Power grid guided resource aggregate evolution method, system and equipment and medium
Through the evolutionary dynamic model constructed by the BP neural network, the optimal market price cap value is calculated to guide flexible resource aggregation, which solves the problem of existing power grid guidance methods deviating from demand, and realizes the precise matching of resource aggregation and the satisfaction of power grid regulation requirements. .
Patent Information
- Application Number
- CN202411202642.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-03
AI Technical Summary
The existing power grid guidance methods fail to effectively grasp the evolution mechanism of the flexible resource aggregation process, resulting in the guidance results deviating from the grid requirements and making it difficult to accurately meet diversified adjustment needs.
Using the evolutionary dynamics model based on BP neural network, the optimal market price cap value is calculated to guide resources by obtaining the current state parameters of the flexible resource aggregate of the power grid and adjusting the initial market price cap value of the task scenario. Aggregate to ensure that the guidance results meet grid requirements.
The mechanism modeling of the resource aggregation process is simplified, and the relationship between the evolutionary drivers of the aggregate and the result mapping is revealed through the dynamic model, which improves the accuracy and matching of the guiding results, and meets the needs of diversified regulation of the power grid.
Smart Images

Figure CN119067697A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of power system automation, and relates to a power grid-guided resource aggregate evolution method, system, equipment and medium. Background Art
[0002] In the process of building new power systems, the proportion of renewable energy continues to increase. Under the influence of multiple factors such as random fluctuations in wind and solar power output, rapid growth in load, and frequent extreme weather, the balance problem of the power grid has become more severe, and the regulation needs of the power grid have become more complex and diverse. With the development of energy Internet technology, the types and quantities of demand-side flexible resources such as distributed renewable energy, multiple adjustable loads, and user-side energy storage are showing a massive trend, and have become a blue ocean for participating in power grid regulation. Flexible resource individuals can autonomously aggregate to form multiple resource aggregates through information interaction with each other, thereby participating in various regulation scenarios such as power grid frequency regulation, peak regulation, and standby, to ensure the stability and reliability of power system operation.
[0003] However, the autonomous aggregation of resources is a dynamic evolution process with strong nonlinear and uncertain characteristics. The profit-seeking nature of flexible resources and the variability of power grid demand are often in conflict. Aggregates formed entirely by autonomous resource aggregation are difficult to accurately meet the diversified regulation needs of the power grid. In this context, the power grid should take certain measures to guide the direction of flexible resource aggregation so that the number of resource aggregates and the regulation capabilities that can be provided match the grid regulation needs. Most of the existing power grid guidance methods are achieved through simple time-of-use electricity price mechanisms and incentive compensation plans. However, due to the failure to grasp the evolutionary mechanism of the flexible resource aggregation process and the lack of understanding of the effectiveness of price incentive signals, the guidance results often deviate from the grid demand. Summary of the invention
[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a grid-guided resource aggregate evolution method, system, device and medium, which can guide flexible resources to be aggregated, and the guiding results meet the grid requirements.
[0005] In order to achieve the above object, the present invention adopts the following technical scheme:
[0006] In one aspect of the present invention, the grid-guided resource aggregate evolution method of the present invention comprises:
[0007] Obtaining current state parameters of the flexible resource aggregate evolution of the target power grid;
[0008] Obtaining the initial market price cap values for various regulation task scenarios of the target power grid;
[0009] Determine guidance targets based on grid demand;
[0010] Inputting the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the flexible resource aggregate evolution of the target power grid into the trained evolutionary dynamics model, obtaining the estimated number of resources participating in various regulation task scenarios when the evolution reaches an equilibrium state under various regulation task scenarios and the time required to evolve from the current state to the equilibrium state;
[0011] Calculate the optimal market price cap value of each regulation task scenario of the target power grid according to the guidance target, the estimated number of resources participating in each regulation task scenario when the evolution reaches the equilibrium state under each regulation task scenario, and the time required to evolve from the current state to the equilibrium state;
[0012] According to the optimal market price cap value under various regulation task scenarios of the target power grid, flexible resources are guided to aggregate.
[0013] The grid-guided resource aggregate evolution method of the present invention is further improved in that:
[0014] Furthermore, the evolutionary dynamics model is constructed based on BP neural network.
[0015] Furthermore, the current state parameters of the evolution of the flexible resource aggregate of the target power grid include the set of regulation task scenarios that can currently be participated in, the number of resources participating in each type of regulation task scenario, the estimated complexity of the flexible resource information connection network, and the historical rate of return under each type of regulation task scenario.
[0016] Furthermore, the guiding target is:
[0017]
[0018] in, is the set of regulation task scenarios expected by the power grid, S j represents the jth adjustment task scenario, j = 1, 2, ..., n, For the jth adjustment task scenario S j The corresponding guidance target, To participate in the jth adjustment task scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required.
[0019] Further, the process of calculating the optimal market price cap value of each regulation task scenario of the target power grid according to the guidance target, the estimated number of resources participating in each regulation task scenario when the evolution reaches the equilibrium state under each regulation task scenario, and the time required to evolve from the current state to the equilibrium state is as follows:
[0020] Calculate the difference between the number of resources involved in each type of adjustment task scenario when the guidance target is reached and the time required to evolve from the current state to the equilibrium state;
[0021] constructing an optimization problem based on the difference;
[0022] Solve the optimization problem to obtain the optimal market price cap value under various regulation task scenarios of the target power grid.
[0023] Furthermore, the optimization problem is:
[0024]
[0025] in, When the evolution reaches equilibrium, participate in the jth adjustment task scenario S j The number of resources, To participate in the jth adjustment demand scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required, For the jth adjustment task scenario S j The time required to evolve from the current state to the equilibrium state, For the jth adjustment task scenario S j The lower limit of the market price cap, For the jth adjustment task scenario S j The market price cap, P j For the jth adjustment task scenario S j The initial market price cap value.
[0026] In a second aspect of the present invention, the grid-guided resource aggregation evolution system of the present invention comprises:
[0027] A first acquisition module is used to acquire current state parameters of the flexible resource aggregate evolution of the target power grid;
[0028] The second acquisition module is used to obtain the initial market price cap value of various regulation task scenarios of the target power grid;
[0029] A determination module, used to determine a guidance target according to power grid demand;
[0030] A prediction module, used to input the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the evolution of the flexible resource aggregate of the target power grid into the trained evolutionary dynamics model, to obtain the estimated number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state under various regulation task scenarios and the time required to evolve from the current state to the equilibrium state;
[0031] The first calculation module is used to calculate the optimal market price cap value under various regulation task scenarios of the target power grid according to the guidance target, the estimated future rate of return under various regulation task scenarios, the number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state, and the time required to evolve from the current state to the equilibrium state;
[0032] The guiding module is used to guide the flexible resources to aggregate according to the optimal market price cap value under various regulation task scenarios of the target power grid.
[0033] The grid-guided resource aggregate evolution system of the present invention is further improved in that:
[0034] Furthermore, the first calculation module includes:
[0035] The second calculation module is used to calculate the difference between the guiding target and the number of resources participating in various adjustment task scenarios when the evolution reaches the equilibrium state and the time required to evolve from the current state to the equilibrium state;
[0036] A construction module, used for constructing an optimization problem according to the difference;
[0037] The solution module is used to solve the optimization problem and obtain the optimal market price cap value under various regulation task scenarios of the target power grid.
[0038] Furthermore, the evolutionary dynamics model is constructed based on BP neural network.
[0039] Furthermore, the current state parameters of the evolution of the flexible resource aggregate of the target power grid include the set of regulation task scenarios that can currently be participated in, the number of resources participating in each type of regulation task scenario, the estimated complexity of the flexible resource information connection network, and the historical rate of return under each type of regulation task scenario.
[0040] Furthermore, the guiding target is:
[0041]
[0042] in, is the set of regulation task scenarios expected by the power grid, S j represents the jth adjustment task scenario, j = 1, 2, ..., n, For the jth adjustment task scenario S j The corresponding guidance target, To participate in the jth adjustment task scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required.
[0043] Furthermore, the optimization problem is:
[0044]
[0045] in, When the evolution reaches equilibrium, participate in the jth adjustment task scenario S j The number of resources, To participate in the jth adjustment demand scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required, For the jth adjustment task scenario S j The time required to evolve from the current state to the equilibrium state, For the jth adjustment task scenario S j The lower limit of the market price cap, For the jth adjustment task scenario S j The market price cap, P j For the jth adjustment task scenario S j The initial market price cap value.
[0046] In a third aspect of the present invention, the computer device of the present invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the grid-guided resource aggregate evolution method when executing the computer program.
[0047] In a fourth aspect of the present invention, the computer-readable storage medium of the present invention stores a computer program, and when the computer program is executed by a processor, the steps of the grid-guided resource aggregate evolution method are implemented.
[0048] The present invention has the following beneficial effects:
[0049] During specific operation, the grid-guided resource aggregate evolution method, system, device and medium of the present invention input the initial market price cap values of various regulation task scenarios of the target grid and the current state parameters of the target grid's flexible resource aggregate evolution into the trained evolutionary dynamics model, and obtain the estimated number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state under various regulation task scenarios, as well as the time required to evolve from the current state to the equilibrium state. The mapping relationship between the evolution motivation and result of the resource aggregate is revealed through the evolutionary dynamics model. Compared with the existing research on resource aggregation process modeling, the cumbersome mechanism modeling process is omitted, and the technology is more concise and practical. In addition, the optimal market price cap values under various regulation task scenarios are calculated in combination with grid demand, and the flexible resources are guided to aggregate so that the guidance results meet the grid demand. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:
[0051] Figure 1 It is the principle diagram of the method of the present invention;
[0052] Figure 2 This is the architecture diagram of the evolutionary dynamics model;
[0053] Figure 3 A flow chart for modeling evolutionary dynamics;
[0054] Figure 4 It is a system structure diagram of the present invention. DETAILED DESCRIPTION
[0055] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all embodiments, and is not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concepts disclosed in the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.
[0056] The accompanying drawings show schematic diagrams of structures according to embodiments disclosed in the present invention. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.
[0057] Embodiment 1
[0058] refer to Figure 1 The grid-guided resource aggregate evolution method of the present invention comprises the following steps:
[0059] 1) Obtain the current state parameters of the flexible resource aggregate evolution of the target power grid;
[0060] The current state parameters of the flexible resource aggregate evolution of the target power grid include the set of adjustment task scenarios that can currently participate S = [S1, S2, ..., S m ], the number of resources involved in various adjustment task scenarios N j , the estimated complexity of the flexible resource information connection network O and the historical rate of return η under various adjustment task scenarios j , j=1,2,...,m.
[0061] Construct the current state matrix as:
[0062]
[0063] Among them, the jth row of the current state matrix corresponds to the adjustment task scenario S j status information.
[0064] 2) Within the permitted range, set the initial market price cap value P for various regulation task scenarios of the target power grid j ;
[0065] 3) Input guidance target according to grid demand;
[0066] The process of step 3) is:
[0067] The evolution direction of the flexible resource aggregate of the target power grid should be guided by the grid regulation demand. When the regulation type and capacity provided by the formed resource aggregate do not match the expected demand of the grid, the grid guides the evolution direction of the aggregate through price guidance signals. Specifically, the grid guidance generally occurs in the following two scenarios:
[0068] The first category: New types of regulation demand for the power grid, which need to be guided to form flexible resource aggregates that can participate in new regulation task scenarios.
[0069] Assume that the existing regulation task scenario of the power grid is:
[0070] S=[S1,S2,...,S i ]
[0071] The required capacity set for each task scenario is:
[0072] C=[C1,C2,...,C i ]
[0073] Among them, C j For the jth adjustment task scenario S j Required regulating capacity.
[0074] When a new regulation task scenario is added to the power grid, the task scenario set and the corresponding demand capacity set are updated as follows:
[0075] S=[S1,S2,...,S i ,...,S m ]
[0076] C=[C1,C2,...,C i ,...,C m ]
[0077] The second category: The type of grid regulation demand remains unchanged, but the degree of demand for the regulation task scenario changes, and it is necessary to guide the increase or decrease of the number of resources participating in the corresponding task scenario.
[0078] In this case, the task scenario set and the corresponding required capacity set are updated as follows:
[0079] S=[S1,S2,...,S i ]
[0080] C=[C'1,C'2,...,C' i ]
[0081] In the above two scenarios, the final regulation requirements of the power grid can be generally described as follows:
[0082] Assume that the set of regulation task scenarios expected by the power grid is The corresponding expected regulation demand capacity set is Then we have:
[0083]
[0084] Since the adjustment capacity of various adjustment task scenarios is closely related to the number of resources participating in the task, for the convenience of observation, the adjustment demand capacity of various task scenarios is converted into the number of resources expected to participate in the task:
[0085]
[0086] in, To participate in the jth adjustment task scenario S j The expected number of resources, For the jth adjustment task scenario S j The expected demand capacity, It is the estimated average adjustable capacity of each flexible resource unit.
[0087] In addition, considering that the regulation requirements of the power grid are complex and changeable, the time required to guide flexible resources to the desired state must be taken into consideration. Therefore, the expected time for the grid guidance to take effect is also an important part of the guidance target.
[0088] Therefore, the final power grid guidance target is expressed as:
[0089]
[0090] in, For the jth adjustment task scenario S j The corresponding bootstrap targets include the expected number of resources and the expected bootstrap effective time, namely:
[0091]
[0092] in, To participate in the jth adjustment demand scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required.
[0093] 4) Inputting the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the flexible resource aggregate evolution of the target power grid into the trained evolutionary dynamics model to obtain prediction results, which include the estimated future yields under various regulation task scenarios, the number of resources participating in various regulation task scenarios when the evolution reaches a balanced state, and the time required to evolve from the current state to the balanced state;
[0094] The process of step 4) is:
[0095] 41) Construct evolutionary dynamics model;
[0096] 411) Determine the main factors that affect resource aggregation results;
[0097] In terms of the factors affecting the results of resource aggregation, considering that resources often act on the principle of maximizing benefits, the historical rate of return and future estimated rate of return of power grid regulation tasks are the primary factors affecting the evolution of resource aggregates. Among them, the future estimated rate of return of tasks cannot be directly obtained. It is necessary to combine the historical power market transactions and predict the future expected task demand capacity and corresponding market price cap of the power grid. At the same time, the aggregation between resources is based on information interaction. The number of resources currently involved in various regulation tasks and the complexity of the information connection network between resources will also have an important impact on the results of resource aggregate evolution. In summary, the main factors affecting the future resource aggregation results are summarized in Table 1.
[0098] Table 1
[0099] Influencing factors Example Historical mission rate of return (%) 50 Future expected mission demand capacity (kW) 50000 Future electricity market price cap (yuan / kW) 0.78 The number of resources currently involved in the adjustment task (number) 1400 Complexity of information connection network between resources 10
[0100] 4111) Historical mission rate of return η;
[0101] After the aggregate responds to the grid task, the grid will evaluate the response effect and clear the settlement. The historical rate of return reflects the income of such regulation tasks in the previous stage. When the historical rate of return η of a certain type of regulation task does not meet the expected value of the resource, it will lead to the number of resources N participating in this type of task scenario. f The historical rate of return η of the adjustment task scenario is:
[0102]
[0103] Among them, C p is the total response capacity, r is the clearing price, R p The total cost of the response.
[0104] 4112) Future estimated rate of return θ;
[0105] The future mission yield θ is subject to the future estimated demand capacity of such missions published by the grid As well as the impact of future market price cap P, the higher the future estimated rate of return, the more resources are willing to participate in this type of adjustment task.
[0106] 4113) The number of resources N currently involved in the adjustment task;
[0107] The number of resources N involved in a certain type of regulation task scenario represents the responsiveness of the resource aggregate to this type of task scenario in the current evolutionary state. At the same time, the more resources involved in the task, the more complex the information interaction relationship between resources, which has an important impact on the results of the aggregate evolution.
[0108] 4114) The network complexity of information connection between resources is O;
[0109] The information connection network interacts between flexible resources to determine each other’s response characteristics and the benefits of each resource aggregate. The complexity of the information network determines the scope and speed of information dissemination, which in turn affects the number of resources involved in the regulation task and the speed of evolution. The information connection network between resources has the characteristics of a scale-free network structure. The complexity O of the network is:
[0110] O=∑ i∈M k i
[0111] Among them, M is the set of all resources participating in a certain type of regulation task of the power grid, k i is the degree of resource individual i, that is, the number of resources that have information interaction relationships with this resource.
[0112] In practice, the network complexity O cannot be directly obtained. In the present invention, it is approximately replaced by the estimated value of the number of interactive resources of a single flexible resource at the current moment.
[0113] 412) Constructing the evolutionary dynamics model framework;
[0114] In the present invention, the evolutionary dynamics model aims to establish a mapping relationship between the main influencing factors (input variables) of resource aggregation and the aggregation results (output variables) to reveal the evolutionary mechanism of the resource aggregation process, so as to predict the future evolutionary results based on the current aggregation state. Among the variables that describe the evolutionary results of the resource aggregate, the variables that the power grid is concerned about can reflect the future demand response capabilities of the resource aggregate, and can be characterized by the number of flexible resources that will participate in various regulation task scenarios in the future. At the same time, considering that the guidance signal of the power grid will not take effect immediately, the model should pay attention to the time it takes for the current number of resources to evolve to the expected number of the power grid. Therefore, the predictive variables of the evolutionary dynamics model include the number of flexible resources N that will participate in the regulation task scenarios in the future. P and the time t required for evolution to reach the corresponding resource quantity P .
[0115] refer to Figure 2 The evolutionary dynamics model described in the present invention includes a prediction model for the scale of aggregated resources involved in regulating tasks under equilibrium, a future task yield prediction module, and a dynamic evolution time prediction model.
[0116] Among them, the prediction model of the scale of aggregated resources participating in the adjustment task in the equilibrium state predicts the number of flexible resources N participating in the adjustment task scenario when the aggregate evolves to the equilibrium state based on the historical task yield η, the future estimated yield θ, the current number of resources N participating in the adjustment task and the complexity of the information connection network O between resources. P for:
[0117] N P =f(η,θ,N,O)
[0118] Among them, the future mission rate of return prediction module is based on the future mission demand capacity As well as the initial power market task price cap P, the estimated future task estimated rate of return θ is expressed as:
[0119]
[0120] The dynamic evolution time prediction model is based on the number of resources N currently involved in the adjustment task and the number of flexible resources N in the future to participate in the adjustment task scenario. P As well as the influence of the complexity O of the information connection network between resources, the dynamic evolution time t required for resources to evolve from the current state to the new equilibrium state is predicted P for:
[0121] t P =h(N,N P ,O).
[0122] 413) Evolutionary dynamics modeling based on BP neural network fitting;
[0123] There is a complex nonlinear mapping law between the influencing factors of resource aggregation and the evolution results. Considering the availability of historical response data, the present invention considers adopting a data-driven approach to establish the final evolutionary dynamics model based on neural network training.
[0124] refer to Figure 3 , obtain the historical yield of a certain type of regulation task, the number of resources participating in the historical task, the complexity of the information connection network between resources, and the future demand capacity and future market price cap of this type of task released by the power grid from the historical response data, record the actual task yield under the above values, the number of resources participating in the task when the aggregation reaches a relative steady state, and the actual evolution time, and use this to construct a training data set, and train the resource scale prediction model of the aggregation of regulation tasks in equilibrium, the future task yield prediction module and the dynamic evolution time prediction model according to the training data set, and select the mapping model with the best training error, data fitting degree and prediction effect of new data as the training equilibrium state participating regulation task aggregation resource scale prediction model, future task yield prediction module and dynamic evolution time prediction model to form a trained evolutionary dynamics model in combination, the evolutionary dynamics model describes the nonlinear mapping law between various influencing factors and resource aggregation results with high accuracy, and provides a scientific and reliable basis for the guidance of the power grid.
[0125] 42) Under the market price cap values of various adjustment task scenarios, the current state parameters of the evolution of the flexible resource aggregate are input into the trained evolutionary dynamics model to obtain the estimated future rate of return θ under various adjustment task scenarios. j, the number of resources participating in various adjustment task scenarios when the evolution reaches equilibrium and the time required to evolve from the current state to the equilibrium state Right now:
[0126]
[0127] 5) According to the guidance target, the estimated future rate of return under various regulation task scenarios, the number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state, and the time required to evolve from the current state to the equilibrium state, the optimal market price cap value under various regulation task scenarios of the target power grid is calculated, and according to the optimal market price cap value under various regulation task scenarios of the target power grid, the flexible resources are guided to aggregate;
[0128] The process of step 5) is:
[0129] 51) Calculate the difference between the number of resources involved in various adjustment task scenarios when the guidance target reaches the equilibrium state and the time required to evolve from the current state to the equilibrium state, that is:
[0130]
[0131] 52) constructing an optimization problem based on the difference, the optimization problem is:
[0132]
[0133] in, For the jth adjustment task scenario S j The lower limit of the market price cap, For the jth adjustment task scenario S j The market price cap is the upper limit.
[0134] 53) Iteratively solve the optimization problem, and update the market price cap value under various regulation task scenarios within the allowed range to minimize the difference between the prediction result and the guidance target, so as to obtain the optimal market price cap value under various regulation task scenarios of the target power grid.
[0135] Embodiment 2
[0136] refer to Figure 4 The grid-guided resource aggregate evolution system of the present invention comprises:
[0137] A first acquisition module is used to acquire current state parameters of the flexible resource aggregate evolution of the target power grid;
[0138] The second acquisition module is used to obtain the initial market price cap value of various regulation task scenarios of the target power grid;
[0139] A determination module, used to determine a guidance target according to power grid demand;
[0140] A prediction module, used to input the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the evolution of the flexible resource aggregate of the target power grid into the trained evolutionary dynamics model, to obtain the estimated number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state under various regulation task scenarios and the time required to evolve from the current state to the equilibrium state;
[0141] The first calculation module is used to calculate the optimal market price cap value of each regulation task scenario of the target power grid according to the guidance target, the estimated number of resources participating in each regulation task scenario when the evolution reaches the equilibrium state under each regulation task scenario, and the time required to evolve from the current state to the equilibrium state;
[0142] The guiding module is used to guide the flexible resources to aggregate according to the optimal market price cap value under various regulation task scenarios of the target power grid.
[0143] As an implementation manner of the present invention, the first calculation module includes:
[0144] The second calculation module is used to calculate the difference between the guiding target and the number of resources participating in various adjustment task scenarios when the evolution reaches the equilibrium state and the time required to evolve from the current state to the equilibrium state;
[0145] A construction module, used for constructing an optimization problem according to the difference;
[0146] The solution module is used to solve the optimization problem and obtain the optimal market price cap value under various regulation task scenarios of the target power grid.
[0147] As an implementation mode of the present invention, the evolutionary dynamics model is constructed based on a BP neural network.
[0148] As an embodiment of the present invention, the current state parameters of the evolution of the flexible resource aggregate of the target power grid include the set of regulation task scenarios that can currently be participated in, the number of resources participating in each type of regulation task scenario, the estimated complexity of the flexible resource information connection network, and the historical rate of return under each type of regulation task scenario.
[0149] As an implementation mode of the present invention, the guiding target is:
[0150]
[0151] in, is the set of regulation task scenarios expected by the power grid, S j represents the jth adjustment task scenario, j = 1, 2, ..., n, For the jth adjustment task scenario S j The corresponding guidance target, To participate in the jth adjustment task scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required.
[0152] As an implementation mode of the present invention, the optimization problem is:
[0153]
[0154] in, When the evolution reaches equilibrium, participate in the jth adjustment task scenario S j The number of resources, To participate in the jth adjustment demand scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required, For the jth adjustment task scenario S j The time required to evolve from the current state to the equilibrium state, For the jth adjustment task scenario S j The lower limit of the market price cap, For the jth adjustment task scenario S j The market price cap, P j is the jth adjustment task scenario S j The market price cap value.
[0155] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.
[0156] Embodiment 3
[0157] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the resource aggregate evolution method guided by the power grid when executing the computer program, for example, comprising: obtaining current state parameters of the flexible resource aggregate evolution of the target power grid; obtaining initial market price cap values of various regulation task scenarios of the target power grid; determining a guidance target according to power grid demand; inputting the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the flexible resource aggregate evolution of the target power grid into a trained evolutionary dynamics model to obtain the estimated number of resources participating in various regulation task scenarios when the evolution reaches an equilibrium state under various regulation task scenarios and the time required for evolution from the current state to the equilibrium state; calculating the optimal market price cap values under various regulation task scenarios of the target power grid according to the guidance target, the estimated number of resources participating in various regulation task scenarios when the evolution reaches an equilibrium state under various regulation task scenarios and the time required for evolution from the current state to the equilibrium state; guiding flexible resources to aggregate according to the optimal market price cap values under the various regulation task scenarios. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, network interface, and memory are interconnected through an internal bus, and the internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.
[0158] Embodiment 4
[0159] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the resource aggregate evolution method guided by the power grid, for example, including: obtaining the current state parameters of the flexible resource aggregate evolution of the target power grid; obtaining the initial market price cap values of various regulation task scenarios of the target power grid; determining the guidance target according to the power grid demand; inputting the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the flexible resource aggregate evolution of the target power grid into a trained evolutionary dynamics model to obtain the estimated number of resources participating in various regulation task scenarios when the evolution reaches a balanced state under various regulation task scenarios and the time required to evolve from the current state to the balanced state; calculating the optimal market price cap values under various regulation task scenarios of the target power grid according to the guidance target, the estimated number of resources participating in various regulation task scenarios when the evolution reaches a balanced state under various regulation task scenarios and the time required to evolve from the current state to the balanced state; guiding the flexible resources to aggregate according to the optimal market price cap values under various regulation task scenarios of the target power grid. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.
[0160] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0161] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0162] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A grid-guided resource aggregate evolution method, characterized in that: include: Obtaining current state parameters of the flexible resource aggregate evolution of the target power grid; Obtaining the initial market price cap values for various regulation task scenarios of the target power grid; Determine guidance targets based on grid demand; Inputting the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the flexible resource aggregate evolution of the target power grid into the trained evolutionary dynamics model, obtaining the estimated number of resources participating in various regulation task scenarios when the evolution reaches an equilibrium state under various regulation task scenarios and the time required to evolve from the current state to the equilibrium state; Calculate the optimal market price cap value of each regulation task scenario of the target power grid according to the guidance target, the estimated number of resources participating in each regulation task scenario when the evolution reaches the equilibrium state under each regulation task scenario, and the time required to evolve from the current state to the equilibrium state; According to the optimal market price cap value under various regulation task scenarios of the target power grid, flexible resources are guided to aggregate.
2. The grid-guided resource aggregate evolution method according to claim 1, characterized in that: The evolutionary dynamics model is constructed based on BP neural network.
3. The grid-guided resource aggregate evolution method according to claim 1, characterized in that: The current state parameters of the evolution of the flexible resource aggregate of the target power grid include the set of regulation task scenarios that can currently be participated in, the number of resources participating in various regulation task scenarios, the estimated complexity of the flexible resource information connection network, and the historical yields under various regulation task scenarios.
4. The grid-guided resource aggregate evolution method according to claim 1, characterized in that: The guiding objectives are: in, is the set of regulation task scenarios expected by the power grid, S j represents the jth adjustment task scenario, j = 1, 2, ..., n, For the jth adjustment task scenario S j The corresponding guidance target, To participate in the jth adjustment task scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required.
5. The grid-guided resource aggregate evolution method according to claim 1, characterized in that: The process of calculating the optimal market price cap value of the target power grid under various regulation task scenarios according to the guidance target, the estimated number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state under various regulation task scenarios, and the time required to evolve from the current state to the equilibrium state is: Calculate the difference between the guiding target and the number of resources participating in various adjustment task scenarios when the evolution reaches the equilibrium state and the time required to evolve from the current state to the equilibrium state; constructing an optimization problem based on the difference; Solve the optimization problem to obtain the optimal market price cap value under various regulation task scenarios of the target power grid.
6. The grid-guided resource aggregate evolution method according to claim 5, characterized in that: The optimization problem is: s.t.P jmin ≤P j ≤P jmax ,j=1,2,...,n in, When the evolution reaches equilibrium, participate in the jth adjustment task scenario S j The number of resources, To participate in the jth adjustment demand scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required, For the jth adjustment task scenario S j The time required to evolve from the current state to the equilibrium state, For the jth adjustment task scenario S j The lower limit of the market price cap, For the jth adjustment task scenario S j The market price cap, P j For the jth adjustment task scenario S j The initial market price cap value.
7. A power grid guided resource aggregation evolution system, characterized in that: include: A first acquisition module is used to acquire current state parameters of the flexible resource aggregate evolution of the target power grid; The second acquisition module is used to obtain the initial market price cap value of various regulation task scenarios of the target power grid; A determination module, used to determine a guidance target according to power grid demand; A prediction module, used to input the initial market price cap values of various regulation task scenarios of the target power grid and the current state parameters of the evolution of the flexible resource aggregate of the target power grid into the trained evolutionary dynamics model, to obtain the estimated number of resources participating in various regulation task scenarios when the evolution reaches the equilibrium state under various regulation task scenarios and the time required to evolve from the current state to the equilibrium state; The first calculation module is used to calculate the optimal market price cap value of each regulation task scenario of the target power grid according to the guidance target, the estimated number of resources participating in each regulation task scenario when the evolution reaches the equilibrium state under each regulation task scenario, and the time required to evolve from the current state to the equilibrium state; The guiding module is used to guide the flexible resources to aggregate according to the optimal market price cap value under various regulation task scenarios of the target power grid.
8. The grid-guided resource aggregation evolution system according to claim 7, characterized in that: The first calculation module includes: The second calculation module is used to calculate the difference between the guiding target and the number of resources participating in various adjustment task scenarios when the evolution reaches the equilibrium state and the time required to evolve from the current state to the equilibrium state; A construction module, used for constructing an optimization problem according to the difference; The solution module is used to solve the optimization problem and obtain the optimal market price cap value under various regulation task scenarios of the target power grid.
9. The grid-guided resource aggregation evolution system according to claim 7, characterized in that: The evolutionary dynamics model is constructed based on BP neural network.
10. The grid-guided resource aggregation evolution system according to claim 7, characterized in that: The current state parameters of the evolution of the flexible resource aggregate of the target power grid include the set of regulation task scenarios that can currently be participated in, the number of resources participating in various regulation task scenarios, the estimated complexity of the flexible resource information connection network, and the historical yields under various regulation task scenarios.
11. The grid-guided resource aggregation evolution system according to claim 7, characterized in that: The guiding objectives are: in, is the set of regulation task scenarios expected by the power grid, S j represents the jth adjustment task scenario, j = 1, 2, ..., n, For the jth adjustment task scenario S j The corresponding guidance target, To participate in the jth adjustment task scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required.
12. The grid-guided resource aggregation evolution system according to claim 8, characterized in that: The optimization problem is: s.t.P jmin ≤P j ≤P jmax ,j=1,2,...,n in, When the evolution reaches equilibrium, participate in the jth adjustment task scenario S j The number of resources, To participate in the jth adjustment demand scenario S j The expected value of the number of resources, To guide resources to reach the jth adjustment task scenario S j The expected time required, For the jth adjustment task scenario S j The time required to evolve from the current state to the equilibrium state, For the jth adjustment task scenario S j The lower limit of the market price cap, For the jth adjustment task scenario S j The market price cap, P j For the jth adjustment task scenario S j The initial market price cap value.
13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the grid-guided resource aggregation evolution method according to any one of claims 1 to 6 are implemented.
14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the grid-guided resource aggregation evolution method according to any one of claims 1 to 6 are implemented.
