strategy π * This will maximize the action value function, that is:

[0068]

[0069] After the historical data of the energy storage power station and the corresponding distribution network are collected, analyzed and sorted, the deep reinforcement learning algorithm is used to establish an intelligent agent to achieve the optimal control strategy through the interaction and learning of the intelligent agent with the environment. Figure 3 shown.

[0070] This application uses the DQN network and the LSTM network to establish an energy storage optimization and control model. Through the interaction between the model and the environment, the intelligent agent is continuously rewarded, thereby continuously optimizing the energy storage control strategy.

[0071] The basic formula of the energy storage model designed in this application is as follows:

[0072]

[0073]

[0074] In the formula, B t is the storage energy of the energy storage power station at the current time t, η c is the charging efficiency of the energy storage station, η d is the discharge efficiency of the energy storage power station, C t is the charging power of the energy storage station at the current time t, D t is the discharge power of the energy storage station at the current time t, B max The maximum storage energy of the energy storage power station, BSC t is the charge state of the energy storage power station at the current time t.

[0075] Then, the parameter values ​​selected by the energy storage optimization model at the time step are determined by combining the historical data of the energy storage power station and the Markov decision process. The state space of the model consists of the power generation of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current time t, that is, the expression of the state space is: s t =[P t ,L t ,BSC t ,t], where s t represents the state space at the current time t; P t represents the power generation of the energy storage power station at the current time t; L t Indicates the distribution network load at the current time t; BSC t Indicates that the energy storage power station is in full load state at the current time t.

[0076] The action space is determined by the insufficient generation of distributed generation. d With excess power generation A e Composition, that is, a t =[A d ,A e ] Define R t is the reward function, which is expressed as:

[0077]

[0078] In the formula, R t Represents the reward function at the current time t.

[0079] Based on LSTM neural network and DQN network, the state and action are used as the input of neural network, and the action value function of energy storage system regulation is obtained through neural network analysis. The construction process of energy storage regulation optimization model based on deep reinforcement learning is as follows: Figure 4 shown.

[0080] This application establishes an energy storage optimization and control model through a deep reinforcement learning algorithm to formulate the best strategy for the operation of the energy storage power station, so as to reduce the load peak in the distribution network, achieve source-load configuration matching of a high proportion of distributed power sources connected to the distribution network, and reduce the situation of negative net load, alleviate the problem of power flow reversal, stabilize the power flow distribution of distribution network nodes with a high proportion of distributed power sources connected, and provide a more flexible and adaptive decision-making plan for the operation of the energy storage power station.

[0081] In another exemplary embodiment of the present application, step 204 specifically includes: according to the site selection and sizing information at the current moment, using the Newton-Raphson distribution network power flow calculation method to determine the initial site selection and sizing plan at the current moment; based on the initial site selection and sizing plan at the current moment, using a multi-objective genetic algorithm to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and sizing plan at the current moment.

[0082] Specifically, this embodiment uses the Newton-Raphson distribution network power flow calculation method to determine the optimal site selection and capacity determination scheme for an energy storage power station in the distribution network according to the accessible location and capacity constraints of the energy storage power station in the distribution network, and uses a multi-objective genetic algorithm to continuously optimize the site selection and capacity determination results. For multivariable nonlinear equations such as power flow calculation, the specific principle of the Newton-Raphson method is as follows:

[0083] F(X k )=-J k ΔX k ;

[0084] X k+1 =X k +ΔX k ;

[0085] In the formula, X k represents the approximate solution of n multivariate functions after the kth iteration, consisting of an n-dimensional column vector, and ΔX k Its corresponding correction value, J k It represents an n×n Jacobian matrix, which can be applied to the distribution network power flow calculation to obtain:

[0086]

[0087] In the formula, P is active power, Q is reactive power, U is node voltage, δ is phase angle, ΔP, ΔQ, and Δδ are the differences in generated power, reactive power, and phase angle of the energy storage power station before and after energy storage optimization and regulation, respectively.

[0088] This embodiment uses a multi-objective genetic algorithm to construct an optimization model for the site selection and sizing problem, aiming to achieve dual minimization of line loss and voltage volatility through a multi-objective genetic algorithm, and thereby determine the optimal site selection and sizing solution for the energy storage power station. The multi-objective genetic algorithm solves complex problems involving multiple optimization objectives by simulating the evolutionary process in nature. Its core strategy is to generate an initial population using the initial site selection and sizing solution obtained by the flow calculation, and then in each generation of evolution, use the selection mechanism to screen out individuals whose fitness meets the preset conditions (such as using the selection mechanism to screen out individuals with higher fitness, which perform better on specific optimization objectives). New genetic information is introduced through crossover and mutation operations to increase the diversity of the population and avoid premature convergence. When the evolutionary process reaches a preset algebraic threshold, the algorithm stops iterating and outputs the optimal solution set for the given problem. These solutions perform well in balancing multiple optimization objectives. Based on this principle, this application constructs an optimization model for the site selection and sizing problem, aiming to achieve dual minimization of line loss and voltage volatility through a multi-objective genetic algorithm, and thereby determine the optimal site selection and sizing solution for the energy storage power station. The model effectively determines the optimal site selection and sizing planning for the energy storage power station. After its access, the voltage amplitude of the node network does not fluctuate too much, while further reducing the line loss of the overall node network and improving the economic benefits of the energy storage power station.

[0089] This embodiment is based on the initial site selection and sizing scheme at the current moment, and adopts a multi-objective genetic algorithm to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and sizing scheme at the current moment, specifically including: determining the population at the current iteration number; each individual in the population represents a site selection and sizing scheme; the population at the initial iteration number includes the initial site selection and sizing scheme; calculating the fitness value of each individual in the population at the current iteration number; the fitness value is calculated based on the line loss and voltage fluctuation; screening the individuals in the population at the current iteration number according to the fitness value and the set selection mechanism to obtain the screened population at the current iteration number; performing crossover and mutation operations on the screened population at the current iteration number to obtain a new population at the current iteration number; judging whether the current iteration number reaches the maximum iteration number; if so, determining the new population at the current iteration number as the optimal site selection and sizing scheme at the current moment; if not, determining the new population at the current iteration number as the population at the next iteration number, and performing the next iteration.

[0090] The process of determining the optimal site location and capacity solution based on a multi-objective genetic algorithm is as follows: Figure 5 The node network of the energy storage power station in the distribution network with the IEEE-14 node system as a sample is shown in Figure 6 As shown, Figure 6 The figure shows the access locations of 14 nodes and energy storage power stations.

[0091] In another exemplary embodiment of the present application, in step 205, the present application evaluates the access effect of the distribution network, analyzes the contribution of the charging and discharging behavior of the energy storage power station to the balance of power supply and demand, and calculates indicators such as the supply-demand ratio and the peak-to-valley difference. The line loss of the distribution network access is evaluated by calculating the wire length, unit length loss and other indicators. The calculation formula of the line loss is:

[0092]

[0093] Among them, DeltaV represents line loss (KV); P represents the active power transmitted by the line (KW); Q represents the reactive power transmitted by the line; R represents the resistance of the line; X represents the reactance of the line; V N Indicates the rated voltage of the line.

[0094] The distribution network line loss assessment method adopted in this embodiment mainly assesses the impact of energy storage power stations participating in the distribution network. By calculating the distribution network stability index, price volatility index, etc., it reflects the regulatory effect of energy storage power stations on the supply and demand relationship of the distribution network. At the same time, it considers the impact of the participation of energy storage power stations on the grid structure, competitive situation, etc., and provides decision-making references for market managers.

[0095] In another exemplary embodiment of the present application, in step 205, the present application evaluates the voltage stability (i.e., voltage volatility) of the distribution network, forms constraints on the sub-model based on the local distribution network-related policies, uses big data to analyze the market's clearing mechanism, and other information, and uses a density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) to perform anomaly detection on the data and clean, convert, and standardize the data to evaluate the voltage volatility of the distribution network. The voltage volatility calculation formula is:

[0096] VS j =V j 4 -4(P j τ b +Q j x b )V j 2 +4(P j τ b +Q j x b );

[0097] Among them, VS j represents the voltage fluctuation at node j; V j represents the voltage of node j; P j represents the active power of node j; Qj represents the reactive power of node j; τ b represents the resistance of the branch before node j; x b Represents the reactance value of the branch before node j.

[0098] This embodiment mainly considers the voltage stability of the energy storage power station participating in the distribution network. By calculating the peak-valley arbitrage income, capacity compensation income, ancillary service income, etc. of the energy storage power station, the operation of the energy storage power station is fully reflected. At the same time, the impact of different factors on income is considered to ensure the comprehensiveness and accuracy of the evaluation results.

[0099] In addition, this application can also evaluate the capacity of the energy storage power station by evaluating the contribution of the energy storage power station to the frequency stability of the power grid, calculating indicators such as frequency deviation and frequency fluctuation rate, analyzing the impact of the charging and discharging behavior of the energy storage power station on the load capacity of the power grid, calculating indicators such as voltage deviation and voltage fluctuation rate, and using the above indicators to establish a continuous monitoring mechanism for the effect of power grid regulation to evaluate the capacity of the energy storage power station. The calculation formula for the capacity of the energy storage power station is:

[0100]

[0101] Where, text represents the capacity of the energy storage power station; K x It represents the required coefficient, which is a coefficient less than 1 and is used to reflect the degree of simultaneous use of energy storage power stations; P i represents the rated power of the i-th energy storage power station; n represents the total number of energy storage power stations.

[0102] This embodiment evaluates the capacity of the energy storage power station, mainly evaluating the impact of the energy storage power station on the grid regulation effect. By calculating the grid load rate, voltage stability index, frequency stability index, etc., it reflects the role of the energy storage power station in alleviating grid fluctuations and improving grid stability. At the same time, the geographical location of the energy storage power station, access mode and other factors that affect the grid regulation effect are considered to provide optimization suggestions for grid operators.

[0103] The overall process of the quality and efficiency evaluation method of the energy storage power station participating in the electricity spot market in the above embodiment is as follows: Figure 7 shown.

[0104] This application is aimed at the mathematical model of energy storage power stations participating in the distribution network, which covers multiple sub-models such as optimization and regulation of energy storage power stations, optimal site selection and sizing planning of energy storage power stations in distribution networks, and multi-dimensional quality and efficiency evaluation after the energy storage power stations participate in the distribution network. Through neural networks, deep reinforcement learning algorithms, multi-objective genetic algorithms, distribution network flow calculation and other methods, two sub-models are established to provide the best strategies for the optimization and regulation of energy storage power stations themselves and the site selection and sizing planning after the energy storage power stations participate in the distribution network, and conduct multi-angle and high-precision evaluation of the power station operation under this strategy to comprehensively reflect the performance of energy storage power stations and their contribution to the power system.

[0105] The quality and efficiency evaluation of energy storage power stations participating in the electricity spot market, under the premise of giving priority to determining the best control scheme and site selection and capacity determination strategy for energy storage power stations participating in the distribution network, collects the transaction data of the distribution network, the operation data of energy storage power stations, the load data of the power grid, the output data of renewable energy, etc., so as to establish a line loss calculation model for energy storage power stations participating in the distribution network, including charging costs, discharge benefits, market subsidies, etc. Developing a quality and efficiency evaluation system for energy storage power stations participating in the electricity spot market that covers three aspects, namely voltage stability, power grid line losses, and power capacity load, can achieve a comprehensive and accurate evaluation of energy storage power stations participating in the electricity spot market in a short period of time.

[0106] The quality and efficiency evaluation method of energy storage power stations participating in the electricity spot market of the present application can be summarized as follows: obtain the historical data of energy storage power stations and the location and capacity information of all power stations in the corresponding distribution network, and then adjust the load of the power station itself and the site selection and sizing strategy of the power station in the distribution network respectively; design an intelligent body based on the deep reinforcement learning algorithm according to the historical data: the energy storage system controller; on this basis, use the LSTM neural network and DQN deep reinforcement learning principles to construct an energy storage control optimization model, and use this model to achieve optimal control of the energy storage power station; at the same time, determine the accessible position and capacity constraints of the energy storage power station in the entire distribution network, and solve a site selection and sizing result based on the Newton-Raphson distribution network flow calculation method; then, use the result as the initial solution, use a multi-objective genetic algorithm to perform iterative calculations, and continuously optimize the results; finally determine the best control plan and site selection and sizing strategy for the energy storage power station to participate in the distribution network, optimize voltage stability, grid line losses, power capacity load and other aspects as much as possible, and improve the quality and efficiency of energy storage power stations participating in distribution network transactions.

[0107] The quality and efficiency evaluation method of the energy storage power station participating in the electricity spot market in the above embodiment has the following advantages:

[0108] (1) The deep reinforcement learning algorithm is used to analyze the historical data of the energy storage power station and plan the future control strategy of the energy storage power station to reduce the load peak in the distribution network and achieve the source-load configuration relationship matching of the distribution network with a high proportion of distributed power sources. At the same time, the situation of negative net load is reduced, the power flow reversal problem is alleviated, and the power flow distribution of the distribution network nodes with a high proportion of distributed power sources is stabilized, providing a more flexible and adaptive decision-making plan for the operation of the energy storage power station.

[0109] (2) Based on the Newton-Raphson distribution network power flow calculation method and deep reinforcement learning algorithm, the optimal strategy is provided for the site selection and sizing of energy storage power stations in the distribution network, and the optimal access location and access capacity of distributed power sources are effectively selected, so that the voltage amplitude of the node network after access does not fluctuate too much, while further reducing the overall line loss and improving the efficiency of energy storage power stations in the distribution network.

[0110] (3) The study covers the evaluation of energy storage power stations participating in the electricity spot market from three aspects: market member benefits, market operation effects, and grid regulation effects. It can achieve a comprehensive and accurate evaluation of the participation of energy storage power stations in the electricity spot market in a short period of time.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a quality and efficiency evaluation device for energy storage power stations participating in the electricity spot market, which is used to implement the quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the quality and efficiency evaluation device for energy storage power stations participating in the electricity spot market provided below can be referred to the limitations of the quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market above, and will not be repeated here.

[0112] In an exemplary embodiment, Figure 8 As shown, a quality and efficiency evaluation device for an energy storage power station participating in a power spot market is provided, comprising:

[0113] The data acquisition module 301 is used to obtain the operating data and site selection and capacity determination information of the distribution network in which the energy storage power station participates at the current moment.

[0114] The parameter determination module 302 is used to determine the state space and reward function at the current moment according to the operating data at the current moment; the state space includes: the power generation power of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current moment; the reward function is determined according to the power generation power of the energy storage power station, the load of the distribution network and the stored energy of the energy storage power station at the current moment.

[0115] The energy storage control strategy optimization module 303 is used to input the state space and reward function at the current moment into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; the energy storage optimization control model is constructed based on a deep reinforcement learning network and a neural network; the deep reinforcement learning network is used to output an action space based on the state space and the reward function; the action space includes: insufficient power generation action and excess power generation action; the neural network is used to obtain an action value function based on the action space output by the deep reinforcement learning network; the optimal energy storage control strategy is the energy storage control strategy corresponding to the maximum action value function; the energy storage control strategy includes: the power generation power of the energy storage power station and the load of the distribution network.

[0116] The site selection and sizing optimization module 304 is used to determine the optimal site selection and sizing solution at the current moment by using the Newton-Raphson distribution network power flow calculation method and the multi-objective genetic algorithm to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation according to the site selection and sizing information at the current moment.

[0117] The simulation scenario quality and efficiency indicator determination module 305 is used to determine the quality and efficiency indicators of the simulation scenario in which the energy storage power station participates in the electricity spot market, using the optimal energy storage control strategy and the optimal site selection and sizing plan to operate, and determine the quality and efficiency indicators of the simulation scenario; the quality and efficiency indicators include: market member benefits, market operation effects and grid regulation effects.

[0118] The actual scenario quality and efficiency indicator determination module 306 is used to determine the quality and efficiency indicators of the actual scenario for the actual scenario in which the energy storage power station participates in the electricity spot market.

[0119] The quality and efficiency evaluation module 307 is used to compare the quality and efficiency indicators of the actual scenario with the quality and efficiency indicators of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario of the energy storage power station participating in the electricity spot market.

[0120] This embodiment uses neural networks, deep reinforcement learning algorithms, multi-objective genetic algorithms, and distribution network flow calculation methods to develop energy storage optimization and regulation for energy storage power stations, determine the optimal energy storage regulation strategy and the optimal location and capacity solution, and on the basis of determining the optimal energy storage regulation strategy and the optimal location and capacity solution, develop a technology for evaluating the quality and efficiency of energy storage power stations participating in the electricity spot market, covering aspects such as market member benefits, market operation effects, and grid regulation effects. This technology solves the problem that existing technologies cannot conduct multi-dimensional quality and efficiency evaluation of the operating conditions of energy storage power stations based on the best optimization strategy. It aims to achieve a comprehensive and accurate evaluation of energy storage power stations participating in the electricity spot market by building a comprehensive evaluation model, and provide decision support for power market managers, energy storage investors, and grid operators.

[0121] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the operating data and site selection and capacity information of the distribution network in which the energy storage power station participates at the current moment. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market is implemented.

[0122] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0124] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0125] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0126] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0127] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, etc., but is not limited thereto.

[0128] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market, characterized in that: The quality and efficiency evaluation method of the energy storage power station participating in the electricity spot market includes: Obtain the current operating data and site selection and capacity information of the distribution network in which the energy storage power station participates; Determine the state space and reward function at the current moment according to the operating data at the current moment; the state space includes: the power generation of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current moment; the reward function is determined according to the power generation of the energy storage power station, the load of the distribution network and the stored energy of the energy storage power station at the current moment; The state space and reward function at the current moment are input into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; the energy storage optimization control model is constructed based on a deep reinforcement learning network and a neural network; the deep reinforcement learning network is used to output an action space based on the state space and the reward function; the action space includes: insufficient power generation action and excess power generation action; the neural network is used to obtain an action value function based on the action space output by the deep reinforcement learning network; the optimal energy storage control strategy is the energy storage control strategy corresponding to the maximum action value function; the energy storage control strategy includes: the power generation power of the energy storage power station and the load of the distribution network; According to the current site selection and capacity determination information, the Newton-Raphson distribution network power flow calculation method and multi-objective genetic algorithm are used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and capacity determination plan at the current moment; For the simulation scenario of energy storage power stations participating in the electricity spot market, the optimal energy storage control strategy and the optimal location and capacity determination scheme are used to operate and determine the quality and efficiency indicators of the simulation scenario; the quality and efficiency indicators include: market member benefits, market operation effects and grid regulation effects; For the actual scenario of energy storage power stations participating in the electricity spot market, determine the quality and efficiency indicators of the actual scenario; The quality and efficiency indicators of the actual scenario are compared with those of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario in which the energy storage power station participates in the electricity spot market.

2. The quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market according to claim 1 is characterized in that: According to the current site selection and capacity determination information, the Newton-Raphson distribution network power flow calculation method and multi-objective genetic algorithm are used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and capacity determination plan at the current moment, including: According to the current site selection and capacity determination information, the Newton-Raphson distribution network power flow calculation method is used to determine the initial site selection and capacity determination plan at the current moment; Based on the initial site selection and sizing scheme at the current moment, a multi-objective genetic algorithm is used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and sizing scheme at the current moment.

3. The quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market according to claim 2 is characterized in that: Based on the initial site selection and capacity determination plan at the current moment, a multi-objective genetic algorithm is used to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation to determine the optimal site selection and capacity determination plan at the current moment, including: Determine the population under the current iteration number; each individual in the population represents a site selection and capacity determination plan; the population under the initial iteration number includes the initial site selection and capacity determination plan; Calculate the fitness value of each individual in the population at the current iteration number; the fitness value is calculated based on line loss and voltage fluctuation; Screening individuals in the population at the current number of iterations according to the fitness value and the set selection mechanism to obtain a screened population at the current number of iterations; Perform crossover and mutation operations on the population screened at the current number of iterations to obtain a new population at the current number of iterations; Determine whether the current number of iterations has reached the maximum number of iterations; If so, the new population at the current number of iterations is determined as the optimal location and capacity solution at the current moment; If not, the new population at the current iteration number is determined as the population at the next iteration number, and the next iteration is performed.

4. The quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market according to claim 1 is characterized in that: The calculation formula of the line loss is: Among them, DeltaV represents line loss; P represents the active power transmitted by the line; Q represents the reactive power transmitted by the line; R represents the resistance of the line; X represents the reactance of the line; V N Indicates the rated voltage of the line; The calculation formula of the voltage fluctuation is: VSj= | Vj4-4(Pjτb+Qjxb)Vj2+4(Pjτb+Qjxb); Among them, VS j represents the voltage fluctuation at node j; V j represents the voltage of node j; P j represents the active power of node j; Q j represents the reactive power of node j; τ b represents the resistance of the branch before node j; x b Represents the reactance value of the branch before node j.

5. The quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market according to claim 1 is characterized in that: The expression of the state space is: s t =[P t ,L t ,BSC t ,t]; Among them, s t represents the state space at the current time t; P t represents the power generation of the energy storage power station at the current time t; L t Indicates the distribution network load at the current time t; BSC t Indicates that the energy storage power station is in full load state at the current time t; The expression of the reward function is: Among them, R t represents the reward function at the current time t; B t Represents the stored energy of the energy storage power station at the current time t.

6. The quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market according to claim 1 is characterized in that: The deep reinforcement learning network adopts a deep Q learning network; the deep Q learning network is implemented based on a Markov decision process.

7. The quality and efficiency evaluation method of energy storage power stations participating in the electricity spot market according to claim 1 is characterized in that: The neural network adopts a long short-term memory network.

8. A quality and efficiency evaluation device for energy storage power stations participating in the electricity spot market, characterized in that: The quality and efficiency evaluation device for the energy storage power station participating in the electricity spot market includes: The data acquisition module is used to obtain the current operating data and site selection and capacity information of the distribution network in which the energy storage power station participates; A parameter determination module is used to determine the state space and reward function at the current moment according to the operating data at the current moment; the state space includes: the power generation of the energy storage power station, the load of the distribution network, the full load state of the energy storage power station and the current moment; the reward function is determined according to the power generation of the energy storage power station, the load of the distribution network and the stored energy of the energy storage power station at the current moment; The energy storage control strategy optimization module is used to input the current state space and reward function into the energy storage optimization control model to obtain the optimal energy storage control strategy at the current moment; the energy storage optimization control model is constructed based on a deep reinforcement learning network and a neural network; the deep reinforcement learning network is used to output an action space based on the state space and the reward function; the action space includes: insufficient power generation action and excess power generation action; the neural network is used to obtain an action value function based on the action space output by the deep reinforcement learning network; the optimal energy storage control strategy is the energy storage control strategy corresponding to the maximum action value function; the energy storage control strategy includes: energy storage power station power generation and distribution network load; The site selection and sizing optimization module is used to determine the optimal site selection and sizing scheme at the current moment based on the site selection and sizing information, using the Newton-Raphson distribution network power flow calculation method and the multi-objective genetic algorithm to perform multiple iterations with the goal of minimizing line loss and voltage fluctuation; A simulation scenario quality and efficiency index determination module is used to determine the quality and efficiency indicators of the simulation scenario in which the energy storage power station participates in the electricity spot market, using the optimal energy storage control strategy and the optimal location and capacity determination plan to operate, and determine the quality and efficiency indicators of the simulation scenario; the quality and efficiency indicators include: market member benefits, market operation effects, and grid regulation effects; The actual scenario quality and efficiency indicator determination module is used to determine the actual scenario quality and efficiency indicators for the actual scenario of energy storage power stations participating in the electricity spot market; The quality and efficiency evaluation module is used to compare the quality and efficiency indicators of the actual scenario with those of the simulated scenario to determine the quality and efficiency evaluation results of the actual scenario in which the energy storage power station participates in the electricity spot market.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the quality and efficiency evaluation method for energy storage power stations participating in the electricity spot market as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the quality and efficiency evaluation method of the energy storage power station participating in the electricity spot market described in any one of claims 1-7 is implemented.

Images