Market regulation electric quantity regulation and control method for matching energy storage with wind power station
Through the CNN-LSTM-ATT model based on attention mechanism, the electricity price prediction and conditional risk threshold calculation are adjusted, and the power declaration of wind storage power stations is solved, and the problem of failure to effectively utilize electricity price changes in the existing technology is realized. Maximize economic benefits in the power market.
Patent Information
- Application Number
- CN202410997244.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-26
AI Technical Summary
The existing wind storage power stations have failed to effectively combine electricity price changes in the power market regulation, which has affected their economic benefits, and have failed to make full use of energy storage facilities to regulate wind power generation.
The CNN-LSTM-ATT model based on attention mechanism is used to predict electricity prices, and the conditional risk threshold is calculated based on historical and real-time electricity price data, the declared electricity is adjusted to maximize profits, and the regulation strategy is determined through a comparison between a few days ago and real-time electricity prices.
By flexibly adjusting power control decisions, the profits of wind and storage power plants are maximized, and economic benefits and resource allocation efficiency are improved in an unstable market environment.
Smart Images

Figure CN119029970A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a method for regulating and controlling the market power of a wind power station in cooperation with energy storage, and belongs to the field of wind power market power management. Background Art
[0002] Among many clean energy sources, wind energy has attracted much attention as a pollution-free, renewable new energy source. However, wind energy is random and volatile, so wind power generation will be affected by factors such as wind speed, temperature, and rainfall. This randomness and volatility will seriously affect the power generation of wind power stations, and thus affect the power quality and grid stability.
[0003] In order to ensure the quality of power and the stability of the power grid, the introduction of energy storage devices has become a commonly adopted solution. When wind power generation exceeds the demand of the power grid, the energy storage system can store the excess power; conversely, when wind power generation is lower than the demand of the power grid, the gap can be filled by releasing the stored energy, thereby effectively improving the utilization rate and predictability of new energy.
[0004] Against the backdrop of accelerating electricity marketization, the combined application of energy storage technology and wind power generation has become an increasingly significant trend. This integration not only helps to increase the proportion of renewable energy in the energy structure, but also effectively cope with the characteristics of large fluctuations and instability of wind energy. In the electricity market environment, formulating a stable regulation strategy is crucial to improving the market competitiveness of wind power. Through a reasonable electricity market participation strategy, the wind-storage combined system can more effectively utilize energy storage facilities, adjust wind power generation, achieve flexible response to the electricity market, and optimize resource allocation. This not only contributes to the sustainable development of wind power, but also reduces the backup pressure of the power system and improves the reliability and economy of power supply. Therefore, in-depth research on the regulation strategy of the wind-storage combined system in the electricity spot market is of great significance, which can provide strong support and guidance for the operation of the future electricity market and the integration of new energy.
[0005] In the existing methods for wind-storage power stations to participate in electricity market regulation, usually only the wind storage electricity that can be provided under the worst scenario is considered, without considering the dynamics of market price changes and the relationship between wind energy. The results are relatively conservative, which is not conducive to wind storage power stations to obtain better economic benefits in the electricity market. Summary of the invention
[0006] In view of the problem that the existing wind power storage electricity control method cannot effectively control the reported electricity in combination with electricity price, thus affecting the economic benefits of wind power storage stations, the present invention provides a market-regulated electricity control method for energy storage in conjunction with wind power stations.
[0007] A method for regulating and controlling the market power of a wind power station in cooperation with energy storage of the present invention comprises:
[0008] A price prediction model based on wind power data is adopted to make predictions based on the wind power data sampled the day before, so as to obtain the day-ahead predicted price and the real-time predicted price. The price prediction model is implemented by using the CNN-LSTM-ATT model based on the attention mechanism.
[0009] The historical conditional risk threshold X is calculated based on the historical day-ahead electricity price data and the historical real-time electricity price data;
[0010] The day-ahead conditional risk threshold Y is calculated based on the day-ahead predicted electricity price and the real-time predicted electricity price;
[0011] If Y≤X, then based on the comparison between the day-ahead forecast electricity price and the real-time forecast electricity price, the declared electricity base is adjusted according to the preset electricity adjustment ratio to determine the current control declared electricity;
[0012] If Y>X, the reported electricity base will be used as the current regulation reported electricity.
[0013] According to the energy storage and wind power station market regulation power control method of the present invention,
[0014] When Y≤X, the method for determining the current control and declared power is:
[0015] If DA ≤λ RT , the current control and declared electricity quantity Q = (1 + x%) Q0;
[0016] Where λ DA is the day-ahead electricity price forecast, λ RT is the real-time forecast of electricity price; x% is the preset electricity adjustment ratio, Q0 is the declared electricity base;
[0017] If DA >λ RT , the current regulation and control reported electricity quantity Q = (1-x%) Q0.
[0018] According to the energy storage and wind power station market regulation method of the present invention, if the current regulation declared quantity Q = (1 + x%) Q0, Q is based on the day-ahead predicted electricity price λ DA Make a declaration; convert the excess electricity x% × Q0 to the real-time predicted electricity price λ RT Repurchase, at this time the current profit E of the wind power station is:
[0019] E=[(1+x%)Q0λ DA -x%Q0λ RT ]=[λ DA +(λ DA -λ RT )x%]Q0;
[0020] If the current control reported electricity quantity Q = (1-x%) Q0, Q is based on the day-ahead predicted electricity price λ DA Make a declaration; convert the remaining electricity x% × Q0 to the real-time predicted electricity price λ RT Sold, the current profit E of the wind power station is:
[0021] E=[(1-x%)Q0λ DA +x%Q0λ RT ]=[λ DA +(λ RT -λ DA )x%]Q0.
[0022] According to the energy storage and wind power station market regulation method of the present invention, if Y>X, the current regulation and declared electricity is Q0, and the current profit E of the wind power station is:
[0023]
[0024] According to the energy storage and wind power station market regulation power control method of the present invention, the current control declaration power Q is the sum of the wind power station power generation and energy storage charging and discharging:
[0025] Q=P t bid Δt=(P t w +P t dch -P t ch )Δt,
[0026] Where P t bid is the control power at the current time t, Δt is the sampling step, P t w is the wind power station power output decision at the current time t, P t dch is the energy storage discharge power at the current time t, P t ch is the energy storage charging power at the current time t;
[0027] 0≤P t w ≤P t wf ,
[0028] Where P t wf The day-ahead forecast of wind power generation at the current time t.
[0029] According to the energy storage and wind power station market regulation method of the present invention, the profit objective function of the wind power station and the spot market is:
[0030]
[0031] Where S represents the total scene set, s represents the sth scene in the total scene set S, and ρ s represents the probability of scene s, T represents the number of sampling time points, represents the imbalance penalty fee, Indicates the battery loss fee;
[0032]
[0033]
[0034] m pun represents the penalty coefficient of unbalanced electricity, λ represents the regulated electricity price, P t da Indicates the amount of electricity regulated the day before, P t rt It represents real-time control of power, and c0 represents the unit cost of charging and discharging.
[0035] According to the energy storage and wind power station market regulation power control method of the present invention, the energy storage discharge power P at the current time t t dch and the energy storage charging power P at the current time t t ch The constraints are:
[0036]
[0037]
[0038] is the maximum discharge power of energy storage, is the maximum charging power of energy storage, is the energy storage discharge state variable, The variable for energy storage charging state:
[0039]
[0040]
[0041] According to the energy storage and wind power station market regulation power control method of the present invention, the state of charge constraint condition of the energy storage system is:
[0042] SOC t =W t / W max
[0043] SOC min ≤SOC t≤SOC max
[0044] Where SOC t is the state of charge of the energy storage system at time t, W t Represents the amount of electricity in the energy storage system at the end of time t, W max Indicates the maximum capacity of the energy storage system, SOC min Indicates the lower limit of the energy storage system, SOC max Indicates the upper limit of the energy storage system.
[0045] According to the energy storage and wind power station market regulation power control method of the present invention, the power W of the energy storage system at the end of time t+1 is t+1 for:
[0046] W t+1 =W t +P t ch η ch Δt-P t dch η dch Δt,
[0047] Where η ch is the charging efficiency, η dch is the discharge efficiency.
[0048] According to the energy storage and wind power station market regulation method of the present invention, the pre-training method of the electricity price prediction model is:
[0049] Establish a wind power data feature set and a wind power data output set; the training samples in the wind power data feature set include: the power load samples output by the wind storage power station for N consecutive hours in the past day, the wind speed samples of the wind storage power station for N consecutive hours in the past day, and the power restriction samples of the wind storage power station for N consecutive hours in the past day; the wind power data output set includes the historical day-ahead electricity price data and the historical real-time electricity price data;
[0050] The electricity price prediction model obtains historical day-ahead predicted electricity price data and historical real-time predicted electricity price data according to the wind power data feature set; by comparing the historical day-ahead predicted electricity price data with the historical real-time predicted electricity price data and the historical day-ahead electricity price data with the historical real-time electricity price data, the network parameters of the electricity price prediction model are adjusted, and finally the electricity price prediction model for real-time prediction is obtained.
[0051] Beneficial effects of the invention: The method of the invention combines the forecast information of the day-ahead electricity price and the real-time electricity price to flexibly adjust the electricity control decision to maximize the profit of the new energy power station.
[0052] The method of the present invention uses historical electricity price data and adopts the long short-term memory convolutional neural network model CNN-LSTM-ATT based on the attention mechanism to predict electricity prices, providing a more reliable basis for the regulation strategy. It introduces the conditional risk threshold as the basis for risk control and uncertainty quantification. Then, according to the comparison between the day-ahead electricity price and the real-time electricity price, the corresponding regulation strategy is adopted to participate in market regulation, so as to maximize the benefits of the wind power station.
[0053] The method of the present invention combines the electricity price forecast results with the conditional risk threshold to construct a control strategy that combines the day-ahead market with the real-time market. Risk management is considered in the control decision to ensure the sustainability of the control strategy in an unstable market environment. The method of the present invention takes into account the dynamics of market price changes and can help power plants make flexible decisions in different market environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 The energy storage system of the present invention cooperates with the market regulation method of wind power station to control the electricity quantity;
[0055] Figure 2 It is a process framework diagram of energy storage cooperating with wind power stations to participate in power market regulation;
[0056] Figure 3 It is a comparison chart of electricity price prediction results of electricity price prediction models implemented by different neural network models;
[0057] Figure 4 yes Figure 3 Comparison chart of error indicators of electricity price forecast results of the electricity price forecast models used;
[0058] Figure 5 This is a cost-profit comparison chart of using different methods to regulate electricity. DETAILED DESCRIPTION
[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0060] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.
[0061] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.
[0062] Specific implementation method 1. Combination Figure 1 and Figure 2 As shown, the present invention provides a method for regulating the market power of energy storage in cooperation with a wind power station, comprising:
[0063] A price prediction model based on wind power data is adopted to make predictions based on the wind power data sampled the day before, so as to obtain the day-ahead predicted price and the real-time predicted price. The price prediction model is implemented by using the CNN-LSTM-ATT model based on the attention mechanism.
[0064] The historical conditional risk threshold X is calculated based on the historical day-ahead electricity price data and the historical real-time electricity price data;
[0065] The day-ahead conditional risk threshold Y is calculated based on the day-ahead predicted electricity price and the real-time predicted electricity price;
[0066] If Y≤X, then based on the comparison between the day-ahead forecast electricity price and the real-time forecast electricity price, the declared electricity base is adjusted according to the preset electricity adjustment ratio to determine the current control declared electricity;
[0067] If Y>X, the reported electricity base will be used as the current regulation reported electricity.
[0068] In this implementation, a conditional value at risk (CVaR) model is introduced to evaluate the risks faced by wind power plants and calculate the conditional risk threshold.
[0069] This implementation method constructs a combined control strategy for the day-ahead market and the real-time market, taking into account the uncertainty of the output of the wind farm and the market price. First, using historical electricity price data, the CNN-LSTM-ATT model is used to predict electricity prices, providing a more reliable basis for the control strategy. Secondly, the conditional value at risk (CVaR) model is introduced to evaluate the risks faced by power plants. By calculating the CVaR threshold, more effective risk control and uncertainty quantification are provided for the proposed control strategy. Then, a control model combining the day-ahead market and the real-time market is constructed. According to the comparison between the day-ahead electricity price and the real-time electricity price, the corresponding control strategy is adopted to maximize the benefits of the wind storage power station. Finally, the effectiveness and feasibility of the method of the present invention can be demonstrated through example analysis. The implementation of the method of the present invention can effectively improve the effectiveness and feasibility of wind storage power stations participating in the regulation of the electricity market.
[0070] Furthermore, when Y≤X, the method for determining the current regulation and control declared electricity is:
[0071] If DA ≤λ RT , the current control and declared electricity quantity Q = (1 + x%) Q0;
[0072] Where λ DA is the day-ahead electricity price forecast, λ RTis the real-time forecast of electricity price; x% is the preset electricity adjustment ratio, Q0 is the declared electricity base;
[0073] If DA >λ RT , the current regulation and control reported electricity quantity Q = (1-x%) Q0.
[0074] In this embodiment, if the current control reported power Q = (1 + x%) Q0, that is, Y ≤ X and λ DA ≤λ RT When Q is based on the day-ahead predicted electricity price λ DA Make a declaration; convert the excess electricity x% × Q0 to the real-time predicted electricity price λ RT Repurchase, at this time the current profit E of the wind power station is:
[0075] E=[(1+x%)Q0λ DA -x%Q0λ RT ]=[λ DA +(λ DA -λ RT )x%]Q0;
[0076] If the current control reported power Q = (1-x%) Q0, that is, Y ≤ X and λ DA >λ RT When Q is based on the day-ahead predicted electricity price λ DA Make a declaration; convert the remaining electricity x% × Q0 to the real-time predicted electricity price λ RT Sold, the current profit E of the wind power station is:
[0077] E=[(1-x%)Q0λ DA +x%Q0λ RT ]=[λ DA +(λ RT -λ DA )x%]Q0.
[0078] Furthermore, if Y>X, the current control-declared electricity quantity is Q0, and the current profit E of the wind power station is:
[0079]
[0080] When Y>X, the electricity price λ is predicted based on the day-ahead DA and real-time predicted electricity price λ RT The higher value should be reported in full.
[0081] In this implementation, in order to ensure that the power control is consistent with the actual situation, the controlled power is the sum of the power generation of the wind power plant and the energy storage charging and discharging, and the decision output power of the new energy power generation must be less than or equal to the predicted power of the new energy power generation a day ago. The specific constraints are as follows:
[0082] The current regulation and control declared power Q is the sum of wind power station power generation and energy storage charging and discharging:
[0083] Q=P t bid Δt=(P t w +P t dch -P t ch )Δt,
[0084] Where P t bid is the control power at the current time t, Δt is the sampling step, P t w is the wind power station power output decision at the current time t, P t dch is the energy storage discharge power at the current time t, P t ch is the energy storage charging power at the current time t;
[0085] 0≤P t w ≤P t wf ,
[0086] Where P t wf The day-ahead forecast of wind power generation at the current time t.
[0087] In this implementation, the profit objective function of the wind power station and the spot market is:
[0088]
[0089] Where S represents the total scene set, s represents the sth scene in the total scene set S, and ρ s represents the probability of scene s, T represents the number of sampling time points, represents the imbalance penalty fee, Indicates the battery loss fee;
[0090]
[0091]
[0092] m pun represents the penalty coefficient of unbalanced electricity, λ represents the regulated electricity price, P t da Indicates the amount of electricity regulated the day before, P t rt It represents real-time control of power, and c0 represents the unit cost of charging and discharging.
[0093] Energy storage system constraints:
[0094] In order to more effectively integrate and balance the fluctuating output of wind power generation while extending the service life of the energy storage system, this implementation introduces some restrictions taking into account the characteristics of the energy storage system itself, including its charging state, charging and discharging amount, and charging and discharging power limitations.
[0095] 1) The charge and discharge power constraint of the energy storage system is mainly determined by its remaining power and characteristics at time t, thus determining the maximum charge and discharge power of the energy storage system at that time. Therefore, the energy storage discharge power P at the current time t is t dch and the energy storage charging power P at the current time t t ch The constraints are:
[0096] When the energy storage system is discharged,
[0097] When the energy storage system is charging,
[0098] is the maximum discharge power of energy storage, is the maximum charging power of energy storage, is the energy storage discharge state variable, The variable for energy storage charging state:
[0099]
[0100]
[0101] 2) In order to optimize the charging and discharging process of the energy storage system and reduce the adverse effects of the state of charge on the system, certain constraints need to be imposed on it. Therefore, the state of charge constraints of the energy storage system are:
[0102] SOC t =W t / W max
[0103] SOC min ≤SOC t ≤SOC max
[0104] Where SOC t is the state of charge of the energy storage system at time t, W t Represents the amount of electricity in the energy storage system at the end of time t, W max Indicates the maximum capacity of the energy storage system, SOC min Indicates the lower limit of the energy storage system, SOC max Indicates the upper limit of the energy storage system.
[0105] The amount of energy storage system at the end of time t+1 is W t+1 for:
[0106] W t+1 =W t +P t ch η ch Δt-P t dch η dch Δt,
[0107] Where η ch is the charging efficiency, η dch is the discharge efficiency.
[0108] In this implementation, the pre-training method of the electricity price prediction model is:
[0109] Establish a wind power data feature set and a wind power data output set; the training samples in the wind power data feature set include: the power load samples output by the wind storage power station for N consecutive hours in the past day, the wind speed samples of the wind storage power station for N consecutive hours in the past day, and the power restriction samples of the wind storage power station for N consecutive hours in the past day; the wind power data output set includes the historical day-ahead electricity price data and the historical real-time electricity price data;
[0110] The electricity price prediction model obtains historical day-ahead predicted electricity price data and historical real-time predicted electricity price data according to the wind power data feature set; by comparing the historical day-ahead predicted electricity price data with the historical real-time predicted electricity price data and the historical day-ahead electricity price data with the historical real-time electricity price data, the network parameters of the electricity price prediction model are adjusted, and finally the electricity price prediction model for real-time prediction is obtained.
[0111] The output results of the electricity price prediction model are the day-ahead electricity price and the real-time electricity price for the next N hours. If a sampling point is taken at an interval of 15 minutes, a total of 4N sampling points will be formed for N consecutive hours.
[0112] Before the training samples in the wind power data feature set are input into the electricity price prediction model for prediction, they are normalized and then used for prediction.
[0113] Commonly used objective evaluation indicators of electricity price prediction models include root mean squared error (RMSE) and mean absolute error (MAE), which can be used to fully evaluate the performance of the algorithm.
[0114]
[0115]
[0116] Where yi represents the actual value of the corresponding electricity price of the i-th sample, It represents the corresponding electricity price forecast value of the i-th sample. The smaller the MAE and RMSE indicators are, the better the prediction effect of the model is.
[0117] Specifically, a sampling point is taken at an interval of 15 minutes, and a total of 4N sampling points are formed for N consecutive hours. The industry standard predicts the next 24 hours and samples at intervals of 1 hour, which is called short-term; predicts the next 4 hours and samples at intervals of 15 minutes, which is called ultra-short-term.
[0118] Verification test:
[0119] In order to verify the effect of the method of the present invention, a wind power station with energy storage equipment is selected to form a wind-storage combined power station as the research object for example simulation analysis. The specific data are as follows: the installed capacity of the wind power station is 220MW, the deviation exemption margin is 5%; the deviation penalty coefficient is 0.5. The capacity of the energy storage equipment is 35MW / 70MWh, the charging and discharging efficiency is 0.9, the unit operating cost is 18 yuan / (MWh), and the initial state of charge is 0.5. The confidence level β of the conditional risk value is 0.95, and the power adjustment ratio is 20%. The wind power output data comes from the real wind power base data set, and the spot electricity price data comes from the market day-ahead and real-time electricity price data set.
[0120] Regarding the electricity price prediction part, three electricity price prediction models are used for comparison, namely, LSTM model, CNN-LSTM model and CNN-LSTM-ATT model of the present invention. Regarding the control strategy part, three strategies are used for comparison, namely: Strategy 1: Control according to net demand and operate without energy storage system; Strategy 2: Full power control based on the highest day-ahead electricity price and real-time electricity price, and use energy storage system for deviation compensation; Strategy 3 ( Figure 5 Strategy proposed in the present invention): the overall control strategy of the method of the present invention is used for control.
[0121] Figure 3 The prediction results of different electricity price prediction models are shown. The predicted values of the three prediction models are consistent with the overall trend of the actual values, but the predicted values of the ATT-CNN-LSTM model are closer to the true values. In contrast, the predicted values of the LSTM model deviate greatly from the true values. This is mainly attributed to the fact that CNN can learn directly from the original input sequence, avoiding the error accumulation that may be caused by manual feature extraction. In the ATT-CNN-LSTM model, the ATT (attention) mechanism is introduced before CNN, which enables the model to extract important information first, thereby optimizing the data input to the LSTM network. Therefore, the ATT-CNN-LSTM model can more effectively capture the characteristics of the input electricity price and load time series, significantly improving the prediction accuracy.
[0122] Figure 4 The comparison results of the error indicators of different models are shown. The advantages of the ATT-CNN-LSTM model in overall prediction accuracy are further demonstrated, including the MAE and RMSE of the three models. Figure 4 It can be observed that the MAE of the ATT-CNN-LSTM model is reduced by 29.8% and 6.2% compared with the LSTM model and the CNN-LSTM model, respectively, while the RMSE is reduced by 24.2% and 5.8% compared with the LSTM model and the CNN-LSTM model, respectively. This is mainly attributed to the fact that ATT can effectively capture dependencies in long sequences, thus making up for the shortcomings of the traditional LSTM model. Therefore, for long input sequences, the ATT-CNN-LSTM model shows higher prediction accuracy and better evaluation indicators than the traditional LSTM and CNN-LSTM models.
[0123] Figure 5 A graph comparing the profits of using the method of the present invention and two other strategies for regulation is shown. Figure 5 It can be clearly seen that the total profit of the strategy proposed in the present invention is 36.54% and 3.6% higher than that of strategy 1 and strategy 2, respectively. However, in terms of regulation profit, the strategy proposed in the present invention is 1,224 yuan less than strategy 2. This is because in the strategy of the present invention, when the day-ahead electricity price is lower than the real-time electricity price, only 80% of the electricity is regulated at the real-time electricity price, and the remaining 20% is regulated at the day-ahead electricity price; while in strategy 2, the entire electricity is regulated at the real-time electricity price, resulting in an increase in regulation profit. Nevertheless, due to the greater risk of deviation, strategy 2 makes the imbalance penalty far exceed that of the strategy proposed in the present invention. Therefore, the overall profit is still lower than that of the strategy proposed in the present invention. It should be noted that strategy 1 operates without an energy storage system, so its battery loss cost is 0.
[0124] Although the present invention is described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the present invention. It should therefore be understood that many modifications may be made to the exemplary embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the various dependent claims and features described herein may be combined in a manner different from that described in the original claims. It should also be understood that the features described in conjunction with a single embodiment may be used in other described embodiments.
Claims
1. A method for regulating the market power of energy storage and wind power station, characterized in that: include: A price prediction model based on wind power data is adopted to make predictions based on the wind power data sampled the day before, so as to obtain the day-ahead predicted price and the real-time predicted price. The price prediction model is implemented by using the CNN-LSTM-ATT model based on the attention mechanism. The historical conditional risk threshold X is calculated based on the historical day-ahead electricity price data and the historical real-time electricity price data; The day-ahead conditional risk threshold Y is calculated based on the day-ahead predicted electricity price and the real-time predicted electricity price; If Y≤X, then based on the comparison between the day-ahead forecast electricity price and the real-time forecast electricity price, the declared electricity base is adjusted according to the preset electricity adjustment ratio to determine the current control declared electricity; If Y>X, the reported electricity base will be used as the current regulation reported electricity.
2. The method for regulating the market power of energy storage and wind power station according to claim 1 is characterized in that: When Y≤X, the method for determining the current control and declared power is: If DA ≤λ RT , the current control and declared electricity quantity Q = (1 + x%) Q0; Where λ DA is the day-ahead electricity price forecast, λ RT is the real-time forecast of electricity price; x% is the preset electricity adjustment ratio, Q0 is the declared electricity base; If DA >λ RT , the current regulation and control reported electricity quantity Q = (1-x%) Q0.
3. The method for regulating the market power of energy storage and wind power station according to claim 2 is characterized in that: If the current control reported electricity quantity Q = (1 + x%) Q0, Q is based on the day-ahead predicted electricity price λ DA Make a declaration; convert the excess electricity x% × Q0 to the real-time predicted electricity price λ RT Repurchase, at this time the current profit E of the wind power station is: E=[(1+x%)Q0λ DA -x%Q0λ RT ]=[λ DA +(λ DA -l RT )x%]Q0; If the current control reported electricity quantity Q = (1-x%) Q0, Q is based on the day-ahead predicted electricity price λ DA Make a declaration; convert the remaining electricity x% × Q0 to the real-time predicted electricity price λ RT Sold, the current profit E of the wind power station is: E=[(1-x%)Q0λ DA +x%Q0λ RT ]=[λ DA +(λ RT -l DA )x%]Q0.
4. The method for regulating the market power of energy storage and wind power station according to claim 3 is characterized in that: If Y>X, the current control-declared electricity quantity is Q0, and the current profit E of the wind power station is:
5. The method for regulating the market power of energy storage and wind power station according to claim 4 is characterized in that: The current regulation and control declared power Q is the sum of wind power station power generation and energy storage charging and discharging: Q=P t bid Δt=(P t w +P t dch -P t ch )Δt, Where P t bid is the control power at the current time t, Δt is the sampling step, P t w is the wind power station power output decision at the current time t, P t dch is the energy storage discharge power at the current time t, P t ch is the energy storage charging power at the current time t; 0≤P t w ≤P t wf , Where P t wf The day-ahead forecast of wind power generation at the current time t.
6. The method for regulating the market power of energy storage and wind power station according to claim 5 is characterized in that: The profit objective function of wind power station and spot market is: Where S represents the total scene set, s represents the sth scene in the total scene set S, and ρ s represents the probability of scene s, T represents the number of sampling time points, represents the imbalance penalty fee, Indicates the battery loss fee; m pun represents the penalty coefficient of unbalanced electricity, λ represents the regulated electricity price, P t da Indicates the amount of electricity regulated the day before, P t rt It represents real-time control of power, and c0 represents the unit cost of charging and discharging.
7. The method for regulating the market power of energy storage and wind power station according to claim 6 is characterized in that: Energy storage discharge power P at current time t t dch and the energy storage charging power P at the current time t t ch The constraints are: is the maximum discharge power of energy storage, is the maximum charging power of energy storage, is the energy storage discharge state variable, The variable for energy storage charging state:
8. The method for regulating the market power of wind power stations in cooperation with energy storage according to claim 7 is characterized in that: The state of charge constraints of the energy storage system are: SOC t =W t / W max SOC min ≤SOC t ≤SOC max Where SOC t is the state of charge of the energy storage system at time t, W t Represents the amount of electricity in the energy storage system at the end of time t, W max Indicates the maximum capacity of the energy storage system, SOC min Indicates the lower limit of the energy storage system, SOC max Indicates the upper limit of the energy storage system.
9. The method for regulating the market power of energy storage and wind power station according to claim 8 is characterized in that: The amount of energy storage system at the end of time t+1 is W t+1 for: W t+1 =W t +P t ch or ch Δt-P t dch or dch Δt, Where η ch is the charging efficiency, η dch is the discharge efficiency.
10. The method for market regulation of electricity volume by energy storage in conjunction with wind power stations according to claim 1 is characterized in that: The pre-training method of the electricity price prediction model is: Establish a wind power data feature set and a wind power data output set; the training samples in the wind power data feature set include: the power load samples output by the wind storage power station for N consecutive hours in the past day, the wind speed samples of the wind storage power station for N consecutive hours in the past day, and the power restriction samples of the wind storage power station for N consecutive hours in the past day; the wind power data output set includes the historical day-ahead electricity price data and the historical real-time electricity price data; The electricity price prediction model obtains historical day-ahead predicted electricity price data and historical real-time predicted electricity price data according to the wind power data feature set; by comparing the historical day-ahead predicted electricity price data with the historical real-time predicted electricity price data and the historical day-ahead electricity price data with the historical real-time electricity price data, the network parameters of the electricity price prediction model are adjusted, and finally the electricity price prediction model for real-time prediction is obtained.
Citation Information
Cited By
Method for enabling energy storage system to cooperate with wind power station to participate in electric quantity bidding in electric power market
CN120013651A
