Multi-scenario Probabilistic Configuration Optimization Method and Device for Virtual Power Plant

Abstract

The present application relates to the technical field of power systems, and particularly to a method and device for optimizing the probabilistic configuration of a virtual power plant in multiple scenarios. The method includes: determining the revenue function of each resource based on a high-dimensional game model, and using the Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue, so as to calculate the opportunity cost of each resource according to the influence conditions and the revenue function; probabilistically modeling the future scenarios of the virtual power plant by using a Markov decision process and Monte Carlo simulation to calculate the expected value of resource revenue, and using a non-linear function to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the virtual power plant; calculating the comprehensive configuration priority of the virtual power plant based on the resource opportunity cost and the matching degree, so that the target virtual power plant performs resource allocation according to the comprehensive configuration priority. Thus, the problems of poor adaptability and robustness of the resource allocation results of the existing optimization configuration methods and high computational complexity are solved.

Description

Technical Field

[0001] This application relates to the technical field of power systems, and particularly to a virtual power plant multi-scenario probabilistic configuration optimization method and device. Background Art

[0002] With the large-scale grid connection of renewable energy in the new power system, its volatility and intermittency characteristics have led to severe challenges in the real-time supply-demand balance of the power system; at the same time, the rapid growth of new types of power loads (such as electric vehicles, data centers) has further exacerbated the system's flexibility requirements. As an emerging technology, the virtual power plant can effectively connect distributed resources with the new power system. Reasonably configuring the distributed resource capacity in the virtual power plant can effectively improve energy utilization efficiency and achieve flexible adjustment of power demand.

[0003] However, traditional optimization configuration methods usually adopt deterministic models and fail to fully consider the uncertainty of market prices, the interdependence between resources, and the randomness of flexibility requirements, resulting in resource allocation results showing low adaptability and robustness; on the other hand, traditional methods usually solve based on nonlinear programming or mixed integer programming. As the number of resources and the number of flexibility requirement scenarios increase, the problem scale grows exponentially, leading to a sharp increase in computational complexity.

[0004] In summary, the adaptability and robustness of the resource allocation results of existing optimization configuration methods are poor, and the computational complexity is high, which urgently needs to be solved. Summary of the Invention

[0005] This application provides a virtual power plant multi-scenario probabilistic configuration optimization method and device to solve problems such as poor adaptability and robustness of the resource allocation results of existing optimization configuration methods and high computational complexity.

[0006] The first aspect embodiment of this application provides a virtual power plant multi-scenario probabilistic configuration optimization method, including the following steps: Based on a preset high-dimensional game model, determine the revenue function of each resource in the target virtual power plant, and use the preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to calculate the resource opportunity cost of each resource according to the influence conditions and the revenue function; perform probabilistic modeling on the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a nonlinear function to characterize the matching degree between the resource regulation characteristics and demand external characteristics of the target virtual power plant; based on the resource opportunity cost and the matching degree, calculate the comprehensive configuration priority of the target virtual power plant, so that the target virtual power plant performs resource allocation according to the comprehensive configuration priority.

[0007] Optionally, in an embodiment of the present application, based on a preset high-dimensional game model, the revenue function of each resource in the target virtual power plant is determined, and the preset Nash equilibrium principle is used to describe the influence condition of the target resource allocation decision on the resource revenue of each resource, so as to calculate the resource opportunity cost of each resource according to the influence condition and the revenue function, including: obtaining the expected output power information and electricity price information of each resource, and based on the expected output power information and the electricity price information, constructing the initial revenue function corresponding to each resource; describing the influence condition of the target resource allocation decision on the resource revenue of each resource according to the high-dimensional game model, the Nash equilibrium principle and the initial revenue function; based on the influence condition of the resource revenue and the revenue function, calculating the revenue of choosing the current gap allocation decision and the revenue of abandoning the current gap allocation decision corresponding to each resource, and calculating the resource opportunity cost corresponding to each resource according to the revenue of choosing the current gap allocation decision and the revenue of abandoning the current gap allocation decision.

[0008] Optionally, in an embodiment of the present application, probabilistic modeling is performed on the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and a non-linear function is used to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant, including: determining the probability distribution of the future scenarios, and weighting the future scenarios according to the probability distribution, so as to transform the revenue function through the weighted future scenarios to obtain a game revenue transformation function; based on a preset Markov decision process and Monte Carlo simulation strategy, and in combination with the game revenue transformation function, performing probabilistic modeling to calculate the expected value of resource revenue; establishing a non-linear function between the resource regulation characteristics and the demand external characteristics, and quantifying the matching degree between the resource regulation characteristics and the demand external characteristics through the non-linear function and the expected value of resource revenue.

[0009] Optionally, in an embodiment of the present application, based on the resource opportunity cost and the matching degree, the comprehensive configuration priority of the target virtual power plant is calculated, so that the target virtual power plant performs resource allocation according to the comprehensive configuration priority, including: generating the initial resource allocation priority corresponding to the target virtual power plant based on the resource opportunity cost and the matching degree, and performing dimensionless processing on the resource opportunity cost and the matching degree, so as to transform the initial resource allocation priority by using the dimensionless processed resource opportunity cost and matching degree to obtain the comprehensive configuration priority; constructing the flexibility demand constraint corresponding to the target virtual power plant, and performing resource allocation according to the comprehensive configuration priority and the flexibility demand constraint.

[0010] Optionally, in an embodiment of the present application, the mathematical expression of the resource opportunity cost is:

[0011]

[0012] wherein, Δ F ( t ) represents t the flexibility requirement at the moment; represents the resource R i at t the expected output power at the moment; t 0 represents the initial moment of the flexibility requirement; t T represents the end moment of the flexibility requirement; C OC,i represents the resource R i opportunity cost of the resource; d i represents the resource R i in the adjustment allocation ratio for the flexibility requirement; d j represents the resource R j adjustment allocation ratio for the flexibility requirement; represents t the electricity price at the moment.

[0013] In the second aspect of the embodiments of the present application, a virtual power plant multi-scenario probabilistic configuration optimization device is provided, including: an accounting module, configured to determine the revenue function of each resource in the target virtual power plant based on a preset high-dimensional game model, and use a preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to conduct resource opportunity cost accounting for each resource according to the influence conditions and the revenue function; a probabilistic modeling module, configured to perform probabilistic modeling on the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant; a resource allocation module, configured to calculate the comprehensive configuration priority of the target virtual power plant based on the resource opportunity cost and the matching degree, so that the target virtual power plant performs resource allocation according to the comprehensive configuration priority.

[0014] Optionally, in an embodiment of the present application, the accounting module includes: a first construction unit, configured to obtain the expected output power information and electricity price information of each resource, and construct an initial revenue function corresponding to each resource based on the expected output power information and the electricity price information; a description unit, configured to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource according to the high-dimensional game model, the Nash equilibrium principle, and the initial revenue function; a first calculation unit, configured to calculate the revenue of selecting the current gap allocation decision and the revenue of abandoning the current gap allocation decision corresponding to each resource based on the influence conditions of the resource revenue and the revenue function, and calculate the resource opportunity cost corresponding to each resource according to the revenue of selecting the current gap allocation decision and the revenue of abandoning the current gap allocation decision.

[0015] Optionally, in an embodiment of the present application, the probabilistic modeling module includes: a weighting unit, configured to determine the probability distribution of the future scenarios, and weight the future scenarios according to the probability distribution to convert the revenue function through the weighted future scenarios to obtain a game revenue conversion function; a second calculation unit, configured to perform probabilistic modeling based on a preset Markov decision process and Monte Carlo simulation strategy, and in combination with the game revenue conversion function, to calculate the expected value of the resource revenue; a quantization unit, configured to establish a non-linear function between the resource regulation characteristics and the external demand characteristics, and quantify the matching degree between the resource regulation characteristics and the external demand characteristics through the non-linear function and the expected value of the resource revenue.

[0016] Optionally, in an embodiment of the present application, the resource allocation module includes: a dimensionless processing unit, configured to generate an initial resource allocation priority corresponding to the target virtual power plant based on the resource opportunity cost and the matching degree, and perform dimensionless processing on the resource opportunity cost and the matching degree, so as to convert the initial resource allocation priority by using the dimensionless processed resource opportunity cost and matching degree to obtain the comprehensive allocation priority; a second construction unit, configured to construct a flexibility demand constraint corresponding to the target virtual power plant, and perform resource allocation according to the comprehensive allocation priority and the flexibility demand constraint.

[0017] Optionally, in an embodiment of the present application, the mathematical expression of the resource opportunity cost is:

[0018]

[0019] where, Δ F ( t ) represents t the flexibility demand at time represents the resource Ri At t the expected output power at the moment; t 0 represents the initial moment of the flexibility requirement; t T represents the end moment of the flexibility requirement; C OC,i represents the R i opportunity cost of the resource; d i represents the R i regulation allocation ratio for the flexibility requirement; d j represents the resource R j regulation allocation ratio for the flexibility requirement; represents t the electricity price at the moment.

[0020] An embodiment of the third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the program to implement the virtual power plant multi-scenario probability configuration optimization method as described in the above embodiment.

[0021] An embodiment of the fourth aspect of this application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the program is executed by a processor, it implements the virtual power plant multi-scenario probability configuration optimization method as above.

[0022] An embodiment of the fifth aspect of this application provides a computer program product, including a computer program, and the computer program is executed to implement the virtual power plant multi-scenario probability configuration optimization method as described above.

[0023] Therefore, the embodiments of this application have the following beneficial effects:

[0024] Embodiments of the present application can determine the revenue function of each resource in the target virtual power plant based on a preset high-dimensional game model, and use the preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to calculate the resource opportunity cost for each resource according to the influence conditions and the revenue function; probabilistically model the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant; based on the resource opportunity cost and the matching degree, calculate the comprehensive allocation priority of the target virtual power plant, so that the target virtual power plant performs resource allocation according to the comprehensive allocation priority. The present application can calculate the opportunity cost of resources based on a high-dimensional game model, quantify the matching degree between resource regulation characteristics and demand external characteristics through a non-linear function, and dynamically generate the comprehensive allocation priority of resources, thereby effectively improving the adaptability and robustness of the resource allocation result. Thus, the problems of poor adaptability and robustness of the resource allocation result of the existing optimization allocation method and high computational complexity are solved.

[0025] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1 is a flowchart of a virtual power plant multi-scenario probabilistic configuration optimization method according to an embodiment of the present application;

[0028] Figure 2 is an example diagram of a virtual power plant multi-scenario probabilistic configuration optimization device according to an embodiment of the present application;

[0029] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0030] Among them, 10 - virtual power plant multi-scenario probabilistic configuration optimization device; 100 - accounting module, 200 - probabilistic modeling module, 300 - resource allocation module; 301 - memory, 302 - processor, 303 - communication interface. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

[0032] The virtual power plant multi-scenario probabilistic configuration optimization method and device according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problems mentioned in the above background art, the present application provides a virtual power plant multi-scenario probabilistic configuration optimization method. In this method, based on a preset high-dimensional game model, the revenue function of each resource in the target virtual power plant is determined, and the preset Nash equilibrium principle is used to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to calculate the resource opportunity cost for each resource according to the influence conditions and the revenue function; the future scenarios of the target virtual power plant are probabilistically modeled to calculate the expected value of resource revenue, and a non-linear function is used to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant; based on the resource opportunity cost and the matching degree, the comprehensive configuration priority of the target virtual power plant is calculated, so that the target virtual power plant performs resource allocation according to the comprehensive configuration priority. The present application can calculate the opportunity cost of resources based on a high-dimensional game model, quantify the matching degree between resource regulation characteristics and demand external characteristics through a non-linear function, and dynamically generate the comprehensive configuration priority of resources, thereby effectively improving the adaptability and robustness of the resource allocation result. Thus, the problems of poor adaptability and robustness of the resource allocation result of the existing optimization configuration method and high computational complexity are solved.

[0033] Specifically, Figure 1 FIG. is a flowchart of a virtual power plant multi-scenario probabilistic configuration optimization method provided by an embodiment of the present application.

[0034] As Figure 1 shown, the virtual power plant multi-scenario probabilistic configuration optimization method includes the following steps:

[0035] In step S101, based on a preset high-dimensional game model, the revenue function of each resource in the target virtual power plant is determined, and the preset Nash equilibrium principle is used to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to calculate the resource opportunity cost for each resource according to the influence conditions and the revenue function.

[0036] The embodiments of the present application can first calculate the opportunity cost of resources based on a high-dimensional game model, comprehensively consider the uncertainty of market prices and the interdependence between resources, and use the Nash equilibrium principle to optimize resource allocation decisions, thereby ensuring the economy and rationality of resource allocation.

[0037] Optionally, in an embodiment of the present application, based on a preset high-dimensional game model, the revenue function of each resource in the target virtual power plant is determined, and the preset Nash equilibrium principle is used to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to conduct resource opportunity cost accounting for each resource according to the influence conditions and the revenue function, including: obtaining the expected output power information and electricity price information of each resource, and based on the expected output power information and electricity price information, constructing the initial revenue function corresponding to each resource; describing the influence conditions of the target resource allocation decision on the resource revenue of each resource according to the high-dimensional game model, the Nash equilibrium principle and the initial revenue function; based on the influence conditions of the resource revenue and the revenue function, calculating the revenue of each resource corresponding to the current gap allocation decision and the revenue of giving up the current gap allocation decision, and calculating the resource opportunity cost corresponding to each resource according to the revenue of the current gap allocation decision and the revenue of giving up the current gap allocation decision.

[0038] Specifically, in the embodiment of the present application, the resource set of the virtual power plant is , and the virtual power plant makes resource allocation decisions for the flexibility gap. In order to account for the opportunity cost of each resource, the embodiment of the present application can define the revenue function of each resource as shown in the following formula:

[0039]

[0040] Among them, is the revenue obtained when resource is configured for the flexibility demand ; represents t the electricity price at time ; represents the expected output power of resource t at time

[0041] Those skilled in the art should understand that the resource revenue not only depends on the currently selected gap, but is also affected by the decisions of other resources. Therefore, resource allocation is a game decision problem, and the selection decisions of multiple resources affect each other. Assume that the allocation decisions of the resources form a decision vector, where represents the allocation decision of resource . The decision of each resource will affect its revenue through the following game model to obtain the corresponding revenue function, as shown in the following formula:

[0042]

[0043] Among them, is the adjustment and allocation ratio of resource for the flexibility demand.

[0044] Secondly, according to the definition of Nash equilibrium in the embodiments of the present application, each resource makes an optimal decision under the condition that the configurations of other resources are known, so as to maximize its own benefit, that is, when the configurations of all other resources are fixed, the configuration decision of the resource will no longer change, and this Nash equilibrium condition can be represented by the following equation:

[0045]

[0046] Wherein, represents the benefit of the resource under the configuration decision vector ; represents the configuration decision vector of other resources except the resource .

[0047] Optionally, in an embodiment of the present application, the mathematical expression of the resource opportunity cost is:

[0048]

[0049] Wherein, Δ F ( t ) represents the flexibility demand at t ; represents the expected output power of the resource R i at t ; t 0 represents the initial moment of the flexibility demand; t T represents the end moment of the flexibility demand; C OC,i represents the resource opportunity cost of the resource R i ; d i represents the regulation allocation ratio of the resource R i to the flexibility demand; d j represents the regulation allocation ratio of the resource R j to the flexibility demand; represents the electricity price at t .

[0050] It should be noted that under this Nash equilibrium condition, the opportunity cost of the resource is calculated from the difference between the benefit brought by its choice of the current gap configuration decision and the maximum benefit that may be brought by giving up the current gap configuration and choosing other gap configurations. This difference is the resource opportunity cost, as shown in the following formula: ​

[0051]

[0052] Among them, Δ F ( t ) represents t the flexibility demand at the moment; represents the resource R i at t the expected output power at the moment; t 0 represents the initial moment of the flexibility demand; t T represents the end moment of the flexibility demand; C OC,i represents the resource R i opportunity cost of the resource; d i represents the resource R i in the regulation allocation ratio for the flexibility demand; d j represents the resource R j regulation allocation ratio for the flexibility demand; represents t the electricity price at the moment.

[0053] Thus, the embodiments of the present application calculate the opportunity cost of the resource based on the high-dimensional game model, thereby providing reliable data support for the subsequent probabilistic modeling and resource allocation.

[0054] In step S102, a probabilistic model is established for the future scenarios of the target virtual power plant to calculate the expected value of the resource revenue, and a non-linear function is used to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant.

[0055] Furthermore, the embodiments of the present application also need to perform probabilistic modeling on the future scenarios by using the Markov decision process and Monte Carlo simulation for the randomness of the flexibility demand, and calculate the expected value of the resource revenue; thereafter, the embodiments of the present application can quantify the matching degree between the resource regulation characteristics (such as regulation rate, capacity) and the demand external characteristics (such as ramp rate requirement) through a non-linear function to dynamically generate the resource allocation priority, so as to ensure that the resources with high matching degree are preferentially allocated.

[0056] Optionally, in an embodiment of the present application, a probabilistic model is established for the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and a non-linear function is used to characterize the matching degree between the resource regulation characteristics and the external demand characteristics of the target virtual power plant, including: determining the probability distribution of future scenarios, weighting the future scenarios according to the probability distribution, and converting the revenue function through the weighted future scenarios to obtain a game revenue conversion function; based on a preset Markov decision process and Monte Carlo simulation strategy, and in combination with the game revenue conversion function, performing probabilistic modeling to calculate the expected value of resource revenue; establishing a non-linear function between the resource regulation characteristics and the external demand characteristics, and quantifying the matching degree between the resource regulation characteristics and the external demand characteristics through the non-linear function and the expected value of resource revenue.

[0057] It should be noted that the above calculation of opportunity cost only considers the relationship between flexibility gap and resource allocation. However, flexibility demand is not a deterministic variable, its occurrence and magnitude are random, and different scenarios have different probability distributions. Therefore, opportunity cost accounting needs to consider different demand scenarios that may occur in the future, and weight these scenarios through probability distribution. The converted resource revenue function is shown in the following formula:

[0058]

[0059] Where, is the joint probability distribution of flexibility demand and electricity price.

[0060] Considering that there may be a long-term dependence between the flexibility gap and the regulation ability of resources, the embodiments of the present application can use the state transition matrix in the Markov decision process to describe the state evolution process, as shown in the following formula:

[0061]

[0062] Where, represents the expected revenue obtained starting from state ; represents the state transition probability; represents the weight of future opportunities.

[0063] To improve the calculation accuracy, the embodiments of the present application introduce Monte Carlo simulation to generate multiple scenarios of flexibility gap demand and market electricity price, and calculate the expected revenue through the simulation results:

[0064]

[0065] Where, N is the number of simulations; is the scenario probability of the occurrence of flexibility demand.

[0066] Furthermore, it can be understood that the configuration priority of virtual power plant resources to fill the flexibility demand should not only be determined according to the opportunity cost (resources with smaller opportunity cost are preferentially configured), but also consider the matching degree between the resource regulation characteristics (such as regulation rate, capacity) and the demand external characteristics (such as ramp rate, power requirement), and dynamically generate resource priorities to ensure that resources with higher matching degree are preferentially configured.

[0067] In order to make the quantification of the matching degree more realistic and refined, the embodiments of the present application introduce a non-linear function to describe the relationship between these variables:

[0068]

[0069] Among them, and respectively represent the non-linear relationship functions between the regulation rate and the regulation ability and the demand external characteristics; and are regulation coefficients used to balance the influence of the regulation rate and the regulation capacity on the matching degree; is the regulation ability of resource at t time; is the response time; is a weighting function, indicating the influence degree of different times on the matching degree; represents the maximum value of the flexibility demand; represents the influence degree of the change of the flexibility demand on the weight.

[0070] Thus, the embodiments of the present application dynamically generate resource priorities through high-dimensional uncertainty modeling and the calculation of the regulation characteristic matching degree, so as to effectively ensure that resources with higher matching degree are preferentially configured, providing data guidance and basis for the multi-scenario probability configuration optimization of virtual power plants.

[0071] In step S103, based on the resource opportunity cost and the matching degree, calculate the comprehensive configuration priority of the target virtual power plant, so that the target virtual power plant performs resource configuration according to the comprehensive configuration priority.

[0072] Furthermore, the embodiments of the present application also need to calculate the comprehensive configuration priority of the virtual power plant based on the resource opportunity cost and the regulation characteristic matching degree, so that the virtual power plant configures resources from high to low according to the comprehensive configuration priority to ensure that the total amount of resource configuration meets the flexibility demand.

[0073] Optionally, in an embodiment of the present application, based on the resource opportunity cost and matching degree, calculate the comprehensive configuration priority of the target virtual power plant, so that the target virtual power plant performs resource allocation according to the comprehensive configuration priority, including: generating the initial resource allocation priority corresponding to the target virtual power plant based on the resource opportunity cost and matching degree, and performing dimensionless processing on the resource opportunity cost and matching degree, so as to use the dimensionless processed resource opportunity cost and matching degree to convert the initial resource allocation priority to obtain the comprehensive configuration priority; constructing the flexibility requirement constraint corresponding to the target virtual power plant, and performing resource allocation according to the comprehensive configuration priority and the flexibility requirement constraint.

[0074] In the actual execution process, the allocation priority of the virtual power plant resources in the embodiment of the present application will be calculated by combining the opportunity cost and the matching degree:

[0075]

[0076] Among them, represents the allocation priority of resource (i.e., the initial resource allocation priority); and represent the weight coefficients, which are used to balance the importance of the opportunity cost and the matching degree in the priority calculation; M i represents the matching degree of resource .

[0077] It should be noted that the opportunity cost in the above formula affects the priority through an inverse relationship. The smaller the opportunity cost of a resource, the higher its allocation priority, while the matching degree is directly weighted into the priority. Resources with a high matching degree will obtain a higher priority. However, the two have inconsistent dimensions, resulting in inaccurate allocation priorities for individual resources. Therefore, dimensionless processing is required, as shown in the following formula:

[0078]

[0079] Among them, X is the original data; X min and X max are the minimum and maximum values of the data respectively.

[0080] Therefore, the above allocation priority (i.e., the initial resource allocation priority) can be converted into the following formula to obtain the corresponding comprehensive configuration priority:

[0081]

[0082] In summary, the virtual power plant will perform resource allocation based on the comprehensive configuration priority from high to low, and the resources The configuration process is as follows:

[0083]

[0084] Among them, represents the configured capacity; represents the maximum configured capacity of the resource.

[0085] In addition, the configuration goal of the virtual power plant needs to meet the flexibility requirements. Therefore, the virtual power plant configuration also needs to meet the following constraints:

[0086]

[0087] In summary, the embodiments of the present application calculate the opportunity cost of resources based on a high-dimensional game model, and quantify the matching degree between the resource regulation characteristics and the demand external characteristics through a non-linear function, so as to dynamically generate the comprehensive configuration priority of resources, enabling the virtual power plant to complete resource configuration according to the configuration priority from high to low, and ensuring that the total amount of resource configuration meets the flexibility requirements.

[0088] According to the virtual power plant multi-scenario probability configuration optimization method proposed by the embodiments of the present application, based on a preset high-dimensional game model, the revenue function of each resource in the target virtual power plant is determined, and the preset Nash equilibrium principle is used to describe the influence conditions of the target resource configuration decision on the resource revenue of each resource, so as to calculate the opportunity cost of each resource according to the influence conditions and the revenue function; probabilistically model the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant; based on the opportunity cost of resources and the matching degree, calculate the comprehensive configuration priority of the target virtual power plant, so that the target virtual power plant performs resource configuration according to the comprehensive configuration priority. The present application can calculate the opportunity cost of resources based on a high-dimensional game model, quantify the matching degree between the resource regulation characteristics and the demand external characteristics through a non-linear function, and dynamically generate the comprehensive configuration priority of resources, thereby effectively improving the adaptability and robustness of the resource configuration result.

[0089] Secondly, a virtual power plant multi-scenario probability configuration optimization device proposed according to the embodiments of the present application will be described with reference to the accompanying drawings.

[0090] Figure 2 is a block diagram of the virtual power plant multi-scenario probability configuration optimization device according to the embodiments of the present application.

[0091] As Figure 2 shown, the virtual power plant multi-scenario probability configuration optimization device 10 includes: an accounting module 100, a probabilistic modeling module 200, and a resource configuration module 300.

[0092] Among them, the accounting module 100 is used to determine the revenue function of each resource in the target virtual power plant based on a preset high-dimensional game model, and use the preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to conduct resource opportunity cost accounting for each resource according to the influence conditions and revenue function.

[0093] The probabilistic modeling module 200 is used to perform probabilistic modeling on the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and demand external characteristics of the target virtual power plant.

[0094] The resource allocation module 300 is used to calculate the comprehensive allocation priority of the target virtual power plant based on the resource opportunity cost and matching degree, so that the target virtual power plant conducts resource allocation according to the comprehensive allocation priority.

[0095] Optionally, in an embodiment of the present application, the accounting module 100 includes: a first construction unit, a description unit, and a first calculation unit.

[0096] Among them, the first construction unit is used to obtain the expected output power information and electricity price information of each resource, and based on the expected output power information and electricity price information, construct the initial revenue function corresponding to each resource.

[0097] The description unit is used to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource according to the high-dimensional game model, the Nash equilibrium principle, and the initial revenue function.

[0098] The first calculation unit is used to calculate the revenue of choosing the current gap allocation decision and the revenue of giving up the current gap allocation decision corresponding to each resource based on the influence conditions of the resource revenue and the revenue function, and calculate the resource opportunity cost corresponding to each resource according to the revenue of choosing the current gap allocation decision and the revenue of giving up the current gap allocation decision.

[0099] Optionally, in an embodiment of the present application, the probabilistic modeling module 200 includes: a weighting unit, a second calculation unit, and a quantification unit.

[0100] Among them, the weighting unit is used to determine the probability distribution of the future scenarios, and weight the future scenarios according to the probability distribution, so as to transform the revenue function through the weighted future scenarios to obtain the game revenue transformation function.

[0101] The second calculation unit is used to perform probabilistic modeling based on a preset Markov decision process and Monte Carlo simulation strategy, and in combination with the game revenue transformation function, to calculate the expected value of resource revenue.

[0102] A quantization unit is used to establish a non - linear function between the resource regulation characteristics and the demand external characteristics, and quantify the matching degree of the resource regulation characteristics and the demand external characteristics through the non - linear function and the expected value of resource revenue.

[0103] Optionally, in an embodiment of the present application, the resource allocation module 300 includes: a dimensionless processing unit and a second construction unit.

[0104] Among them, the dimensionless processing unit is used to generate the initial resource allocation priority corresponding to the target virtual power plant based on the resource opportunity cost and the matching degree, and perform dimensionless processing on the resource opportunity cost and the matching degree, so as to convert the initial resource allocation priority by using the dimensionless - processed resource opportunity cost and matching degree to obtain the comprehensive allocation priority.

[0105] The second construction unit is used to construct the flexibility demand constraint corresponding to the target virtual power plant, and perform resource allocation according to the comprehensive allocation priority and the flexibility demand constraint.

[0106] Optionally, in an embodiment of the present application, the mathematical expression of the resource opportunity cost is:

[0107]

[0108] Where, Δ F ( t ) represents t the flexibility demand at time represents the resource R i at t the expected output power at time; t 0 represents the initial time of the flexibility demand; t T represents the end time of the flexibility demand; C OC,i represents the resource R i 's resource opportunity cost; d i represents the resource R i 's regulation allocation ratio for the flexibility demand; d j represents the resource R j 's regulation allocation ratio for the flexibility demand; represents t the electricity price at time.

[0109] It should be noted that the foregoing explanation of the embodiments of the virtual power plant multi - scenario probability configuration optimization method also applies to the virtual power plant multi - scenario probability configuration optimization device of this embodiment, and will not be elaborated here.

[0110] The virtual power plant multi-scenario probabilistic configuration optimization device proposed according to the embodiments of the present application includes an accounting module 100, which is used to determine the revenue function of each resource in the target virtual power plant based on a preset high-dimensional game model, and use the preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to calculate the resource opportunity cost of each resource according to the influence conditions and revenue function; a probabilistic modeling module 200, which is used to perform probabilistic modeling on the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and the demand external characteristics of the target virtual power plant; a resource allocation module 300, which is used to calculate the comprehensive allocation priority of the target virtual power plant based on the resource opportunity cost and the matching degree, so that the target virtual power plant performs resource allocation according to the comprehensive allocation priority, thereby effectively improving the adaptability and robustness of the resource allocation result.

[0111] Figure 3 The structural schematic diagram of the electronic device provided by the embodiments of the present application. The electronic device may include:

[0112] A memory 301, a processor 302, and a computer program stored on the memory 301 and executable on the processor 302.

[0113] When the processor 302 executes the program, it implements the virtual power plant multi-scenario probabilistic configuration optimization method provided in the above embodiments.

[0114] Furthermore, the electronic device further includes:

[0115] A communication interface 303, which is used for communication between the memory 301 and the processor 302.

[0116] The memory 301 is used to store a computer program executable on the processor 302.

[0117] The memory 301 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0118] If the memory 301, the processor 302, and the communication interface 303 are implemented independently, the communication interface 303, the memory 301, and the processor 302 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 3 only a thick line is used to represent it in Figure 3 , but it does not mean that there is only one bus or one type of bus.

[0119] Optionally, in a specific implementation, if the memory 301, the processor 302, and the communication interface 303 are integrated on a single chip, the memory 301, the processor 302, and the communication interface 303 can communicate with each other through an internal interface.

[0120] The processor 302 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0121] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above virtual power plant multi-scenario probability configuration optimization method is implemented.

[0122] The embodiments of the present application further provide a computer program product, including a computer program, and when the computer program is executed, it is used to implement the above virtual power plant multi-scenario probability configuration optimization method.

[0123] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0124] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0125] Any process or method description shown in the flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions may be executed in a manner that is not in the order shown or discussed, including in a substantially simultaneous manner according to the involved functions or in the reverse order, which should be understood by those skilled in the art to which the embodiments of this application belong.

[0126] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0127] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0128] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0129] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0130] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A probabilistic configuration optimization method for a virtual power plant in multiple scenarios, characterized in that, Including the following steps: Based on a preset high-dimensional game model, determine the revenue function of each resource in the target virtual power plant, and use the preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to conduct resource opportunity cost accounting for each resource according to the influence conditions and the revenue function; Perform probabilistic modeling on the future scenarios of the target virtual power plant to calculate the expected resource revenue value, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and the external demand characteristics of the target virtual power plant; Based on the resource opportunity cost and the matching degree, calculate the comprehensive configuration priority of the target virtual power plant, so that the target virtual power plant conducts resource allocation according to the comprehensive configuration priority; Obtain the expected output power information and electricity price information of each resource, and based on the expected output power information and the electricity price information, construct the revenue function corresponding to each resource; According to the high-dimensional game model, the Nash equilibrium principle and the revenue function, describe the influence conditions of the target resource allocation decision on the resource revenue of each resource; Based on the influence conditions of the resource revenue and the revenue function, calculate the revenue of choosing the current gap allocation decision and the revenue of giving up the current gap allocation decision corresponding to each resource, and calculate the resource opportunity cost corresponding to each resource according to the revenue of choosing the current gap allocation decision and the revenue of giving up the current gap allocation decision; Determine the probability distribution of the future scenarios, and weight the future scenarios according to the probability distribution, so as to transform the revenue function through the weighted future scenarios to obtain the game revenue transformation function; Based on the preset Markov decision process and Monte Carlo simulation strategy, and combined with the game revenue transformation function, conduct probabilistic modeling to calculate the expected resource revenue value; Establish a non-linear function between the resource regulation characteristics and the external demand characteristics, and quantify the matching degree between the resource regulation characteristics and the external demand characteristics through the non-linear function and the expected resource revenue value; Wherein, the mathematical expression of the resource opportunity cost is: Among them, Δ F ( t ) represents t the flexibility requirement at the moment; represents the resource R i at t the expected output power at the moment; t 0 represents the initial moment of the flexibility requirement; t T represents the end moment of the flexibility requirement; C OC,i represents the R i opportunity cost of the resource; d i represents the R i adjustment allocation ratio for the flexibility requirement; d j represents the resource R j adjustment allocation ratio for the flexibility requirement; represents t the electricity price at the moment.

2. The virtual power plant multi-scenario probabilistic configuration optimization method according to claim 1, wherein The calculating the comprehensive configuration priority of the target virtual power plant based on the resource opportunity cost and the matching degree, so that the target virtual power plant conducts resource allocation according to the comprehensive configuration priority includes: Based on the resource opportunity cost and the matching degree, generate the initial resource configuration priority corresponding to the target virtual power plant, and perform dimensionless processing on the resource opportunity cost and the matching degree, so as to transform the initial resource configuration priority by using the dimensionless processed resource opportunity cost and matching degree to obtain the comprehensive configuration priority; Construct the flexibility demand constraint corresponding to the target virtual power plant, and conduct resource allocation according to the comprehensive configuration priority and the flexibility demand constraint.

3. A virtual power plant multi-scenario probabilistic configuration optimization device, characterized in that Including: The accounting module is used to determine the revenue function of each resource in the target virtual power plant based on a preset high-dimensional game model, and use the preset Nash equilibrium principle to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource, so as to conduct resource opportunity cost accounting for each resource according to the influence conditions and the revenue function; The probabilistic modeling module is used to perform probabilistic modeling on the future scenarios of the target virtual power plant to calculate the expected value of resource revenue, and use a non-linear function to characterize the matching degree between the resource regulation characteristics and the external demand characteristics of the target virtual power plant; The resource allocation module is used to calculate the comprehensive allocation priority of the target virtual power plant based on the resource opportunity cost and the matching degree, so that the target virtual power plant conducts resource allocation according to the comprehensive allocation priority; The first construction unit is used to obtain the expected output power information and electricity price information of each resource, and construct the revenue function corresponding to each resource based on the expected output power information and the electricity price information; The description unit is used to describe the influence conditions of the target resource allocation decision on the resource revenue of each resource according to the high-dimensional game model, the Nash equilibrium principle and the revenue function; The first calculation unit is used to calculate the revenue of choosing the current gap allocation decision and the revenue of giving up the current gap allocation decision corresponding to each resource based on the influence conditions of the resource revenue and the revenue function, and calculate the resource opportunity cost corresponding to each resource according to the revenue of choosing the current gap allocation decision and the revenue of giving up the current gap allocation decision; The weighting unit is used to determine the probability distribution of the future scenarios, and weight the future scenarios according to the probability distribution, so as to transform the revenue function through the weighted future scenarios to obtain a game revenue transformation function; The second calculation unit is used to perform probabilistic modeling based on a preset Markov decision process and Monte Carlo simulation strategy, and combine the game revenue transformation function to calculate the expected value of the resource revenue; The quantization unit is used to establish a non-linear function between the resource regulation characteristics and the external demand characteristics, and quantify the matching degree between the resource regulation characteristics and the external demand characteristics through the non-linear function and the expected value of the resource revenue; Among them, the mathematical expression of the resource opportunity cost is: Among them, Δ F ( t ) represents t the flexibility requirement at time represents the resource R i at t the expected output power at time t 0 represents the initial time of the flexibility requirement; t T represents the end time of the flexibility requirement; C OC,i represents the R i opportunity cost of the resource; d i represents the R i adjustment allocation ratio for the flexibility requirement; d j represents the resource R j adjustment allocation ratio for the flexibility requirement; represents t the electricity price at time 4. An electronic device, characterized in that, including: A memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the virtual power plant multi-scenario probabilistic configuration optimization method according to any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the virtual power plant multi-scenario probabilistic configuration optimization method according to any one of claims 1-2.

6. A computer program product, comprising a computer program, characterized in that, The program is executed to be used to implement the virtual power plant multi-scenario probabilistic configuration optimization method according to any one of claims 1-2.

Images