Virtual power plant transaction path planning method and system based on multi-energy driving

By determining the settlement driving probability between energy markets and applying it to the transaction path planning of virtual power plants, the problem of difficulty in distinguishing dominance in multi-energy market transactions is solved, and the rationalization of resource allocation and optimization of transaction settlement is achieved.

CN118917502APending Publication Date: 2024-11-08HUANENG ZHEJIANG ENERGY SALES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410827604.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-25
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

It is difficult for virtual power plants to distinguish the dominance of the energy market when trading and settlement with multiple energy markets, resulting in disorderly transaction settlement and difficulty in obtaining the maximum settlement income.

Method used

By obtaining transaction data, determine the settlement driving probability between each energy market, and assign it to the settlement process between the virtual power plant and each energy market, realize the adaptive planning settlement sequence, use the BP neural network to calculate the income results based on transaction data, and optimize the Transaction path.

Benefits of technology

It realizes the dominance of distinguishing the energy market during transaction settlement between virtual power plants and various energy markets, obtains rational allocation of transaction resources, and improves the optimization effect of the settlement process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917502A_ABST
    Figure CN118917502A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of virtual power plants, in particular to a virtual power plant transaction path planning method and system based on multi-energy driving, and the method comprises the following steps: obtaining transaction data used for the settlement between a virtual power plant and a plurality of energy markets, the transaction path planning data is used for planning a settlement sequence between the virtual power plant and each energy market; based on the transaction path planning data, determining settlement driving probabilities among the energy markets; and endowing the settlement driving probability to a settlement process between the virtual power plant and each energy market to obtain a multi-energy driving settlement process capable of automatically planning the execution sequence of the settlement process. According to the invention, when transaction settlement is carried out between the virtual power plant and each energy market, the dominance of the energy market is distinguished, and the transaction settlement sequence conforming to reasonable transaction resource configuration is obtained.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of virtual power plants, and in particular to a method and system for planning transaction paths of virtual power plants based on multi-energy drive. Background Art

[0002] A virtual power plant is a power coordination management system that uses advanced information and communication technologies and software systems to achieve the aggregation and coordinated optimization of DERs such as DG, energy storage systems, controllable loads, and electric vehicles, so that it can participate in the power market and power grid operation as a special power plant. The core of the concept of a virtual power plant can be summarized as "communication" and "aggregation". The key technologies of a virtual power plant mainly include coordinated control technology, smart metering technology, and information and communication technology.

[0003] At present, in order to promote the enthusiasm of virtual power plant operators, increase the level of new energy consumption, and form a stable coordination and interaction capability between virtual power plants and power grids, virtual power plants are traded in a graded manner, which greatly optimizes the resource allocation between virtual power plants. Therefore, the transaction management of virtual power plants can ensure the stability of virtual power plant transactions.

[0004] When conducting graded transactions on virtual power plants, existing technologies mostly consider the cost structure of virtual power plants, or the characteristics of internal resources, or the degree of clean energy consumption, but rarely consider the settlement sequence planning of virtual power plants. However, virtual power plants can participate in multiple energy market transactions such as the electricity market, natural gas market, and carbon trading market as a whole. When conducting transactions and settlements with various energy markets, it is difficult to distinguish the dominance of the energy market, resulting in disordered transaction settlements, making it difficult to obtain the maximum settlement benefits, and unreasonable allocation of transaction resources. Summary of the invention

[0005] The purpose of the present invention is to provide a virtual power plant transaction path planning method based on multi-energy drive, so as to solve the technical problem in the prior art that it is difficult to distinguish the dominance of the energy market when the virtual power plant conducts transactions and settlements with various energy markets, resulting in disordered transactions and settlements, making it difficult to obtain the maximum settlement benefits.

[0006] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0007] A virtual power plant transaction path planning method based on multi-energy drive includes the following steps:

[0008] Acquire transaction data used for settlement between the virtual power plant and multiple energy markets as transaction path planning data for planning the settlement sequence between the virtual power plant and each energy market;

[0009] Determining settlement drive probabilities between various energy markets based on the transaction path planning data;

[0010] The settlement driving probability is assigned to the settlement process between the virtual power plant and each energy market, and a multi-energy driven settlement process that can automatically plan the execution order of the settlement process is obtained. , so as to realize the adaptive planning of the transaction path of the virtual power plant.

[0011] As a preferred solution of the present invention, the energy market includes: an electric energy market, a natural gas market, and a carbon trading market.

[0012] As a preferred solution of the present invention, the transaction data of the electric energy market includes the scale of aggregatable resources, the scale of total load, and the electricity clearing price of the electric energy market;

[0013] The transaction data of the carbon market includes the carbon trading volume and carbon clearing price in the carbon trading market;

[0014] The transaction data of the natural gas market include the natural gas trading volume and natural gas clearing price in the natural gas market.

[0015] As a preferred solution of the present invention, the method for determining the settlement driving probability includes:

[0016] In the transaction path planning data, the discrete degree of the transaction data between the virtual power plant and each energy market is determined respectively as the transaction data complexity of each energy market;

[0017] The transaction data complexity is: In the formula, Lj t is the complexity of the transaction data Dj at the tth settlement moment, Dj i is the transaction data Dj at the i-th settlement time between the 1st settlement time and the t-th settlement time, Dj∈[D1,D2,D3];

[0018] Convert the complexity of transaction data in each energy market into the difficulty of calculating the settlement process;

[0019] The difficulty of the calculation is: Pj t =a*Lj t +(1-a)*Pj (t-1) , where Pj t is the difficulty of calculating the settlement process corresponding to the transaction data Dj at the tth settlement moment, Pj (t-1) is the difficulty of calculating the settlement process corresponding to the transaction data Dj at the (t-1)th settlement time, a is a constant coefficient, a∈[0,1]; [when t=2, Pj1=0]

[0020] Determine the settlement drive probability for each energy market using the measurement difficulty;

[0021] The settlement driving probability is: Kj t=-[1-1 / (1+Pj t )]log[1 / (1+Pj t )], where Kj t It is the settlement driving probability of the energy market corresponding to the transaction data Dj at the tth settlement moment.

[0022] As a preferred solution of the present invention, the settlement process is driven by a neural network deployed between the virtual power plant and various energy markets for calculating the revenue results based on the transaction data;

[0023] Among them, the settlement process between the virtual power plant and the electric energy market is: M1 t =BP(D1 t ), where M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement moment, BP is the BP neural network;

[0024] The settlement process between the virtual power plant and the natural gas market is: M2 t =BP(D2 t ), where M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, BP is the BP neural network;

[0025] The settlement process between the virtual power plant and the carbon market is: M3 t =BP(D3 t ), where M3 t is the revenue of the virtual power plant in the carbon market at the tth settlement moment, D3 t is the transaction data of the carbon market at the tth settlement moment, and BP is the BP neural network.

[0026] As a preferred solution of the present invention, the multi-energy driven settlement process is:

[0027] (M1 t ,M2 t ,M3 t )={K1 t *BP(D1 t ),K2 t *BP(D2 t ),K3 t *BP(D3 t )};

[0028] Where, M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1t is the transaction data of the electric energy market at the tth settlement time, M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, M3 t is the revenue of the virtual power plant in the carbon trading market at the tth settlement moment, D3 t is the transaction data of the carbon trading market at the tth settlement time, K1 t is the settlement driving probability of the electric energy market at the tth settlement moment, K2 t is the settlement driving probability of the natural gas market at the tth settlement time, K3 t is the settlement driving probability between carbon markets at the tth settlement moment.

[0029] As a preferred solution of the present invention, the loss function of training the BP neural network is an error function between the profit result output by the BP neural network and the real value of the profit.

[0030] As a preferred solution of the present invention, the transaction data between the virtual power plant and various energy markets are normalized.

[0031] As a preferred solution of the present invention, the present invention provides a virtual power plant transaction path planning system based on multi-energy drive, which is applied to the virtual power plant transaction path planning method based on multi-energy drive, and the system includes:

[0032] A data acquisition unit for acquiring transaction data used for settlement between the virtual power plant and multiple energy markets;

[0033] A data processing unit, configured to determine the settlement driving probability between various energy markets based on the transaction path planning data;

[0034] The path planning unit assigns the settlement driving probability to the settlement process between the virtual power plant and each energy market, and obtains a multi-energy driven settlement process that can automatically plan the execution order of the settlement process.

[0035] As a preferred solution of the present invention, the multi-energy driving settlement process constructed by the path planning unit is:

[0036] (M1 t ,M2 t ,M3 t )={K1 t *BP(D1 t ),K2 t *BP(D2 t ),K3 t *BP(D3 t )};

[0037] Where, M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement time, M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, M3 t is the revenue of the virtual power plant in the carbon trading market at the tth settlement moment, D3 t is the transaction data of the carbon trading market at the tth settlement time, K1 t is the settlement driving probability of the electric energy market at the tth settlement moment, K2 t is the settlement driving probability of the natural gas market at the tth settlement time, K3 t is the settlement driving probability between carbon markets at the tth settlement moment.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention determines the settlement driving probability between various energy markets based on the transaction path planning data, assigns the settlement driving probability to the settlement process between the virtual power plant and various energy markets, and obtains a multi-energy driven settlement process that can automatically plan the execution order of the settlement process. When the virtual power plant conducts transaction settlement with various energy markets, it can achieve the dominance of distinguishing the energy markets and obtain a transaction settlement order that conforms to the rational allocation of transaction resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0041] Figure 1 A flow chart of a virtual power plant transaction path planning method provided by an embodiment of the present invention;

[0042] Figure 2 A block diagram of a virtual power plant transaction path planning system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, the present invention provides a virtual power plant transaction path planning method based on multi-energy drive, comprising the following steps:

[0045] Acquire transaction data used for settlement between the virtual power plant and multiple energy markets as transaction path planning data for planning the settlement sequence between the virtual power plant and each energy market;

[0046] Determine the settlement drive probability between various energy markets based on transaction path planning data;

[0047] The settlement-driven probability is assigned to the settlement process between the virtual power plant and various energy markets, and a multi-energy-driven settlement process is obtained which can automatically plan the execution order of the settlement process.

[0048] The present invention utilizes the dominance of various energy markets to plan the settlement order between the virtual power plant and various energy markets. The stronger the dominance, the higher the settlement order, thereby improving the rationality of the configuration of the virtual power plant's settlement resources and optimizing the settlement process of the virtual power plant.

[0049] The present invention determines the dominance of the energy market through the transaction data of various energy markets, and equates the dominance to the settlement-driven probability. That is, the stronger the dominance, the higher the settlement-driven probability. The energy market dominates the virtual power plant settlement, or drives the settlement process of the virtual power plant.

[0050] Among them, the more complex the transaction data of the energy market, the more difficult it is to calculate the neural network in the settlement process. The more difficult the calculation of the neural network is, the more resources are needed to train the neural network. Therefore, this energy market needs to occupy a dominant position in the virtual power plant settlement process to ensure the accuracy of the calculation of the settlement process, thereby ensuring the accurate calculation of the settlement income between the virtual power plant and the settlement process.

[0051] The present invention associates the settlement drive probability with the complexity of transaction data, so that the higher the complexity of the transaction data, the higher the settlement drive probability.

[0052] Furthermore, the present invention combines the settlement-driven probability with the settlement process of each energy market, so that the settlement process of the energy market with a higher settlement-driven probability has a higher weight, so that in the virtual power plant revenue settlement process, resources are given priority to calculate the revenue results, ensuring that the settlement process that is more difficult to calculate has high accuracy, and the settlement process that is easier to calculate has high accuracy due to simple transaction data and simple calculation, and does not need to occupy too many computing resources. Therefore, the settlement-driven probability provided by the present invention can enable the easy-to-calculate calculation process to give up computing resources to the difficult-to-calculate calculation process, thereby ensuring that all settlement processes maintain high accuracy.

[0053] In summary, the present invention can realize adaptive sequence planning of each settlement process through settlement driven probability, and dynamically plan the settlement path according to the difficulty of calculating the settlement process at each transaction moment. The higher the difficulty, the stronger the settlement dominance and the earlier the settlement sequence. Adaptive path planning realizes the rational allocation of settlement resources of the virtual power plant.

[0054] The transaction data of the electric energy market includes the scale of aggregated resources, total load scale, and electricity clearing price of the electric energy market. The revenue of the virtual power plant in the electric energy market is (scale of aggregated resources - total load scale) * electricity clearing price.

[0055] The transaction data of the carbon trading market includes the carbon trading volume and carbon clearing price of the carbon trading market. The income of the virtual power plant in the carbon trading market is the carbon trading volume*carbon clearing price;

[0056] The transaction data included in the natural gas market include the natural gas transaction volume and natural gas clearing price in the natural gas market. The revenue of the virtual power plant in the natural gas market is the natural gas transaction volume*natural gas clearing price;

[0057] The transaction data of the natural gas market include the natural gas trading volume and natural gas clearing price in the natural gas market.

[0058] The present invention determines the dominance of the energy market through the transaction data of each energy market, and equates the dominance to the settlement driving probability, that is, the stronger the dominance, the higher the settlement driving probability, and the energy market occupies a dominant position in the virtual power plant settlement, or drives the settlement process of the virtual power plant, as follows:

[0059] Methods for determining settlement drive probability include:

[0060] In the transaction path planning data, the discrete degree of the transaction data between the virtual power plant and each energy market is determined respectively as the transaction data complexity of each energy market;

[0061] The transaction data complexity is: In the formula, Lj tis the complexity of the transaction data Dj at the tth settlement moment, Dj i is the transaction data Dj at the i-th settlement time between the 1st settlement time and the t-th settlement time, Dj∈[D1,D2,D3];

[0062] Convert the complexity of transaction data in each energy market into the difficulty of calculating the settlement process;

[0063] The difficulty of calculation is: Pj t =a*Lj t +(1-a)*Pj (t-1) , where Pj t is the difficulty of calculating the settlement process corresponding to the transaction data Dj at the tth settlement moment, Pj (t-1) is the difficulty of calculating the settlement process corresponding to the transaction data Dj at the (t-1)th settlement time, a is a constant coefficient, a∈[0,1]; t≥2, when t=2, Pj1=0;

[0064] Using the difficulty of calculation, the settlement drive probability of each energy market is determined;

[0065] The settlement driving probability is: Kj t =-[1-1 / (1+Pj t )]log[1 / (1+Pj t )], where Kj t It is the settlement driving probability of the energy market corresponding to the transaction data Dj at the tth settlement moment.

[0066] The more complex the transaction data of an energy market, the more difficult it is to calculate the neural network in the settlement process. The more difficult the calculation of the neural network is, the more resources are needed to train the neural network. Therefore, this energy market needs to occupy a dominant position in the virtual power plant settlement process to ensure the accuracy of the calculation of the settlement process, thereby ensuring the accurate calculation of the settlement income between the virtual power plant and the settlement process.

[0067] The present invention associates the settlement drive probability with the complexity of transaction data, so that the higher the complexity of the transaction data, the higher the settlement drive probability.

[0068] The settlement process is driven by a neural network deployed between the virtual power plant and various energy markets, which is used to calculate the profit results based on transaction data;

[0069] Among them, the settlement process between the virtual power plant and the electric energy market is: M1 t =BP(D1 t ), where M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 tis the transaction data of the electric energy market at the tth settlement moment, BP is the BP neural network;

[0070] The settlement process between the virtual power plant and the natural gas market is: M2 t =BP(D2 t ), where M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, BP is the BP neural network;

[0071] The settlement process between the virtual power plant and the carbon market is: M3 t =BP(D3 t ), where M3 t is the revenue of the virtual power plant in the carbon market at the tth settlement moment, D3 t is the transaction data of the carbon market at the tth settlement moment, and BP is the BP neural network.

[0072] The multi-energy driven settlement process is as follows:

[0073] (M1 t ,M2 t ,M3 t )={K1 t *BP(D1 t ),K2 t *BP(D2 t ),K3 t *BP(D3 t )};

[0074] Where, M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement time, M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, M3 t is the revenue of the virtual power plant in the carbon trading market at the tth settlement moment, D3 t is the transaction data of the carbon trading market at the tth settlement time, K1 t is the settlement driving probability of the electric energy market at the tth settlement moment, K2 t is the settlement driving probability of the natural gas market at the tth settlement time, K3 t is the settlement driving probability between carbon markets at the tth settlement moment.

[0075] The present invention combines the settlement driving probability with the settlement process of each energy market, so that the settlement process of the energy market with a higher settlement driving probability has a higher weight, so that in the virtual power plant profit settlement process, resources are given priority to calculate the profit results, ensuring that the settlement process that is more difficult to calculate has high accuracy, and the settlement process that is easier to calculate has high accuracy due to simple transaction data and simple calculation, and does not need to occupy too many computing resources. Therefore, the settlement driving probability provided by the present invention can enable the calculation process that is easy to calculate to give up computing resources to the calculation process that is difficult to calculate, thereby ensuring that all settlement processes maintain high accuracy.

[0076] The present invention can realize adaptive sequence planning of each settlement process through settlement-driven probability. At each transaction moment, the settlement path can be dynamically planned according to the difficulty of the settlement process. The higher the difficulty, the stronger the settlement dominance and the earlier the settlement sequence. Adaptive path planning realizes the rational allocation of settlement resources of the virtual power plant.

[0077] The loss function of training the BP neural network is the error function between the profit result output by the BP neural network and the true value of the profit.

[0078] Normalize the transaction data between virtual power plants and various energy markets.

[0079] like Figure 2 As shown, the present invention provides a virtual power plant transaction path planning system based on multi-energy drive, which is applied to a virtual power plant transaction path planning method based on multi-energy drive, and the system includes:

[0080] A data acquisition unit for acquiring transaction data used for settlement between the virtual power plant and multiple energy markets;

[0081] A data processing unit, for determining settlement drive probabilities between various energy markets based on transaction path planning data;

[0082] The path planning unit assigns the settlement-driven probability to the settlement process between the virtual power plant and various energy markets, and obtains a multi-energy-driven settlement process that can automatically plan the execution order of the settlement process.

[0083] The multi-energy drive settlement process constructed by the path planning unit is:

[0084] (M1 t ,M2 t ,M3 t )={K1 t *BP(D1 t ),K2 t *BP(D2 t ),K3 t *BP(D3 t)};

[0085] Where, M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement time, M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, M3 t is the revenue of the virtual power plant in the carbon trading market at the tth settlement moment, D3 t is the transaction data of the carbon trading market at the tth settlement time, K1 t is the settlement driving probability of the electric energy market at the tth settlement moment, K2 t is the settlement driving probability of the natural gas market at the tth settlement time, K3 t is the settlement driving probability between carbon markets at the tth settlement moment.

[0086] The present invention determines the settlement driving probability between various energy markets based on transaction path planning data, assigns the settlement driving probability to the settlement process between the virtual power plant and various energy markets, and obtains a multi-energy driven settlement process that can automatically plan the execution order of the settlement process. When the virtual power plant conducts transaction settlement with various energy markets, it can achieve the dominance of distinguishing the energy markets and obtain a transaction settlement order that conforms to the rational allocation of transaction resources.

[0087] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A virtual power plant transaction path planning method based on multi-energy drive, characterized in that: The following steps are involved: Acquire transaction data used for settlement between the virtual power plant and multiple energy markets as transaction path planning data for planning the settlement sequence between the virtual power plant and each energy market; Determining settlement drive probabilities between various energy markets based on the transaction path planning data; The settlement-driven probability is assigned to the settlement process between the virtual power plant and various energy markets, thereby obtaining a multi-energy-driven settlement process that can automatically plan the execution order of the settlement process.

2. According to the method for planning a virtual power plant transaction path based on multi-energy drive according to claim 1, it is characterized by: The energy market includes: electricity market, natural gas market, and carbon trading market.

3. According to a multi-energy driven virtual power plant transaction path planning method according to claim 2, it is characterized by: The transaction data of the electric energy market includes the scale of aggregated resources, total load scale, and electricity clearing price in the electric energy market; The transaction data of the carbon market includes the carbon trading volume and carbon clearing price in the carbon trading market; The transaction data of the natural gas market include the natural gas trading volume and natural gas clearing price in the natural gas market.

4. According to a multi-energy driven virtual power plant transaction path planning method according to claim 1, it is characterized by: The method for determining the settlement driving probability includes: In the transaction path planning data, the discrete degree of the transaction data between the virtual power plant and each energy market is determined respectively as the transaction data complexity of each energy market; The transaction data complexity is: In the formula, Lj t is the complexity of the transaction data Dj at the tth settlement moment, Dj i is the transaction data Dj at the i-th settlement time between the 1st settlement time and the t-th settlement time, Dj∈[D1,D2,D3]; Convert the complexity of transaction data in each energy market into the difficulty of calculating the settlement process; The difficulty of the calculation is: Pj t =a*Lj t +(1-a)*Pj (t-1) , where Pj t is the difficulty of calculating the settlement process corresponding to the transaction data Dj at the tth settlement moment, Pj (t-1) is the difficulty of calculating the settlement process corresponding to the transaction data Dj at the (t-1)th settlement time, a is a constant coefficient, a∈[0,1]; Determine the settlement drive probability for each energy market using the measurement difficulty; The settlement driving probability is: Kj t =-[1-1 / (1+Pj t )]log[1 / (1+Pj t )], where Kj t It is the settlement driving probability of the energy market corresponding to the transaction data Dj at the tth settlement moment.

5. According to a multi-energy driven virtual power plant transaction path planning method according to claim 4, it is characterized by: The settlement process is driven by a neural network deployed between the virtual power plant and various energy markets, which is used to calculate the profit results based on the transaction data; Among them, the settlement process between the virtual power plant and the electric energy market is: M1 t =BP(D1 t ), where M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement moment, BP is the BP neural network; The settlement process between the virtual power plant and the natural gas market is: M2 t =BP(D2 t ), where M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, BP is the BP neural network; The settlement process between the virtual power plant and the carbon market is: M3 t =BP(D3 t ), where M3 t is the revenue of the virtual power plant in the carbon market at the tth settlement moment, D3 t is the transaction data of the carbon market at the tth settlement moment, and BP is the BP neural network.

6. According to claim 5, a virtual power plant transaction path planning method based on multi-energy drive is characterized in that: The multi-energy driven settlement process is as follows: <h2 style=";text-align:left;direction:ltr">(M1<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> M2<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> M3<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> )={K1<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> *BP(D1<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> K2<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> *BP(D2<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> K3<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> *BP(D3<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> )}; Where, M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement time, M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, M3 t is the revenue of the virtual power plant in the carbon trading market at the tth settlement moment, D3 t is the transaction data of the carbon trading market at the tth settlement time, K1 t is the settlement driving probability of the electric energy market at the tth settlement moment, K2 t is the settlement driving probability of the natural gas market at the tth settlement time, K3 t is the settlement driving probability between carbon markets at the tth settlement moment.

7. The method for planning a virtual power plant transaction path based on multi-energy drive according to claim 6 is characterized in that: The loss function of training the BP neural network is the error function between the profit result output by the BP neural network and the true value of the profit.

8. The method for planning a virtual power plant transaction path based on multi-energy drive according to claim 7 is characterized in that: Normalize the transaction data between virtual power plants and various energy markets.

9. A virtual power plant transaction path planning system based on multi-energy drive, characterized in that: A virtual power plant transaction path planning method based on multi-energy drive applied to any one of claims 1-8, the system comprising: A data acquisition unit for acquiring transaction data used for settlement between the virtual power plant and multiple energy markets; A data processing unit, configured to determine the settlement driving probability between various energy markets based on the transaction path planning data; The path planning unit assigns the settlement driving probability to the settlement process between the virtual power plant and each energy market, and obtains a multi-energy driven settlement process that can automatically plan the execution order of the settlement process.

10. The virtual power plant transaction path planning system based on multi-energy drive according to claim 9 is characterized in that: The multi-energy drive settlement process constructed by the path planning unit is: <h2 style=";text-align:left;direction:ltr">(M1<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> M2<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> M3<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> )={K1<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> *BP(D1<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> K2<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> *BP(D2<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> K3<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> *BP(D3<h2 style=";text-align:left;direction:ltr"> t <h2 style=";text-align:left;direction:ltr"> )}; Where, M1 t is the revenue of the virtual power plant in the electric energy market at the tth settlement moment, D1 t is the transaction data of the electric energy market at the tth settlement time, M2 t is the revenue of the virtual power plant in the natural gas market at the tth settlement time, D2 t is the transaction data of the natural gas market at the tth settlement time, M3 t is the revenue of the virtual power plant in the carbon trading market at the tth settlement moment, D3 t is the transaction data of the carbon trading market at the tth settlement time, K1 t is the settlement driving probability of the electric energy market at the tth settlement moment, K2 t is the settlement driving probability of the natural gas market at the tth settlement time, K3 t is the settlement driving probability between carbon markets at the tth settlement moment.