Electrochemical energy storage power station operation control method suitable for spot transaction

Abstract

The invention discloses an electrochemical energy storage power station operation control method suitable for spot transaction. The method comprises the following steps: collecting and processing original data; decomposing the data by using ensemble empirical mode decomposition, and training the decomposed signal by using a grey wolf-LSMT network; the prediction is corrected; establishing a power balance formula of the power grid based on the generative adversarial network; establishing a total objective function model, outputting a prediction scene of a total objective function by using a generator, generating a scene and performing scene reduction; and establishing constraint conditions. The LSMT and the grey wolf algorithm are used for real-time prediction, the objective function of the long-period income and the power grid stability index of the electrochemical energy storage power station is established through the generative adversarial network, the optimal control method of the electrochemical energy storage power station is found, the charging and discharging stability of the electrochemical energy storage power station is improved, the operation efficiency of a power plant power unit is optimized, and the power grid stability is improved. The economic benefit maximization is realized, the real-time dynamic balance between the supply and demand of the electrochemical energy storage power station and the power grid is realized, and the consumption rate of new energy is improved.

Description

Technical Field

[0001] The present invention relates to the field of energy storage technology, and in particular to an operation control method of an electrochemical energy storage power station suitable for spot trading. Background Art

[0002] Existing electrochemical energy storage technologies, such as lithium-ion battery energy storage systems, have shown great potential in participating in grid spot trading, being used for peak shaving and valley filling, and absorbing new energy. Using electrochemical energy storage to store new energy and power generation during valley hours, and discharging it into the grid during peak hours to reduce the load of power plants, can enable the units of power plants to balance the power of the time periods as much as possible and improve the absorption of new energy. However, the power characteristics of electrochemical energy storage have significant time-dependent degradation problems, that is, as the number of charge and discharge cycles increases, its energy storage capacity and discharge performance gradually decrease. In addition, at the stage when the energy storage is about to be discharged to the exhaustion of energy, the electrochemical energy storage device often cannot provide a stable discharge current, which directly affects the ability of distributed electrochemical energy storage to provide stable power reserves for the power grid system. Therefore, it is difficult for the grid to accurately regulate the amount of power provided to the power plant to the optimal production and operation power of the power plant, resulting in a decrease in the quality of power supply to the grid, and at the same time, the operating efficiency of the power units of the power plant has not been optimized.

[0003] On the other hand, there is a contradiction between the maximization of the economic benefits of electrochemical energy storage and the highest stability and quality of the power grid. In order to meet this challenge, it is necessary to develop a system and method that can accurately control electrochemical energy storage based on the real-time power characteristics of electrochemical energy storage and real-time data on the supply and demand sides of the power grid. The system and method should be able to form an effective point control strategy and control algorithm to ensure that while meeting the power demand, the power supply quality of the power grid is improved and the power units of the power plant can operate in the best working state. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an electrochemical energy storage power station operation control method suitable for spot trading, so as to realize the charging and discharging regulation of the electrochemical energy storage power station in the power grid within a single cycle according to the real-time prediction of wind and solar power output and power load, so as to make the long-term benefits of the electrochemical energy storage power station and the power supply stability of the power grid and the operating status of the power plant in the best balance state.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: An electrochemical energy storage power station operation control method suitable for spot trading includes the following steps: S1. Collection and processing of raw data; raw data include historical wind and solar power generation, historical power load, peak and valley power metering periods, number and characteristic parameters of generator sets, and number and capacity of electrochemical energy storage groups; S2, based on the historical power load data and historical wind and solar power generation in S1, use ensemble empirical mode decomposition to decompose the data, and use the Grey Wolf-LSMT network to train the decomposed signal; S3: Use the model trained in S2 to predict and correct the current power load to obtain the power load prediction value of each component. Wind and photovoltaic power generation , the predicted values ​​of each component signal are superimposed to obtain the real-time power load prediction value Wind and photovoltaic power generation and make corrections; S4, based on the generative adversarial network, the power balance formula of the power grid is established by combining the power load forecast value in S3, the wind photovoltaic power generation power forecast value in S4, and the charging and discharging state of the electrochemical energy storage; S5. Based on the balance formula, the single-cycle economic benefit objective function formula of electrochemical energy storage and the grid quality evaluation formula are established to obtain the long-cycle net benefit objective function , for the long-term net profit objective function The total objective function model is obtained by setting weights respectively with the grid stability evaluation formula, and the prediction scenario of the total objective function is output by the generator to generate scenarios and reduce them; S6. Establish constraints for wind and solar power generation and electrochemical energy storage control, and output optimal electrochemical energy storage power station operation control decisions.

[0006] A method for the operation and control of an electrochemical energy storage power station suitable for spot trading is proposed. The method includes the collection and processing of raw data, data prediction based on ensemble empirical mode decomposition (EEMD) and gray wolf-LSTM network, prediction and correction of power load and wind and photovoltaic power generation, establishment of power grid power balance formula based on generative adversarial network (GAN), construction of economic benefit and power grid quality evaluation formula, establishment of total objective function model and output of optimal control decision. This method realizes the precise control of electrochemical energy storage power station by combining deep learning algorithm and optimization algorithm, aiming to balance the supply and demand of power grid, improve the power supply quality and the operation efficiency of power plant. The prediction accuracy of power load and wind and photovoltaic power generation is improved by decomposing and training data through EEMD and gray wolf-LSTM network. The power grid power balance formula based on GAN can adjust the charging and discharging strategy of electrochemical energy storage power station in real time to ensure the balance of power grid supply and demand. By constructing the economic benefit objective function and power grid quality evaluation formula and setting up the total objective function model, the dual optimization of economic benefit and power grid quality is achieved.

[0007] In the above S1, the original data is collected by collecting data at intervals, and the processing is carried out by eliminating obvious outliers and filling in missing values.

[0008] The specific steps in the above S2 are: S2.1. Processed power load data Add a standard normal distribution of white noise , historical wind and solar power generation Add a standard normal distribution of white noise , the specific formula is as follows: ; ; In the above formula Indicates The white noise sequence added is Indicates The white noise sequence added is Indicates The additional noise signal of the experiment, Indicates Additional noise signal for the experiment; S2.2. New signal sequences Perform empirical mode decomposition EMD and get modal components and 1 residual component: ; in, and for The first transient components and residual components, Represents the average trend of the power load signal; For new signal sequences Perform empirical mode decomposition EMD and get modal components and 1 residual component: ; in, and for The first transient components and residual components, Represents the average trend of wind and solar power generation power signal; Step2.3, repeat Step2.1 and Step2.2 N times, and get The collection is: ; ; Step2.4, the corresponding Performing ensemble average operation, the final component of the ensemble empirical mode decomposition EEMD is obtained as: ; ; In the above formula The first indivual Quantity; The first indivual Quantity; Step 2.5, build an LSTM network to train each component signal; Step 2.6, in the LSTM network, For the The data input of the component signal at the moment, is the cell state at the previous moment, where the initial state is set to 0. is the LSTM cell output at the previous moment. These three quantities are all passed into the cell. The specific calculation formula is as follows: ; ; ; ; ; ; ; In the above formula, , , Represent the forget gate, input gate and output gate respectively; and tanh function are activation functions; W and b are related coefficient matrices and biases; Step 2.7, introduce the GWO algorithm to optimize the parameters of LSTM. The GWO algorithm automatically optimizes the network parameters by simulating the ecological phenomenon of wolf pack hunting. There are 4 levels of wolves in the wolf pack, namely Alpha, Beta, Delta and Omega. Alpha is the only leader in the wolf pack. The hunting of the wolf pack is divided into three stages: Step 2.7.1, surround; Under the leadership of the Alpha wolf, the wolf pack first surrounds the prey. The mathematical model is as follows: ; ; In the above formula, the following table irepresents the number of iterations, ; D is the distance between the gray wolf and the prey; The number of iterations is i The prey position vector at time ; The number of iterations is i The position vector of the gray wolf at time ; The number of iterations is i Gray wolf position vector at +1; A and C is the coefficient vector, A and C The expression is: ; ; In the above formula and is a random vector whose elements are in the range of [0, 1]; a is a control parameter, which decreases linearly from 2 to 0 as the number of iterations increases; Step 2.7.2, Hunting; After the wolf pack surrounds the prey, the Alpha, Beta, and Delta wolves are closest to the prey. The wolf pack will approach the prey under the leadership of the Alpha, Beta, and Delta wolves. The position of the Omega wolf is updated as follows: ; ; ; ; ; ; ; In the above formula , , They are the distances between the current Omega wolf and the Alpha wolf, Beta wolf, and Delta wolf respectively; , , They are the position vectors of Alpha wolf, Beta wolf and Delta wolf respectively; Step 2.7.3, attack; the goal of this stage is to capture the prey, that is, to obtain the optimal solution of the LSTM network parameters; the GWO algorithm simulates the process of approaching the prey by reducing the value of a; when a gradually decreases, the element value of A is also in the interval [-a, a]. When , the wolf pack can attack the prey, that is, the LSTM network parameters find the optimal solution; Step 2.8, use the WGO algorithm to optimize the parameters of the LSTM network, including the number of hidden layer nodes, learning rate and number of iterations.

[0009] The data prediction process based on ensemble empirical mode decomposition (EEMD) and gray wolf-LSTM network includes adding white noise, performing empirical mode decomposition (EMD), ensemble averaging, building an LSTM network for training, and introducing the gray wolf optimization (GWO) algorithm to optimize the parameters of LSTM. It can more accurately capture the nonlinear characteristics of the data, improve the prediction accuracy, automatically optimize the parameters of the LSTM network, and improve the generalization ability of the model.

[0010] The real-time power load forecast value in S3 above Wind and photovoltaic power generation for: ; .

[0011] The power balance formula of the power grid in S4 above is: + - =0 in, , is the total number of generating units, To put the fixed power part of the generator set into operation, To put the frequency regulation power part of the generator set into operation, is the number of generating units put into operation, , is the interconnection line power, is the real-time power of electrochemical energy storage, When is the discharge state, It is in charging state.

[0012] A power grid power balance formula based on generative adversarial network (GAN) is proposed. This formula combines the power load forecast value, wind and solar power generation forecast value, and the charging and discharging status of electrochemical energy storage to achieve power balance of the power grid. This power balance formula is used as the condition for subsequent adversarial network generation.

[0013] The single-cycle economic benefit objective function of electrochemical energy storage in S5 above is:

[0014] Where T is the measurement period, , is the real-time power during discharge, When the electrochemical energy storage is not in the discharge state, the value is 0. The off-grid electricity price during discharge, calculated based on the coal-fired power price; , The peak electricity price is , The electricity price is flat. , The electricity price is in the off-peak period. , and They are the real-time charging power during peak, flat and valley periods, respectively. When not in charging state during peak, flat and valley periods, the three values ​​are 0; is the capacity compensation income, For transmission and distribution costs, Other costs include equipment maintenance costs, operation and maintenance costs, and capacity electricity charges; As the use cycle of electrochemical energy storage increases, the internal resistance of the battery pack increases, and the charging and discharging time increases, which reduces the economic benefits of a single cycle, thus affecting the investment returns of electrochemical energy storage. From the perspective of maximizing the economic benefits of electrochemical investment, the goal is to maximize the unit capacity income in the long term. The long-term income objective function is for: ; in For the benefits of electrochemical energy storage during its life cycle, is the number of metering cycles of the electrochemical energy storage life cycle, Q is the electrochemical energy storage capacity; Long-term net profit objective function for: ; in is the investment cost, C is the investment cost of energy storage per unit capacity; is the electrochemical battery degradation efficiency loss, To decay the efficiency loss coefficient of the battery life cycle; From the perspective of grid stability and long-term benefits of power plants, the single-cycle startup time of each generator set is The average number of generator sets V is a long-term guarantee for high power supply quality. The average number of generator sets V is:

[0015] in, is the average number of generator sets started in a single cycle, The real-time startup number; Single cycle start time of each generator set and the average generator unit rate V and the long-term net profit objective function To ensure the mutual restraint relationship, weights are set for both and the total objective function R is obtained: ; in, and is the long-term net profit objective function and the weight of the average number of generator sets rate V. When the value of the objective function R is the set value, the long-term net profit objective function The relationship between the average number of generator sets rate V and the increase and decrease of the two is one.

[0016] The construction process of the single-cycle economic benefit objective function, long-cycle net income objective function and grid quality evaluation formula of electrochemical energy storage is described in detail, and a total objective function model is established to balance economic benefits and grid quality. By constructing the economic benefit objective function and grid quality evaluation formula, and establishing the total objective function model, the dual optimization of economic benefits and grid quality is achieved. The total objective function model provides a clear optimization target for the operation control of the electrochemical energy storage power station, which helps to improve decision-making efficiency.

[0017] In the above S5, the generator is used to output the prediction scenario of the total objective function, and the scenario is generated and reduced as follows: The original data is used as training samples to train the generator and discriminator of the generative adversarial network; historical data consistent with the current day's scenario is extracted, and multiple prediction scenarios are output using the trained generator, and the prediction scenarios are corrected using the trained discriminator: The generated prediction scenarios are divided into groups according to similarity, and one scenario in each group is selected as the typical scenario. The sum of the reduced scenario probabilities is 1. K scenarios are randomly selected from the generated scenarios as the initial clustering centers. According to the principle of the closest distance to the clustering center, the objects are assigned to each category. According to the minimum distance principle, a new clustering center is found to replace the original clustering center.

[0018] The constraints in S6 above include: Average generator unit rate constraint: ; and are the minimum and maximum values ​​for normal operation of the power plant, respectively; Long-term net profit objective function constraints: ; and They are the minimum long-period net benefit and the maximum long-period net benefit of the electrochemical energy storage power station respectively; Capacity constraints of electrochemical energy storage stations: ; in, is the mean value of the power load, k is the ratio of the capacity of the electrochemical energy storage station to the mean value of the power load, and are the minimum and maximum values ​​of the ratio; Charge and discharge about: ; in, is the ratio of discharge power to charge power in a single cycle, For single cycle The minimum value of .

[0019] The present invention provides an electrochemical energy storage power station operation control method suitable for spot trading. Through historical power grid data, LSMT and Gray Wolf Algorithm are used to make real-time predictions on wind and solar output and power load during daytime trading, and an objective function of long-term revenue and power grid stability index of the electrochemical energy storage power station is established through a generative adversarial network. The optimal control method of the electrochemical energy storage power station is found through power balance constraints and power grid constraints. The method ensures the improvement of charging and discharging stability of the electrochemical energy storage power station, ensures the power supply quality of the power grid, optimizes the operating efficiency of the power plant power unit, realizes the maximization of economic benefits, realizes the real-time dynamic balance between the supply and demand of the electrochemical energy storage power station and the power grid, and improves the absorption rate of new energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings and embodiments.

[0022] like Figure 1 As shown, the operation control method of the electrochemical energy storage power station applicable to spot trading includes the following steps: S1. Collection and processing of raw data; raw data include historical wind and solar power generation, historical power load, peak and valley power metering periods, number and characteristic parameters of generator sets, and number and capacity of electrochemical energy storage groups; S2, based on the historical power load data and historical wind and solar power generation in S1, use ensemble empirical mode decomposition to decompose the data, and use the Grey Wolf-LSMT network to train the decomposed signal; S3: Use the model trained in S2 to predict and correct the current power load to obtain the power load prediction value of each component. Wind and photovoltaic power generation , the predicted values ​​of each component signal are superimposed to obtain the real-time power load prediction value Wind and photovoltaic power generation and make corrections; S4, based on the generative adversarial network, the power balance formula of the power grid is established by combining the power load forecast value in S3, the wind photovoltaic power generation power forecast value in S4, and the charging and discharging state of the electrochemical energy storage; S5. Based on the balance formula, the single-cycle economic benefit objective function formula of electrochemical energy storage and the grid quality evaluation formula are established to obtain the long-cycle net benefit objective function , for the long-term net profit objective function The total objective function model is obtained by setting weights respectively with the grid stability evaluation formula, and the prediction scenarios of the total objective function are output by the generator to generate scenarios and reduce them; S6. Establish constraints for wind and solar power and electrochemical energy storage control, and output optimal electrochemical energy storage power station operation control decisions.

[0023] In the above S1, the original data is collected by collecting data at intervals, and the processing is carried out by eliminating obvious outliers and filling in missing values.

[0024] The specific steps in the above S2 are: S2.1. Processed power load data Add a standard normal distribution of white noise , historical wind and solar power generation Add a standard normal distribution of white noise , the specific formula is as follows: ; ; In the above formula Indicates The white noise sequence added is Indicates The white noise sequence added is Indicates The additional noise signal of the experiment, Indicates Additional noise signal for the experiment; S2.2. New signal sequences Perform empirical mode decomposition EMD and get modal components and 1 residual component: ; in, and for The first transient components and residual components, Represents the average trend of the power load signal; For new signal sequences Perform empirical mode decomposition EMD and get modal components and 1 residual component: ; in, and for The first transient components and residual components, Represents the average trend of wind and solar power generation power signal; Step2.3, repeat Step2.1 and Step2.2 N times, and get The collection is: ; ; Step2.4, the corresponding Performing ensemble average operation, the final component of the ensemble empirical mode decomposition EEMD is obtained as: ; ; In the above formula The first indivual Quantity; The first indivual Quantity; Step 2.5, build an LSTM network to train each component signal; Step 2.6, in the LSTM network, For the The data input of the component signal at the moment, is the cell state at the previous moment, where the initial state is set to 0. is the LSTM cell output at the previous moment. These three quantities are all passed into the cell. The specific calculation formula is as follows: ; ; ; ; ; ; ; In the above formula, , , Represent the forget gate, input gate and output gate respectively; and tanh function are activation functions; W and b are related coefficient matrices and biases; Step 2.7, introduce the GWO algorithm to optimize the parameters of LSTM. The GWO algorithm automatically optimizes the network parameters by simulating the ecological phenomenon of wolf pack hunting. There are 4 levels of wolves in the wolf pack, namely Alpha, Beta, Delta and Omega. Alpha is the only leader in the wolf pack. The hunting of the wolf pack is divided into three stages: Step 2.7.1, surround; Under the leadership of the Alpha wolf, the wolf pack first surrounds the prey. The mathematical model is as follows: ; ; In the above formula, the following table i represents the number of iterations, ; D is the distance between the gray wolf and the prey; The number of iterations is i The prey position vector at time ; The number of iterations is i The position vector of the gray wolf at time ; The number of iterations is i The gray wolf position vector at +1; A and C is the coefficient vector, A and C The expression is: ; ; In the above formula and is a random vector whose elements are in the range of [0, 1]; a is a control parameter, which decreases linearly from 2 to 0 as the number of iterations increases; Step 2.7.2, Hunting; After the wolf pack surrounds the prey, the Alpha, Beta, and Delta wolves are closest to the prey. The wolf pack will approach the prey under the leadership of the Alpha, Beta, and Delta wolves. The position of the Omega wolf is updated as follows: ; ; ; ; ; ; ; In the above formula , , They are the distances between the current Omega wolf and the Alpha wolf, Beta wolf, and Delta wolf respectively; , , They are the position vectors of Alpha wolf, Beta wolf and Delta wolf respectively; Step 2.7.3, attack; the goal of this stage is to capture the prey, that is, to obtain the optimal solution of the LSTM network parameters; the GWO algorithm simulates the process of approaching the prey by reducing the value of a; when a gradually decreases, the element value of A is also in the interval [-a, a]. When , the wolf pack can attack the prey, that is, the LSTM network parameters find the optimal solution; Step 2.8, use the WGO algorithm to optimize the parameters of the LSTM network, including the number of hidden layer nodes, learning rate and number of iterations.

[0025] The real-time power load forecast value in S3 above Wind and photovoltaic power generation for: ; .

[0026] The power balance formula of the power grid in S4 above is: + - =0 in, , is the total number of generating units, To put the fixed power part of the generator set into operation, To put the frequency regulation power part of the generator set into operation, is the number of generating units put into operation, , is the interconnection line power, is the real-time power of electrochemical energy storage, When is the discharge state, It is in charging state.

[0027] The single-cycle economic benefit objective function of electrochemical energy storage in S5 above is:

[0028] Where T is the measurement period, , is the real-time power during discharge, When the electrochemical energy storage is not in the discharge state, the value is 0. The off-grid electricity price during discharge, calculated based on the coal-fired power price; , The peak electricity price is , The electricity price is flat. , The electricity price is in the off-peak period. , and They are the real-time charging power during peak, flat and valley periods, respectively. When not in charging state during peak, flat and valley periods, the three values ​​are 0; is the capacity compensation income, For transmission and distribution costs, Other costs include equipment maintenance costs, operation and maintenance costs, and capacity electricity charges; As the use cycle of electrochemical energy storage increases, the internal resistance of the battery pack increases, and the charging and discharging time increases, which reduces the economic benefits of a single cycle, thus affecting the investment returns of electrochemical energy storage. From the perspective of maximizing the economic benefits of electrochemical investment, the goal is to maximize the unit capacity income in the long term. The long-term income objective function is for: ; in For the benefits of electrochemical energy storage during its life cycle, is the number of metering cycles of the electrochemical energy storage life cycle, Q is the electrochemical energy storage capacity; Long-term net profit objective function for: ; in is the investment cost, C is the investment cost of energy storage per unit capacity; is the electrochemical battery degradation efficiency loss, To decay the efficiency loss coefficient of the battery life cycle; From the perspective of grid stability and long-term benefits of power plants, the single-cycle startup time of each generator set is The average number of generator sets V is a long-term guarantee for high power supply quality. The average number of generator sets V is:

[0029] in, is the average number of generator sets started in a single cycle, The real-time startup number; Single cycle start time of each generator set and the average generator unit rate V and the long-term net profit objective function To ensure the mutual restraint relationship, weights are set for both and the total objective function R is obtained: ; in, and is the long-term net profit objective function and the weight of the average number of generator sets rate V. When the value of the objective function R is the set value, the long-term net profit objective function The relationship between the average number of generator sets rate V and the increase and decrease of the two is one.

[0030] In the above S5, the generator is used to output the prediction scenario of the total objective function, and the scenario is generated and reduced as follows: The original data is used as training samples to train the generator and discriminator of the generative adversarial network; historical data consistent with the current day's scenario is extracted, and multiple prediction scenarios are output using the trained generator, and the prediction scenarios are corrected using the trained discriminator: The generated prediction scenarios are divided into groups according to similarity, and one scenario in each group is selected as the typical scenario. The sum of the reduced scenario probabilities is 1. K scenarios are randomly selected from the generated scenarios as the initial clustering centers. According to the principle of the closest distance to the clustering center, the objects are assigned to each category. According to the minimum distance principle, a new clustering center is found to replace the original clustering center.

[0031] The constraints in S6 above include: Average generator unit rate constraint: ; and are the minimum and maximum values ​​for normal operation of the power plant, respectively; Long-term net profit objective function constraints: ; and They are the minimum long-term net income and maximum long-term net income of the electrochemical energy storage power station. When it is lower than the minimum long-term net income, the electrochemical energy storage power station cannot obtain continuous investment. When it is higher than the maximum long-term net income, it will cause disorderly growth of the power station. Capacity constraints of electrochemical energy storage stations: ; in, is the mean value of the power load, k is the ratio of the capacity of the electrochemical energy storage station to the mean value of the power load, and are the minimum and maximum values ​​of the ratio; Charge and discharge about: ; in, is the ratio of discharge power to charge power in a single cycle, For single cycle The minimum value of .

Claims

1. An electrochemical energy storage power station operation control method suitable for spot trading, characterized in that: The following steps are involved: S1. Collection and processing of raw data; raw data include historical wind and solar power generation, historical power load, peak and valley power metering periods, number and characteristic parameters of generator sets, and number and capacity of electrochemical energy storage groups; S2, based on the historical power load data and historical wind and solar power generation in S1, use ensemble empirical mode decomposition to decompose the data, and use the Grey Wolf-LSMT network to train the decomposed signal; S3: Use the model trained in S2 to predict and correct the current power load to obtain the power load prediction value of each component. Wind and photovoltaic power generation , the predicted values ​​of each component signal are superimposed to obtain the real-time power load prediction value Wind and photovoltaic power generation and make corrections; S4, based on the generative adversarial network, the power balance formula of the power grid is established by combining the power load forecast value in S3, the wind photovoltaic power generation power forecast value in S4, and the charging and discharging state of the electrochemical energy storage; S5. Based on the balance formula, the single-cycle economic benefit objective function formula of electrochemical energy storage and the grid quality evaluation formula are established to obtain the long-cycle net benefit objective function , for the long-term net profit objective function The total objective function model is obtained by setting weights respectively with the grid stability evaluation formula, and the prediction scenario of the total objective function is output by the generator to generate scenarios and reduce them; S6. Establish constraints for wind and solar power generation and electrochemical energy storage control, and output optimal electrochemical energy storage power station operation control decisions.

2. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 1 is characterized in that: In the above-mentioned S1, the original data is collected by collecting data at intervals, and the operations of eliminating obvious outliers and filling missing values ​​are adopted during processing.

3. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 2 is characterized in that: The specific steps in S2 are: S2.

1. Processed power load data Add a standard normal distribution of white noise , historical wind and solar power generation Add a standard normal distribution of white noise , the specific formula is as follows: ； ； In the above formula Indicates The white noise sequence added is Indicates The white noise sequence added is Indicates The additional noise signal of the experiment, Indicates Additional noise signal for the experiment; S2.

2. New signal sequences Perform empirical mode decomposition EMD and get modal components and 1 residual component: ; in, and for The first transient components and residual components, Represents the average trend of the power load signal; For new signal sequences Perform empirical mode decomposition EMD and get modal components and 1 residual component: ; in, and for The first transient components and residual components, Represents the average trend of wind and solar power generation power signal; Step2.3, repeat Step2.1 and Step2.2 N times, and get The collection is: ； ； Step2.4, the corresponding Performing ensemble average operation, the final component of the ensemble empirical mode decomposition EEMD is obtained as: ； ； In the above formula The first indivual Quantity; The first indivual Quantity; Step 2.5, build an LSTM network to train each component signal; Step 2.6, in the LSTM network, For the The data input of the component signal at the moment, is the cell state at the previous moment, where the initial state is set to 0. is the LSTM cell output at the previous moment. These three quantities are all passed into the cell. The specific calculation formula is as follows: ； ； ； ； ； ； ； In the above formula, , , Represent the forget gate, input gate and output gate respectively; and tanh function are activation functions; W and b are related coefficient matrices and biases; Step 2.7, introduce the GWO algorithm to optimize the parameters of LSTM. The GWO algorithm automatically optimizes the network parameters by simulating the ecological phenomenon of wolf pack hunting. There are four levels of wolves in the wolf pack, namely Alpha, Beta, Delta and Omega. Alpha is the only leader in the wolf pack. The hunting of the wolf pack is divided into three stages: Step 2.7.1, surround; Under the leadership of the Alpha wolf, the wolf pack first surrounds the prey. The mathematical model is as follows: ； ； In the above formula, the following table i represents the number of iterations, ; D is the distance between the gray wolf and the prey; The number of iterations is i The prey position vector at time ; The number of iterations is i The position vector of the gray wolf at time ; The number of iterations is i The gray wolf position vector at +1; A and C is the coefficient vector, A and C The expression is: ； ； In the above formula and is a random vector whose elements are in the range of [0, 1]; a is a control parameter, which decreases linearly from 2 to 0 as the number of iterations increases; Step 2.7.2, Hunting; After the wolf pack surrounds the prey, the Alpha, Beta, and Delta wolves are closest to the prey. The wolf pack will approach the prey under the leadership of the Alpha, Beta, and Delta wolves. The position of the Omega wolf is updated as follows: ； ； ； ； ； ； ； In the above formula , , They are the distances between the current Omega wolf and the Alpha wolf, Beta wolf, and Delta wolf respectively; , , They are the position vectors of Alpha wolf, Beta wolf and Delta wolf respectively; Step 2.7.3, attack; the goal of this stage is to capture the prey, that is, to obtain the optimal solution of the LSTM network parameters; the GWO algorithm simulates the process of approaching the prey by reducing the value of a; when a gradually decreases, the element value of A is also in the interval [-a, a]. When , the wolf pack can attack the prey, that is, the LSTM network parameters find the optimal solution; Step 2.8, use the WGO algorithm to optimize the parameters of the LSTM network, including the number of hidden layer nodes, learning rate and number of iterations.

4. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 3 is characterized in that: The real-time power load forecast value in S3 Wind and photovoltaic power generation for: ； 。 5. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 4 is characterized in that: The power balance formula of the power grid in S4 is: + - =0 in, , is the total number of generating units, To put the fixed power part of the generator set into operation, To put the frequency regulation power part of the generator set into operation, is the number of generating units put into operation, , is the interconnection line power, is the real-time power of electrochemical energy storage, When is the discharge state, It is in charging state.

6. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 5 is characterized in that: The single-cycle economic benefit objective function of electrochemical energy storage in S5 is: Where T is the measurement period, , is the real-time power during discharge, When the electrochemical energy storage is not in the discharge state, the value is 0. The off-grid electricity price during discharge, calculated based on the coal-fired power price; , The peak electricity price is , The electricity price is flat. , The electricity price is in the off-peak period. , and They are the real-time charging power during peak, flat and valley periods, respectively. When not in charging state during peak, flat and valley periods, the three values ​​are 0; is the capacity compensation income, For transmission and distribution costs, Other costs include equipment maintenance costs, operation and maintenance costs, and capacity electricity charges; As the use cycle of electrochemical energy storage increases, the internal resistance of the battery pack increases, and the charging and discharging time increases, which reduces the economic benefits of a single cycle, thus affecting the investment returns of electrochemical energy storage. From the perspective of maximizing the economic benefits of electrochemical investment, the goal is to maximize the unit capacity income in the long term. The long-term income objective function is for: ； in For the benefits of electrochemical energy storage during its life cycle, is the number of metering cycles of the electrochemical energy storage life cycle, Q is the electrochemical energy storage capacity; Long-term net profit objective function for: ； in is the investment cost, C is the investment cost of energy storage per unit capacity; is the electrochemical battery degradation efficiency loss, To decay the efficiency loss coefficient of the battery life cycle; From the perspective of grid stability and long-term benefits of power plants, the single-cycle startup time of each generator set is The average number of generator sets V is a long-term guarantee for high power supply quality. The average number of generator sets V is: in, is the average number of generator sets started in a single cycle, The real-time startup number; Single cycle start time of each generator set and the average generator unit rate V and the long-term net profit objective function To ensure the mutual restraint relationship, weights are set for both and the total objective function R is obtained: ； in, and is the long-term net profit objective function and the weight of the average number of generator sets rate V. When the value of the objective function R is the set value, the long-term net profit objective function The relationship between the average number of generator sets rate V and the increase and decrease of the two is one.

7. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 6 is characterized in that: In the above S5, the prediction scenario of the total objective function is outputted by the generator, and the scenario is generated and reduced as follows: The original data is used as training samples to train the generator and discriminator of the generative adversarial network; historical data consistent with the current day's scenario is extracted, and multiple prediction scenarios are output using the trained generator, and the prediction scenarios are corrected using the trained discriminator: The generated prediction scenarios are divided into groups according to similarity, and one scenario in each group is selected as the typical scenario. The sum of the reduced scenario probabilities is 1. K scenarios are randomly selected from the generated scenarios as the initial clustering centers. According to the principle of the closest distance to the clustering center, the objects are assigned to each category. According to the minimum distance principle, a new clustering center is found to replace the original clustering center.

8. The electrochemical energy storage power station operation control method suitable for spot trading according to claim 7 is characterized in that: The constraints in S6 include: Average generator unit rate constraint: ; and are the minimum and maximum values ​​for normal operation of the power plant, respectively; Long-term net profit objective function constraints: ； and They are the minimum long-period net benefit and the maximum long-period net benefit of the electrochemical energy storage power station respectively; Capacity constraints of electrochemical energy storage stations: ； in, is the mean value of the power load, k is the ratio of the capacity of the electrochemical energy storage station to the mean value of the power load, and are the minimum and maximum values ​​of the ratio; Charge and discharge about: ； in, is the ratio of discharge power to charge power in a single cycle, For single cycle The minimum value of .

Images