A distributed power market trading platform based on blockchain

Abstract

The present invention relates to the field of electric power technology, and discloses a distributed power market-oriented trading platform based on blockchain, comprising a power generation data collection module for acquiring power generation data from power production units; an electricity consumption data collection module for acquiring electricity consumption data of terminal users from a transmission system; a blockchain transaction data acquisition module for acquiring transaction information; a data preprocessing module for generating a period data set; a feature construction module for generating power generation characteristics, electricity consumption characteristics, and transaction characteristics; a transaction legitimacy judgment module for inputting power generation characteristics, electricity consumption characteristics, and transaction characteristics into a first model, and the first model outputs a value indicating whether the transaction is abnormal based on the edge feature; the present invention provides a distributed power market-oriented trading platform based on blockchain, which monitors power trading behavior conducted through a blockchain network through the transaction relationship, network structure, and limited transaction information of the blockchain network.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and more specifically, to a distributed power supply market trading platform based on blockchain. Background Art

[0002] While typical power trading blockchains don't require a third-party management organization to maintain transaction trust, the transaction platform nodes within the blockchain network serve as the core of transactions, creating a blockchain network centered around the transaction platform nodes. This somewhat weakens the distributed nature of the blockchain network, but the transaction platform node can obtain detailed information about all transactions, facilitating statistical analysis. An improved approach eliminates the transaction platform node, eliminating a single transaction core. However, transactions in this form no longer flow through a single node, making detailed transaction information inaccessible and inconvenient for statistical analysis. If detailed transaction information were collected from each node through other means, the power trading blockchain would be rendered ineffective. Understanding only the transaction information broadcasted by the blockchain network would make it impossible to identify dishonest behavior in power trading. Summary of the Invention

[0003] The present invention provides a distributed power market trading platform based on blockchain, which monitors power trading behaviors conducted through the blockchain network through the transaction relationships, network structure and limited transaction information of the blockchain network.

[0004] In at least one embodiment of the present disclosure, a distributed power market trading platform based on blockchain is provided, comprising:

[0005] The blockchain system includes blockchain nodes used to constitute the blockchain system. The blockchain nodes are used by power production units or end users. One power production unit uses one blockchain node, and one end user uses one blockchain node.

[0006] A power generation data collection module, which is used to obtain power generation data from power generation units;

[0007] An electricity consumption data collection module is used to obtain electricity consumption data of end users from the power transmission system;

[0008] Blockchain transaction data acquisition module, which is used to obtain transaction information from the blockchain;

[0009] A data preprocessing module is used to collect transaction information, power generation data and power consumption data within the same time period to generate a period data set;

[0010] Electricity consumption data includes total electricity consumption, peak-time electricity consumption, normal-time electricity consumption, and off-peak electricity consumption of end users;

[0011] The feature construction module generates power generation features for power production units based on power generation data, generates power consumption features for end users based on power consumption data, constructs edges between power production units and end users with transactions, and generates transaction features for edges based on transaction information between power production units and end users.

[0012] The transaction legitimacy judgment module inputs the power generation characteristics, power consumption characteristics and transaction characteristics into the first model. The first model includes a transformation layer, an information fusion layer, a transaction relationship fusion layer and a first fully connected layer. The transformation layer is used to map the power generation characteristics, power consumption characteristics and transaction characteristics to the same feature space. The information fusion layer inputs the power generation characteristics, power consumption characteristics and the transaction relationship matrix representing the connection relationship of the blockchain nodes, and outputs the node characteristics of the blockchain nodes. The transaction relationship fusion layer is used to splice the node characteristics of the blockchain nodes with the transaction characteristics of the edges to generate edge features and input them into the first fully connected layer, and output the value of whether the transaction represented by the edge features is abnormal.

[0013] In at least one embodiment of the present disclosure, the time period is an artificially set length of time.

[0014] In at least one embodiment of the present disclosure, the first fully connected layer outputs two values, which respectively represent an abnormal transaction and a normal transaction, and the larger value is taken as the judgment result.

[0015] In at least one embodiment of the present disclosure, the element value of the transaction relationship matrix is ​​0 or 1, and the element in the i-th row and j-th column represents the transaction relationship between the i-th blockchain node and the j-th blockchain node. If there is a transaction, the element value is 1, otherwise the element value is 0.

[0016] In at least one embodiment of the present disclosure, the method of the information fusion layer is as follows:

[0017] U1=ReLU(HXW1)

[0018]

[0019] Where X represents the input feature matrix, a row vector of the original feature matrix represents the original feature of a blockchain node, the original feature of the blockchain node is the power generation feature or the power consumption feature, U1 represents the node feature matrix of the blockchain node, represents the sum of the transaction relationship matrix and the identity matrix, express The degree matrix of W1 represents the information fusion trainable parameter.

[0020] In at least one embodiment of the present disclosure, the transaction relationship fusion layer method is as follows:

[0021] y mn=concat(u m ,u n ,x mn )

[0022] y mn The edge feature connecting the mth and nth blockchain nodes, x mn represents the transaction characteristics of the edge connecting the mth and nth blockchain nodes, u m and u n Represent the row vectors of the mth and nth rows of U1 respectively.

[0023] In at least one embodiment of the present disclosure, a distributed power market transaction method based on blockchain is provided, comprising the following steps:

[0024] Obtaining power generation data from power production units;

[0025] Obtaining end-user electricity consumption data from the transmission system;

[0026] Get transaction information from the blockchain;

[0027] Collect transaction information, power generation data, and power consumption data within the same time period to generate a period data set;

[0028] Based on the power generation data, power generation characteristics are generated for the power production units. Based on the power consumption data, power consumption characteristics are generated for the end users. Edges are constructed between the power production units and end users where transactions occur. Transaction characteristics are generated for the edges based on the transaction information between the power production units and end users.

[0029] The power generation characteristics, power consumption characteristics and transaction characteristics are input into the first model. The first model includes a transformation layer, an information fusion layer, a transaction relationship fusion layer and a first fully connected layer. The transformation layer is used to map the power generation characteristics, power consumption characteristics and transaction characteristics to the same feature space. The information fusion layer inputs the power generation characteristics, power consumption characteristics and the transaction relationship matrix representing the connection relationship of the blockchain nodes, and outputs the node characteristics of the blockchain nodes. The transaction relationship fusion layer is used to splice the node characteristics of the blockchain nodes with the transaction characteristics of the edges to generate edge features and input them into the first fully connected layer, and output the value of whether the transaction represented by the edge feature is abnormal.

[0030] In at least one embodiment of the present disclosure, a storage medium is provided, which stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a computer, one or more steps of the aforementioned blockchain-based distributed power market trading method are performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is an exemplary module diagram of a distributed power market trading platform based on blockchain provided by at least one embodiment of the present disclosure;

[0032] Figure 2 This is an exemplary flow chart of a blockchain-based distributed power market trading method provided by at least one embodiment of the present disclosure;

[0033] Figure 3 A storage medium is provided by at least one embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0035] Figure 1 An exemplary module diagram of a blockchain-based distributed power market trading platform 100 provided for at least one embodiment of the present disclosure.

[0036] For example, Figure 1 As shown, at least one embodiment of the present disclosure provides a distributed power market trading platform 100 based on blockchain, including:

[0037] Blockchain system 101, blockchain system 101 is an existing structural part and is constructed using the existing organizational method of blockchain system 101. A brief description is as follows: it includes blockchain nodes used to constitute blockchain system 101. Blockchain nodes are used by power production units or end users. One power production unit uses one blockchain node, and one end user uses one blockchain node.

[0038] A power generation data collection module 102 is used to obtain power generation data from power generation units;

[0039] The power consumption data collection module 103 is used to obtain the power consumption data of the end users from the power transmission system;

[0040] Blockchain transaction data acquisition module 104, which is used to obtain transaction information from the blockchain;

[0041] The data preprocessing module 105 is used to collect transaction information, power generation data and power consumption data within the same time period to generate a period data set; in the embodiment disclosed below, the length of a time period is one day, which can of course be adaptively changed to one week, one month or one year.

[0042] Transaction information includes electricity consumption, total transaction price, and transaction object (the transaction object can be represented by the blockchain node number). From a computational perspective, the unit price of the transaction can be calculated based on the electricity consumption and total transaction price. The transaction time (real-time, day-ahead, medium- to long-term) can be estimated based on the total transaction price and the historical electricity consumption of the end user. Although the specific transaction information is lacking, it is still possible to obtain some specific information based on the available information.

[0043] Power generation data includes the total power generation of power production units, average power generation during peak hours, average power generation during normal hours, average power generation during off-peak hours, and power generation resource consumption;

[0044] The amount of power generation resource consumption varies for different types of power production units. For example, for thermal power plants (including thermal power generation and cogeneration), resource consumption can be coal, oil, etc., and is calculated as resource consumption through pricing. For wind farms and hydropower plants, resource consumption can be recorded as 0. Therefore, resource consumption can reflect the power generation type and cost of a power production unit.

[0045] Electricity consumption data includes total electricity consumption, peak-time electricity consumption, normal-time electricity consumption, and off-peak electricity consumption of end users;

[0046] The feature construction module 106 generates power generation features for power production units based on power generation data, generates power consumption features for end users based on power consumption data, constructs edges between power production units and end users with transactions, and generates transaction features for edges based on transaction information between power production units and end users.

[0047] The transaction legitimacy judgment module 107 inputs the power generation characteristics, power consumption characteristics and transaction characteristics into the first model. The first model includes a transformation layer, an information fusion layer, a transaction relationship fusion layer and a first fully connected layer. The transformation layer is used to map the power generation characteristics, power consumption characteristics and transaction characteristics to the same feature space. The information fusion layer inputs the power generation characteristics, power consumption characteristics and the transaction relationship matrix representing the connection relationship of the blockchain nodes, and outputs the node characteristics of the blockchain nodes. The transaction relationship fusion layer is used to splice the node characteristics of the blockchain nodes with the transaction characteristics of the edges to generate edge features and input them into the first fully connected layer, and output the value of whether the transaction represented by the edge features is abnormal.

[0048] In one embodiment of the present disclosure, the first fully connected layer outputs two values, which respectively represent an abnormal transaction and a normal transaction, and the larger value is taken as the judgment result.

[0049] In one embodiment of the present disclosure, the element value of the transaction relationship matrix is ​​0 or 1, and the element in the i-th row and j-th column represents the transaction relationship between the i-th blockchain node and the j-th blockchain node. If there is a transaction, the element value is 1, otherwise the element value is 0.

[0050] In one embodiment of the present disclosure, the method of the information fusion layer is as follows:

[0051] U1=ReLU(HXW1)

[0052]

[0053] Where X represents the input feature matrix, a row vector of the original feature matrix represents the original feature of a blockchain node, the original feature of the blockchain node is the power generation feature or the power consumption feature, U1 represents the node feature matrix of the blockchain node, represents the sum of the transaction relationship matrix and the identity matrix, express The degree matrix of W1 represents the information fusion trainable parameter.

[0054] In one embodiment of the present disclosure, the transaction relationship fusion layer method is as follows:

[0055] y mn =concat(u m ,u n ,x mn )

[0056] y mn The edge feature connecting the mth and nth blockchain nodes, x mn represents the transaction characteristics of the edge connecting the mth and nth blockchain nodes, u m and u n Represent the row vectors of the mth and nth rows of U1 respectively.

[0057] The judgment result of the transaction legitimacy judgment module 107 has a good detection effect on abnormal transaction behaviors such as low-price competition, collusion in bidding, and medium- and long-term malicious excess electricity purchases.

[0058] Figure 2 An exemplary flowchart of a blockchain-based distributed power market trading method provided for at least one embodiment of the present disclosure.

[0059] For example, Figure 2 As shown, at least one embodiment of the present disclosure provides a distributed power market trading method based on blockchain, comprising the following steps:

[0060] Step S101, obtaining power generation data from a power generation unit;

[0061] Step S102, obtaining the power consumption data of the end user from the power transmission system;

[0062] Step S103, obtaining transaction information from the blockchain;

[0063] Step S104, collecting transaction information, power generation data, and power consumption data within the same time period to generate a period data set;

[0064] Step S105: Generate power generation characteristics for the power generation unit based on the power generation data, generate power consumption characteristics for the end user based on the power consumption data, build edges between the power generation unit and the end user where transactions occur, and generate transaction characteristics for the edges based on the transaction information between the power generation unit and the end user.

[0065] Step S106: Input the power generation characteristics, power consumption characteristics, and transaction characteristics into the first model. The first model includes a transformation layer, an information fusion layer, a transaction relationship fusion layer, and a first fully connected layer. The transformation layer is used to map the power generation characteristics, power consumption characteristics, and transaction characteristics into the same feature space. The information fusion layer inputs the power generation characteristics, power consumption characteristics, and a transaction relationship matrix representing the connection relationship between blockchain nodes, and outputs the node characteristics of the blockchain nodes. The transaction relationship fusion layer is used to splice the node characteristics of the blockchain nodes with the transaction characteristics of the edges to generate edge features, which are input into the first fully connected layer and output a value indicating whether the transaction represented by the edge feature is abnormal.

[0066] Figure 3 A storage medium 300 provided for at least one embodiment of the present disclosure stores non-transitory computer-readable instructions 310. When the non-transitory computer-readable instructions 310 are executed by a computer, one or more steps of the aforementioned blockchain-based distributed power market trading method are performed.

[0067] The above describes the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

[0068] In the figure: Blockchain-based distributed power market trading platform 100;

[0069] Blockchain Systems 101;

[0070] Power generation data collection module 102;

[0071] Electricity consumption data collection module 103;

[0072] Blockchain transaction data acquisition module 104;

[0073] Data preprocessing module 105;

[0074] Feature construction module 106;

[0075] Transaction legitimacy judgment module 107;

[0076] Storage medium 300;

[0077] Non-transitory computer-readable instructions 310 .

Claims

1. A distributed power market trading platform based on blockchain, characterized by: include: A blockchain system, comprising blockchain nodes for constituting the blockchain system, wherein the blockchain nodes are used by power production units or end users; A power generation data collection module, which is used to obtain power generation data from power generation units; An electricity consumption data collection module is used to obtain electricity consumption data of end users from the power transmission system; Blockchain transaction data acquisition module, which is used to obtain transaction information from the blockchain; A data preprocessing module is used to collect transaction information, power generation data and power consumption data within the same time period to generate a period data set; The feature construction module generates power generation features for power generation units based on power generation data, generates power consumption features for end users based on power consumption data, constructs edges between power generation units and end users where transactions occur, and generates transaction features for edges based on transaction information between power generation units and end users; The transaction legitimacy judgment module inputs the power generation characteristics, power consumption characteristics and transaction characteristics into the first model. The first model includes a transformation layer, an information fusion layer, a transaction relationship fusion layer and a first fully connected layer. The transformation layer is used to map the power generation characteristics, power consumption characteristics and transaction characteristics to the same feature space. The information fusion layer inputs the power generation characteristics, power consumption characteristics and the transaction relationship matrix representing the connection relationship of the blockchain nodes, and outputs the node characteristics of the blockchain nodes. The transaction relationship fusion layer is used to splice the node characteristics of the blockchain nodes with the transaction characteristics of the edges to generate edge features and input them into the first fully connected layer, and output the value of whether the transaction represented by the edge features is abnormal.

2. A distributed power market trading platform based on blockchain according to claim 1, characterized in that: The time period is an artificially set length of time.

3. A distributed power market trading platform based on blockchain according to claim 1, characterized in that: The first fully connected layer outputs two values, one representing an abnormal transaction and the other representing a normal transaction. The larger value is taken as the judgment result.

4. A distributed power market trading platform based on blockchain according to claim 1, characterized in that: The element value of the transaction relationship matrix is ​​0 or 1. The element in the i-th row and j-th column represents the transaction relationship between the i-th blockchain node and the j-th blockchain node. If there is a transaction, the element value is 1, otherwise the element value is 0.

5. A distributed power market trading platform based on blockchain according to claim 1 or 4, characterized in that: The method of the information fusion layer is as follows: ； ； Where X represents the original feature matrix of the input, and a row vector of the original feature matrix represents the original feature of a blockchain node. The original feature of the blockchain node is the power generation feature or the power consumption feature. Represents the node feature matrix of the blockchain node, represents the sum of the transaction relationship matrix and the identity matrix, express The degree matrix of represents the information fusion trainable parameters.

6. A distributed power market trading platform based on blockchain according to claim 1, characterized in that: The transaction relationship fusion layer method is as follows: ； represents the edge feature of the edge connecting the mth and nth blockchain nodes, Represents the transaction characteristics of the edge connecting the mth and nth blockchain nodes, and Respectively The row vectors of the mth and nth rows of .

7. A distributed power market trading method based on blockchain, characterized in that: The following steps are involved: Obtaining power generation data from power production units; Obtaining end-user electricity consumption data from the transmission system; Get transaction information from the blockchain; Collect transaction information, power generation data, and power consumption data within the same time period to generate a period data set; Generate power generation features for power generation units based on power generation data, generate power consumption features for end users based on power consumption data, construct edges between power generation units and end users where transactions occur, and generate transaction features for edges based on transaction information between power generation units and end users; The power generation characteristics, power consumption characteristics and transaction characteristics are input into the first model. The first model includes a transformation layer, an information fusion layer, a transaction relationship fusion layer and a first fully connected layer. The transformation layer is used to map the power generation characteristics, power consumption characteristics and transaction characteristics to the same feature space. The information fusion layer inputs the power generation characteristics, power consumption characteristics and the transaction relationship matrix representing the connection relationship of the blockchain nodes, and outputs the node characteristics of the blockchain nodes. The transaction relationship fusion layer is used to splice the node characteristics of the blockchain nodes with the transaction characteristics of the edges to generate edge features and input them into the first fully connected layer, and output the value of whether the transaction represented by the edge feature is abnormal.

8. A storage medium, characterized in that: Non-transitory computer-readable instructions are stored, and when the non-transitory computer-readable instructions are executed by a computer, one or more steps in the blockchain-based distributed power market trading method as described in claim 7 are performed.

Images