Output scheduling method and apparatus for renewable energy power plant, and computer device, computer-readable storage medium and computer program product

Abstract

The present application relates to the technical field of power grids, and particularly relates to an output scheduling method and apparatus for a renewable energy power plant, and a computer device, a computer-readable storage medium and a computer program product. The method comprises: on the basis of a renewable energy output prediction scenario set for each renewable energy station in a renewable energy power plant, determining a target renewable energy output reference parameter and a target renewable energy output prediction error parameter of each renewable energy station, and on the basis of the target renewable energy output reference parameter and the target renewable energy output prediction error parameter of each renewable energy station, determining a renewable energy output uncertainty set for each renewable energy station; and by using the renewable energy output uncertainty set for each renewable energy station as a constraint condition, solving an output scheduling objective function pre-constructed for the renewable energy power plant, so as to obtain a target net output value of each renewable energy station, such that output scheduling is performed on each renewable energy station. By means of using the method, the function of an energy storage apparatus configured in a renewable energy power plant can be fully exerted.

Description

Power dispatching methods, devices, computer equipment, computer-readable storage media, and computer program products for new energy power plants Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for power dispatching of a new energy power plant. Background Technology

[0002] The output of new energy sources is highly unstable. New energy power plants often store excess new energy power in energy storage devices to effectively mitigate the instability of new energy output and enhance the reliability of the power output of new energy power plants.

[0003] However, some new energy power plants lack a scheduling mechanism for independently utilizing energy storage devices, resulting in the energy storage devices configured in new energy power plants not being fully utilized. Summary of the Invention

[0004] Therefore, it is necessary to address the technical problem that the role of energy storage devices configured in new energy power plants cannot be fully utilized, and to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can fully utilize the role of energy storage devices configured in new energy power plants.

[0005] Firstly, this application provides a method for dispatching the output of a new energy power plant, including:

[0006] Obtain a set of predicted renewable energy output scenarios for each renewable energy power station in a renewable energy power plant;

[0007] Based on the set of predicted renewable energy output scenarios for each renewable energy power station, the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station are determined. Based on the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station, the set of uncertainties in renewable energy output for each renewable energy power station is determined.

[0008] Using the uncertainty set of renewable energy output of each renewable energy power station as a constraint, the output scheduling objective function pre-constructed for the renewable energy power plant is solved to obtain the target net output value of each renewable energy power station; the target net output value includes the target renewable energy predicted output value and the target energy storage output value;

[0009] According to the target net output value of each new energy power station, the output of each new energy power station is scheduled.

[0010] In one embodiment, determining the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters for each renewable energy power station based on the renewable energy output prediction scenario set for each renewable energy power station includes:

[0011] For each new energy power station, a target new energy output prediction scenario is determined from the set of new energy output prediction scenarios of the new energy power station, where the corresponding new energy predicted output value is greater than that of other new energy output prediction scenarios.

[0012] Based on the predicted new energy output value of the target new energy output prediction scenario, initialize the new energy output benchmark parameters and the new energy output prediction error parameters;

[0013] Based on the set of new energy power output prediction scenarios, the new energy power output benchmark parameters and the new energy power output prediction error parameters are iteratively updated to obtain the target new energy power output benchmark parameters and target new energy power output prediction error parameters that meet the iteration conditions.

[0014] In one embodiment, the step of iteratively updating the renewable energy output benchmark parameters and the renewable energy output prediction error parameters based on the renewable energy output prediction scenario set to obtain target renewable energy output benchmark parameters and target renewable energy output prediction error parameters that satisfy the iteration conditions includes:

[0015] Based on the set of new energy power output prediction scenarios, the new energy power output benchmark parameters, and the new energy power output prediction error parameters, solve for the first and second parameters in the uncertainty region constraint function of the new energy power station;

[0016] If either the first parameter or the second parameter is greater than or equal to the condition parameter corresponding to the iteration condition, the new energy output benchmark parameter and the new energy output prediction error parameter are updated to obtain the updated new energy output benchmark parameter and the updated new energy output prediction error parameter.

[0017] The updated renewable energy output benchmark parameter is used as the new renewable energy output benchmark parameter, and the updated renewable energy output prediction error parameter is used as the new renewable energy output prediction error parameter. The steps of solving the first and second parameters in the uncertainty region constraint function of the renewable energy power station based on the renewable energy output prediction scenario set, the renewable energy output benchmark parameter, and the renewable energy output prediction error parameter are returned until the first and second parameters obtained are both less than the condition parameter. The corresponding renewable energy output benchmark parameter is determined as the target renewable energy output benchmark parameter, and the corresponding renewable energy output prediction error parameter is determined as the target renewable energy output prediction error parameter.

[0018] In one embodiment, updating the renewable energy output benchmark parameters and the renewable energy output prediction error parameters to obtain updated renewable energy output benchmark parameters and updated renewable energy output prediction error parameters includes:

[0019] The new energy output benchmark parameters are updated according to the preset first update step size to obtain the updated new energy output benchmark parameters.

[0020] The new energy output prediction error parameters are updated according to the preset second update step size to obtain the updated new energy output prediction error parameters.

[0021] In one embodiment, the initialization of the renewable energy output benchmark parameters and renewable energy output prediction error parameters based on the renewable energy output prediction value of the target renewable energy output prediction scenario includes:

[0022] Both the new energy output benchmark parameter and the new energy output prediction error parameter are initialized to half of the new energy predicted output value corresponding to the target new energy output prediction scenario.

[0023] In one embodiment, the pre-built output scheduling objective function is constructed in the following manner:

[0024] For each scheduling period of the new energy power plant, determine the unit penalty price under the scheduling period, determine the time-of-use electricity price of the new energy power plant under the scheduling period, and determine the day-ahead new energy predicted output value and day-ahead new energy output predicted error value of each new energy power plant under the scheduling period.

[0025] Determine the charging efficiency and discharging efficiency of the energy storage device of each new energy power station, and determine the preset prediction error threshold corresponding to each new energy power station;

[0026] Based on the unit penalty price for each scheduling period, the time-of-use price of the new energy power plant for each scheduling period, the day-ahead predicted output value and the day-ahead predicted output error value of each new energy power station for each scheduling period, the charging efficiency and the discharging efficiency of the energy storage device of each new energy power station, and the preset prediction error threshold corresponding to each new energy power station, an output scheduling objective function for the new energy power plant is constructed with the goal of maximizing the output revenue of the new energy power plant.

[0027] Secondly, this application also provides a power output dispatching device for a new energy power plant, comprising:

[0028] The scenario set acquisition module is used to acquire the scenario set for predicting the new energy output of each new energy power station in the new energy power plant;

[0029] The power output information determination module is used to determine the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station based on the new energy power output prediction scenario set for each new energy power station, and to determine the new energy power output uncertainty set for each new energy power station based on the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station.

[0030] The objective function solving module is used to solve the pre-constructed output scheduling objective function for each new energy power plant, using the set of uncertainties in the new energy output of each new energy power plant as constraints, to obtain the target net output value of each new energy power plant; the target net output value includes the target predicted new energy output value and the target energy storage output value;

[0031] The power station output scheduling module is used to schedule the output of each new energy power station according to the target net output value of each new energy power station.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0033] Obtain a set of predicted renewable energy output scenarios for each renewable energy power station in a renewable energy power plant;

[0034] Based on the set of predicted renewable energy output scenarios for each renewable energy power station, the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station are determined. Based on the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station, the set of uncertainties in renewable energy output for each renewable energy power station is determined.

[0035] Using the uncertainty set of renewable energy output of each renewable energy power station as a constraint, the output scheduling objective function pre-constructed for the renewable energy power plant is solved to obtain the target net output value of each renewable energy power station; the target net output value includes the target renewable energy predicted output value and the target energy storage output value;

[0036] According to the target net output value of each new energy power station, the output of each new energy power station is scheduled.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] Obtain a set of predicted renewable energy output scenarios for each renewable energy power station in a renewable energy power plant;

[0039] Based on the set of predicted renewable energy output scenarios for each renewable energy power station, the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station are determined. Based on the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station, the set of uncertainties in renewable energy output for each renewable energy power station is determined.

[0040] Using the uncertainty set of renewable energy output of each renewable energy power station as a constraint, the output scheduling objective function pre-constructed for the renewable energy power plant is solved to obtain the target net output value of each renewable energy power station; the target net output value includes the target renewable energy predicted output value and the target energy storage output value;

[0041] According to the target net output value of each new energy power station, the output of each new energy power station is scheduled.

[0042] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0043] Obtain a set of predicted renewable energy output scenarios for each renewable energy power station in a renewable energy power plant;

[0044] Based on the set of predicted renewable energy output scenarios for each renewable energy power station, the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station are determined. Based on the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station, the set of uncertainties in renewable energy output for each renewable energy power station is determined.

[0045] Using the uncertainty set of renewable energy output of each renewable energy power station as a constraint, the output scheduling objective function pre-constructed for the renewable energy power plant is solved to obtain the target net output value of each renewable energy power station; the target net output value includes the target renewable energy predicted output value and the target energy storage output value;

[0046] According to the target net output value of each new energy power station, the output of each new energy power station is scheduled.

[0047] The aforementioned power output scheduling method, device, computer equipment, computer-readable storage medium, and computer program product for new energy power plants first obtain a set of predicted new energy output scenarios for each new energy station in the new energy power plant. Then, based on the predicted new energy output scenarios for each new energy station, the target new energy output benchmark parameters and target new energy output prediction error parameters for each new energy station are determined. Based on these parameters, the new energy output uncertainty set for each new energy station is also determined. Next, using the new energy output uncertainty set for each new energy station as a constraint, a pre-constructed power output scheduling objective function for the new energy power plant is solved to obtain the target net power output value for each new energy station. The target net power output value includes the target predicted new energy output value and the target energy storage output value. Finally, power output scheduling is performed for each new energy station according to its target net power output value. In this way, by using the set of predicted renewable energy output scenarios for each renewable energy power plant, the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters for constructing the renewable energy output uncertainty set can be determined, thereby constructing the renewable energy output uncertainty set for that renewable energy power plant. Based on the renewable energy output uncertainty set for each renewable energy power plant, the pre-constructed output scheduling objective function for the renewable energy power plant can be solved to obtain the target renewable energy predicted output value and target energy storage output value for each renewable energy power plant, thus enabling output scheduling for each renewable energy power plant. The renewable energy power plant output scheduling method based on the above process can determine the target renewable energy predicted output value and target energy storage output value for each renewable energy power plant, allowing the energy storage devices configured in the renewable energy power plant to fully play their role. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 is a flowchart illustrating the power output scheduling method for a new energy power plant in one embodiment;

[0050] Figure 2 is a flowchart illustrating the steps of determining the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters for each renewable energy power station based on the renewable energy output prediction scenario set for each renewable energy power station in one embodiment.

[0051] Figure 3 is a flowchart illustrating the steps in one embodiment of iteratively updating the new energy output benchmark parameters and new energy output prediction error parameters based on a set of new energy output prediction scenarios to obtain the target new energy output benchmark parameters and target new energy output prediction error parameters that meet the iteration conditions.

[0052] Figure 4 is a flowchart illustrating the steps of constructing the output scheduling objective function in one embodiment;

[0053] Figure 5 is a flowchart illustrating the power output scheduling method for a new energy power plant in another embodiment;

[0054] Figure 6 is a structural block diagram of the power output dispatching device of a new energy power plant in one embodiment;

[0055] Figure 7 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0058] In one embodiment, as shown in Figure 1, a method for power output scheduling of a new energy power plant is provided. This embodiment illustrates the application of this method to a server. It is understood that this method can also be applied to a terminal, or to a system including both a server and a terminal, and is implemented through interaction between the server and the terminal. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. In this embodiment, the method includes the following steps:

[0059] Step S102: Obtain the set of new energy output prediction scenarios for each new energy power station in the new energy power plant.

[0060] A new energy power plant includes new energy generator sets and energy storage devices. A new energy power plant includes at least one new energy power station; each new energy power station consists of at least one new energy generator set; and each new energy power station is equipped with at least one energy storage device to store excess new energy power from the generator sets at that power station.

[0061] Specifically, the server first obtains a set of predicted renewable energy output scenarios for each renewable energy power station of the renewable energy power plant.

[0062] Step S104: Based on the set of new energy power output prediction scenarios for each new energy power station, determine the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station. Based on the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station, determine the set of new energy power output uncertainties for each new energy power station.

[0063] Among them, the target renewable energy output benchmark parameter is used to characterize the benchmark situation of renewable energy output of renewable energy power plants; in practical applications, the target renewable energy output benchmark parameter is the renewable energy output benchmark value.

[0064] Among them, the target new energy power output prediction error parameter is used to characterize the reference situation of the new energy power output prediction error of the new energy power station; the new energy power output prediction error is used to characterize the error between the target new energy predicted power output value and the actual new energy power output value; in practical applications, the new energy power output prediction error can be the error value between the target new energy predicted power output value and the actual new energy power output value, or it can be the fluctuation value between the two, where the fluctuation value is between [-1,1].

[0065] Among them, the uncertainty set of new energy power output is characterized by uncertainty variables to represent the uncertainty of new energy power stations in the power output process.

[0066] Specifically, for each renewable energy power station, the server determines, based on the renewable energy output prediction field set of that power station, a target renewable energy output benchmark parameter to characterize the benchmark situation of the renewable energy output of that power station, and a target renewable energy output prediction error parameter to characterize the reference situation of the renewable energy output prediction error of that power station; then, based on the target renewable energy output benchmark parameter and the target renewable energy output prediction error parameter, a renewable energy output uncertainty set is constructed for that power station, which characterizes the uncertainty of the power station in the output process through uncertainty variables.

[0067] In practical applications, the uncertainty set of new energy output is a box-shaped uncertainty set.

[0068] In practical applications, the uncertainty set of new energy output is shown in Equation 1:

[0069]

[0070] in, This refers to a collection of new energy power stations under a new energy power plant; 'i' represents the identifier of the new energy power station; U i Let P' be the set of uncertainties in the renewable energy output of the i-th renewable energy power station. i The target predicted new energy output value for the i-th new energy power station; Let be the target renewable energy output prediction error parameter for the i-th renewable energy power station; This represents the average value of the target renewable energy output prediction error parameters for each renewable energy power station. Let r be the target renewable energy output benchmark parameter for the i-th renewable energy power station; i Let r be the uncertainty variable of the new energy source for the i-th new energy power station. i ∈[-1,1]; ||·|| denotes the norm.

[0071] Furthermore, according to duality theory, based on Equation 1 above, we can obtain the equality constraints shown in Equation 2:

[0072]

[0073] Where M is the preset error threshold for predicting new energy output, which can be either the error value threshold or the error rate threshold; N represents the norm, usually referring to the 1-norm, 2-norm, or ∞-norm.

[0074] Step S106: Using the uncertainty set of new energy output of each new energy power station as a constraint, solve the output scheduling objective function pre-constructed for the new energy power plant to obtain the target net output value of each new energy power station.

[0075] The output scheduling objective function aims to maximize the revenue of new energy power plants during the output process. The revenue of new energy power plants during the output process mainly considers the following two factors: the net output revenue of new energy power plants (including new energy output and energy storage output), and the penalty cost caused by the error between the predicted output value of the target new energy and the actual output value of the new energy.

[0076] The target net power output includes the target predicted power output of new energy sources and the target power output of energy storage.

[0077] Among them, the target new energy predicted output value refers to the new energy predicted output value of the new energy power station, and the target energy storage output value refers to the energy storage output value of the energy storage device corresponding to the new energy power station.

[0078] Specifically, the server uses the set of uncertainties in the renewable energy output of each renewable energy power station as a constraint on the pre-constructed output scheduling objective function for the renewable energy power plant. Combined with other constraints of the output scheduling objective function, the server solves the output scheduling objective function to obtain the target renewable energy predicted output value and the target energy storage output value for each renewable energy power station.

[0079] Step S108: Dispatch the output of each new energy power station according to the target net output value of each new energy power station.

[0080] Specifically, for each new energy power station, the server schedules the output of the new energy power station according to the target new energy predicted output value and the target energy storage output value, so that the new energy power station outputs new energy and energy storage power according to the corresponding target new energy predicted output value and target energy storage output value.

[0081] In the aforementioned power output scheduling method for new energy power plants, firstly, the server obtains a set of predicted new energy power output scenarios for each new energy power station in the new energy power plant; then, based on the set of predicted new energy power output scenarios for each new energy power station, the server determines the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station, and based on the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station, determines the set of uncertainties in new energy power output for each new energy power station; next, using the set of uncertainties in new energy power output for each new energy power station as constraints, the server solves the pre-constructed power output scheduling objective function for the new energy power plant to obtain the target net power output value for each new energy power station; the target net power output value includes the target predicted new energy power output value and the target energy storage power output value; finally, the server performs power output scheduling for each new energy power station according to the target net power output value for each new energy power station. In this way, by using the set of renewable energy output prediction scenarios for each renewable energy power plant, the server can determine the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters used to construct the renewable energy output uncertainty set, thereby constructing the renewable energy output uncertainty set for that renewable energy power plant. Based on the renewable energy output uncertainty set for each renewable energy power plant, the server can solve the pre-constructed output scheduling objective function for the renewable energy power plant, obtaining the target renewable energy predicted output value and target energy storage output value for each renewable energy power plant, and thus enabling output scheduling for each renewable energy power plant. Based on the above process, the renewable energy power plant output scheduling method allows the server to determine the target renewable energy predicted output value and target energy storage output value for each renewable energy power plant, ensuring that the energy storage devices configured in the renewable energy power plant can fully play their role.

[0082] In an exemplary embodiment, as shown in Figure 2, step S104 above, based on the set of new energy power output prediction scenarios for each new energy power station, determines the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station, specifically including the following steps:

[0083] Step S202: For each new energy power station, determine the target new energy power output prediction scenario from the set of new energy power output prediction scenarios of the new energy power station, where the corresponding new energy predicted power output value is greater than that of the other new energy power output prediction scenarios.

[0084] Step S204: Based on the predicted power output value of the target new energy power output prediction scenario, initialize the new energy power output benchmark parameters and the new energy power output prediction error parameters.

[0085] Step S206: Based on the set of new energy power output prediction scenarios, iteratively update the new energy power output benchmark parameters and new energy power output prediction error parameters to obtain the target new energy power output benchmark parameters and target new energy power output prediction error parameters that meet the iteration conditions.

[0086] Each new energy power output prediction scenario has a corresponding new energy power output prediction value.

[0087] The iteration condition can be the number of iterations or the corresponding condition parameter.

[0088] Specifically, for each renewable energy power station, the server determines the target renewable energy output baseline parameters and target renewable energy output prediction error parameters as follows:

[0089] First, the server determines the new energy power output prediction scenario with the largest new energy power output value from the set of new energy power output prediction scenarios of the new energy power station, and identifies this new energy power output prediction scenario as the target new energy power output prediction scenario.

[0090] Then, the server initializes the renewable energy output benchmark parameters and renewable energy output prediction error parameters based on the renewable energy output prediction value of the target renewable energy output prediction scenario.

[0091] Next, the server iteratively updates the renewable energy output benchmark parameters and renewable energy output prediction error parameters based on the occurrence probability and renewable energy output prediction value of each renewable energy output prediction scenario in the renewable energy output prediction scenario set. This process continues until the updated renewable energy output benchmark parameters and renewable energy output prediction error parameters meet the iteration conditions. The updated renewable energy output benchmark parameters that meet the iteration conditions are then determined as the target renewable energy output benchmark parameters, and the updated renewable energy output prediction error parameters that meet the iteration conditions are also determined as the target renewable energy output prediction error parameters.

[0092] In this embodiment, the server, based on the set of renewable energy output prediction scenarios for renewable energy power plants, can initialize the renewable energy output benchmark parameters and renewable energy output prediction error parameters for the renewable energy power plants, and iteratively update the renewable energy output benchmark parameters and renewable energy output prediction error parameters to obtain the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters for the renewable energy power plants. The above process fully considers the actual situation of different renewable energy output prediction scenarios, thus improving the robustness of the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters, thereby improving the reliability of the target net output value obtained in subsequent solutions.

[0093] In an exemplary embodiment, as shown in Figure 3, step S206 above, based on the set of new energy power output prediction scenarios, iteratively updates the new energy power output benchmark parameters and new energy power output prediction error parameters to obtain the target new energy power output benchmark parameters and target new energy power output prediction error parameters that meet the iteration conditions. Specifically, this includes the following steps:

[0094] Step S302: Based on the set of new energy power output prediction scenarios, the new energy power output benchmark parameters, and the new energy power output prediction error parameters, solve for the first and second parameters in the uncertainty region constraint function of the new energy power station.

[0095] Step S304: If either the first parameter or the second parameter is greater than or equal to the condition parameter corresponding to the iteration condition, update the new energy power output benchmark parameter and the new energy power output prediction error parameter to obtain the updated new energy power output benchmark parameter and the updated new energy power output prediction error parameter.

[0096] Step S306: The updated renewable energy output benchmark parameter is used as the new renewable energy output benchmark parameter, and the updated renewable energy output prediction error parameter is used as the new renewable energy output prediction error parameter. The process returns to the step of solving the first and second parameters in the uncertainty region constraint function of the renewable energy power station based on the renewable energy output prediction scenario set, the renewable energy output benchmark parameter, and the renewable energy output prediction error parameter. This process continues until both the first and second parameters obtained are less than the condition parameters. The corresponding renewable energy output benchmark parameter is then determined as the target renewable energy output benchmark parameter, and the corresponding renewable energy output prediction error parameter is determined as the target renewable energy output prediction error parameter.

[0097] Among them, the new energy power output benchmark parameter determined as the target new energy power output benchmark parameter refers to the new energy power output benchmark parameter that is calculated to satisfy both the first parameter and the second parameter of the condition parameter; the new energy power output prediction error parameter determined as the target new energy power output prediction error parameter refers to the new energy power output prediction error parameter that is calculated to satisfy both the first parameter and the second parameter of the condition parameter.

[0098] Specifically, the server iteratively updates the renewable energy output benchmark parameters and renewable energy output prediction error parameters as follows:

[0099] First, for each renewable energy power station, the server substitutes the occurrence probability and predicted renewable energy output value of each renewable energy output prediction scenario corresponding to that power station, as well as the renewable energy output benchmark parameters and renewable energy output prediction error parameters, into the uncertainty region constraint function of that power station to solve for the first and second parameters in the uncertainty region constraint function; whereby the uncertainty region constraint function is shown in Equation 3:

[0100]

[0101] Among them, Ω i Let be the constraint function for the uncertainty region of the i-th renewable energy power station; Let P be the set of predicted renewable energy output scenarios for the i-th renewable energy power station, where k is the identifier of the predicted renewable energy output scenario; i,k P′ represents the probability of the k-th renewable energy output prediction scenario occurring at the i-th renewable energy power station. i,k θ1 is the predicted renewable energy output value for the k-th renewable energy output prediction scenario of the i-th renewable energy power station; θ1 is the first parameter; θ ∞ This is the second parameter.

[0102] Then, if either the first parameter or the second parameter obtained from the calculation is greater than or equal to the condition parameter corresponding to the iteration condition, the server updates the new energy power output benchmark parameter and the new energy power output prediction error parameter to obtain the updated new energy power output benchmark parameter and the updated new energy power output prediction error parameter.

[0103] Next, the server uses the updated renewable energy output benchmark parameters as the new renewable energy output benchmark parameters and the updated renewable energy output prediction error parameters as the new renewable energy output prediction error parameters, and returns to step S302 to continue calculating the new first parameter and the new second parameter until both the calculated first parameter and the second parameter are less than the condition parameters corresponding to the iteration conditions. Then, the renewable energy output benchmark parameters that satisfy the first and second parameters are determined as the target renewable energy output benchmark parameters, and the renewable energy output prediction error parameters that satisfy the first and second parameters are determined as the target renewable energy output prediction error parameters.

[0104] In this embodiment, the server, based on the set of renewable energy output prediction scenarios for renewable energy power plants and the constraint function of the uncertainty region of renewable energy power plants, can solve for the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters of renewable energy power plants. The above process fully considers the actual situation and uncertainty factors of different renewable energy output prediction scenarios, thus improving the robustness of the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters, and thereby improving the reliability of the target net output value obtained in the subsequent solution.

[0105] In an exemplary embodiment, step S304 above, updating the new energy power output benchmark parameters and the new energy power output prediction error parameters to obtain updated new energy power output benchmark parameters and updated new energy power output prediction error parameters, specifically includes the following: updating the new energy power output benchmark parameters according to a preset first update step size to obtain updated new energy power output benchmark parameters; updating the new energy power output prediction error parameters according to a preset second update step size to obtain updated new energy power output prediction error parameters.

[0106] Specifically, this application pre-sets a first update step size for the new energy power output benchmark parameter and a second update step size for the new energy power output prediction error parameter. When either the first parameter or the second parameter calculated by the server is greater than or equal to the condition parameter, as shown in Formula 4, the new energy power output benchmark parameter is updated according to the first update step size to obtain the updated new energy power output benchmark parameter. Then, the new energy power output prediction error parameter is updated according to the pre-set second update step size to obtain the updated new energy power output prediction error parameter.

[0107]

[0108] Where υ is the first update step size and τ is the second update step size; To update the benchmark parameters for new energy power output, To update the error parameters for predicting the output of new energy sources.

[0109] In this embodiment, the server can iteratively update the renewable energy output benchmark parameters and renewable energy output prediction error parameters based on a preset update step size.

[0110] In an exemplary embodiment, step S204 above, which initializes the new energy output benchmark parameter and the new energy output prediction error parameter based on the new energy predicted output value of the target new energy output prediction scenario, specifically includes the following: both the new energy output benchmark parameter and the new energy output prediction error parameter are initialized to half of the new energy predicted output value corresponding to the target new energy output prediction scenario.

[0111] Specifically, when initializing the renewable energy output benchmark parameters and renewable energy output prediction error parameters, the server first initializes the renewable energy output benchmark parameters to half of the renewable energy predicted output value corresponding to the target renewable energy output prediction scenario. Then, it initializes the renewable energy output prediction error parameters to the difference between the renewable energy predicted output value corresponding to the target renewable energy output prediction scenario and the initialized renewable energy output benchmark parameters. Since the initialized renewable energy output benchmark parameters are half of the renewable energy predicted output value corresponding to the target renewable energy output prediction scenario, the difference between the renewable energy predicted output value corresponding to the target renewable energy output prediction scenario and the initialized renewable energy output benchmark parameters is also actually half of the renewable energy predicted output value corresponding to the target renewable energy output prediction scenario. That is, the renewable energy output prediction error parameters are also initialized to half of the renewable energy predicted output value corresponding to the target renewable energy output prediction scenario.

[0112] In this embodiment, the server can initialize the new energy output benchmark parameters and new energy output prediction error parameters by using the new energy predicted output value of the target new energy output prediction scenario.

[0113] In an exemplary embodiment, the condition parameter corresponding to the iterative condition in the iterative update of the renewable energy output benchmark parameter and the renewable energy output prediction error parameter in this application is half of the renewable energy predicted output value of the target renewable energy output prediction scenario.

[0114] In an exemplary embodiment, as shown in FIG4, the pre-built output scheduling objective function in any embodiment of this application is constructed through the following steps:

[0115] Step S402: For each scheduling period in the various scheduling periods of the new energy power plant, determine the unit penalty price under the scheduling period, determine the time-of-use electricity price of the new energy power plant under the scheduling period, and determine the day-ahead new energy predicted output value and the day-ahead new energy output predicted error value of each new energy power plant under the scheduling period.

[0116] Step S404: Determine the charging efficiency and discharging efficiency of the energy storage device for each new energy power station, and determine the preset prediction error threshold for each new energy power station.

[0117] Step S406: Based on the unit penalty price under each scheduling period, the time-of-use price of the new energy power plant under each scheduling period, the day-ahead predicted output value and day-ahead predicted output error value of each new energy power plant under each scheduling period, the charging efficiency and discharging efficiency of the energy storage device of each new energy power plant, and the preset prediction error threshold corresponding to each new energy power plant, the output scheduling objective function of the new energy power plant is constructed with the goal of maximizing the output revenue of the new energy power plant.

[0118] The unit penalty price refers to the unit penalty cost for the error between the predicted output value of the target new energy source and the actual output value of the new energy source and the preset prediction error threshold; the preset prediction error threshold is used to constrain the error range between the predicted output value of the target new energy source and the actual output value of the new energy source.

[0119] Among them, time-of-use pricing is the price at which new energy power plants sell electricity to the public during the corresponding dispatch period.

[0120] Among them, the predicted output value of new energy sources refers to the predicted output value of target new energy sources in the corresponding dispatch period of the previous day.

[0121] Among them, the current daytime renewable energy output forecast error value refers to the renewable energy output forecast error value under the corresponding dispatch period on the previous day.

[0122] Specifically, for each scheduling period of a new energy power plant, the unit penalty price for that scheduling period is first determined, the time-of-use price for that new energy power plant during that scheduling period is determined, and the day-ahead predicted output value and day-ahead predicted output error value for each new energy power station of that new energy power plant during that scheduling period are determined.

[0123] Next, for each new energy power station of the new energy power plant, the server determines the charging efficiency and discharging efficiency of the energy storage device configured in the new energy power station, as well as the corresponding preset prediction error threshold for the new energy power station.

[0124] Finally, the server combines the unit penalty price for each scheduling period, the time-of-use price of the new energy power plant for each scheduling period, the daily predicted output value and daily predicted output error value of each new energy power station for each scheduling period, the charging efficiency and discharging efficiency of the energy storage device of each new energy power station, and the preset prediction error threshold corresponding to each new energy power station. The server constructs the output scheduling objective function of the new energy power plant with the optimization objective of maximizing the output revenue of the new energy power plant between the target net output (including the target new energy predicted output and energy storage output) and the penalty cost caused by the error between the target new energy predicted output value and the actual new energy output value.

[0125] In practical applications, the output scheduling objective function of new energy power plants is shown in Formula 5:

[0126]

[0127] Where T is the set of scheduling periods for new energy power plants, and t is the identifier of the scheduling period for new energy power plants; ρ t P represents the time-of-use electricity price for new energy power plants during the t-th dispatch period;i,t Let the target net output value of the i-th renewable energy power station in the t-th scheduling period be (including the target renewable energy predicted output value and the target energy storage output value, and the target net output value is the variable to be solved in the output scheduling objective function); For the i-th renewable energy power station during the t-th scheduling period, if the actual output of the renewable energy is higher than the predicted output of the target renewable energy, the penalty fee is incurred because the error between the actual output of the renewable energy and the predicted output of the target renewable energy exceeds a preset prediction error threshold. For the i-th renewable energy power station, during the t-th scheduling period, if the actual output of renewable energy is lower than the target renewable energy predicted output, the penalty fee is incurred because the error between the actual output of renewable energy and the target renewable energy predicted output exceeds a preset prediction error threshold.

[0128] in, and This can be further expressed as Formula 6:

[0129]

[0130] Among them, the current forecast error value of new energy power output includes and This represents the positive value of the day-ahead renewable energy output prediction error for the i-th renewable energy power station during the t-th scheduling period (the error value when the actual renewable energy output is higher than the target renewable energy prediction output). This represents the negative value of the day-ahead renewable energy output prediction error for the i-th renewable energy power station during the t-th scheduling period (the error value when the actual renewable energy output is lower than the target renewable energy prediction output); it is easy to understand that... and One of them is zero.

[0131] Where, Δe′ i The preset prediction error threshold is the i-th new energy power station; Let be the day-ahead predicted power output of the i-th renewable energy power station during the t-th dispatch period; Let be the charging efficiency of the energy storage device at the i-th renewable energy power station. Let θ be the discharge efficiency of the energy storage device at the i-th renewable energy power station; t Let be the unit penalty price for the t-th scheduling period.

[0132] in, Let be the charging power of the energy storage device at the i-th renewable energy power station during the t-th dispatch period, used to reduce the error between the predicted output value and the actual output value of the target renewable energy. Let be the discharge power of the energy storage device at the i-th renewable energy power station during the t-th dispatch period, used to reduce the error between the predicted and actual output of the target renewable energy source. It is easy to understand that... and For variables.

[0133] In this embodiment, the server, based on information such as the unit penalty price, time-of-use price, day-ahead predicted output of new energy, day-ahead predicted output error, charging efficiency, discharging efficiency, and preset prediction error threshold of the new energy power plant, can construct an output scheduling objective function for the new energy power plant with the optimization objective of maximizing the revenue of the new energy power plant at the target net output (including the target predicted output of new energy and energy storage output) and the penalty cost caused by the error between the target predicted output value and the actual output value of new energy. Based on the constructed output scheduling objective function, the output revenue of the new energy power plant can be maximized between the target net output revenue and the penalty cost.

[0134] It should be noted that in related technologies, the output scheduling objective function as shown in Formulas 5 and 6 above is usually subject to the following constraints:

[0135] First, there exists a predicted output constraint as shown in Equation 7:

[0136]

[0137] Secondly, there exists a net output constraint as shown in Formula 8:

[0138]

[0139] Furthermore, there are other physical constraints, mainly including constraints on the connection of energy storage SOC (State of Charge) and the number of energy storage cycles, which are unified as shown in Formula 9:

[0140] g(x)≤0 (Formula 9)

[0141] As shown in Formula 7, the predicted output constraint assumes that the new energy power plant has a relatively accurate predicted output value for the new energy power plant and carries out the output scheduling. However, in actual operation, the prediction accuracy of the new energy predicted output value is often low. This means that in the above output scheduling objective function, the predicted output constraint using 0 to the new energy predicted output value as the output boundary of the new energy power plant may deviate far from the optimal solution under the actual situation, and may also lead to the optimization result being too conservative.

[0142] In the power output dispatching method for new energy power plants provided in this application, the power output uncertainty set of new energy as shown in Formula 1 is used to replace the predicted power output constraint shown in Formula 7. By extracting the uncertainty data related to new energy, the predicted power output constraint of new energy power plants is reconstructed. This reduces the conservatism of the power output dispatching objective function while improving the economy and ensuring the engineering implementation value of the power output dispatching objective function.

[0143] In an exemplary embodiment, as shown in Figure 5, another method for power output scheduling of a new energy power plant is provided. Taking the application of this method to a server as an example, the method includes the following steps:

[0144] Step S502: Obtain the set of new energy output prediction scenarios for each new energy power station in the new energy power plant.

[0145] Step S504: For each new energy power station, determine the target new energy power output prediction scenario from the set of new energy power output prediction scenarios of the new energy power station, where the corresponding new energy predicted power output value is greater than that of the other new energy power output prediction scenarios.

[0146] Step S506: Based on the predicted power output value of the target renewable energy power output prediction scenario, initialize the renewable energy power output benchmark parameters and the renewable energy power output prediction error parameters.

[0147] Step S508: Based on the set of new energy power output prediction scenarios, iteratively update the new energy power output benchmark parameters and new energy power output prediction error parameters to obtain the target new energy power output benchmark parameters and target new energy power output prediction error parameters that meet the iteration conditions.

[0148] Step S510: Based on the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters of each renewable energy power station, determine the renewable energy output uncertainty set of each renewable energy power station.

[0149] Step S512: Using the uncertainty set of new energy output of each new energy power station as a constraint, solve the output scheduling objective function pre-constructed for the new energy power plant to obtain the target net output value of each new energy power station.

[0150] Step S514: Dispatch the output of each new energy power station according to the target net output value of each new energy power station.

[0151] In this embodiment, by using the set of predicted renewable energy output scenarios for each renewable energy power plant, the server can determine the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters used to construct the renewable energy output uncertainty set, thereby constructing the renewable energy output uncertainty set for that renewable energy power plant. Based on the renewable energy output uncertainty set for each renewable energy power plant, the server can solve the pre-constructed output scheduling objective function for the renewable energy power plant, obtaining the target renewable energy predicted output value and target energy storage output value for each renewable energy power plant, and thus enabling output scheduling for each renewable energy power plant. Based on the above process, the renewable energy power plant output scheduling method allows the server to determine the target renewable energy predicted output value and target energy storage output value for each renewable energy power plant, ensuring that the role of the energy storage devices configured in the renewable energy power plant is fully utilized.

[0152] To more clearly illustrate the power output dispatching method for new energy power plants provided in the embodiments of this application, a specific embodiment is used below to describe the power output dispatching method for new energy power plants. However, it should be understood that the embodiments of this application are not limited thereto. In one exemplary embodiment, this application also provides a model improvement method for new energy combined with energy storage to participate in the electricity market, specifically including the following steps:

[0153] Existing models for renewable energy combined with energy storage to participate in the electricity market generally include output scheduling objective functions as shown in Equations 5 and 6, and constraints as shown in Equations 7 to 9. In other words, these technologies assume that renewable energy power plants have a relatively accurate predicted output value for power generation. However, in actual operation, the prediction accuracy of renewable energy output values ​​is often low. This means that the output constraints in the aforementioned output scheduling objective function, which use 0 to the predicted renewable energy output value as the output boundary for renewable energy power plants, may deviate significantly from the optimal solution under actual conditions, and may also lead to overly conservative optimization results.

[0154] Therefore, this embodiment provides a model improvement method that retains the overall structure of the model in related technologies and reconstructs the predictive output constraints of the model by extracting uncertainty data related to new energy sources. The specific process is as follows:

[0155] The server is reconstructed using a robust optimization approach, with the set of new energy power output represented by a box-shaped uncertainty set, resulting in the new energy power output uncertainty set shown in Formulas 1 and 2. The new energy power output uncertainty set is then used to replace the predicted power output constraints in related technologies.

[0156] At this point, the original model has been initially improved into a robust optimization general model form; when the uncertainty set of new energy output is in... and When a specific value is selected, the improved model is equivalent to the original model, and decision-makers can flexibly choose... and The value of is used to broaden and narrow the feasible region of the improved model, thereby achieving a balance between economy and conservatism in the improved model.

[0157] To further enhance the operability and practicality of the improved model, the model improvement method provided in this embodiment also includes a corresponding computational process for solving the problem. and

[0158] Specifically, the server iteratively solves the problem based on the uncertainty region constraint function shown in Equation 3 and the set of new energy power output prediction scenarios for new energy power plants. and

[0159] In this embodiment, firstly, a robust optimization model for new energy combined with energy storage participating in the electricity market is proposed based on norm theory. This model can flexibly construct robust optimization models for uncertainties in different application scenarios, considering the uncertainty of new energy output while retaining the overall structure of the original model, thus possessing strong engineering value. Secondly, an automatic boundary adjustment scheme is designed using a set of new energy output prediction scenarios. The conservatism of the model after boundary adjustment can be further reduced, improving the economic value of the model and making the optimization results closer to actual operational needs. In summary, the model improvement method for new energy combined with energy storage participating in the electricity market provided in this embodiment comprehensively considers the inaccuracy of new energy prediction, rewrites the existing model for new energy combined with energy storage participating in the electricity market, and the improved model retains the overall structure of the original model, has strong interpretability, and can be flexibly extended to other similar application scenarios in the future.

[0160] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0161] Based on the same inventive concept, this application also provides a power output scheduling device for a new energy power plant to implement the power output scheduling method of the new energy power plant described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the power output scheduling device for new energy power plants provided below can be found in the limitations of the power output scheduling method for new energy power plants described above, and will not be repeated here.

[0162] In an exemplary embodiment, as shown in FIG6, a power output scheduling device for a new energy power plant is provided, comprising: a scenario set acquisition module 602, a power output information determination module 604, an objective function solution module 606, and a power plant power output scheduling module 608, wherein:

[0163] The scenario set acquisition module 602 is used to acquire the scenario set for predicting the new energy output of each new energy power station in the new energy power plant.

[0164] The output information determination module 604 is used to determine the target new energy output benchmark parameters and target new energy output prediction error parameters for each new energy power station based on the new energy output prediction scenario set for each new energy power station, and to determine the new energy output uncertainty set for each new energy power station based on the target new energy output benchmark parameters and target new energy output prediction error parameters for each new energy power station.

[0165] The objective function solving module 606 is used to solve the pre-constructed output scheduling objective function for each new energy power plant, using the set of uncertainties in the new energy output of each new energy power plant as constraints, to obtain the target net output value of each new energy power plant; the target net output value includes the target predicted new energy output value and the target energy storage output value.

[0166] The power station output scheduling module 608 is used to schedule the output of each new energy power station according to the target net output value of each new energy power station.

[0167] In an exemplary embodiment, the output information determination module 604 is further configured to, for each renewable energy power station, determine a target renewable energy output prediction scenario from the renewable energy output prediction scenario set of the renewable energy power station whose corresponding renewable energy predicted output value is greater than that of the other renewable energy output prediction scenarios; initialize renewable energy output benchmark parameters and renewable energy output prediction error parameters based on the renewable energy predicted output value of the target renewable energy output prediction scenario; and iteratively update the renewable energy output benchmark parameters and renewable energy output prediction error parameters based on the renewable energy output prediction scenario set to obtain target renewable energy output benchmark parameters and target renewable energy output prediction error parameters that satisfy the iteration conditions.

[0168] In an exemplary embodiment, the power output information determination module 604 is further configured to: solve for the first parameter and the second parameter in the uncertainty region constraint function of the new energy power station based on the new energy power output prediction scenario set, the new energy power output benchmark parameter, and the new energy power output prediction error parameter; update the new energy power output benchmark parameter and the new energy power output prediction error parameter if either of the first parameter or the second parameter is greater than or equal to the condition parameter corresponding to the iteration condition, to obtain the updated new energy power output benchmark parameter and the updated new energy power output prediction error parameter; use the updated new energy power output benchmark parameter as the new new energy power output benchmark parameter, use the updated new energy power output prediction error parameter as the new new energy power output prediction error parameter, and return to the step of solving for the first parameter and the second parameter in the uncertainty region constraint function of the new energy power station based on the new energy power output prediction scenario set, the new energy power output benchmark parameter, and the new energy power output prediction error parameter, until both the first parameter and the second parameter obtained are less than the condition parameter, and determine the corresponding new energy power output benchmark parameter as the target new energy power output benchmark parameter and the corresponding new energy power output prediction error parameter as the target new energy power output prediction error parameter.

[0169] In an exemplary embodiment, the power output information determination module 604 is further configured to update the new energy power output reference parameters according to a preset first update step size to obtain the updated new energy power output reference parameters; and update the new energy power output prediction error parameters according to a preset second update step size to obtain the updated new energy power output prediction error parameters.

[0170] In an exemplary embodiment, the power output information determination module 604 is further configured to initialize both the new energy power output benchmark parameter and the new energy power output prediction error parameter to half of the new energy predicted power output value corresponding to the target new energy power output prediction scenario.

[0171] In an exemplary embodiment, the power output dispatching device for a new energy power plant further includes an objective function construction module. This module determines, for each dispatching period within each dispatching period of the new energy power plant, the unit penalty price, the time-of-use price, and the predicted daily new energy output and predicted daily new energy output error for each new energy power plant during the dispatching period. It also determines the charging and discharging efficiency of the energy storage device for each new energy power plant, and a preset prediction error threshold for each new energy power plant. Based on the unit penalty price, the time-of-use price, the predicted daily new energy output and predicted daily new energy output error for each new energy power plant during each dispatching period, the charging and discharging efficiency, and the preset prediction error threshold, the objective function for power output dispatching of the new energy power plant is constructed with the goal of maximizing the power output revenue of the new energy power plant.

[0172] Each module in the power output dispatching device of the aforementioned new energy power plant can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0173] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram is shown in Figure 7. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores day-ahead output data of a new energy power plant. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a power output scheduling method for a new energy power plant.

[0174] Those skilled in the art will understand that the structure shown in Figure 7 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0175] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0176] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0177] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0178] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0179] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0180] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for dispatching the output of a new energy power plant, characterized in that, The method includes: Obtain a set of predicted renewable energy output scenarios for each renewable energy power station in a renewable energy power plant; Based on the set of predicted renewable energy output scenarios for each renewable energy power station, the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station are determined. Based on the target renewable energy output benchmark parameters and the target renewable energy output prediction error parameters for each renewable energy power station, the set of uncertainties in renewable energy output for each renewable energy power station is determined. Using the uncertainty set of renewable energy output of each renewable energy power station as a constraint, the output scheduling objective function pre-constructed for the renewable energy power plant is solved to obtain the target net output value of each renewable energy power station; the target net output value includes the target renewable energy predicted output value and the target energy storage output value; According to the target net output value of each new energy power station, the output of each new energy power station is scheduled.

2. The method according to claim 1, characterized in that, The set of renewable energy output prediction scenarios for each renewable energy power station determines the target renewable energy output benchmark parameters and target renewable energy output prediction error parameters for each renewable energy power station, including: For each new energy power station, a target new energy output prediction scenario is determined from the set of new energy output prediction scenarios of the new energy power station, where the corresponding new energy predicted output value is greater than that of other new energy output prediction scenarios. Based on the predicted new energy output value of the target new energy output prediction scenario, initialize the new energy output benchmark parameters and the new energy output prediction error parameters; Based on the set of new energy power output prediction scenarios, the new energy power output benchmark parameters and the new energy power output prediction error parameters are iteratively updated to obtain the target new energy power output benchmark parameters and target new energy power output prediction error parameters that meet the iteration conditions.

3. The method according to claim 2, characterized in that, The process of iteratively updating the renewable energy output benchmark parameters and the renewable energy output prediction error parameters based on the renewable energy output prediction scenario set to obtain target renewable energy output benchmark parameters and target renewable energy output prediction error parameters that satisfy the iteration conditions includes: Based on the set of new energy power output prediction scenarios, the new energy power output benchmark parameters, and the new energy power output prediction error parameters, solve for the first and second parameters in the uncertainty region constraint function of the new energy power station; If either the first parameter or the second parameter is greater than or equal to the condition parameter corresponding to the iteration condition, the new energy output benchmark parameter and the new energy output prediction error parameter are updated to obtain the updated new energy output benchmark parameter and the updated new energy output prediction error parameter. The updated renewable energy output benchmark parameter is used as the new renewable energy output benchmark parameter, and the updated renewable energy output prediction error parameter is used as the new renewable energy output prediction error parameter. The steps of solving the first and second parameters in the uncertainty region constraint function of the renewable energy power station based on the renewable energy output prediction scenario set, the renewable energy output benchmark parameter, and the renewable energy output prediction error parameter are returned until the first and second parameters obtained are both less than the condition parameter. The corresponding renewable energy output benchmark parameter is determined as the target renewable energy output benchmark parameter, and the corresponding renewable energy output prediction error parameter is determined as the target renewable energy output prediction error parameter.

4. The method according to claim 3, characterized in that, The process of updating the renewable energy output benchmark parameters and the renewable energy output prediction error parameters to obtain updated renewable energy output benchmark parameters and updated renewable energy output prediction error parameters includes: The new energy output benchmark parameters are updated according to the preset first update step size to obtain the updated new energy output benchmark parameters. The new energy output prediction error parameters are updated according to the preset second update step size to obtain the updated new energy output prediction error parameters.

5. The method according to claim 2, characterized in that, The process of initializing the renewable energy output benchmark parameters and renewable energy output prediction error parameters based on the renewable energy output prediction scenario includes: Both the new energy output benchmark parameter and the new energy output prediction error parameter are initialized to half of the new energy predicted output value corresponding to the target new energy output prediction scenario.

6. The method according to any one of claims 1 to 5, characterized in that, The pre-constructed output scheduling objective function is obtained through the following method: For each scheduling period of the new energy power plant, determine the unit penalty price under the scheduling period, determine the time-of-use electricity price of the new energy power plant under the scheduling period, and determine the day-ahead new energy predicted output value and day-ahead new energy output predicted error value of each new energy power plant under the scheduling period. Determine the charging efficiency and discharging efficiency of the energy storage device of each new energy power station, and determine the preset prediction error threshold corresponding to each new energy power station; Based on the unit penalty price for each scheduling period, the time-of-use price of the new energy power plant for each scheduling period, the day-ahead predicted output value and the day-ahead predicted output error value of each new energy power station for each scheduling period, the charging efficiency and the discharging efficiency of the energy storage device of each new energy power station, and the preset prediction error threshold corresponding to each new energy power station, an output scheduling objective function for the new energy power plant is constructed with the goal of maximizing the output revenue of the new energy power plant.

7. A power output dispatching device for a new energy power plant, characterized in that, The device includes: The scenario set acquisition module is used to acquire the scenario set for predicting the new energy output of each new energy power station in the new energy power plant; The power output information determination module is used to determine the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station based on the new energy power output prediction scenario set for each new energy power station, and to determine the new energy power output uncertainty set for each new energy power station based on the target new energy power output benchmark parameters and target new energy power output prediction error parameters for each new energy power station. The objective function solving module is used to solve the pre-constructed output scheduling objective function for each new energy power plant, using the set of uncertainties in the new energy output of each new energy power plant as constraints, to obtain the target net output value of each new energy power plant; the target net output value includes the target predicted new energy output value and the target energy storage output value; The power station output scheduling module is used to schedule the output of each new energy power station according to the target net output value of each new energy power station.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images