Method, System, Device and Storage Medium for Determining Bidding Capacity of Virtual Power Plant

Abstract

The present invention belongs to the field of power automation, and discloses a method, system, device and storage medium for determining the bidding capacity of a virtual power plant. By obtaining the predicted power generation and the predicted error distribution of uncontrollable power sources in the virtual power plant on the bidding day, as well as the maximum power generation of controllable power sources in the virtual power plant on the bidding day; according to the predicted error distribution of uncontrollable power sources on the bidding day, several reserved capacities and the deviation power of each reserved capacity of the controllable power sources on the bidding day are obtained; the preset power generation determination model is solved to obtain the maximum profit of the virtual power plant participating in the power market and the power generation power under the maximum profit for each reserved capacity; the reserved capacity with the maximum profit of the virtual power plant participating in the power market among all reserved capacities is obtained, and the power generation power under this reserved capacity is used as the bidding capacity. It realizes the maximum participation of the actual power generation power of uncontrollable power sources, greatly reduces the wind curtailment and light curtailment amounts, effectively promotes the consumption of clean energy, and reduces the overall power generation cost.

Description

Technical Field

[0001] The present invention belongs to the field of power automation and relates to a method, system, device and storage medium for determining the bidding capacity of a virtual power plant. Background Art

[0002] With the advancement of the power market reform, a spot market has been initially established. In the future, with the further development of the power market, the power market will form a situation where multiple markets such as an energy market, a reserve market, and a flexible peak shaving market coexist. At the same time, as a virtual power plant containing multiple types of power sources, its economic significance in participating in the power market has become increasingly significant, and the technology of virtual power plants containing multiple power sources participating in multiple power markets needs to be further explored.

[0003] Currently, when a virtual power plant containing multiple power sources participates in the power market, the bidding capacity of wind power and photovoltaic power generation in the virtual power plant in the market is usually the available electricity or guaranteed electricity obtained from historical data. However, due to the uncertainty of the output of wind power and photovoltaic power generation, such a method will lead to relatively serious phenomena of wind curtailment and light curtailment, resulting in serious waste of clean energy and further increasing the overall power generation cost. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned disadvantages of the prior art and provide a method, system, device and storage medium for determining the bidding capacity of a virtual power plant.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] In the first aspect of the present invention, a method for determining the bidding capacity of a virtual power plant includes the following steps:

[0007] Obtain the predicted power generation and predicted error distribution of uncontrollable power sources on the bidding day of the virtual power plant, and the maximum power generation of controllable power sources on the bidding day of the virtual power plant;

[0008] According to the predicted error distribution of uncontrollable power sources on the bidding day, obtain several reserved capacities on the bidding day of controllable power sources and the deviation power of each reserved capacity;

[0009] According to the predicted power generation of uncontrollable power sources on the bidding day, the maximum power generation of controllable power sources on the bidding day, and several reserved capacities on the bidding day of controllable power sources and the deviation power of each reserved capacity, solve the preset power generation determination model to obtain the maximum profit of the virtual power plant participating in the power market and the power generation at the maximum profit under each reserved capacity;

[0010] Obtain the reserved capacity with the maximum maximum profit of the virtual power plant participating in the power market among all reserved capacities, and use the power generation at the maximum profit of the virtual power plant participating in the power market under this reserved capacity as the bidding capacity.

[0011] A further improvement in the method for determining the bidding capacity of the virtual power plant of the present invention lies in:

[0012] The specific method for obtaining the predicted power generation and the predicted error distribution of the uncontrollable power sources on the bidding day of the virtual power plant is as follows:

[0013] Obtain the meteorological prediction data on the bidding day, the historical meteorological prediction data of the first preset number of days before the bidding day, and the actual power generation of the uncontrollable power sources of the second preset number of days before the bidding day;

[0014] According to the meteorological prediction data on the bidding day and the historical meteorological prediction data of the third preset number of days before the bidding day, through a preset power generation prediction model, obtain the predicted power generation of the uncontrollable power sources on the bidding day; wherein, the third preset number and the second preset number are both less than the first preset number;

[0015] According to the historical meteorological prediction data of the first preset number of days before the bidding day, through a preset power generation prediction model, obtain the predicted power generation of the uncontrollable power sources on the second preset number of days of the bidding day;

[0016] According to the predicted power generation and the actual power generation of the uncontrollable power sources on the second preset number of days before the bidding day, obtain the predicted error data of the second preset number of the uncontrollable power sources, and through normal distribution fitting of the predicted error data of the second preset number of the uncontrollable power sources, obtain the predicted error distribution of the uncontrollable power sources on the bidding day.

[0017] The power generation prediction model is obtained by training a preset artificial neural network model through the historical meteorological prediction data of several days before the bidding day and the actual power generation of the uncontrollable power sources of several days before the bidding day.

[0018] The specific method for obtaining several reserved capacities of the controllable power sources on the bidding day according to the predicted error distribution of the uncontrollable power sources on the bidding day is as follows:

[0019] Obtain several probability groups; wherein, each probability group includes a first probability value and a second probability value, and the first probability value is less than the second probability value;

[0020] Traverse each probability group, take the quantile of the predicted error distribution under the first probability value of the current probability group as the negative reserved capacity, and take the quantile of the predicted error distribution under the second probability value of the current probability group as the positive reserved capacity; combine the negative reserved capacity and the positive reserved capacity to obtain the reserved capacity of the controllable power sources under the current probability group; after the traversal is completed, obtain several reserved capacities of the controllable power sources on the bidding day.

[0021] The reserved capacities include three, and each reserved capacity includes a negative reserved capacity and a positive reserved capacity; the negative reserved capacities of the three reserved capacities are successively the negative value of the standard deviation of the prediction error distribution, twice the negative value of the standard deviation of the prediction error distribution, and three times the negative value of the standard deviation of the prediction error distribution, and the positive reserved capacities are successively the standard deviation of the prediction error distribution, twice the standard deviation of the prediction error distribution, and three times the standard deviation of the prediction error distribution.

[0022] The deviation powers all include under-generation power and over-generation power;

[0023] The specific method for obtaining the deviation power of each reserved capacity according to the prediction error distribution of the uncontrollable power source is: through the following formula, the over-generation power P of each reserved capacity is obtained up :

[0024]

[0025] Through the following formula, the under-generation power P of each reserved capacity is obtained down :

[0026]

[0027] where f(x) is the prediction error distribution, x is the random variable of the prediction error distribution, μ is the expectation of the prediction error distribution, σ is the standard deviation of the prediction error distribution, α is the probability value corresponding to the negative reserved capacity in each reserved capacity as the quantile of the prediction error distribution, is the probability value corresponding to the positive reserved capacity in each reserved capacity as the quantile of the prediction error distribution.

[0028] The power generation power determination model is constructed with the maximum profit of the virtual power plant participating in the power market as the optimization goal and the capacity constraints of each market in which the virtual power plant participates in the power market, the operation constraints of each controllable power source in the virtual power plant, and the reserved capacity constraints of the controllable power sources in the virtual power plant for the uncontrollable power sources as the constraint conditions.

[0029] In the second aspect of the present invention, a bidding capacity determination system for a virtual power plant includes:

[0030] A data acquisition module, configured to acquire the predicted power generation power and prediction error distribution of the uncontrollable power sources on the bidding day of the virtual power plant, and the maximum power generation power of the controllable power sources on the bidding day of the virtual power plant;

[0031] A reservation and deviation determination module, configured to obtain several reserved capacities on the bidding day of the controllable power source and the deviation power of each reserved capacity according to the prediction error distribution of the uncontrollable power source on the bidding day;

[0032] A model solving module, which is used to solve a preset power generation power determination model according to the predicted power generation power on the bidding date of uncontrollable power sources, the maximum power generation power on the bidding date of controllable power sources, several reserved capacities on the bidding date of controllable power sources, and the deviation power of each reserved capacity, so as to obtain the maximum profit of the virtual power plant participating in the power market and the power generation power under the maximum profit under each reserved capacity;

[0033] A bidding capacity determination module, which is used to obtain the reserved capacity with the maximum profit of the virtual power plant participating in the power market among all reserved capacities, and use the power generation power under the maximum profit of the virtual power plant participating in the power market under this reserved capacity as the bidding capacity.

[0034] In the third aspect of the present invention, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned bidding capacity determination method for the virtual power plant are implemented.

[0035] In the fourth aspect of the present invention, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned bidding capacity determination method for the virtual power plant are implemented.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The bidding capacity determination method for the virtual power plant of the present invention realizes compensating for the deviation between the predicted power and the actual power of the uncontrollable power source through the controllable power source by obtaining the prediction error distribution of the uncontrollable power source and determining the reserved capacity of the controllable power source based on this. Moreover, according to the predicted power generation power of the uncontrollable power source, the maximum power generation power of the controllable power source, several reserved capacities of the controllable power source, and the deviation power of each reserved capacity, through a preset power generation power determination model, the maximum profit of the virtual power plant participating in the power market under different reserved capacities is determined, and by comparing the maximum profits of the virtual power plant participating in the power market under different reserved capacities, the optimal reserved capacity is obtained, and the power generation power under the maximum profit of the virtual power plant participating in the power market under the optimal reserved capacity is used as the bidding capacity, so as to maximize the participation of the actual power generation power of the uncontrollable power source, greatly reduce the wind rejection rate and light rejection rate, effectively promote the consumption of clean energy, and thus reduce the overall power generation cost. Description of the Drawings

[0038] Figure 1 It is a flow block diagram of the bidding capacity determination method for the virtual power plant according to the embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of the normal distribution fitting of the wind power source prediction error distribution according to the embodiment of the present invention;

[0040] Figure 3 The block diagram of the bidding capacity determination system for the virtual power plant according to the embodiment of the present invention. Specific embodiments

[0041] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0043] The present invention will be further described in detail below with reference to the accompanying drawings:

[0044] See Figure 1 , in an embodiment of the present invention, a method for determining the bidding capacity of a virtual power plant is provided. By converting the prediction error of uncontrollable power sources into the reserved capacity of controllable power sources, the maximum consumption of the actual power generation of uncontrollable power sources is realized, thereby reducing the overall power generation cost of the virtual power plant. Specifically, the method for determining the bidding capacity of the virtual power plant includes the following steps.

[0045] S1: Obtain the predicted power generation and the distribution of prediction errors of uncontrollable power sources in the virtual power plant, and the maximum power generation of controllable power sources in the virtual power plant.

[0046] Among them, uncontrollable power sources are power sources with uncertain output, such as wind power sources and photovoltaic power sources, and controllable power sources are power sources with certain output, such as energy storage power stations, gas turbines, and hydropower stations.

[0047] Preferably, the specific method for obtaining the predicted power generation of uncontrollable power sources and the distribution of prediction errors in the virtual power plant is as follows: Obtain the meteorological prediction data on the bidding day, the historical meteorological prediction data for the first preset number of days before the bidding day, and the actual power generation of uncontrollable power sources for the second preset number of days before the bidding day; According to the meteorological prediction data on the bidding day and the historical meteorological prediction data for the third preset number of days before the bidding day, through a preset power generation prediction model, obtain the predicted power generation of uncontrollable power sources; where the third preset number and the second preset number are both less than the first preset number; According to the historical meteorological prediction data for the first preset number of days before the bidding day, through a preset power generation prediction model, obtain the predicted power generation of uncontrollable power sources for the second preset number of days on the bidding day; According to the predicted power generation and the actual power generation of uncontrollable power sources for the second preset number of days on the bidding day, obtain the prediction error data for the second preset number of uncontrollable power sources, and fit the prediction error data for the second preset number of uncontrollable power sources through a normal distribution to obtain the distribution of prediction errors of uncontrollable power sources.

[0048] Among them, the power generation prediction model is obtained by training a preset artificial neural network model with the historical meteorological prediction data for several days before the bidding day and the actual power generation of uncontrollable power sources. Specifically, in this embodiment, the bidding day, that is, the date of participating in the power market, the historical meteorological prediction data and the actual power generation of uncontrollable power sources for each day in the previous 3 months are selected as training data, and the preset artificial neural network model is trained with the historical meteorological prediction data and the actual power generation for each continuous 14 days, and the data on the 15th day is used as the test set. Therefore, a set of prediction data can be obtained from the data for each continuous 15 days. Among them, the artificial neural network model is a neural network model built manually. The number of input neurons is selected as the types of meteorological information, such as wind speed, wind direction, temperature, humidity, air pressure, and light intensity, etc. The input layer data is the historical meteorological prediction data per hour, the number of output neurons is 1, and the output layer data is the predicted power generation of uncontrollable power sources. The number of neurons in the hidden layer can be set to 11, but it is not limited to this and can be changed according to the specific prediction effect. The training function is selected as the trainlm function, and the node transfer function is selected as the purelin function.

[0049] After the above training, a power generation prediction model is obtained, and then the predicted power generation and the distribution of prediction errors of uncontrollable power sources are obtained according to the power generation prediction model. Specifically, in this embodiment, the first preset number is set to 90, the second preset number is set to 76, and the third preset number of days is 14.

[0050] By inputting the meteorological prediction data on the bidding date and the historical meteorological prediction data for the 14 days before the bidding date into the power generation prediction model, the predicted power generation of the uncontrollable power source on the bidding date is obtained. At the same time, according to the historical meteorological prediction data for the 90 days before the bidding date, taking 15 days as a period, continuously inputting into the power generation prediction model, the predicted power generation of the uncontrollable power source 76 days before the bidding date is obtained. In this embodiment, taking each hour as the research object, the predicted power generation is the power prediction data per hour. By comparing the predicted power generation of the uncontrollable power source 76 days before the bidding date with the actual power generation, the power prediction error data per hour within 76 days is obtained. Furthermore, through the method of normal distribution fitting, the probability distribution followed by these power prediction error data is obtained, and this is used as the prediction error distribution of the uncontrollable power source on the bidding date. See Figure 2 , which shows the frequency distribution histogram of the prediction error distribution of a wind power source for a certain hour and the fitted normal distribution.

[0051] S2: According to the prediction error distribution of the uncontrollable power source, several reserved capacities of the controllable power source and the deviation power of each reserved capacity are obtained.

[0052] Specifically, the specific method for obtaining several reserved capacities of the controllable power source on the bidding date according to the prediction error distribution of the uncontrollable power source on the bidding date is as follows: Obtain several probability groups; where each probability group includes a first probability value and a second probability value, and the first probability value is less than the second probability value; traverse each probability group, take the quantile of the prediction error distribution under the first probability value of the current probability group as the negative reserved capacity, and take the quantile of the prediction error distribution under the second probability value of the current probability group as the positive reserved capacity; combine the negative reserved capacity and the positive reserved capacity to obtain the reserved capacity of the controllable power source under the current probability group; after traversing, obtain several reserved capacities of the controllable power source on the bidding date. Among them, the probability groups can be set artificially in advance.

[0053] Preferably, in this embodiment, based on the 3σ theorem in statistics, in the normal distribution, the probability that the numerical distribution is in (μ 1 -σ 1 , μ 1 +σ 1 ) is 0.683, the probability that the distribution is in (μ 1 -2σ 1 , μ 1 +2σ 1 ) is 0.955, and the probability that the distribution is in (μ 1 -3σ 1 , μ 1 +3σ 1 ) is 0.997. Among them, μ 1 is the expectation of the normal distribution, and σ 1is the standard deviation of the normal distribution. Therefore, three reserved capacities are set for the controllable power sources in the virtual power plant for the uncontrollable power sources, which are 1σ, 2σ, and 3σ respectively. σ is the standard deviation of the prediction error distribution, and each reserved capacity includes a negative reserved capacity and a positive reserved capacity; specifically, the negative reserved capacities of the three reserved capacities are successively the negative value of the standard deviation of the prediction error distribution, twice the standard deviation of the prediction error distribution, and three times the standard deviation of the prediction error distribution, and the positive reserved capacities are successively the standard deviation of the prediction error distribution, twice the standard deviation of the prediction error distribution, and three times the standard deviation of the prediction error distribution.

[0054] Taking the selected reserved capacity of 1σ as an example, the expression of the prediction error distribution is as shown in Equation (1):

[0055]

[0056] Among them, f(x) is the prediction error distribution, and x is the random variable of the prediction error distribution.

[0057] Based on the prediction error distribution and combined with the normal distribution quantile, the power generation power fluctuation range of the uncontrollable power source at a certain confidence level can be obtained as shown in Equation (2):

[0058]

[0059] Among them, f -1 ( α ) and correspond to the quantiles of the set probability values α and respectively, which are obtained from the characteristics of the normal distribution. When , there is That is, the probability that the actual wind power is within the selected wind power fluctuation range is 68.26%. P is the predicted power generation power of the uncontrollable power source. Using this interval as the reserved capacity reserved by the controllable power source for the uncontrollable power source, that is, increasing the power generation capacity and reducing the power generation capacity.

[0060] After determining several reserved capacities on the bidding day of the controllable power source, the deviation power of each reserved capacity should also be considered. Among them, the deviation power includes both under-generation power and over-generation power. The specific method for obtaining the deviation power of each reserved capacity according to the prediction error distribution of the uncontrollable power source is as follows: Through Equation (3), the over-generation power P up of each reserved capacity is obtained:

[0061]

[0062] Through Equation (4), the under-generation power P down of each reserved capacity is obtained:

[0063]

[0064] Among them, α is the probability value corresponding to the negative reserved capacity in each reserved capacity as the quantile of the prediction error distribution, is the probability value corresponding to the positive reserved capacity in each reserved capacity as the quantile of the prediction error distribution.

[0065] Specifically, in this embodiment, taking the reserved capacity of 1σ as an example, the uncontrollable power sources include wind power sources and photovoltaic power sources, and the over-generation power P up (t) and under-generation power P down (t) in the t-th period of each reserved capacity are obtained through equations (5) and (6) respectively:

[0066]

[0067]

[0068] Among them, t represents the period serial number. In this embodiment, one hour is taken as one period.

[0069] S3: According to the predicted power generation of the uncontrollable power source, the maximum power generation of the controllable power source, the several reserved capacities of the controllable power source, and the deviation power of each reserved capacity, solve the preset power generation determination model to obtain the maximum profit of the virtual power plant participating in the power market and the power generation at the maximum profit under each reserved capacity.

[0070] Among them, the power generation determination model is constructed with the maximum profit of the virtual power plant participating in the power market as the optimization goal and the capacity constraints of each market in which the virtual power plant participates, the operation constraints of each controllable power source in the virtual power plant, and the reserved capacity constraints of the controllable power source in the virtual power plant for the uncontrollable power source as the constraint conditions.

[0071] Specifically, the profit of the virtual power plant participating in the power market is obtained from the daily operation costs of various power sources in the virtual power plant, the deviation power penalty costs, and the revenues from participating in various markets. In this embodiment, the optimization goal of the power generation determination model is shown in the following equation (7):

[0072] max Y E +Y RS +Y RU +Y RD -p vpp (7)

[0073] Among them, Y E 、Y RS 、Y RU and Y RDThe revenues obtained by the virtual power plant participating in the energy market, reserve market, upward regulation market, and downward regulation market in the power market can be calculated by Equation (8):

[0074]

[0075] Among them, p E (t), p RS (t), p RU (t), and p RD (t) are the prices of the energy market, reserve market, upward ramping market, and downward ramping market respectively, and P E (t), P RS (t), P RU (t), and P RD (t) are the powers of the virtual power plant participating in the energy market, reserve market, upward ramping market, and downward ramping market respectively.

[0076] p vpp is the total daily operating cost of the virtual power plant, as shown in Equation (9):

[0077] p vpp = p W + p PV + p ES + p GT + p H + p down - p up (9)

[0078] Among them, p W and p PV are the daily costs of wind power generation and photovoltaic power generation participating in the energy market respectively, p ES is the daily cost of the energy storage power station participating in the day-ahead market, P GT is the power generation cost of the gas turbine, P H is the daily cost of hydropower operation, p down and p up are the under-generation power penalty cost and over-generation power penalty cost of the virtual power plant respectively.

[0079] Specifically, for the cost characteristics of wind power and photovoltaic power, the expression of their costs mainly calculates the levelized cost during the life cycle by combining the initial investment cost with the depreciation rate. Therefore, the power generation cost models of wind power and photovoltaic power in the day-ahead market can be expressed as Equations (10) and (11):

[0080]

[0081]

[0082] Among them, PW (t) and P PV (t) are the capacities of wind power generation and photovoltaic power generation participating in the energy market, with the unit of MWh, C W and C PV are the levelized costs per hour of wind power generation and photovoltaic power generation respectively, with the unit of yuan / MWh.

[0083] For the energy storage power station, its costs mainly include the capacity cost of purchasing batteries once, the operation and maintenance cost, and the cost caused by the energy storage power station charging from the power grid, as shown in Equation (12):

[0084]

[0085] Among them, C bat is the battery capacity cost evenly distributed to each day for purchasing energy storage batteries once, C omES (t) is the operation and maintenance cost at the t-th hour, C chpur (t) is the cost of charging from the power grid at the t-th hour.

[0086] The operation and maintenance cost of the energy storage power station is as shown in Equation (13):

[0087]

[0088] Among them, C ESpom is the operation and maintenance cost per unit power in the whole life cycle, r is the discount rate, P ESrated is the maximum charge-discharge power of the energy storage power station, C ESeom is the operation and maintenance cost per unit capacity in the whole life cycle, W ES (t) is the electricity quantity of energy storage charging or discharging at the t-th hour, with the unit of MWh.

[0089] The cost of the energy storage power station purchasing electric energy from the energy market for charging can be calculated by Equation (14):

[0090] C chpur (t) = P chpur (t)p E (t) (14)

[0091] Among them, P chpur (t) is the power of the energy storage power station purchasing for charging from the power market at the t-th hour, p E (t) is the price of the energy market, with the unit of yuan / MWh.

[0092] The cost of gas turbine power generation consists of the operation cost (quadratic curve) and the start-stop cost, as shown in (15):

[0093]

[0094] Among them, PGT (t) is the operating power of the gas turbine, C GT0 , C GT1 and C GT2 are the constant term, the linear term and the quadratic term coefficient of the operating cost of the gas turbine, with the units of yuan, yuan / MWh, yuan / (MWh)2, λ su and λ sd are the prices for unit start-up and shut-down of the unit, with the unit of yuan, u su (t) and u sd (t) is a binary variable, indicating that the gas turbine starts or stops once in the t-th period.

[0095] The hydropower station is convenient to start and stop, and its start-up and shut-down costs can be ignored. The daily cost of hydropower operation is constructed as shown in Equation (16):

[0096]

[0097] where, P H (t) is the power of the hydropower station in the t-th period, C Hom is the operation and maintenance cost of the hydropower station, P H-max is the maximum power generation of the hydropower station, i.e., the installed capacity, C Hd is the cost of the unit power investment cost depreciated to each day, T H is the service life of the hydropower station, with the unit of year.

[0098] For the economic penalty caused by the deviation power, the under-generation power penalty cost is constructed as shown in Equation (17), and the over-generation power penalty cost is as shown in (18):

[0099]

[0100]

[0101] where, and respectively represent the penalty coefficients when the virtual power plant has under-generation power and over-generation power. Since a small amount of over-generation is settled at a price lower than the market price, the virtual power plant only makes less profit and does not suffer losses. Therefore, there are and

[0102] Specifically, the constraint conditions of the power generation power determination model include the capacity constraints of the virtual power plant participating in each market in the power market, the operation constraints of each controllable power source in the virtual power plant, and the reserved capacity constraints of the controllable power sources in the virtual power plant for the uncontrollable power sources.

[0103] Among them, the capacity constraints of the virtual power plant participating in each market are as shown in Equations (19) to (23):

[0104] 0 ≤ P E P(t) = P W P(t) + P PV P(t) + P disch P(t) + P GT P(t) + P H P(t) - P chvpp P(t)(19)

[0105] 0 ≤ P RS P(t) = P RS,ES1 P(t) + P RS,GT1 P(t) + P RS,H1 P(t)(20)

[0106] 0 ≤ P RU P(t) = P RU,ES1 P(t) + P RU,GT1 P(t) + P RU,H1 P(t)(21)

[0107] 0 ≤ P RD P(t) = P RD,ES1 P(t) + P RD,GT1 P(t) + P RD,H1 P(t)(22)

[0108] 0 ≤ P m,ES1 P(t), P m,GT1 P(t), P m,H1 P(t), m ∈ {RS, RU, RD} (23)

[0109] Among them, P disch P(t) is the discharge power of the energy storage power station, and P chvpp P(t) is the charging energy of the energy storage power station, indicating that the charging energy of the energy storage power station is obtained from within the virtual power plant. P m,ES1 P(t), P m,GT1 P(t) and P m,H1 P(t) (m ∈ {RS, RU, RD}) respectively represent the capacities of the energy storage power station, gas turbine, and hydropower station participating in the reserve market, upward regulation market, and downward regulation market, all of which are greater than 0. Equation (19) indicates that the capacity of the virtual power plant participating in the energy market is equal to the sum of the energies output by various physical entities to the power grid. Equations (20) to (22) respectively represent that the virtual power plant participates in the three auxiliary service markets, namely the reserve market, upward regulation market, and downward regulation market, and all are participated in by the three power sources of the energy storage power station, gas turbine, and hydropower station.

[0110] The operation constraints of each controllable power source in the virtual power plant include the energy storage power station constraint, gas turbine constraint, and hydropower station constraint. Among them, the energy storage power station constraint is shown in Equations (24) to (38):

[0111] P chP(t) = P chnet P(t)+P chpur P(t)(24)

[0112] 0 ≤ P ch P(t) ≤ [1 - M 1 P(t)]P ESmax (25)

[0113] 0 ≤ P disch P(t) ≤ M 1 P(t)P ESmax (26)

[0114] M 1 M(t) = 0,1 (27)

[0115] 0 ≤ P n,ES2 P(t), n ∈ {RU, RD} (28)

[0116] 0 ≤ P disch P(t)+P RS,ES P(t)+P RU,ES1 P(t)+P RU,ES2 P(t) ≤ P ESmax (29)

[0117] 0 ≤ P ch P(t)+P RD,ES1 P(t)+P RD,ES2 P(t) ≤ P ESmax (30)

[0118] - P ESmax ≤ P disch P(t)-P RD,ES1 P(t)-P RD,ES2 P(t) (31)

[0119]

[0120]

[0121] 0 ≤ P RS,ES P(t)+0.25P RU,ES1 P(t)+P RU,ES2 P(t) ≤ βE ESmax (34)

[0122] 0 ≤ 0.25P RD,ES1 P(t)+P RD,ES2 P(t) ≤ βE ESmax (35)

[0123]

[0124] E ESmin ≤ EES \((t)\leq E\) ESmax (37)

[0125] E ES (24)=E ES (0) (38)

[0126] Among them, equations (24)-(27) represent the constraints of energy storage charging and discharging. Only charging or discharging operations are allowed at the same time. Equation (28) represents the non-negativity of the power reserved by the energy storage for the UPS. Equation (29) means that the power of the energy storage power station participating in the power generation market discharge, the reserved reserve market, the upward ramping ancillary service market, and the discharge power reserved for the UPS cannot exceed the maximum rated power of the energy storage. Similarly, equation (30) means that the power of the energy storage power station for charging, the downward ramping ancillary service market, and the charging power reserved for the UPS cannot exceed the maximum rated power of the energy storage. Equation (31) means that the energy storage participating in the downward ramping market based on discharging and the charging capacity reserved for the UPS cannot exceed the charging power of the energy storage. Equations (32)-(36) further limit the capacity participating in each market in combination with the state of charge of the energy storage battery. The coefficient 0.25 is the equivalent conversion for the flexible peak shaving market dispatch duration of 15 minutes. \(\eta\) represents the charging and discharging power of the energy storage, and \(\beta\) represents the proportion of the capacity that the energy storage is allowed to participate in the ancillary service market in the maximum state of charge of the energy storage, and can take 0.1. At the same time, E ESmin 、E ESmax and E ES (t) represent the maximum state of charge, the minimum state of charge, and the state of charge at the beginning of the \(t\)th period of the energy storage respectively. Equations (37) and (38) are their constraint conditions.

[0127] The constraints of the gas turbine are shown in equations (39) to (43):

[0128] M 2 (t)P GTmin \(\leq P\) GT (t)+P RS,GT (t)+P RU,GT1 (t)+P RU,GT1 (t)\(\leq M\) 2 (t)P GTmax (39)

[0129] M 3 (t)P GTmin \(\leq P\) GT (t)-P RD,GT1 (t)-P RD,GT1 (t)\(\leq M\) 3 (t)P GTmax (40)

[0130] M 2 (t),M 3(t) = 0, 1 (41)

[0131] 0 ≤ P n,GT2 (t), n ∈ {RU, RD} (42)

[0132] -P GT,ramp ≤ P GT (t + 1) - P GT (t) ≤ P GT,ramp (43)

[0133] where M 2 (t), M 3 (t) are binary variables. Due to the minimum technical output of the gas turbine, Equation (39) indicates that the additional output of the gas turbine participating in the reserve market, downward regulation market, and reserved for uncontrollable power sources on the basis of power generation is between the maximum technical output P GTmin and the minimum technical output P GTmax , or equal to 0. Similarly, Equation (40) also restricts the reduced output of the gas turbine participating in the downward regulation market and reserved for uncontrollable power sources on the basis of power generation. Equation (42) is the non - negative constraint on the additional or reduced power reserved by the gas turbine for uncontrollable power sources, and Equation (43) represents the ramp - rate constraint of the gas turbine, where P GTramp is the maximum ramp - rate capacity of the gas turbine, in MW / h.

[0134] The hydropower station is as shown in Equations (44) to (47):

[0135] 0 ≤ P H (t) + P RS,H (t) + P RU,H1 (t) + P RU,H2 (t) ≤ P Hmax (44)

[0136] 0 ≤ P H (t) - P RD,H1 (t) - P RD,H2 (t) (45)

[0137] 0 ≤ P n,H2 (t), n ∈ {RU, RD} (46)

[0138]

[0139] where Equation (44) indicates that the sum of the power P RS,H (t) of the hydropower station participating in the reserve market, the power P RU,H1 (t) participating in the upward regulation market, and the additional output P RU,H2 (t) reserved for uncontrollable power sources is less than the maximum power P HmaxSimilarly, the power \(P\) of the hydropower station participating in the downward peak shaving market in Equation (45), and the reduced output \(P\) reserved for uncontrollable power sources RD,H1 (t) cannot exceed the power generation at the current moment. Equation (46) is the non - negative constraint on the additional or reduced power reserved for uncontrollable power sources by the hydropower station. Since the power generation of each hydropower station is affected by water resources and can be flexibly adjusted within a certain time period, Equation (47) represents the limitation on the total daily power generation of the hydropower station, and the daily allowable power generation is \(Q\). RD,H2 (t) cannot exceed the power generation at the current moment. Equation (46) is the non - negative constraint on the additional or reduced power reserved for uncontrollable power sources by the hydropower station. Since the power generation of each hydropower station is affected by water resources and can be flexibly adjusted within a certain time period, Equation (47) represents the limitation on the total daily power generation of the hydropower station, and the daily allowable power generation is \(Q\). Hmax 。

[0140] The reserved capacity constraints of controllable power sources for uncontrollable power sources in the virtual power plant are shown in Equations (48) and (49):

[0141] \(P\) RU,ES2 (t)+ \(P\) RU,GT2 (t)+ \(P\) RU,H2 (t)= - [\(\mu\) W (t)- \(\sigma\) W (t)] - [\(\mu\) PV (t)- \(\sigma\) PV (t)] (48)

[0142] \(P\) RD,ES2 (t)+ \(P\) RD,GT2 (t)+ \(P\) RD,H2 (t)= [\(\mu\) W (t)+ \(\sigma\) W (t)]+ [\(\mu\) PV (t)+ \(\sigma\) PV (t)] (49)

[0143] The above equations respectively represent the equality constraints on the additional or reduced output reserved for uncontrollable power sources by controllable power sources. Here, the power fluctuation range of uncontrollable power sources is one - fold of \(\sigma\).

[0144] By modeling the profit of the virtual power plant participating in the power market, the capacity constraints of each market in which the virtual power plant participates, the operation constraints of each controllable power source in the virtual power plant, and the reserved capacity constraints of controllable power sources for uncontrollable power sources in the virtual power plant, a power generation power determination model is obtained. It is a mixed - integer convex programming problem with a quadratic term in the objective function and can be solved using the CPLEX solver to obtain the global optimal solution.

[0145] Specifically, traverse each reserved capacity, and input the predicted power generation of uncontrollable power sources on the bidding date, the maximum power generation of controllable power sources on the bidding date, and the deviation power of the current reserved capacity and the current reserved capacity of controllable power sources into the power generation power determination model to obtain the maximum profit of the virtual power plant participating in the electricity market and the power generation power under the maximum profit at the current reserved capacity. After completing the traversal, the maximum profit of the virtual power plant participating in the electricity market and the power generation power under the maximum profit at each reserved capacity are obtained.

[0146] S4: Obtain the reserved capacity with the maximum profit of the virtual power plant participating in the electricity market among all reserved capacities, and use the power generation power under the maximum profit of the virtual power plant participating in the electricity market at this reserved capacity as the bidding capacity.

[0147] Specifically, select one reserved capacity with the maximum profit of the virtual power plant participating in the electricity market from all reserved capacities, and consider this reserved capacity as the optimal reserved capacity. When bidding for the virtual power plant, use this reserved capacity as the standard, and use the power generation power under the maximum profit of the virtual power plant participating in the electricity market at this reserved capacity as the bidding capacity to achieve the full consumption of uncontrollable power sources and reduce wind and light curtailment. Among them, the power generation power under the maximum profit includes the power generation power of controllable and uncontrollable power sources in the virtual power plant.

[0148] The method for determining the bidding capacity of the virtual power plant of the present invention, for uncontrollable power sources in the virtual power plant, such as wind power sources and photovoltaic power sources, based on the training of an artificial neural network model, predicts the power generation of uncontrollable power sources in the virtual power plant through meteorological information, and can obtain the predicted power generation of uncontrollable power sources. By analyzing the error between the predicted power generation and the actual power generation of multiple test sets, the probability distribution of the prediction error of uncontrollable power sources can be obtained. By selecting the prediction error interval at a certain probability as the reserved capacity that the remaining controllable power sources need to bear, the prediction technology is reasonably used to process the available power and fluctuation range of uncontrollable power sources. At the same time, based on the deviation power cost of uncontrollable power sources exceeding the reserved capacity, the daily operating cost and revenue of controllable power sources, an objective function for maximizing the profit of the virtual power plant is established. Further, for various types of power sources, the constraint conditions for their participation in the energy market, reserve market, and flexible peak shaving market are characterized, and a power generation power determination model for the virtual power plant in a multi-class electricity market environment is constructed. Moreover, the optimal reserved capacity is determined by comparing different reserved capacities. The economic penalty caused by the power volatility of uncontrollable power sources is fully considered, and measures to reduce its volatility by using controllable power sources are taken. Finally, a model for participating in multiple markets is constructed, providing technical support for various power sources in the virtual power plant to participate in multi-class electricity markets.

[0149] The following is an apparatus embodiment of the present invention, which can be used to implement the method embodiment of the present invention. For details not disclosed in the apparatus embodiment, please refer to the method embodiment of the present invention.

[0150] See Figure 3 , in another embodiment of the present invention, a virtual power plant bidding capacity determination system is provided, which can be used to implement the above-mentioned virtual power plant bidding capacity determination method. Specifically, the virtual power plant bidding capacity determination system includes a data acquisition module, a reserve and deviation determination module, a model solution module, and a bidding capacity determination module.

[0151] Among them, the data acquisition module is used to acquire the predicted power generation and predicted error distribution of uncontrollable power sources on the bidding day of the virtual power plant, and the maximum power generation of controllable power sources on the bidding day of the virtual power plant; the reserve and deviation determination module is used to obtain a plurality of reserve capacities on the bidding day of the controllable power source and the deviation power of each reserve capacity according to the predicted error distribution of the uncontrollable power source on the bidding day; the model solution module is used to solve a preset power generation determination model according to the predicted power generation of the uncontrollable power source on the bidding day, the maximum power generation of the controllable power source on the bidding day, and the plurality of reserve capacities and the deviation power of each reserve capacity on the bidding day of the controllable power source, and obtain the maximum profit of the virtual power plant participating in the power market and the power generation at the maximum profit under each reserve capacity; the bidding capacity determination module is used to obtain the reserve capacity with the maximum profit of the virtual power plant participating in the power market among all the reserve capacities, and use the power generation at the maximum profit of the virtual power plant participating in the power market under this reserve capacity as the bidding capacity.

[0152] Preferably, the data acquisition module includes an uncontrollable power source acquisition module and a controllable power source acquisition module.

[0153] Among them, the uncontrollable power source acquisition module is used to acquire the meteorological prediction data on the bidding day, the historical meteorological prediction data of the first preset number of days before the bidding day, and the actual power generation of the uncontrollable power source of the second preset number of days before the bidding day; according to the meteorological prediction data on the bidding day and the historical meteorological prediction data of the third preset number of days before the bidding day, through a preset power generation prediction model, obtain the predicted power generation of the uncontrollable power source on the bidding day; where the third preset number and the second preset number are both less than the first preset number; according to the historical meteorological prediction data of the first preset number of days before the bidding day, through a preset power generation prediction model, obtain the predicted power generation of the second preset number of days of the uncontrollable power source on the bidding day; according to the predicted power generation and actual power generation of the second preset number of days of the uncontrollable power source before the bidding day, obtain the predicted error data of the second preset number of the uncontrollable power source, and fit the predicted error data of the second preset number of the uncontrollable power source through a normal distribution to obtain the predicted error distribution of the uncontrollable power source on the bidding day.

[0154] The controllable power source acquisition module is used to acquire the maximum power generation of the controllable power sources in the virtual power plant.

[0155] Preferably, the reserve and deviation determination module includes a reserve capacity determination module. The reserve capacity determination module is used to obtain a number of probability groups; each probability group includes a first probability value and a second probability value, and the first probability value is less than the second probability value; traverse each probability group, and use the quantile of the prediction error distributed under the first probability value of the current probability group as the negative reserve capacity, and use the quantile of the prediction error distributed under the second probability value of the current probability group as the positive reserve capacity; combine the negative reserve capacity and the positive reserve capacity to obtain the reserve capacity of the controllable power source under the current probability group; after the traversal is completed, obtain a number of reserve capacities for the tender day of the controllable power source.

[0156] Preferably, the deviation power includes both under-generation power and over-generation power; the reserve and deviation determination module includes a deviation power determination module. The deviation power determination module is used to obtain the over-generation power P of each reserve capacity through the following formula up :

[0157]

[0158] Through the following formula, obtain the under-generation power P of each reserve capacity down :

[0159]

[0160] where f(x) is the prediction error distribution, x is the random variable of the prediction error distribution, μ is the expectation of the prediction error distribution, σ is the standard deviation of the prediction error distribution, α is the probability value corresponding to the negative reserve capacity in each reserve capacity as the quantile of the prediction error distribution, is the probability value corresponding to the positive reserve capacity in each reserve capacity as the quantile of the prediction error distribution.

[0161] In another embodiment of the present invention, a computer device is provided. The computer device includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function. The processor described in the embodiment of the present invention can be used for the operation of the method for determining the bidding capacity of a virtual power plant.

[0162] In another embodiment of the present invention, a storage medium is also provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space that stores the operating system of the terminal. And in this storage space, one or more instructions suitable for being loaded and executed by the processor are also stored. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the method for determining the bidding capacity of a virtual power plant in the above embodiments.

[0163] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0164] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0165] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0166] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, so that the instructions executed on the computer or other programmable devices provide steps for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent substitutions, and any modification or equivalent substitution that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for determining the bidding capacity of a virtual power plant, characterized in that, it includes the following steps: Obtain the predicted power generation and the predicted error distribution of the uncontrollable power sources in the virtual power plant on the bidding day, and the maximum power generation of the controllable power sources in the virtual power plant on the bidding day; Obtain a number of probability groups; each probability group includes a first probability value and a second probability value, and the first probability value is less than the second probability value; traverse each probability group, and use the quantile of the predicted error distribution at the first probability value of the current probability group as the negative reserve capacity, and use the quantile of the predicted error distribution at the second probability value of the current probability group as the positive reserve capacity; Combine the negative reserve capacity and the positive reserve capacity to obtain the reserve capacity of the controllable power sources under the current probability group; After the traversal is completed, obtain a number of reserve capacities of the controllable power sources on the bidding day; Obtain the deviation power of each reserve capacity, and the deviation power includes under-generation power and over-generation power; The over-generation power P of each reserved capacity is obtained by the following formula up and the under-generation power P down : Among them, f(x) is the prediction error distribution, x is the random variable of the prediction error distribution, μ is the expectation of the prediction error distribution, and σ1 is the current reserved capacity. α is the probability value corresponding to the negative reserved capacity in the current reserved capacity when it is used as the quantile of the prediction error distribution. is the probability value corresponding to the positive reserved capacity in the current reserved capacity when it is used as the quantile of the prediction error distribution. According to the predicted power generation of the uncontrollable power sources on the bidding day, the maximum power generation of the controllable power sources on the bidding day, the number of reserve capacities of the controllable power sources on the bidding day, and the deviation power of each reserve capacity, solve the preset power generation determination model to obtain the maximum profit of the virtual power plant participating in the electricity market and the power generation at the maximum profit under each reserve capacity; Obtain the reserve capacity with the maximum maximum profit of the virtual power plant participating in the electricity market among all the reserve capacities, and use the power generation at the maximum profit of the virtual power plant participating in the electricity market under this reserve capacity as the bidding capacity.

2. The method for determining the bidding capacity of a virtual power plant according to claim 1, characterized in that, the specific method for obtaining the predicted power generation and the predicted error distribution of the uncontrollable power sources in the virtual power plant is: Obtain the meteorological forecast data on the bidding day, the historical meteorological forecast data of the first preset number of days before the bidding day, and the actual power generation of the uncontrollable power sources on the second preset number of days before the bidding day; According to the meteorological forecast data on the bidding day and the historical meteorological forecast data of the third preset number of days before the bidding day, obtain the predicted power generation of the uncontrollable power sources on the bidding day through a preset power generation prediction model; wherein, both the third preset number and the second preset number are less than the first preset number; According to the historical meteorological forecast data of the first preset number of days before the bidding day, obtain the predicted power generation of the uncontrollable power sources on the second preset number of days before the bidding day through a preset power generation prediction model; According to the predicted power generation and the actual power generation of the uncontrollable power sources on the second preset number of days before the bidding day, obtain the predicted error data of the second preset number of the uncontrollable power sources, and fit the predicted error data of the second preset number of the uncontrollable power sources through a normal distribution to obtain the predicted error distribution of the uncontrollable power sources on the bidding day.

3. The method for determining the bidding capacity of a virtual power plant according to claim 2, characterized in that, the power generation prediction model is obtained by training a preset artificial neural network model with the historical meteorological forecast data of a number of days before the bidding day and the actual power generation of the uncontrollable power sources on a number of days before the bidding day.

4. The method for determining the bidding capacity of a virtual power plant according to claim 1, characterized in that, The reserved capacities include three, and each reserved capacity includes a negative reserved capacity and a positive reserved capacity; the negative reserved capacities of the three reserved capacities are successively the negative value of the standard deviation of the predicted error distribution, twice the negative value of the standard deviation of the predicted error distribution, and three times the negative value of the standard deviation of the predicted error distribution, and the positive reserved capacities are successively the standard deviation of the predicted error distribution, twice the standard deviation of the predicted error distribution, and three times the standard deviation of the predicted error distribution.

5. The method for determining the bidding capacity of a virtual power plant according to claim 1, characterized in that, the power generation power determination model is constructed with the maximum profit of the virtual power plant participating in the power market as the optimization objective and with the capacity constraints of each market in which the virtual power plant participates in the power market, the operation constraints of each controllable power source in the virtual power plant, and the reserved capacity constraints of the controllable power sources in the virtual power plant for the uncontrollable power sources as the constraint conditions.

6. A system for determining the bidding capacity of a virtual power plant based on the method for determining the bidding capacity of a virtual power plant according to claim 1, characterized in that, it includes: a data acquisition module, configured to acquire the predicted power generation power and the predicted error distribution of the uncontrollable power sources on the bidding day of the virtual power plant, and the maximum power generation power of the controllable power sources on the bidding day of the virtual power plant; a reserved and deviation determination module, configured to obtain several reserved capacities on the bidding day of the controllable power sources and the deviation power of each reserved capacity according to the predicted error distribution of the uncontrollable power sources on the bidding day; a model solving module, configured to solve a preset power generation power determination model according to the predicted power generation power of the uncontrollable power sources on the bidding day, the maximum power generation power of the controllable power sources on the bidding day, and several reserved capacities on the bidding day of the controllable power sources and the deviation power of each reserved capacity, to obtain the maximum profit of the virtual power plant participating in the power market and the power generation power under the maximum profit for each reserved capacity; a bidding capacity determination module, configured to obtain the reserved capacity with the maximum maximum profit of the virtual power plant participating in the power market among all the reserved capacities, and use the power generation power under the maximum profit of the virtual power plant participating in the power market under this reserved capacity as the bidding capacity.

7. A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the steps of the method for determining the bidding capacity of a virtual power plant according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method for determining the bidding capacity of a virtual power plant according to any one of claims 1 to 5 are implemented.

Images