Power distribution network resource regulation method and device, storage medium and electronic equipment

Abstract

The application provides a power distribution network resource regulation method and device, a storage medium and an electronic device, and belongs to the technical field of power grid control. The power distribution network resource regulation method is applied to a virtual power plant of the power distribution network. The method comprises the following steps: acquiring real-time data of a regulation subject, wherein the regulation subject comprises photovoltaic, energy storage, charging piles and loads of multiple virtual partitions, and each virtual partition corresponds to a transformer area; based on the real-time data of the regulation subject, an optimal adjustment strategy is determined by using a preset distributed collaborative operation model, the preset distributed collaborative operation model is used to minimize the total adjustment cost of the regulation subject as an objective, and the decision-making behavior of the regulation subject under the condition of incomplete information is described by using a Bayesian game theory; and the regulation subject is controlled based on the optimal adjustment strategy. Distributed energy can be accurately controlled.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid control, in particular to a power distribution network resource regulation method, a power distribution network resource regulation device, a machine readable storage medium and an electronic device. BACKGROUND

[0002] As a new generation of intelligent control technology integrating "source-load-storage" multi-link resources, virtual power plants can break geographical restrictions and realize energy interconnection and sharing in a wide area. Virtual power plants integrate dispersed photovoltaic, wind power, energy storage, electric vehicles, controllable loads and other resources into a unified controllable "virtual unit", which is coordinated by intelligent algorithms to make up for the defects of small scale and large fluctuations of single distributed resources. Virtual power plants are the core hub of building a new power system, and their value lies not only in technology integration, but also in restructuring the power ecology - from "centralized supply" to "distributed coordination", and from "source following load" to "source grid load storage interaction". Virtual power plants will become the standard infrastructure for the intelligentization of power systems.

[0003] In the context of global power systems, virtual power plants use advanced metering, communication and control technologies to integrate distributed energy resources at each node of the power grid into a virtual power plant, like a bridge connecting high and low voltage grids, breaking down the barriers between wholesale and retail markets, optimizing resource allocation, and occupying a commanding position in the electricity market.

[0004] However, existing virtual power plants are mostly controlled under complete information conditions, that is, each game player in the game is fully aware of the strategy set and profit function of other game players. However, the game optimization process based on complete information is too idealistic. In the optimization and scheduling of power system planning and operation and power market, each participant is reluctant to share private information due to privacy protection and other reasons, which makes it impossible to obtain some information or some participants' information is not known to other participants, making the control of virtual power plants less accurate. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a power distribution network resource regulation method, a power distribution network resource regulation device, a machine readable storage medium and an electronic device, which introduces Bayesian game theory to describe the decision-making behavior of each regulation and control subject in the virtual power plant under non-complete information conditions, so that the optimal adjustment strategy is more accurate, thereby accurately controlling distributed energy.

[0006] To achieve the above purpose, the first aspect of the present application provides a power distribution network resource regulation method applied to a virtual power plant of the power distribution network, the power distribution network resource regulation method comprising:

[0007] Obtaining real-time data of a regulation subject, the regulation subject including photovoltaic, energy storage, charging piles and loads in multiple virtual partitions, each virtual partition corresponding to a transformer district;

[0008] Based on the real-time data of the regulation subject, an optimal adjustment strategy is determined by using a preset distributed collaborative operation model, the preset distributed collaborative operation model being used to describe decision behaviors of the regulation subject under non-complete information conditions by using a Bayesian game theory with the objective of minimizing total adjustment costs of the regulation subject.

[0009] Based on the optimal adjustment strategy, the regulation subject is controlled.

[0010] In the embodiments of the present application, based on the real-time data of the regulation subject, the optimal adjustment strategy is determined by using the preset distributed collaborative operation model, including:

[0011] Based on the real-time data of the regulation subject, the preset distributed collaborative operation model is solved by using Bayesian learning to obtain the optimal adjustment strategy.

[0012] In the embodiments of the present application, based on the real-time data of the regulation subject, the preset distributed collaborative operation model is solved by using Bayesian learning to obtain the optimal adjustment strategy, including:

[0013] An initial belief and an initial strategy of the regulation subject are set;

[0014] Based on the real-time data of the regulation subject, the belief and the strategy are iteratively updated until the updated belief and strategy satisfy a preset convergence condition, and the optimal adjustment strategy is obtained.

[0015] In the embodiments of the present application, based on the real-time data of the regulation subject, the belief and the strategy are iteratively updated until the updated belief and strategy satisfy a preset convergence condition, and the optimal adjustment strategy is obtained, including:

[0016] Based on the real-time data of the regulation subject, a Bayesian Nash equilibrium condition is solved to obtain a new strategy;

[0017] Based on the new strategy and an objective function in the preset distributed collaborative operation model, a new electricity price is calculated;

[0018] Based on the new strategy, the belief is updated to obtain a new belief;

[0019] It is judged whether the new strategy and the new belief satisfy a preset convergence condition;

[0020] In a case where it is determined that the new strategy and the new belief satisfy the preset convergence condition, the optimal adjustment strategy is obtained.

[0021] In the embodiment of the present application, the objective function in the preset distributed cooperative operation model is:

[0022]

[0023] wherein, is the strategy of each game party, is the private type of each game party, represents the cost, represents photovoltaic, represents energy storage, represents charging piles, represents load, is a balance weight coefficient, is a target regulation power.

[0024] In the embodiment of the present application, the construction process of the preset distributed cooperative operation model comprises:

[0025] Based on the regulation subject, a game party set is determined;

[0026] The private type and strategy space of each game party in the game party set are obtained;

[0027] Based on the private type and strategy space of each game party, the utility function of each game party is constructed;

[0028] With the goal of maximizing the expected utility, based on the utility function of each game party, the Bayes Nash equilibrium condition is constructed;

[0029] With the optimization goal of minimizing the total regulation cost of the regulation subject, the objective function is constructed, and the distributed cooperative operation model is obtained.

[0030] In the embodiment of the present application, the obtaining of the private type and strategy space of each game party in the game party set comprises:

[0031] The output regulation amount of the photovoltaic, the charge and discharge power of the energy storage, the charging plan offset amount of the charging pile, and the demand response amount of the load are obtained;

[0032] Based on the output regulation amount of the photovoltaic, the charge and discharge power of the energy storage, the charging plan offset amount of the charging pile, and the demand response amount of the load, the strategy space of each game party in the game party set is obtained;

[0033] The light prediction error distribution parameter of the photovoltaic, the capacity attenuation cost of the energy storage, the user demand elasticity of the charging pile, and the price sensitivity of the load are obtained;

[0034] ​​obtain a private type of each game party in the set of game parties based on the photovoltaic light illumination prediction error distribution parameter, the energy storage capacity attenuation cost, the charging pile user demand elasticity, and the load price sensitivity.

[0035] In the embodiment of the application, the control of the regulation subject based on the optimal adjustment strategy comprises:

[0036] The output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile, and / or the demand response amount of the load are adjusted based on the optimal adjustment strategy.

[0037] The second aspect of the application provides a power distribution network resource adjustment device applied to a virtual power plant of a power distribution network, and the power distribution network resource adjustment device comprises:

[0038] An acquisition module is configured to acquire real-time data of a regulation subject, wherein the regulation subject comprises photovoltaics, energy storages, charging piles, and loads of a plurality of virtual partitions, each virtual partition corresponding to a transformer area;

[0039] A determination module is configured to determine an optimal adjustment strategy based on the real-time data of the regulation subject by using a preset distributed collaborative operation model, wherein the preset distributed collaborative operation model is used to describe decision-making behaviors of the regulation subject under non-complete information conditions by using a Bayesian game theory with the objective of minimizing total adjustment costs of the regulation subject.

[0040] A control module is configured to control the regulation subject based on the optimal adjustment strategy.

[0041] In the embodiment of the application, the determination module comprises:

[0042] A solving submodule is configured to solve the preset distributed collaborative operation model by using Bayesian learning based on the real-time data of the regulation subject, and obtain the optimal adjustment strategy.

[0043] In the embodiment of the application, the solving submodule comprises:

[0044] A setting unit is configured to set an initial belief and an initial strategy of the regulation subject.

[0045] An iteration unit is configured to iteratively update the belief and the strategy based on the real-time data of the regulation subject until the updated belief and the strategy satisfy a preset convergence condition, and obtain the optimal adjustment strategy.

[0046] The third aspect of the application provides an electronic device, which comprises:

[0047] at least one processor;

[0048] a memory connected with the at least one processor;

[0049] The memory stores instructions executable by the at least one processor, and the at least one processor implements the power distribution network resource adjustment method by executing the instructions stored in the memory.

[0050] The fourth aspect of the application provides a machine-readable storage medium, which stores instructions, and the instructions make the processor be configured to execute the power distribution network resource adjustment method when the processor executes the instructions.

[0051] Through the above technical solution, the real-time data of the control subject is obtained by the virtual power plant of the power distribution network, the control subject includes a plurality of virtual partition photovoltaic, energy storage, charging pile and load, each virtual partition corresponds to a transformer area; based on the real-time data of the control subject, the optimal adjustment strategy is determined by using a preset distributed collaborative operation model, the preset distributed collaborative operation model is used to minimize the total adjustment cost of the control subject as the target, and the decision-making behavior of the control subject under the condition of incomplete information is described by using the Bayesian game theory; based on the optimal adjustment strategy, the control subject is controlled. By introducing the Bayesian game theory to describe the decision-making behavior of each control subject in the virtual power plant under the condition of incomplete information, the optimal adjustment strategy obtained is more accurate, so that the distributed energy can be accurately controlled. By dividing the large-scale distributed energy resources into a plurality of geographical or functional sub-areas, the global collaborative optimization is realized while ensuring the autonomous decision-making of each sub-area, thereby effectively ensuring the maximum consumption of large-scale distributed energy and improving the flexibility and stability of the power distribution network.

[0052] Other features and advantages of the embodiments of the application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0053] The accompanying drawings are included to provide a further understanding of the embodiments of the application, and constitute a part of the specification, and are used together with the following specific embodiments to explain the embodiments of the application, but do not constitute a limitation on the embodiments of the application. In the drawings:

[0054] Figure 1 The flowchart of the power distribution network resource adjustment method according to the embodiments of the application is schematically shown;

[0055] Figure 2 The hierarchical partition collaborative operation architecture of the virtual power plant according to the embodiments of the application is schematically shown;

[0056] Figure 3 The structural block diagram of the power distribution network resource adjustment device according to the embodiments of the application is schematically shown;

[0057] Figure 4 Fig. 1 shows a schematic diagram of the internal structure of a computer device according to an embodiment of the present application.

[0058] Legend of reference signs

[0059] 410 - acquisition module; 420 - determination module; 430 - control module; A01 - processor; A02 - network interface; A03 - internal memory; A04 - display screen; A05 - input device; A06 - non-volatile storage medium; B01 - operating system; B02 - computer program. DETAILED DESCRIPTION

[0060] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative and explanatory and are not intended to limit the present application.

[0061] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application comply with relevant provisions of laws and regulations. In the embodiments of the present application, some industry existing solutions, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0062] It should be noted that if the present application embodiments involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative positional relationship, movement, etc. between components in a certain posture (as shown in the drawings), if the certain posture changes, the directional indications will also change accordingly.

[0063] In addition, if the present application embodiments involve descriptions of "first", "second", etc., the descriptions of "first", "second", etc. are only for description purposes and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features with "first" and "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection claimed by the present application.

[0064] Please refer to Figure 1 , Figure 1A flowchart of a power distribution network resource regulation method according to an embodiment of the present application is schematically shown. The embodiment provides a power distribution network resource regulation method applied to a virtual power plant of the power distribution network, and the power distribution network resource regulation method comprises the following steps:

[0065] Step 210: acquiring real-time data of a regulation subject, the regulation subject comprising photovoltaic, energy storage, charging piles and loads of a plurality of virtual partitions, each virtual partition corresponding to a transformer area;

[0066] In the embodiment, the virtual power plant of the power distribution network serves as a virtual energy management system, aggregates each virtual partition by using advanced communication technology and power transmission and distribution lines, and collaboratively controls distributed energy according to a certain operation strategy. Please refer to Figure 2 , Figure 2 A virtual power plant hierarchical partition collaborative operation architecture schematic diagram according to an embodiment of the present application is schematically shown. The virtual power plant hierarchical partition collaborative operation architecture comprises a partition autonomous layer, a global optimization layer, a virtual power plant layer and a main grid power system layer. The partition autonomous layer comprises photovoltaic, energy storage, charging stations and adjustable loads, and can be constructed into a virtual partition by distributed resources in the same regional power distribution network, that is, a transformer area of a power distribution network constitutes a virtual partition, and photovoltaic, energy storage, charging stations and adjustable loads in the transformer area are regulation subjects of the virtual partition. The real-time data of the above-mentioned regulation subject refers to real-time data of each distributed resource in each virtual partition, such as photovoltaic output and load response. The above-mentioned acquisition can be achieved by sending the real-time collected data of each transformer area to the virtual power plant of the power distribution network.

[0067] Step 220: determining an optimal adjustment strategy by using a preset distributed collaborative operation model based on the real-time data of the regulation subject, the preset distributed collaborative operation model being used to minimize the total adjustment cost of the regulation subject as an objective, and describing decision behaviors of the regulation subject under non-complete information condition by using Bayesian game theory;

[0068] In the embodiment, the virtual power plant determines the optimal adjustment strategy by using the preset distributed collaborative operation model based on the real-time data of all regulation subjects. The above-mentioned preset distributed collaborative operation model can be obtained by constructing based on Bayesian game in advance.

[0069] Among them, a complete Bayesian game contains the following five basic elements:

[0070] (1) Game party: an individual or organization participating in the defined Bayesian game, independently making decisions and independently bearing results.

[0071] (2) Type of game player: In the non-complete information game, the type of game player is divided by the non-public information. Each game player can have one or more types, and different types will affect the decision of the game player. Assume that the type of game player is , and , represents the set of all types of game player .

[0072] (3) Conditional probability: On the basis of the belief of "natural" action , the game player infers the probability of the actual type combination of other game players under the condition that the type of game player is , that is, to find the conditional probability . According to the Bayes formula, we have:

[0073] ,

[0074] In the formula, represents the type space composed of the type set of other game players except game player .

[0075] (4) Strategy space of game player: All the strategies that the game player can choose under his possible type. Assume that the strategy space of game player under type is .

[0076] (5) Utility of game player: Corresponding to each possible strategy selection of each game player, there is a result that the game player needs to bear independently to represent the gain and loss of the game player under the strategy combination. The utility function of each game player is defined as the benefit minus the cost , and depends on the own strategy , the action of other participants and the private type .

[0077] In some embodiments, the construction process of the preset distributed collaborative operation model includes:

[0078] First, based on the regulation subject, the game player set is determined;

[0079] In this embodiment, the game player set can be represented as , wherein represents photovoltaic, represents energy storage,​ represents a charging pile, represents a load. It should be noted that it can be determined according to the actual situation of the virtual partition, can include one or more of photovoltaic, energy storage, charging pile and load, or can also include other distributed energy sources.

[0080] Then, the private type and strategy space of each game party in the game party set are obtained;

[0081] In this embodiment, each game party has a private type to represent incomplete information (such as photovoltaic prediction error, energy storage cost, load elasticity, etc.), which cannot be directly observed by other game parties, but is known to be subject to a prior distribution probability .

[0082] In some embodiments, the obtaining of the private type and strategy space of each game party in the game party set comprises:

[0083] First, the output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile and the demand response amount of the load are obtained;

[0084] Second, based on the output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile and the demand response amount of the load, the strategy space of each game party in the game party set is obtained;

[0085] Third, the illumination prediction error distribution parameter of the photovoltaic, the capacity attenuation cost of the energy storage, the user demand elasticity of the charging pile and the price sensitivity of the load are obtained;

[0086] Fourth, based on the illumination prediction error distribution parameter of the photovoltaic, the capacity attenuation cost of the energy storage, the user demand elasticity of the charging pile and the price sensitivity of the load, the private type of each game party in the game party set is obtained.

[0087] In this embodiment, the strategy of the game party , for the photovoltaic, the output adjustment amount , the private type contains the illumination prediction error distribution parameter, is the maximum adjustment power; for the energy storage, the charging and discharging power , the private type contains the capacity attenuation cost, , is the maximum charging power and the maximum discharging power; for the charging pile, the charging plan offset amount , the private type Includes user demand flexibility, Maximum delay time; for load, demand response time. Private type Including electricity price sensitivity, This represents the maximum load that can be reduced.

[0088] By acquiring the output adjustment of the photovoltaic system, the charging and discharging power of the energy storage system, the charging plan offset of the charging pile, and the demand response of the load, the strategy space of each player can be constructed. The solar illumination prediction error distribution parameters of the photovoltaic system, the capacity decay cost of the energy storage system, the user demand elasticity of the charging pile, and the electricity price sensitivity of the load can determine the private type of each player, so as to better construct a Bayesian game model.

[0089] Then, based on the private type and strategy space of each player, the utility function of each player is constructed.

[0090] In this embodiment, the game players The utility function can be expressed as:

[0091] ,

[0092] in, As the game player The effect, As the game player The benefits, As the game player The cost.

[0093] For photovoltaic power, electricity sales revenue typically depends on the electricity price. and actual power generation ,Right now The cost refers to operation and maintenance costs, such as fixed costs or power generation losses, which can be expressed as: , It is a constant.

[0094] For energy storage, the profit comes from peak-valley arbitrage, which involves buying low and selling high to profit from the price difference, i.e.: The cost is battery degradation, which can be expressed as: ,in, The energy storage battery degradation coefficient can be determined in advance. This refers to the state of charge of the energy storage battery.

[0095] For charging stations, the revenue comes from demand response subsidies, i.e. ,in, For demand response; the cost is the loss of user satisfaction, which can be expressed as: ,in, The satisfaction sensitivity coefficient can be determined in advance.

[0096] For the load, the benefit is the electricity price discount, that is , wherein The actual electricity consumption can be obtained, The discount price of unit load reduction can be determined in advance; the cost is the energy inconvenience cost, which can be expressed as: , wherein The elasticity coefficient reflects the sensitivity of the user to the reduction, which can be determined in advance according to the actual situation.

[0097] Then, based on the utility function of each game player, the Bayesian Nash equilibrium condition is constructed by maximizing the expected utility.

[0098] In this embodiment, each game player updates the belief under the condition that the strategies and type distributions of other game players are given , and can select the strategy that maximizes the expected utility, which is expressed as:

[0099] .

[0100] Finally, the objective function is constructed to obtain the distributed collaborative operation model by minimizing the total adjustment cost of the virtual partition.

[0101] The objective function in the preset distributed collaborative operation model is:

[0102] ,

[0103] , wherein The strategy of each game player is The private type of each game player is , which represents the cost, , represents photovoltaic, represents energy storage, represents charging piles, represents load, The balance weight coefficient can be set in advance, The target adjustment power is

[0104] Each participant obtains the individual optimal action based on the current electricity price and type, and the VPP adjusts the electricity price so that the aggregation result of the individual optimal action approximates the target. The action of each game player can be associated with the objective function by the following steps:

[0105] Each game player solves the local optimization problem based on the current electricity price and type .

[0106] ,

[0107] wherein, is the benefit of participating in VPP regulation, is the cost of participating in regulation, such as photovoltaic light abandonment, energy storage attenuation, etc. is the tracking and iteration of the initial value of VPP, and VPP adjusts the electricity price so that the aggregate result of individual optimal action approaches the target . .

[0108] is the strategy of each game party, is the private type of each game party, and the target function is participated in by energy storage, photovoltaic, etc. It is assumed that the amount to be regulated is known, and the meaning of the target function is to try to approach the regulated amount by regulating various distributed energy. Here, it can all be energy storage, all be photovoltaic, or be energy storage + photovoltaic. Each participant obtains individual optimal action based on the current electricity price and type, and VPP adjusts the electricity price so that the aggregate result of individual optimal action approaches the target value, i.e. the adjustment amount.

[0109] By introducing Bayesian game theory to describe the decision-making behavior of each subject in the virtual power plant (VPP) under incomplete information conditions, it is helpful to accurately regulate the resources of each virtual partition.

[0110] In some embodiments, based on the real-time data of the regulation subject, a preset distributed collaborative operation model is used to determine an optimal adjustment strategy, including:

[0111] Based on the real-time data of the regulation subject, a Bayesian learning is used to solve the preset distributed collaborative operation model to obtain an optimal adjustment strategy.

[0112] In this embodiment, Bayesian learning can be used for solving. Bayesian learning dynamically updates the posterior probability distribution of the participant type through the prior distribution and real-time data, thereby improving the solving accuracy of the target function.

[0113] In some embodiments, based on the real-time data of the regulation subject, a Bayesian learning is used to solve the preset distributed collaborative operation model to obtain an optimal adjustment strategy, including:

[0114] First, set the initial belief and initial strategy of the regulation subject;

[0115] Then, based on the real-time data of the regulation subject, the belief and the strategy are iteratively updated until the updated belief and strategy satisfy a preset convergence condition, and an optimal adjustment strategy is obtained.

[0116] The belief and the strategy are iteratively updated based on the real-time data of the regulation subject until the updated belief and strategy satisfy a preset convergence condition, and an optimal adjustment strategy is obtained.

[0117] In the first step, based on the real-time data of the regulation subject, the Bayesian Nash equilibrium condition is solved to obtain a new strategy.

[0118] In the second step, based on the new strategy and the objective function in the preset distributed collaborative operation model, a new electricity price is calculated.

[0119] In the third step, based on the new strategy, the belief is updated to obtain a new belief.

[0120] In the fourth step, it is judged whether the new strategy and the new belief satisfy a preset convergence condition.

[0121] In the fifth step, when it is determined that the new strategy and the new belief satisfy the preset convergence condition, an optimal adjustment strategy is obtained.

[0122] In this embodiment, first, the prior distribution probability of each subject is set, and the prior distribution probability of each participant type can be assumed based on historical data or expert knowledge , i.e., the prior distribution probability of the private type of each game party, for example, is a Gaussian distribution Then, the initial value of each subject is calculated Then, each game party solves the Bayesian Nash equilibrium strategy according to its own type and the type distribution of others , and the Bayesian Nash equilibrium result is:

[0123] ,

[0124] According to the newly observed action , the posterior distribution probability of each subject type is updated as:

[0125] .

[0126] Finally, based on the Bayesian Nash equilibrium result, the objective function of the preset distributed collaborative operation model is calculated to obtain an optimal adjustment strategy of the virtual partition.

[0127] In this embodiment, all actions are collected, the total deviation is calculated, and the electricity price is updated :

[0128] ,

[0129] wherein, is the round electricity price, is the calculated next round electricity price.

[0130] The convergence condition is: and wherein, is the target deviation tolerance, i.e. the allowed error between the total adjustment amount of the virtual power plant and the target value, is the belief distribution change tolerance, which is the upper limit of the change amplitude of the type distribution of the game parties in adjacent two iterations.

[0131] The Bayesian Nash equilibrium only guarantees the individual optimization of each subject under a given electricity price, but the initial electricity price may not make the total adjustment amount meet the target, and the electricity price needs to be adjusted synchronously to maintain system balance. Through real-time updating of data (such as light intensity, load demand, and electricity price fluctuation), the Bayesian can continuously correct the probability distribution of photovoltaic output prediction and charging demand, and reduce the randomness influence of intermittent renewable energy (such as photovoltaic). The strategy can be automatically adjusted according to new data, for example: if the actual output of photovoltaic is continuously lower than the prediction, the Bayesian model will reduce the future prediction value and trigger the discharge of energy storage to compensate. When the demand for charging piles suddenly increases, the priority of energy storage is dynamically adjusted to avoid overload of the power grid. An accurate distributed collaborative operation model can be constructed.

[0132] Step 230: controlling the regulation subject based on the optimal adjustment strategy.

[0133] In this embodiment, according to the optimal adjustment strategy, the object to be adjusted and the corresponding action can be determined, and then the instruction is sent to the regulation subject for regulation.

[0134] In some embodiments, the controlling the regulation subject based on the optimal adjustment strategy comprises:

[0135] adjusting the output adjustment amount of the photovoltaic and / or the charging / discharging power of the energy storage and / or the charging plan offset amount of the charging pile and / or the demand response amount of the load based on the optimal adjustment strategy.

[0136] In this embodiment, if the object to be adjusted in the optimal adjustment strategy is photovoltaic, the output adjustment amount of the photovoltaic is adjusted; if the object to be adjusted in the optimal adjustment strategy is energy storage, the charging / discharging power of the energy storage is adjusted; if the object to be adjusted in the optimal adjustment strategy is charging pile, the charging plan offset amount of the charging pile is adjusted; if the object to be adjusted in the optimal adjustment strategy is load, the demand response amount of the load is adjusted. ​

[0137] By regulating the output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile, and the demand response amount of the load, various distributed energy can be reliably regulated.

[0138] In the implementation process, real-time data of a regulation subject is obtained by a virtual power plant of a power distribution network, the regulation subject includes photovoltaics, energy storages, charging piles and loads of multiple virtual partitions, each virtual partition corresponds to a transformer area; based on the real-time data of the regulation subject, an optimal adjustment strategy is determined by using a preset distributed collaborative operation model, the preset distributed collaborative operation model is used to describe decision behaviors of the regulation subject under incomplete information conditions by using Bayesian game theory, with the goal of minimizing total regulation costs of the regulation subject; and the regulation subject is controlled based on the optimal adjustment strategy. By introducing Bayesian game theory to describe decision behaviors of each regulation subject in the virtual power plant (VPP) under incomplete information conditions, the obtained optimal adjustment strategy is more accurate, so that the distributed energy can be accurately controlled. By dividing large-scale distributed energy resources into multiple geographical or functional sub-areas, global collaborative optimization is realized while ensuring autonomous decision-making of each sub-area, thereby effectively ensuring maximum consumption of large-scale distributed energy and improving flexibility and stability of the power distribution network.

[0139] Please refer to Figure 3 , Figure 3 A structural block diagram of a power distribution network resource regulation device according to an embodiment of the application is schematically shown. The embodiment provides a power distribution network resource regulation device applied to a virtual power plant of the power distribution network, and the power distribution network resource regulation device includes an acquisition module 410, a determination module 420 and a control module 430, wherein:

[0140] The acquisition module 410 is configured to acquire real-time data of a regulation subject, the regulation subject including photovoltaics, energy storages, charging piles and loads of multiple virtual partitions, each virtual partition corresponding to a transformer area;

[0141] The determination module 420 is configured to determine an optimal adjustment strategy based on the real-time data of the regulation subject by using a preset distributed collaborative operation model, the preset distributed collaborative operation model being used to describe decision behaviors of the regulation subject under incomplete information conditions by using Bayesian game theory, with the goal of minimizing total regulation costs of the regulation subject;

[0142] The control module 430 is configured to control the regulation subject based on the optimal adjustment strategy.

[0143] The determination module 420 includes:

[0144] The solving submodule is configured to solve the preset distributed collaborative operation model based on real-time data of the regulation subject by using Bayesian learning to obtain an optimal adjustment strategy.

[0145] The solving submodule includes:

[0146] The setting unit is configured to set an initial belief and an initial strategy of the regulation subject.

[0147] The iteration unit is configured to iteratively update the belief and the strategy based on real-time data of the regulation subject until the updated belief and strategy satisfy a preset convergence condition to obtain an optimal adjustment strategy.

[0148] The power distribution network resource regulation device includes a processor and a memory, the above-mentioned acquisition module 410, determination module 420 and control module 430 are stored in the memory as program units, and the corresponding functions are realized by the processor executing the above-mentioned program units stored in the memory.

[0149] The processor includes a core, and the core calls the corresponding program units from the memory.

[0150] The memory can include a non-permanent memory in a computer readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0151] The embodiment of the application provides a machine readable storage medium, which stores a program, and the program is executed by a processor to realize the power distribution network resource regulation method.

[0152] The embodiment of the application provides a processor, which is used for running a program, and the program is executed to perform the power distribution network resource regulation method.

[0153] In one embodiment, a computer device can be provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in Figure 4As shown in the figure. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operating system B01 and the computer program B02 in the non-volatile storage medium A06 to run. The network interface A02 of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor A01 to implement a power distribution network resource regulation method. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0154] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0155] In one embodiment, the power distribution network resource regulation apparatus provided by the present application can be implemented in the form of a computer program, which can run on a computer device as shown in the figure. Figure 4 The memory of the computer device can store various program modules constituting the power distribution network resource regulation apparatus, such as the acquisition module 410, the determination module 420 and the control module 430 shown in the figure. The computer program composed of various program modules makes the processor execute the steps in the power distribution network resource regulation method of each embodiment of the present application described in the specification. Figure 3

[0156] The computer device shown in the figure can execute step 210 by the acquisition module 410 in the power distribution network resource regulation apparatus shown in the figure, execute step 220 by the determination module 420, and execute step 230 by the control module 430. Figure 4 Figure 3 The present application provides a device, the device comprising a processor, a memory, and a program stored in the memory and executable on the processor, and applied to a virtual power plant of the power distribution network; the processor executes the program to implement the following steps:

[0157] The present application provides a device, the device comprising a processor, a memory, and a program stored in the memory and executable on the processor, and applied to a virtual power plant of the power distribution network; the processor executes the program to implement the following steps:

[0158] ​Obtaining real-time data of a regulation subject, the regulation subject including a plurality of virtual partitions of photovoltaic, energy storage, charging piles and loads, each virtual partition corresponding to a transformer district;

[0159] Based on the real-time data of the regulation subject, an optimal adjustment strategy is determined by using a preset distributed collaborative operation model, the preset distributed collaborative operation model being used to describe decision behaviors of the regulation subject under non-complete information conditions by using a Bayesian game theory with a target of minimizing total adjustment costs of the regulation subject.

[0160] Based on the optimal adjustment strategy, the regulation subject is controlled.

[0161] In one embodiment, based on the real-time data of the regulation subject, the optimal adjustment strategy is determined by using the preset distributed collaborative operation model, including:

[0162] Based on the real-time data of the regulation subject, the preset distributed collaborative operation model is solved by using Bayesian learning to obtain the optimal adjustment strategy.

[0163] In one embodiment, based on the real-time data of the regulation subject, the optimal adjustment strategy is obtained by solving the preset distributed collaborative operation model by using Bayesian learning, including:

[0164] An initial belief and an initial strategy of the regulation subject are set.

[0165] Based on the real-time data of the regulation subject, the belief and the strategy are iteratively updated until the updated belief and strategy satisfy a preset convergence condition to obtain the optimal adjustment strategy.

[0166] In one embodiment, based on the real-time data of the regulation subject, the optimal adjustment strategy is obtained by iteratively updating the belief and the strategy until the updated belief and strategy satisfy a preset convergence condition, including:

[0167] Based on the real-time data of the regulation subject, a Bayesian Nash equilibrium condition is solved to obtain a new strategy.

[0168] Based on the new strategy and an objective function in the preset distributed collaborative operation model, a new electricity price is calculated.

[0169] Based on the new strategy, the belief is updated to obtain a new belief.

[0170] It is judged whether the new strategy and the new belief satisfy a preset convergence condition.

[0171] In a case where it is determined that the new strategy and the new belief satisfy the preset convergence condition, the optimal adjustment strategy is obtained.

[0172] In one embodiment, the objective function in the preset distributed collaborative operation model is:

[0173]

[0174] wherein, is the strategy of each game party, is the private type of each game party, represents the cost, represents photovoltaic, represents energy storage, represents charging piles, represents load, is a balance weight coefficient, is a target regulation power.

[0175] In one embodiment, the construction process of the preset distributed collaborative operation model comprises:

[0176] Based on the regulation subject, a game party set is determined;

[0177] The private type and strategy space of each game party in the game party set are obtained;

[0178] Based on the private type and strategy space of each game party, the utility function of each game party is constructed;

[0179] Based on the utility function of each game party, a Bayesian Nash equilibrium condition is constructed with the goal of maximizing the expected utility;

[0180] A target function is constructed with the optimization goal of minimizing the total regulation cost of the regulation subject, to obtain a distributed collaborative operation model.

[0181] In one embodiment, the obtaining of the private type and strategy space of each game party in the game party set comprises:

[0182] The output regulation amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile, and the demand response amount of the load are obtained;

[0183] Based on the output regulation amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile, and the demand response amount of the load, the strategy space of each game party in the game party set is obtained;

[0184] The illumination prediction error distribution parameter of the photovoltaic, the capacity attenuation cost of the energy storage, the user demand elasticity of the charging pile, and the price sensitivity of the load are obtained;

[0185] ​​obtain a private type of each game party in the set of game parties based on the photovoltaic light prediction error distribution parameter, the energy storage capacity attenuation cost, the charging pile user demand elasticity, and the load price sensitivity.

[0186] In an embodiment, the controlling the regulation subject based on the optimal adjustment strategy comprises:

[0187] adjusting, based on the optimal adjustment strategy, the output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile, and / or the demand response amount of the load.

[0188] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) having computer-usable program code embodied therein.

[0189] 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 embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, 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 apparatus to produce a machine, so that the instructions that are executed by the processor of the computer or other programmable data processing apparatus generate an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0190] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture that includes an instruction apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 the steps of a function specified in one or more blocks.

[0192] In one typical arrangement, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0193] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technologies, about which the processor can execute instructions. The memory can be a memory storage device of any type.

[0194] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0195] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to encompass a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without further limitation, an element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0196] The above merely provides an embodiment of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A power distribution grid resource conditioning method, characterized by, The virtual power plant applied to the power distribution network, the power distribution network resource regulation method comprises: Obtain real-time data of the control subject, the control subject including photovoltaic, energy storage, charging pile and load of multiple virtual partitions, each virtual partition corresponding to a transformer area; Based on the real-time data of the control subject, an optimal adjustment strategy is determined by using a preset distributed collaborative operation model, the preset distributed collaborative operation model being used to minimize the total adjustment cost of the control subject as the target, and the decision-making behavior of the control subject under incomplete information conditions being described by using Bayesian game theory; Based on the optimal adjustment strategy, the control subject is controlled; The construction process of the preset distributed collaborative operation model comprises: Based on the control subject, a set of game parties is determined; Obtain the private type and strategy space of each game party in the set of game parties; wherein the private type of the photovoltaic includes illumination prediction error distribution parameters; the private type of the energy storage includes capacity attenuation cost; the private type of the charging pile includes user demand elasticity; the private type of the load includes price sensitivity; the strategy space of each game party in the set of game parties is obtained, including: the output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile and the demand response amount of the load; based on the output adjustment amount of the photovoltaic, the charging and discharging power of the energy storage, the charging plan offset amount of the charging pile and the demand response amount of the load, the strategy space of each game party in the set of game parties is obtained; Based on the private type and strategy space of each game party, the utility function of each game party is constructed; Based on the utility function of each game party, a Bayesian Nash equilibrium condition is constructed to maximize the expected utility as the target; A target function is constructed to minimize the total adjustment cost of the control subject as the optimization target, and a distributed collaborative operation model is obtained; The preset distributed collaborative operation model is solved by using Bayesian learning based on the real-time data of the control subject, and the optimal adjustment strategy is obtained; The preset distributed collaborative operation model is solved by using Bayesian learning based on the real-time data of the control subject, and the optimal adjustment strategy is obtained; The initial belief and initial strategy of the control subject are set; The belief and strategy are iteratively updated based on the real-time data of the control subject until the updated belief and strategy meet the preset convergence condition, and the optimal adjustment strategy is obtained; The belief and strategy are iteratively updated based on the real-time data of the control subject until the updated belief and strategy meet the preset convergence condition, and the optimal adjustment strategy is obtained; Based on the real-time data of the control subject, a new strategy is obtained by solving the Bayesian Nash equilibrium condition; Based on the new strategy and the target function in the preset distributed collaborative operation model, a new price is calculated. ​ updating the belief to obtain a new belief based on the new strategy; determining whether the new strategy and the new belief satisfy a preset convergence condition; obtaining an optimal adjustment strategy in a case where it is determined that the new strategy and the new belief satisfy the preset convergence condition.

2. The power distribution grid resource conditioning method of claim 1, wherein, The objective function in the preset distributed collaborative operation model is: ， wherein, is a strategy of each player, is a private type of each player, denotes a cost, , denotes photovoltaic, denotes energy storage, denotes charging piles, denotes load, is a balancing weight coefficient, is a target regulating power.

3. The power distribution grid resource conditioning method of claim 1, wherein, obtaining a private type of each game party in the set of game parties, including: obtaining the illumination prediction error distribution parameter of the photovoltaic, the capacity attenuation cost of the energy storage, the user demand elasticity of the charging pile, and the price sensitivity of the load; obtaining the private type of each game party in the set of game parties based on the illumination prediction error distribution parameter of the photovoltaic, the capacity attenuation cost of the energy storage, the user demand elasticity of the charging pile, and the price sensitivity of the load.

4. The power distribution grid resource conditioning method of claim 1, wherein, controlling the regulation subject based on the optimal adjustment strategy, including: adjusting the output adjustment amount of the photovoltaic, and / or the charging and discharging power of the energy storage, and / or the charging plan offset amount of the charging pile, and / or the demand response amount of the load based on the optimal adjustment strategy.

5. A power distribution grid resource conditioning device, characterized by, The virtual power plant applied to the power distribution network, the power distribution network resource adjustment device includes: An acquisition module is configured to acquire real-time data of a regulation subject, the regulation subject including photovoltaics, energy storages, charging piles, and loads of a plurality of virtual partitions, each virtual partition corresponding to a transformer area. A determination module is configured to determine an optimal adjustment strategy based on the real-time data of the regulation subject by using a preset distributed collaborative operation model, the preset distributed collaborative operation model being used to describe decision-making behaviors of the regulation subject under incomplete information conditions by using a Bayesian game theory with the objective of minimizing total adjustment costs of the regulation subject. The construction process of the preset distributed collaborative operation model includes determining a set of game parties based on the regulation subject, obtaining private types and strategy spaces of each game party in the set of game parties, constructing utility functions of the game parties based on the private types and the strategy spaces of the game parties, constructing a Bayesian Nash equilibrium condition based on the utility functions of the game parties with the objective of maximizing expected utility, and constructing an objective function with the optimization objective of minimizing the total adjustment costs of the regulation subject to obtain a distributed collaborative operation model. A control module is configured to control the regulation subject based on the optimal adjustment strategy. The determination module includes: A solving submodule is configured to solve the objective function in the preset distributed collaborative operation model based on the real-time data of the regulation subject by using Bayesian learning to obtain the optimal adjustment strategy. The solving submodule includes: The setting unit is configured to set an initial belief and an initial strategy of the regulation subject; The iteration unit is configured to iteratively update the belief and the strategy based on real-time data of the regulation subject until the updated belief and strategy satisfy a preset convergence condition, and obtain an optimal adjustment strategy; wherein the iteratively updating the belief and the strategy based on the real-time data of the regulation subject until the updated belief and strategy satisfy the preset convergence condition, and obtaining the optimal adjustment strategy, comprises: solving a Bayesian Nash equilibrium condition based on the real-time data of the regulation subject to obtain a new strategy; calculating a new electricity price based on the new strategy and an objective function in the preset distributed collaborative operation model; updating the belief based on the new strategy to obtain a new belief; determining whether the new strategy and the new belief satisfy the preset convergence condition; and obtaining the optimal adjustment strategy in a case where it is determined that the new strategy and the new belief satisfy the preset convergence condition.

6. An electronic device, comprising: The electronic device includes: at least one processor; a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the power distribution network resource regulation method according to any one of claims 1 to 4 by executing the instructions stored in the memory.

7. A machine-readable storage medium having stored thereon instructions, the instructions being executable by a machine to cause the machine to perform operations comprising: The instructions, when executed by the processor, cause the processor to be configured to perform the power distribution network resource regulation method according to any one of claims 1 to 4.

Images