Green power transaction method, system and device and medium

Abstract

The invention relates to a green power transaction method, system and device, and a medium. The method comprises the following steps: obtaining related data of green power; extracting a first feature and a second feature of the green power related data; constructing a green power income model based on the first feature and the second feature; constructing a green electric power bidding model according to the income model; constructing a risk assessment and quantification model; according to the income model, the green electricity bidding model and the risk assessment and quantification model, constructing a green electricity transaction electricity quantity decomposition model; obtaining a green electricity transaction electricity quantity decomposition scheme by solving the green electricity transaction electricity quantity decomposition model; according to the method, a profit model, a green power bidding model, a risk assessment and quantification model and a transaction electric quantity decomposition model are constructed, and the models jointly support decision and optimization of green power transaction.

Description

Technical Field

[0001] The present invention relates to a green power trading method, system, equipment and medium, belonging to the technical field of green power market. Background Art

[0002] In the electricity market, integrated distribution companies dominate due to their huge market share. This integrated operation model helps to alleviate the problem of excessive market power exercised by large power generation groups in the wholesale market to a certain extent. However, when it comes to the assessment of the weight of renewable energy consumption responsibility, these large integrated distribution companies may use their market dominance to reduce the cost of fulfilling renewable energy consumption responsibilities by lowering the price of green electricity or green certificates. This behavior may have an adverse impact on market fairness and the development of renewable energy.

[0003] The patent document with the patent number "CN117788082A" discloses a method and system for making power market quotation decisions based on power price forecasting. The problem with this method is that it may rely more on the accuracy of power price forecasting and quotation decisions in terms of risk assessment, and the risk assessment of market changes and uncertain factors may be relatively simple. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes a green power trading method, system, device and medium.

[0005] The technical solution of the present invention is as follows:

[0006] A green power trading method comprises the following steps:

[0007] Acquire green power related data, including power generation, power demand data, power generation cost, power transmission loss data, power market policy data, and green power transaction price data;

[0008] Extracting a first feature and a second feature of green power related data;

[0009] Constructing a green electricity revenue model based on the first and second characteristics;

[0010] Construct a green power bidding model based on the revenue model;

[0011] Construct risk assessment and quantification models;

[0012] Construct a green power trading volume decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model;

[0013] By solving the green power trading quantity decomposition model, a green power trading quantity decomposition solution is obtained.

[0014] As a preferred implementation, the method for extracting the first feature is:

[0015] Construct a two-dimensional matrix of green power related data;

[0016] Map the elements of the two-dimensional matrix into the feature space to form a two-dimensional signal;

[0017] Get the first feature based on the two-dimensional signal:

[0018]

[0019] in, represents the eigenvalue of the two-dimensional signal of green power related data at position (i, j), δ represents the activation function, W(m, n) represents the weight of the convolution kernel, α represents the bias term, γ(i+m,j+n) represents the power reading of green power related data at position (i+m,j+n), and i, j, m, n represent the coordinate index;

[0020] The extraction method of the second characteristic feature is:

[0021]

[0022] Among them, ρ t represents the eigenvalue at time t, softmax() represents the vector mapping to the probability distribution function, ε represents the weight matrix, represents the hidden state at time t, represents a gated recurrent unit, represents the hidden state at time t-1, ω t represents the green power related data at time t, and β represents the bias term.

[0023] As a preferred implementation, the revenue model is expressed as:

[0024]

[0025] in, Indicates income, represents the transaction price data of green electricity, (δ,t) represents the power generation at time t, C i (δ,t) represents the power generation cost at time t, α represents the weight, and τ represents the amount of electricity allocated in the green electricity market.

[0026] As a preferred implementation, the green power bidding model is expressed as:

[0027]

[0028] Among them, V CVaR () represents the risk value prediction function, V CVaR (δ,t) represents the risk value of green power trading conditions under power generation (δ,t), min δ,t Represents the minimum function.

[0029] As a preferred implementation, the risk assessment and quantification model is constructed as follows:

[0030]

[0031] Among them, R final represents the final prediction result, β represents the weight, R i The i-th prediction component, σ j represents the jth weight component, f j (X) The j-th prediction component.

[0032] As a preferred implementation, the green power trading quantity decomposition model is expressed as:

[0033]

[0034] Where E represents the total power, t represents the time, W t represents the weight at time t, P t represents the power generation at time t, C t represents the electricity demand data at time t, g t represents the proportion of green electricity at time t, P(·) represents the probability function, i and j represent index variables, and W ij represents the weight coefficient, It represents the green electricity transaction volume provided by electricity producer i to consumer j, and f() represents the total electricity solution function.

[0035] As a preferred implementation, the green power trading quantity decomposition model is solved by using a CPLEX commercial solver to obtain a decomposition plan of the green power trading quantity at time t.

[0036] On the other hand, the present invention also provides a green power trading system, comprising:

[0037] Data acquisition module: acquiring green power related data, including power generation, power demand data, power generation cost, power transmission loss data, power market policy data and green power transaction price data;

[0038] Feature extraction module: extracting the first feature and the second feature of green power related data;

[0039] A revenue model building module: building a revenue model of green electricity based on the first feature and the second feature;

[0040] Green power bidding model construction module: construct a green power bidding model based on the revenue model;

[0041] Risk assessment and quantitative model building module: build risk assessment and quantitative models;

[0042] Green power trading volume decomposition model construction module: constructs a green power trading volume decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model;

[0043] Model solving module: by solving the green power trading quantity decomposition model, a green power trading quantity decomposition solution is obtained.

[0044] On the other hand, the present invention further provides an electronic device having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the green power trading method as described in any embodiment of the present invention.

[0045] On the other hand, the present invention also provides a computer-readable storage medium for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the green electricity trading method as described in any embodiment of the present invention.

[0046] The present invention has the following beneficial effects:

[0047] The present invention helps to reduce the dominant position of large integrated companies in the market by constructing a green electricity trading method, thereby allocating green electricity more fairly, avoiding reducing the cost of fulfilling the responsibility of renewable energy consumption by lowering prices, and is conducive to the healthy development of the market. Through precise data analysis and model construction, the supply and demand relationship of green electricity can be more effectively predicted and managed, thereby improving the utilization rate of renewable energy and promoting the development of green energy. Risk assessment and quantification models can help market participants better identify and manage potential risks in the transaction process, reduce uncertainties caused by factors such as price fluctuations, and enhance market stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention is a flowchart for implementing the method. DETAILED DESCRIPTION

[0049] 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.

[0050] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0051] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0052] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0053] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0054] Embodiment 1:

[0055] See also Figure 1 , a green electricity trading method, comprising the following steps:

[0056] Acquire green power related data, including power generation, power demand data, power generation cost, power transmission loss data, power market policy data, and green power transaction price data;

[0057] First, we will comprehensively collect all kinds of data related to green electricity. These data include but are not limited to:

[0058] Power generation: Real-time recording of green power output of each power production unit.

[0059] Electricity demand data: Detailed records of electricity demand in different regions or users, including electricity consumption time period, electricity consumption and electricity consumption type.

[0060] Power generation costs: including fuel costs, operation and maintenance costs, equipment depreciation, etc. These cost data are crucial for evaluating the benefits of electricity trading.

[0061] Power transmission loss data: Records the loss of power during transmission, which helps to accurately calculate the actual amount of power available.

[0062] Electricity market policy data: including government subsidies, tax policies, environmental regulations, etc. These data have a direct impact on electricity trading prices and market supply and demand relationships.

[0063] Green electricity transaction price data: records the transaction price of green electricity in the market and its fluctuations, providing important reference for the bidding model.

[0064] The accuracy and diversity of the data are ensured, providing a solid foundation for subsequent analysis and model building. These data can fully reflect the market status of green electricity and provide strong support for trading decisions.

[0065] Extracting a first feature and a second feature of green power related data;

[0066] Constructing a green electricity revenue model based on the first and second characteristics;

[0067] Construct a green power bidding model based on the revenue model;

[0068] Construct risk assessment and quantification models;

[0069] Construct a green power trading volume decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model;

[0070] By solving the green power trading quantity decomposition model, a green power trading quantity decomposition solution is obtained.

[0071] In this step, the system uses advanced algorithms to extract features from the collected data. The first feature is mainly extracted through the convolutional neural network (CNN), using the convolution kernel and activation function to identify the features of the two-dimensional signal of the data. The second feature is extracted through the gated recurrent unit (GRU) in the recurrent neural network (RNN), focusing on the temporal characteristics of the data.

[0072] First feature extraction: Use CNN to process the spatial features in the data and extract the key information in the data through convolution operations and activation functions.

[0073] The second feature extraction: Use GRU to process the time series features in the data, and extract the dynamic information in the data by capturing the correlation between the data at different time points.

[0074] As a preferred implementation, the method for extracting the first feature is:

[0075] Construct a two-dimensional matrix of green power related data;

[0076] Map the elements of the two-dimensional matrix into the feature space to form a two-dimensional signal;

[0077] Get the first feature based on the two-dimensional signal:

[0078]

[0079] in, represents the eigenvalue of the two-dimensional signal of green power related data at position (i, j), δ represents the activation function, W(m, n) represents the weight of the convolution kernel, α represents the bias term, γ(i+m,j+n) represents the power reading of green power related data at position (i+m,j+n), and i, j, m, n represent the coordinate index;

[0080] The extraction method of the second characteristic feature is:

[0081]

[0082] Among them, ρ t represents the eigenvalue at time t, softmax() represents the vector mapping to the probability distribution function, ε represents the weight matrix, represents the hidden state at time t, represents a gated recurrent unit, represents the hidden state at time t-1, ω t represents the green power related data at time t, and β represents the bias term.

[0083] The features extracted through deep learning technology can more accurately reflect the dynamic changes and potential laws of green electricity, and provide high-quality feature input for subsequent model construction.

[0084] Based on the extracted first and second features, the system constructs a revenue model, which comprehensively considers factors such as green electricity transaction price, power generation, power generation cost, and market policy, and calculates the expected revenue of power trading through weighted summation and other methods.

[0085] As a preferred implementation, the revenue model is expressed as:

[0086]

[0087] in, Indicates income, represents the transaction price data of green electricity, (δ,t) represents the power generation at time t, C i (δ,t) represents the power generation cost at time t, α represents the weight, and τ represents the amount of electricity allocated in the green electricity market.

[0088] The revenue model can intuitively reflect the economic benefits of green electricity and provide decision-making basis for traders. By continuously optimizing the model parameters, the accuracy and reliability of revenue forecasts can be improved.

[0089] Based on the revenue model, the system further constructs a green power bidding model. This model helps power traders make more informed decisions during the bidding process by predicting the risk value of power transactions. At the same time, the model also considers the impact of power generation on the risk value of green power trading conditions, ensuring that traders can pursue maximum returns while controlling risks.

[0090] As a preferred implementation, the green power bidding model is expressed as:

[0091]

[0092] Among them, V CVaR () represents the risk value prediction function, V CVaR (δ,t) represents the risk value of green power trading conditions under power generation (δ,t), min δ,t Represents the minimum function.

[0093] The bidding model enables traders to maximize their own interests under the premise of controllable risks. At the same time, by dynamically adjusting the bidding strategy, it can adapt to market changes and improve the flexibility and competitiveness of transactions.

[0094] In order to more comprehensively assess the risks of power trading, the system also builds a risk assessment and quantification model. The model accurately predicts and quantifies the potential risks in the power trading process by integrating multiple prediction methods and weight allocation. This helps traders identify risks in advance and take corresponding measures to prevent them.

[0095] As a preferred implementation, the risk assessment and quantification model is constructed as follows:

[0096]

[0097] Among them, R final represents the final prediction result, β represents the weight, R i The i-th prediction component, σ j represents the jth weight component, f j (X) The j-th predicted component.

[0098] Risk assessment and quantitative models help traders better identify and manage risks and reduce uncertainty caused by price fluctuations and other factors. By formulating response strategies in advance, market stability and trading sustainability can be enhanced.

[0099] The system constructs a green power trading electricity decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model. The model aims to reasonably allocate the total electricity to different trading periods and trading objects to maximize the benefits and minimize the risks of power trading.

[0100] As a preferred implementation, the green power trading quantity decomposition model is expressed as:

[0101]

[0102] Where E represents the total power, t represents the time, W t represents the weight at time t, P t represents the power generation at time t, C t represents the electricity demand data at time t, g t represents the proportion of green electricity at time t, P(·) represents the probability function, i and j represent index variables, and W ij represents the weight coefficient, It represents the green electricity transaction volume provided by electricity producer i to consumer j, and f() represents the total electricity solution function.

[0103] The electricity decomposition model helps to achieve fair distribution and efficient use of green electricity. By optimizing the electricity decomposition plan, the utilization rate of renewable energy can be improved and the development of green energy can be promoted. At the same time, the model can also provide traders with a clear electricity allocation plan to facilitate trading and settlement.

[0104] Finally, the system solves the green power trading volume decomposition model through the CPLEX commercial solver. Through optimization algorithms and efficient computing power, the system can quickly obtain the decomposition plan of green power trading volume in each time period and between each trading object. This provides clear trading guidance for power traders and helps to achieve fair, efficient and sustainable development of the power market.

[0105] As a preferred implementation, the green power trading quantity decomposition model is solved by using a CPLEX commercial solver to obtain a decomposition plan of the green power trading quantity at time t.

[0106] The efficiency and accuracy of the solution algorithm ensure the feasibility and practicality of the power decomposition plan. By formulating a detailed power decomposition plan, traders can better manage the supply and demand of green electricity and improve the efficiency and benefits of transactions.

[0107] The weights involved in this embodiment are all preset by technicians based on experience and are not limited here.

[0108] Embodiment 2:

[0109] The present invention also provides a green power trading system, comprising:

[0110] Data acquisition module: acquiring green power related data, including power generation, power demand data, power generation cost, power transmission loss data, power market policy data and green power transaction price data;

[0111] Feature extraction module: extracting the first feature and the second feature of green power related data;

[0112] A revenue model building module: building a revenue model of green electricity based on the first feature and the second feature;

[0113] Green power bidding model construction module: construct a green power bidding model based on the revenue model;

[0114] Risk assessment and quantitative model building module: build risk assessment and quantitative models;

[0115] Green power trading volume decomposition model construction module: constructs a green power trading volume decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model;

[0116] Model solving module: by solving the green power trading quantity decomposition model, a green power trading quantity decomposition solution is obtained.

[0117] Embodiment three:

[0118] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the green power trading method as described in any embodiment of the present invention is implemented.

[0119] Embodiment 4:

[0120] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the green power trading method as described in any embodiment of the present invention is implemented.

[0121] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0122] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0125] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A green power trading method, characterized in that: The following steps are involved: Acquire green power related data, including power generation, power demand data, power generation cost, power transmission loss data, power market policy data, and green power transaction price data; Extracting a first feature and a second feature of green power related data; Constructing a green electricity revenue model based on the first and second characteristics; Construct a green power bidding model based on the revenue model; Construct risk assessment and quantification models; Construct a green power trading volume decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model; By solving the green power trading quantity decomposition model, a green power trading quantity decomposition solution is obtained.

2. The green power trading method according to claim 1, characterized in that: The method for extracting the first feature is: Construct a two-dimensional matrix of green power related data; Map the elements of the two-dimensional matrix into the feature space to form a two-dimensional signal; Get the first feature based on the two-dimensional signal: in, represents the eigenvalue of the two-dimensional signal of green power related data at position (i, j), δ represents the activation function, W(m, n) represents the weight of the convolution kernel, α represents the bias term, γ(i+m,j+n) represents the power reading of green power related data at position (i+m,j+n), and i, j, m, n represent the coordinate index; The extraction method of the second characteristic feature is: Among them, ρ t represents the eigenvalue at time t, softmax() represents the vector mapping to the probability distribution function, ε represents the weight matrix, represents the hidden state at time t, θ represents the gated recurrent unit, represents the hidden state at time t-1, ω t represents the green power related data at time t, and β represents the bias term.

3. The green power trading method according to claim 2, characterized in that: The revenue model is expressed as: in, Indicates income, represents the transaction price data of green electricity, (δ,t) represents the power generation at time t, C i (δ,t) represents the power generation cost at time t, α represents the weight, and τ represents the amount of electricity allocated in the green electricity market.

4. The green power trading method according to claim 3, characterized in that: The green power bidding model is expressed as: Among them, V CVaR () represents the risk value prediction function, V CVaR (δ,t) represents the risk value of green power trading conditions under power generation (δ,t), min δ,t Represents the minimum function.

5. The green power trading method according to claim 1, characterized in that: The risk assessment and quantification model is expressed as: Among them, R final represents the final prediction result, β represents the weight, R i The i-th prediction component, σ j represents the jth weight component, f j (X) The j-th prediction component.

6. The green power trading method according to claim 4 or 5, characterized in that: The green power trading quantity decomposition model is expressed as: Where E represents the total power, t represents the time, W t represents the weight at time t, P t represents the power generation at time t, C t represents the electricity demand data at time t, g t represents the proportion of green electricity at time t, P(·) represents the probability function, i and j represent index variables, and W ij represents the weight coefficient, It represents the green electricity transaction volume provided by electricity producer i to consumer j, and f() represents the total electricity solution function.

7. The green power trading method according to claim 6, characterized in that: The green power trading quantity decomposition model is solved by using the CPLEX commercial solver to obtain a decomposition plan of the green power trading quantity at time t.

8. A green power trading system, characterized in that: include: Data acquisition module: acquiring green power related data, including power generation, power demand data, power generation cost, power transmission loss data, power market policy data and green power transaction price data; Feature extraction module: extracting the first feature and the second feature of green power related data; A revenue model building module: building a revenue model of green electricity based on the first feature and the second feature; Green power bidding model construction module: construct a green power bidding model based on the revenue model; Risk assessment and quantitative model building module: build risk assessment and quantitative models; Green power trading volume decomposition model construction module: constructs a green power trading volume decomposition model based on the revenue model, green power bidding model, and risk assessment and quantification model; Model solving module: by solving the green power trading quantity decomposition model, a green power trading quantity decomposition solution is obtained.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the green power trading method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the green power trading method according to any one of claims 1 to 7 is implemented.

Images