New energy distribution and storage power station day-ahead bidding method and system considering wind and light uncertainty

Abstract

The invention discloses a new energy distribution and storage power station day-ahead bidding method and system considering wind and light uncertainty, and belongs to the field of power market design, and the method comprises the steps: generating a scene considering wind and light output uncertainty based on the historical data information of a new energy distribution and storage power station; after wind power output scenes are reduced by using a K-medoids clustering algorithm, a day-ahead bidding strategy is formulated with the purpose of maximizing the total power generation income of each scene, and a day-ahead bidding plan is formulated and dynamically adjusted according to the real-time condition of the new energy distribution and storage power station. According to the method, a more accurate day-ahead market bidding strategy is formulated, the problem of uncertainty of wind and light output is solved, maximum utilization of natural resources such as wind and light is realized, and sustainable development of new energy is promoted.

Description

Technical Field

[0001] The present invention relates to the field of power market design, and in particular to a day-ahead bidding method and system for a new energy power station with storage and distribution that takes into account the uncertainty of wind and solar power. Background Art

[0002] At present, the technology of new energy power generation is developing rapidly, and the installed capacity of wind and solar power generation is increasing. Large-scale new energy power generation can provide efficient electricity supply and solve the problems of environmental pollution and fossil energy shortage. However, new energy represented by wind power and photovoltaic power generation has the characteristics of intermittency and uncertainty. There is also a serious phenomenon of "abandoning wind and light" in new energy, which restricts the further large-scale development and utilization of new energy. In order to reduce the abandonment rate of new energy and improve the utilization efficiency of new energy, it is an effective method for new energy distribution and storage power stations to reasonably participate in the day-ahead market. However, in the process of market transactions, the execution of trading electricity needs to consider the uncertainty of wind and solar power output and many factors such as policies and technologies. Under the current market mechanism, it is difficult for new energy distribution and storage power stations to formulate strategies for participating in the day-ahead market, and it is difficult to control the output deviation, which has caused great difficulties for the formulation of bidding strategies for new energy distribution and storage power stations to participate in the day-ahead market.

[0003] At present, the research on bidding strategies for new energy power stations with storage and distribution participating in the day-ahead market mainly focuses on modeling the uncertainty itself to quantify its uncertainty. However, most of the scenarios considered when solving the problem are relatively simple, and the results are relatively conservative, which is not conducive to new energy power stations with storage and distribution obtaining higher economic benefits in the electricity market. Summary of the invention

[0004] In response to the bidding strategy problem in the day-ahead market of new energy power stations with storage and distribution under high proportion of new energy access mentioned in the background technology, the purpose of the present invention is to provide a day-ahead bidding technology for new energy power stations with storage and distribution that takes into account the uncertainty of wind and solar power. It aims to deal with the uncertainty problem of parameters by adopting a random optimization method. The optimal solution is related to all input scenarios. When the scenario changes, the optimal solution will change. On this basis, a bidding strategy for the day-ahead market is formulated, thereby maximizing the utilization of natural resources such as wind and light and promoting the sustainable development of new energy.

[0005] In order to achieve the above technical objectives, the present application provides a method for bidding for a new energy storage power station taking into account the uncertainty of wind and solar power, including the following steps:

[0006] Based on the historical data information of the new energy storage power station, generate scenarios that take into account the uncertainty of wind and solar power output;

[0007] After using the K-medoids clustering algorithm to reduce the wind power output scenarios, a day-ahead bidding strategy is formulated with the goal of maximizing the total power generation revenue in each scenario. The day-ahead bidding plan is compiled and dynamically adjusted according to the real-time situation of the new energy storage power station.

[0008] Preferably, in the process of obtaining scenarios that take into account the uncertainty of wind and solar power output, the output power of renewable energy is predicted through a long short-term memory model based on historical data information, and the clearing price is predicted through an LSTM algorithm using historical data to obtain scenarios that take into account the uncertainty of wind and solar power output.

[0009] Preferably, in the process of obtaining scenarios that take into account the uncertainty of wind and solar power output, based on the prediction results of new energy output power and clearing prices, multiple scenarios of output and price uncertainty and their occurrence probabilities are obtained through scenario generation technology, and the probability density function of the uncertainty quantity is obtained from historical data. Then, a large number of scenarios are generated through Monte Carlo simulation method to describe the uncertainty.

[0010] Preferably, in the process of reducing wind power output scenarios, a scenario set that takes into account the day-ahead electricity price, real-time electricity price and uncertainty in new energy output is obtained by reducing wind power output scenarios.

[0011] Preferably, in the process of formulating a day-ahead bidding strategy with the goal of maximizing the total power generation revenue in each scenario, the bidding model of the new energy power station participating in the day-ahead energy market is expressed as:

[0012]

[0013] In the formula, represents the revenue obtained by new energy power station i from participating in the day-ahead energy market bidding during period t; π t is the day-ahead electricity price at time t in scenario s; Δt is the length of a single period; is the bid electricity amount in period t; It represents the penalty cost loss of output deviation of renewable energy power station i in period t; is the deviation power of new energy power station i in period t; c p is the deviation penalty loss coefficient; represents the operating cost of the new energy power station i and its self-equipped energy storage during period t; c e is the unit power operation cost coefficient of the energy storage system; and They represent the decision-making output power of renewable energy generation and the charging and discharging power of energy storage in the tth period respectively; ρ s represents the probability of s scenarios; S represents the total set of scenarios;

[0014] The current bid electricity volume is the sum of the power generation of new energy and the energy storage charging and discharging volume:

[0015]

[0016] Preferably, in the process of formulating a day-ahead bidding strategy with the goal of maximizing the total power generation revenue in each scenario, the constraints for formulating the day-ahead bidding strategy include new energy power generation output constraints, energy storage system operating power constraints, and energy storage system power constraints.

[0017] Preferably, in the process of obtaining the constraint conditions, the renewable energy power generation output power constraint is expressed as:

[0018]

[0019] In the formula, It represents the predicted power of new energy electricity in the tth period of the new energy distribution and storage station i.

[0020] Preferably, in the process of obtaining the constraint conditions, the energy storage system operating power constraint is expressed as:

[0021]

[0022] f1+f2≤1

[0023] f1,f2∈{0,1}

[0024] Where: P max It is the maximum charging and discharging power limit of energy storage; f1 and f2 are the flags of energy storage charging and discharging actions, both are 0-1 variables and only one variable can be 1 at the same time.

[0025] Preferably, in the process of obtaining the constraint condition, the energy storage system power constraint is expressed as:

[0026]

[0027] Soc _min ≤Soc(t)≤Soc _max

[0028] Where Soc(t) and Soc(t-1) are the Soc values ​​of the energy storage device at time t and t-1 respectively; χ is the self-discharge rate of the energy storage device; η c and η d are the charging efficiency and discharging efficiency of the energy storage device respectively; E c is the capacity of the energy storage device; Soc _max and Soc _min They respectively represent the upper and lower limits of the energy storage Soc.

[0029] The present invention discloses a day-ahead bidding system for a new energy power station with storage and distribution that takes into account the uncertainty of wind and solar power. The system is used to implement the day-ahead bidding method for a new energy power station with storage and distribution that takes into account the uncertainty of wind and solar power mentioned above. The system comprises:

[0030] The scenario generation module is used to generate scenarios that take into account the uncertainty of wind and solar power output based on the historical data information of the new energy storage power station;

[0031] The bidding strategy generation module is used to formulate a day-ahead bidding strategy with the goal of maximizing the total power generation revenue of each scenario after reducing the wind power output scenario using the K-medoids clustering algorithm, and to prepare and dynamically adjust the day-ahead bidding plan based on the real-time situation of the new energy storage power station.

[0032] The present invention discloses the following technical effects:

[0033] The present invention develops a more accurate day-ahead market bidding strategy, overcomes the uncertainty of wind and solar power output, realizes the maximum utilization of natural resources such as wind and light, and promotes the sustainable development of new energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0036] Figure 2 It is a comparison of the power reported in the energy market of scenario A and scenario B described in the present invention;

[0037] Figure 3 It is a comparison of the energy market reported power of scenario A and scenario B described in the present invention, where (a) represents scenario A and (b) represents scenario B. DETAILED DESCRIPTION

[0038] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0039] like Figure 1-3 As shown, the present invention provides a day-ahead bidding technology for a new energy storage power station taking into account the uncertainty of wind and solar power, which specifically includes the following contents:

[0040] Step 1: Scenario generation considering the uncertainty of wind and solar power output:

[0041] Consider the characteristics of wind and solar power output and describe its uncertainty.

[0042] Firstly, historical data information is used to predict the output power of renewable energy using the Long Short-Term Memory (LSTM) model, and historical data is used to predict the clearing price through the LSTM algorithm.

[0043] Secondly, considering that the predicted value is not completely accurate, a small fluctuation in the value in the actual situation may also have a greater impact on the result. Therefore, multiple scenarios of output and price uncertainty and their occurrence probabilities are obtained through scenario generation technology, and the probability density function of the uncertainty is obtained from historical data. Then, a large number of scenarios are generated through Monte Carlo simulation to describe the uncertainty. The relationship between the actual value and the predicted value can be expressed as: The relationship between the actual value and the predicted value can be expressed as:

[0044] P actual =P predict +P err or (1)

[0045] Where: P actual Indicates the actual value; P predict represents the predicted value; P error Represents the prediction error.

[0046] Step 2: Reduce wind power output scenarios based on K-medoids clustering algorithm:

[0047] Based on the generation of uncertain parameters for different scenarios, a limited number of representative typical application scenarios are obtained through scenario reduction technology, which mainly considers the scenario set of day-ahead electricity price, real-time electricity price and new energy output uncertainty.

[0048] Since errors may produce some abnormal scenes when randomly sampling to generate scenes, the K-medoids algorithm is selected for scene reduction to ensure that the reduced scenes can effectively represent the original scenes as much as possible.

[0049] The principle of scene reduction by K-medoids algorithm is to set the unreduced scenes as set Ω and find an optimal subset S to replace the original set Ω. This process can be expressed as:

[0050]

[0051] In the formula, ρ i For scene A i Probability of occurrence; d(A i ,A j ) is the distance between two scenes.

[0052] The specific steps are as follows:

[0053] Step 2.1: Randomly select K points in the data set Ω as initial medoids, which will serve as the initial cluster centers.

[0054] Step 2.2: For each non-medoid point in the dataset, calculate its distance to all K medoids and assign it to the cluster with the nearest medoid. The distance calculation formula is as follows:

[0055]

[0056] Where M j It is medoid, a ik and m jk A i and M j Coordinates in the kth dimension, where n is the dimension of the data.

[0057] Step 2.3: In each cluster, replace the current medoid with other non-medoid points in the cluster. The replacement criterion is to minimize the total distance (or cost) from all points in the cluster to the new medoid after replacement.

[0058] Step 2.4: Repeat the assignment and update steps until the medoids no longer change or the preset maximum number of iterations is reached.

[0059] Step 2.5: When the algorithm converges, output the final K clusters and the medoid of each cluster.

[0060] Step 2.6: Calculate the probability of the scene after reduction, ρ i =N i / N, that is, the ratio of the number of scenes in the i-th category to the total number of scenes after reduction.

[0061] After reduction, the characteristics of each scene have significant differences, and the sum of the probabilities of all scenes is 1. The K value is selected according to the elbow rule.

[0062] Step 3: Formulate a day-ahead bidding strategy with the goal of maximizing total power generation revenue in each scenario

[0063] Since the scale of new energy power stations is relatively small in the market competition process, their bidding behavior will not affect the market clearing electricity price. Therefore, as the recipient of the market electricity price, the new energy power station reasonably optimizes its bidding strategy according to the price changes in each period of the market, so as to maximize its benefits. The bidding model of new energy power stations participating in the day-ahead energy market can be expressed as:

[0064]

[0065]

[0066] In the formula, represents the revenue obtained by new energy power station i from participating in the day-ahead energy market bidding during period t; π t is the day-ahead electricity price at time t in scenario s; Δt is the length of a single period; is the bid electricity amount in period t; It represents the penalty cost loss of output deviation of renewable energy power station i in period t; is the deviation power of new energy power station i in period t; c p is the deviation penalty loss coefficient; represents the operating cost of the new energy power station i and its self-equipped energy storage during period t; c e is the unit power operation cost coefficient of the energy storage system; and They represent the decision-making output power of renewable energy generation and the charging and discharging power of energy storage in the tth period respectively; ρ s represents the probability of s scenarios; S represents the total set of scenarios.

[0067] The current bid electricity volume is the sum of the power generation of new energy and the energy storage charging and discharging volume:

[0068]

[0069] At the same time, the model should run according to the following constraints:

[0070] 1) Constraints on the output power of renewable energy power generation.

[0071]

[0072] In the formula, It represents the predicted power of new energy electricity in the tth period of the new energy distribution and storage station i.

[0073] 2) Energy storage system operation power constraints. To ensure the feasibility of energy storage charging and discharging and participating in frequency regulation, the energy storage is arranged to perform only a single action at the same time. The constraint condition expression is:

[0074]

[0075]

[0076] f1+f2≤1 (12)

[0077] f1,f2∈{0,1}(13)

[0078] Where: P max is the maximum charge and discharge power limit of energy storage; f1 and f2 are the flags of energy storage charging and discharging actions, both of which are 0-1 variables and only one variable can be 1 at the same time, which ensures the feasibility of energy storage function.

[0079] 3) Energy storage system power constraints. The relationship between the charging and discharging power of energy storage and the state of charge (Soc) needs to be considered. When the energy storage device is charged, the Soc rises accordingly, and vice versa, when the energy storage discharges the output power, the Soc decreases. The power model of energy storage can be expressed as follows:

[0080]

[0081] Where Soc(t) and Soc(t-1) are the Soc values ​​of the energy storage device at time t and t-1 respectively; χ is the self-discharge rate of the energy storage device; η c and η d are the charging efficiency and discharging efficiency of the energy storage device respectively; E c It is the capacity of the energy storage device in kWh.

[0082] In addition, the energy storage device should also meet the upper and lower limit constraints of Soc, that is, to ensure that the energy storage device is not over-discharged or over-charged, as shown in formula (15):

[0083] Soc _min ≤Soc(t)≤Soc _max (15)

[0084] Among them, Soc _max and Soc_min They respectively represent the upper and lower limits of the energy storage Soc.

[0085] Step 4: Determine the reserved output capacity of energy storage and optimize the day-ahead market bidding strategy

[0086] Step 4.1: Use scenario generation and reduction techniques to generate multiple day-ahead clearing prices and renewable energy output scenario data from renewable energy power plants in the day-ahead phase and input them into the model in step three.

[0087] Step 4.2: Based on the actual data of the new energy station, obtain the operation and dispatch plan of the energy storage in the power plant, determine the reserved output space, and prepare and dynamically adjust the day-ahead bidding plan based on the real-time situation.

[0088] Example: Taking a new energy storage power station as an example, simulation modeling and case analysis are carried out in the MATLAB development environment, and the gurobi9.0 solver is called by Yalmip for solution. The new energy day-ahead predicted output and actual output synchronous measurement data of the power station from May 4 to May 31, 2023 are selected for analysis, with 15 minutes as a measurement point. The price and equipment parameter settings are shown in Table 1 and Table 2.

[0089] Table 1 Price parameters

[0090] parameter Value Energy trading electricity price 520 Deviation Penalty Coefficient 676 Energy storage life loss factor 11.88

[0091] Table 2 Equipment parameters

[0092] parameter Value Total power limit 110，50 Energy storage self-discharge rate 0 Energy storage charging efficiency 0.92 Energy storage discharge efficiency 0.92 Energy storage rated capacity 300 Initial energy storage capacity 60 State of charge upper limit 0.9 Lower limit of charge state 0.15

[0093] The following two scenarios are set: ① Scenario A, the new energy power station does not allocate storage to participate in the day-ahead market ② Scenario B, configure energy storage of reasonable capacity according to the new energy output uncertainty model, and set up reserved energy storage output capacity based on this to participate in the day-ahead market. The two scenarios are compared as follows:

[0094] Depend on Figure 2 It can be seen that in the time periods of 00:45-01:00, 09:45-12:15, 22:00-22:15, etc., the energy market reported power of scenario B is less than the energy market reported power of scenario A. This is because the setting of the reserved energy storage output capacity has squeezed the discharge space of energy storage, and the behavior of using energy storage to increase the energy market reported power and increase the electricity sales revenue is therefore hindered. In the time periods of 01:15-01:30, 15:00-15:15, 16:15-16:30, etc., the energy market reported power of scenario B is greater than the energy market reported power of scenario A. During these time periods, the discharge space of energy storage is sufficient, and the new energy distribution storage power station increases the discharge power of energy storage to increase the energy market reported power, thereby reducing the negative impact of the reserved energy storage output capacity setting on the economic efficiency of the energy market.

[0095] But by Figure 3 It can be seen that without setting up energy storage, all deviation power cannot be smoothed, and the new energy power station therefore bears high deviation penalties; while the new energy power station with storage bears part of the depreciation cost brought by the reserved output, but only a small amount of deviation power exceeds the smoothing capacity of the energy storage.

[0096] In summary, the day-ahead bidding model and method for new energy storage power stations considering the uncertainty of wind and solar power provided by the present invention can significantly reduce costs. The comparison of the revenue results of the two scenarios is shown in Table 3:

[0097] Table 3 Comparison of the revenue results of the two scenarios, unit: 10,000 yuan

[0098]

[0099] It can be seen that the day-ahead bidding model and method for new energy power stations with storage and wind power that take into account the uncertainty of wind and solar power provided by the present invention can save 60,400 yuan in costs caused by deviation power, and the bidding strategy formulated by the present invention is of great significance to promoting real-time balance, safe and stable operation of the power grid.

[0100] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A day-ahead bidding method for renewable energy power stations with storage considering the uncertainty of wind and solar power, characterized by: The following steps are involved: Based on the historical data information of the new energy storage power station, generate scenarios that take into account the uncertainty of wind and solar power output; After reducing the wind power output scenarios using the K-medoids clustering algorithm, a day-ahead bidding strategy is formulated with the goal of maximizing the total power generation revenue of each scenario, and the day-ahead bidding plan is compiled and dynamically adjusted according to the real-time situation of the new energy distribution and storage power station.

2. The day-ahead bidding method for a new energy storage power station considering the uncertainty of wind and solar power according to claim 1 is characterized by: In the process of obtaining scenarios that take into account the uncertainty of wind and solar power output, based on the historical data information, the output power of renewable energy is predicted through the long short-term memory model, and the clearing price is predicted through the LSTM algorithm using historical data to obtain scenarios that take into account the uncertainty of wind and solar power output.

3. The day-ahead bidding method for a new energy storage power station considering the uncertainty of wind and solar power according to claim 2 is characterized by: In the process of obtaining scenarios that take into account the uncertainty of wind and solar power output, based on the prediction results of new energy output power and clearing prices, scenario generation technology is used to obtain multiple scenarios of output and price uncertainty and their occurrence probabilities. The probability density function of the uncertainty quantity is obtained from historical data, and then a large number of scenarios are generated through the Monte Carlo simulation method to describe the uncertainty.

4. The method for bidding for a new energy power station with storage and distribution considering the uncertainty of wind and solar power according to claim 3 is characterized by: In the process of reducing wind power output scenarios, a scenario set that takes into account the day-ahead electricity price, real-time electricity price and uncertainty in new energy output is obtained through reducing wind power output scenarios.

5. The day-ahead bidding method for a new energy storage power station considering the uncertainty of wind and solar power according to claim 4 is characterized by: In the process of formulating the day-ahead bidding strategy with the goal of maximizing the total power generation revenue in each scenario, the bidding model of new energy power stations participating in the day-ahead energy market is expressed as: In the formula, represents the revenue obtained by new energy power station i from participating in the day-ahead energy market bidding during period t; π t is the day-ahead electricity price at time t in scenario s; Δt is the length of a single period; is the bid electricity amount in period t; It represents the penalty cost loss of output deviation of renewable energy power station i in period t; is the deviation power of new energy power station i in period t; c p is the deviation penalty loss coefficient; represents the operating cost of the new energy power station i and its self-equipped energy storage during period t; c e is the unit power operation cost coefficient of the energy storage system; and They represent the decision-making output power of renewable energy generation and the charging and discharging power of energy storage in the tth period respectively; ρ s represents the probability of s scenarios; S represents the total set of scenarios; The current bid electricity volume is the sum of the power generation of new energy and the energy storage charging and discharging volume:

6. The method for bidding for a new energy power station with storage and distribution considering the uncertainty of wind and solar power according to claim 5 is characterized by: In the process of formulating a day-ahead bidding strategy with the goal of maximizing the total power generation revenue in each scenario, the constraints for formulating the day-ahead bidding strategy include the output power constraint of new energy power generation, the operating power constraint of the energy storage system, and the power constraint of the energy storage system.

7. The day-ahead bidding method for a new energy storage power station considering the uncertainty of wind and solar power according to claim 6 is characterized by: In the process of obtaining constraint conditions, the output power constraint of renewable energy power generation is expressed as: In the formula, It represents the predicted power of new energy electricity in the tth period of the new energy distribution and storage station i.

8. The method for bidding for a new energy power station with storage and distribution considering the uncertainty of wind and solar power according to claim 7 is characterized by: In the process of obtaining constraint conditions, the energy storage system operating power constraint is expressed as: f1+f2≤1 f1,f2∈{0,1} Where: P max It is the maximum charging and discharging power limit of energy storage; f1 and f2 are the flags of energy storage charging and discharging actions, both are 0-1 variables and only one variable can be 1 at the same time.

9. The method for bidding for a new energy power station with storage and distribution considering the uncertainty of wind and solar power according to claim 8 is characterized by: In the process of obtaining constraint conditions, the energy storage system power constraint is expressed as: Soc _min ≤Soc(t)≤Soc _max Where Soc(t) and Soc(t-1) are the Soc values ​​of the energy storage device at time t and t-1 respectively; χ is the self-discharge rate of the energy storage device; η c and η d are the charging efficiency and discharging efficiency of the energy storage device respectively; E c is the capacity of the energy storage device; Soc _max and Soc _min They respectively represent the upper and lower limits of the energy storage Soc.

10. A day-ahead bidding system for renewable energy power stations with storage considering the uncertainty of wind and solar power, characterized by: The system is used to implement the day-ahead bidding method for a new energy storage power station considering the uncertainty of wind and solar power as claimed in any one of claims 1 to 9, and the system comprises: The scenario generation module is used to generate scenarios that take into account the uncertainty of wind and solar power output based on the historical data information of the new energy storage power station; The bidding strategy generation module is used to formulate a day-ahead bidding strategy with the goal of maximizing the total power generation revenue of each scenario after reducing the wind power output scenario using the K-medoids clustering algorithm, and to prepare and dynamically adjust the day-ahead bidding plan based on the real-time situation of the new energy distribution and storage power station.

Images