An artificial intelligence-based multi-source power market transaction and settlement management system and method

Abstract

The application discloses a kind of multi-source electric power market transaction and settlement management system and method based on artificial intelligence, comprising the following steps: step one, data acquisition;Step two, data preprocessing;Step three, dynamic settlement rule determination;Step four, real-time settlement.The application uses data preprocessing module to identify and repair abnormal data points, to improve data reliability, thereby improving the accuracy of the settlement system;Different settlement rules are established based on the prediction of new energy power generation and power demand, and the uncertainty of new energy power generation is adapted by using dynamic settlement rules, thereby promoting power supply and demand balance;Using blockchain technology and smart contract, real-time recording and automatic settlement of electric power transaction data are realized, thereby improving the trading activity and liquidity of the power market.

Description

Technical Field

[0001] This invention belongs to the field of electricity market trading and settlement technology, and in particular relates to a multi-source electricity market trading and settlement management system and method based on artificial intelligence. Background Technology

[0002] Electricity market settlement is a crucial step in clearing funds between power generators, power consumers, and other market participants after electricity transactions are completed. Its accuracy and efficiency directly affect the stable operation of the electricity market.

[0003] With a high proportion of renewable energy integrated into the power system, flexible resources such as energy storage and adjustable loads are playing an increasingly important role in maintaining system stability and economic efficiency. The intermittent and uncertain nature of renewable energy generation increases the complexity of supply and demand matching in the electricity trading market. In the settlement process, the settlement system needs to perform high-frequency calculations based on complex electricity data and real-time market prices. However, due to market price volatility and the randomness of renewable energy output, the accuracy and timeliness of settlement results face challenges. Delays or errors during data acquisition or transmission can lead to settlement lags or errors.

[0004] Therefore, existing electricity market settlement systems and methods have the following drawbacks: 1. The accuracy of existing settlement systems depends on the raw data collected, but due to the lack of testing of the raw data, the accuracy of settlement results cannot be guaranteed; 2. Existing settlement systems use fixed settlement rules, which are inflexible and difficult to adapt to the uncertainties of new energy power generation, and cannot promote the balance of power supply and demand. When new energy power generation experiences a sudden increase or decrease in power generation due to weather changes, the fixed settlement rules cannot respond in a timely manner, which can easily lead to losses for power generators and inability for power consumers to obtain a stable power supply, thereby affecting the optimal allocation of resources in the entire electricity market; 3. Existing settlement systems cannot achieve real-time settlement, resulting in a long delay in fund clearing after the transaction is completed. This prevents power generators from obtaining power generation revenue in a timely manner, which seriously inhibits the trading activity and liquidity of the electricity market. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the technical problem this invention aims to solve is to provide an artificial intelligence-based multi-source power market trading and settlement management system and method that effectively improves data reliability and the accuracy of the settlement system; adapts to the uncertainties of new energy power generation and promotes the balance of power supply and demand; and realizes real-time recording and automatic settlement of power trading data.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a multi-source electricity market trading and settlement management system based on artificial intelligence, comprising:

[0007] The data acquisition module is used to collect data from new energy power generation equipment, as well as data on user electricity consumption and power generation by power generation companies, and transmit the collected data to the data storage module.

[0008] The data storage module is used to store the collected raw data, preprocessed data, algorithms required by the system, smart contracts corresponding to the settlement rules, and pre-edited settlement rules;

[0009] The data preprocessing module is used to identify and remove outlier data points and repair missing data points, and to normalize the data.

[0010] The dynamic settlement rule determination module uses the autoregressive integral moving average algorithm and the long short-term memory network algorithm to predict the power generation of new energy sources, and weights and fuses the prediction results to improve the prediction accuracy. It also predicts the electricity demand, selects the pre-edited settlement rules based on the power generation of new energy sources and the electricity demand, and sends them to the smart contract management module.

[0011] The smart contract management module is used to call the corresponding smart contract according to the selected settlement rules and deploy the settlement rules on the blockchain;

[0012] The real-time settlement execution module is used to acquire electricity market data in real time. Through the blockchain oracle mechanism, it introduces off-chain data into the blockchain and provides the data to the smart contract for settlement calculation. When the preset settlement conditions are met, the smart contract is automatically triggered to calculate the revenue of the power generation company and the electricity cost of the user, and automatically completes the transfer and recording of funds.

[0013] The aforementioned AI-based multi-source electricity market trading and settlement management system includes a data acquisition module comprising a sensor data acquisition unit, a meter data acquisition unit, and a data transmission unit.

[0014] The aforementioned AI-based multi-source electricity market trading and settlement management system includes a data storage module comprising a raw database, a preprocessing database, an algorithm library, a settlement rule library, and a smart contract library.

[0015] The aforementioned AI-based multi-source electricity market trading and settlement management system includes a data preprocessing module comprising an anomaly detection unit, an anomaly processing unit, and a data integration unit. The anomaly detection unit uses the K-means algorithm to detect anomaly data, and the anomaly processing unit uses linear interpolation to repair missing data.

[0016] The aforementioned AI-based multi-source electricity market trading and settlement management system includes a dynamic settlement rule determination module comprising a new energy power generation prediction unit, an electricity demand prediction unit, and a settlement rule selection unit. The new energy power generation prediction unit obtains new energy power generation through the prediction results of a weighted fusion autoregressive integral moving average algorithm and a long short-term memory network algorithm. The electricity demand prediction unit uses a multilayer perceptron algorithm to predict electricity demand.

[0017] The aforementioned AI-based multi-source electricity market trading and settlement management system includes a smart contract management module comprising a smart contract deployment unit and a smart contract invocation unit.

[0018] The aforementioned AI-based multi-source electricity market trading and settlement management system includes a real-time settlement execution module comprising a data acquisition unit, a settlement calculation unit, and a fund transfer and recording unit.

[0019] A multi-source electricity market trading and settlement method based on artificial intelligence includes the following steps:

[0020] Step 1: Data Collection;

[0021] Step 2: Data preprocessing;

[0022] Step 3: Determine the dynamic settlement rules;

[0023] Step 4: Real-time settlement;

[0024] In step one, the data acquisition module is used to collect data from the new energy power generation equipment and the electricity meter, and then stores the data in the data storage module.

[0025] In step two, the data preprocessing module is used to preprocess the data collected in step one, detect and remove abnormal data, supplement missing data, and finally normalize the data and store it in the data storage module.

[0026] In step three, the dynamic settlement rule determination module predicts the new energy power generation and power demand based on the preprocessed data in step two, and selects the settlement rule accordingly.

[0027] In step four, the smart contract management module calls the corresponding smart contract based on the settlement rules selected in step three. When the preset settlement conditions are met, the real-time settlement execution module automatically triggers the execution of the smart contract to complete the automatic settlement.

[0028] In the aforementioned AI-based multi-source electricity market trading and settlement method, step one includes new energy power generation equipment data, which includes wind power generation equipment data and solar power generation equipment data.

[0029] In the aforementioned AI-based multi-source electricity market trading and settlement method, step three, the process of predicting renewable energy power generation, is as follows: Let the renewable energy power generation predicted by the autoregressive integral moving average algorithm be... The new energy power generation predicted by the Long Short-Term Memory Network algorithm is The formula for the weighted fusion prediction result is as follows:

[0030] ;

[0031] in, and These are the weights of the prediction results from the autoregressive integral moving average algorithm and the long short-term memory network algorithm, respectively, and they satisfy... The weights can be optimized based on historical prediction errors. Specifically, let the mean square error of the autoregressive integral moving average algorithm be... The mean square error of the Long Short-Term Memory (LSTM) network algorithm is The weight calculation formula is as follows:

[0032] ;

[0033] .

[0034] The advantages of the multi-source electricity market trading and settlement management system and method based on artificial intelligence are as follows: This invention utilizes a data preprocessing module to identify and repair abnormal data points, thereby improving data reliability and thus enhancing the accuracy of the settlement system; it establishes different settlement rules based on the prediction of new energy power generation and electricity demand, and adopts dynamic settlement rules to adapt to the uncertainty of new energy power generation, thereby promoting the balance of electricity supply and demand; it utilizes blockchain technology and smart contracts to realize real-time recording and automatic settlement of electricity trading data, thereby improving the trading activity and liquidity of the electricity market. Attached Figure Description

[0035] Figure 1 This is a system structure block diagram of the present invention;

[0036] Figure 2 This is a block diagram of the data storage module structure of the present invention;

[0037] Figure 3 This is a structural block diagram of the data preprocessing module of the present invention;

[0038] Figure 4 This is a structural block diagram of the dynamic settlement rule determination module of the present invention;

[0039] Figure 5 This is a structural block diagram of the real-time settlement execution module of the present invention;

[0040] Figure 6 This is a flowchart of the method of the present invention.

[0041] In the diagram: 1. Data Acquisition Module; 11. Sensor Data Acquisition Unit; 12. Electricity Meter Data Acquisition Unit; 13. Data Transmission Unit; 2. Data Storage Module; 21. Raw Database; 22. Preprocessing Database; 23. Algorithm Library; 24. Settlement Rule Library; 25. Smart Contract Library; 3. Data Preprocessing Module; 31. Abnormal Data Detection Unit; 32. Abnormal Data Processing Unit; 33. Data Integration Unit; 4. Dynamic Settlement Rule Judgment Module; 41. New Energy Power Generation Prediction Unit; 42. Electricity Demand Prediction Unit; 43. Settlement Rule Selection Unit; 5. Smart Contract Management Module; 51. Smart Contract Deployment Unit; 52. Smart Contract Calling Unit; 6. Real-time Settlement Execution Module; 61. Data Acquisition Unit; 62. Settlement Calculation Unit; 63. Fund Transfer and Recording Unit. Detailed Implementation

[0042] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] In this invention, unless otherwise stated, directional terms such as "upper" and "lower" generally refer to the upper and lower positions of the device in its actual use or operating state, specifically the drawing directions in the accompanying drawings; while "inner" and "outer" refer to the outline of the device. Furthermore, in the description of this application, the term "comprising" means "including but not limited to". The terms first, second, third, etc., are used merely as illustrative purposes and do not impose numerical requirements or establish an order. The term "multiple" means "two or more".

[0044] like Figure 1-5 As shown, an artificial intelligence-based electricity market settlement system includes a data acquisition module 1, a data storage module 2, a data preprocessing module 3, a dynamic settlement rule determination module 4, a smart contract management module 5, and a real-time settlement execution module 6. The data storage module 2 establishes data connections with the data acquisition module 1, the data preprocessing module 3, the dynamic settlement rule determination module 4, the smart contract management module 5, and the real-time settlement execution module 6, respectively. The smart contract management module 5 establishes data connections with both the dynamic settlement rule determination module 4 and the real-time settlement execution module 6.

[0045] The data acquisition module 1 is used to collect data from new energy power generation equipment and electricity meter data. The data storage module 2 is used to store the data. The data preprocessing module 3 is used to preprocess the collected data. The dynamic settlement rule determination module 4 is used to select settlement rules. The smart contract management module 5 is used to call the corresponding smart contract based on the selected settlement rule. The real-time settlement execution module 6 is used to automatically trigger the execution of the smart contract and complete the automatic settlement when the preset settlement conditions are met. The data acquisition module 1 includes a sensor data acquisition unit 11, an electricity meter data acquisition unit 12, and a data transmission unit 13. The sensor data acquisition unit 11 is used to collect data from new energy power generation equipment. The electricity meter data acquisition unit 12 is used to collect data on user electricity consumption and power generation by power generation companies. The data transmission unit 13 is used to transmit the collected data to the data storage module 2.

[0046] The data storage module 2 includes a raw database 21, a preprocessing database 22, an algorithm library 23, a settlement rule library 24, and a smart contract library 25. The raw database 21 is used to store the collected raw data, the preprocessing database 22 is used to store the preprocessed data, the algorithm library 23 is used to store the algorithms required by the system, the smart contract library 25 is used to store the smart contracts corresponding to the settlement rules, and the settlement rule library 24 is used to store the pre-edited settlement rules.

[0047] The data preprocessing module 3 includes an anomaly detection unit 31, an anomaly processing unit 32, and a data integration unit 33. The anomaly detection unit 31 uses the K-means algorithm to detect anomaly data, the anomaly processing unit 32 uses linear interpolation to repair missing data, the anomaly detection unit 31 is used to identify and remove anomaly data points, the anomaly processing unit 32 is used to repair missing data points, and the data integration unit 33 is used to normalize the data.

[0048] The dynamic settlement rule determination module 4 includes a new energy power generation prediction unit 41, an electricity demand prediction unit 42, and a settlement rule selection unit 43. The new energy power generation prediction unit 41 obtains the new energy power generation by weighted fusion of the prediction results of the autoregressive integral moving average algorithm and the long short-term memory network algorithm. The electricity demand prediction unit 42 uses the multilayer perceptron algorithm to predict the electricity demand. The new energy power generation prediction unit 41 uses the autoregressive integral moving average algorithm and the long short-term memory network algorithm to predict the new energy power generation, and weighted fusion of the prediction results to improve the prediction accuracy. The electricity demand prediction unit 42 is used to predict the electricity demand. The settlement rule selection unit 43 selects the pre-edited settlement rule based on the new energy power generation and the electricity demand, and sends it to the smart contract management module 5.

[0049] The smart contract management module 5 includes a smart contract deployment unit 51 and a smart contract invocation unit 52. The smart contract invocation unit 52 is used to invoke the corresponding smart contract according to the selected settlement rule, and the smart contract deployment unit 51 is used to deploy the settlement rule on the blockchain.

[0050] The real-time settlement execution module 6 includes a data acquisition unit 61, a settlement calculation unit 62, and a fund transfer and recording unit 63. The data acquisition unit 61 is used to acquire electricity market data in real time. The settlement calculation unit 62 is used to trigger the execution of smart contracts and calculate the revenue of power generation companies and the electricity costs of users. The fund transfer and recording unit 63 is used to automatically complete the transfer and recording of funds.

[0051] like Figure 6 As shown, the present invention provides a multi-source electricity market trading and settlement method based on artificial intelligence, which includes the following steps:

[0052] Step 1: Data Collection;

[0053] Step 2, data preprocessing;

[0054] Step 3: Determine the dynamic settlement rules;

[0055] Step 4: Real-time settlement.

[0056] In step one, data acquisition module 1 is used to collect data from new energy power generation equipment and electricity meter data, and store them in data storage module 2; among which, the data from new energy power generation equipment includes data from wind power generation equipment and data from solar power generation equipment.

[0057] In step two, the data preprocessing module 3 is used to preprocess the data collected in step one, detect and remove abnormal data, supplement missing data, and finally normalize the data and store it in the data storage module 2.

[0058] In step three, the dynamic settlement rule determination module 4 predicts the renewable energy generation and electricity demand based on the preprocessed data from step two, and selects the settlement rule accordingly. The process of predicting renewable energy generation is as follows: Let the renewable energy generation predicted by the autoregressive integral moving average algorithm be... The new energy power generation predicted by the Long Short-Term Memory Network algorithm is The formula for the weighted fusion prediction result is as follows:

[0059] ;

[0060] in, and These are the weights of the prediction results from the autoregressive integral moving average algorithm and the long short-term memory network algorithm, respectively, and they satisfy... The weights can be optimized based on historical prediction errors. Specifically, let the mean square error of the autoregressive integral moving average algorithm be... The mean square error of the Long Short-Term Memory (LSTM) network algorithm is The weight calculation formula is as follows:

[0061]

[0062] ;

[0063] In step four, the smart contract management module 5 calls the corresponding smart contract based on the settlement rules selected in step three. When the preset settlement conditions are met, the real-time settlement execution module 6 automatically triggers the execution of the smart contract to complete the automatic settlement.

[0064] In summary, the advantages of this invention are as follows: During use, the data acquisition module 1 collects data from new energy power generation equipment and electricity meter data, and stores it in the data storage module 2. The data preprocessing module 3 preprocesses the collected data, detects and removes abnormal data, and supplements missing data. Finally, the data is normalized and stored in the data storage module 2. The dynamic settlement rule determination module 4 predicts the new energy power generation and electricity demand based on the preprocessed data and selects a settlement rule accordingly. The smart contract management module 5 calls the corresponding smart contract based on the selected settlement rule. When the preset settlement conditions are met, the real-time settlement execution module 6 automatically triggers the execution of the smart contract to complete the automatic settlement.

[0065] In data acquisition module 1, sensor data acquisition unit 11 is used to collect data from new energy power generation equipment, such as wind speed and solar intensity; meter data acquisition unit 12 is used to collect user electricity consumption and power generation data from power generation companies; and data transmission unit 13 is used to transmit the collected data to data storage module 2. In data storage module 2, raw database 21 is used to store the collected raw data; preprocessing database 22 is used to store preprocessed data; algorithm library 23 is used to store the algorithms required by the system; smart contract library 25 is used to store smart contracts corresponding to the settlement rules; and settlement rule library 24 is used to store pre-edited settlement rules, which are edited according to the new energy power generation and electricity demand. For example, when forecasting electricity demand for the coming week, if the electricity forecast indicates sufficient renewable energy generation in a region during weekdays, but the demand forecast indicates higher demand during weekday evenings and weekends, a cross-period settlement strategy can be developed. During weekdays with sufficient renewable energy generation, users can be encouraged to charge their energy storage devices at lower prices, with discounts offered to those participating in energy storage charging. The discount amount is dynamically adjusted based on the difference between generation and demand. During peak demand weekday evenings and weekends, electricity prices are increased, and priority is given to settling accounts for electricity released by energy storage devices, providing higher returns for energy storage operators to balance electricity supply and demand and improve energy efficiency. When both renewable energy generation and electricity demand forecasts point to extreme situations of tight or surplus electricity supply, emergency response settlement rules are triggered. For example, if the electricity forecast indicates that the generation of major renewable energy power generation facilities in a region will decrease sharply in the next few hours due to severe weather, while the demand forecast indicates that electricity demand will rise sharply during the same period due to large-scale industrial activities or extreme weather, the settlement system immediately activates emergency response settlement rules, providing significant economic compensation to users participating in emergency demand response and encouraging them to reduce unnecessary electricity consumption.

[0066] In the data preprocessing module 3, the abnormal data detection unit 31 is used to identify and remove abnormal data points, the abnormal data processing unit 32 is used to repair missing data points, and the data integration unit 33 is used to normalize the data. In the dynamic settlement rule determination module 4, the new energy power generation prediction unit 41 uses the autoregressive integral moving average algorithm and the long short-term memory network algorithm to predict new energy power generation, and then weights and fuses the prediction results to improve the prediction accuracy. The electricity demand prediction unit 42 is used to predict electricity demand, and the settlement rule selection unit 43 selects a pre-edited settlement rule based on the new energy power generation and electricity demand, and sends it to the smart contract management module 5. In the smart contract management module 5, the smart contract invocation unit 52 is used to invoke the corresponding smart contract according to the selected settlement rules, and the smart contract deployment unit 51 is used to deploy the settlement rules on the blockchain. In the real-time settlement execution module 6, the data acquisition unit 61 is used to acquire real-time electricity market data, such as real-time electricity consumption, power generation data, and electricity price data. Through the blockchain's oracle mechanism, off-chain data is introduced into the blockchain and provided to the smart contract for settlement calculation. When the preset settlement conditions are met, the settlement calculation unit 62 automatically triggers the execution of the smart contract to calculate the revenue of the power generation company and the electricity cost of the user. The fund transfer and recording unit 63 is used to automatically complete the transfer and recording of funds.

[0067] Of course, the above description is not intended to limit the present invention, and the present invention is not limited to the examples given above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of the present invention should be protected by the present invention.

Claims

1. A multi-source electricity market trading and settlement management system based on artificial intelligence, characterized in that, include: The data acquisition module (1) is used to collect data from new energy power generation equipment, as well as data on user electricity consumption and power generation of power generation enterprises, and transmit the collected data to the data storage module (2). The data storage module (2) is used to store the collected raw data, preprocessed data, algorithms required by the system, smart contracts corresponding to the settlement rules, and pre-edited settlement rules; The data preprocessing module (3) is used to identify and remove abnormal data points and repair missing data points, and to normalize the data. The dynamic settlement rule determination module (4) uses the autoregressive integral moving average algorithm and the long short-term memory network algorithm to predict the power generation of new energy, and weights and fuses the prediction results to improve the prediction accuracy. It also predicts the power demand, selects the pre-edited settlement rules based on the power generation of new energy and the power demand, and sends them to the smart contract management module (5). The smart contract management module (5) is used to call the corresponding smart contract according to the selected settlement rules and deploy the settlement rules on the blockchain; The real-time settlement execution module (6) is used to obtain electricity market data in real time. Through the oracle mechanism of the blockchain, it introduces off-chain data into the blockchain and provides the data to the smart contract for settlement calculation. When the preset settlement conditions are met, the smart contract is automatically triggered to calculate the revenue of the power generation company and the electricity cost of the user, and automatically completes the transfer and recording of funds. The dynamic settlement rule determination module (4) includes a new energy power generation prediction unit (41), a power demand prediction unit (42), and a settlement rule selection unit (43). The new energy power generation prediction unit (41) obtains the new energy power generation through the prediction results of the weighted fusion autoregressive integral moving average algorithm and the long short-term memory network algorithm. The power demand prediction unit (42) uses the multilayer perceptron algorithm to predict the power demand.

2. The multi-source electricity market trading and settlement management system based on artificial intelligence according to claim 1, characterized in that: The data acquisition module (1) includes a sensor data acquisition unit (11), a meter data acquisition unit (12), and a data transmission unit (13).

3. The multi-source electricity market trading and settlement management system based on artificial intelligence according to claim 1, characterized in that: The data storage module (2) includes a raw database (21), a preprocessing database (22), an algorithm library (23), a settlement rule library (24), and a smart contract library (25).

4. The multi-source electricity market trading and settlement management system based on artificial intelligence according to claim 1, characterized in that: The data preprocessing module (3) includes an abnormal data detection unit (31), an abnormal data processing unit (32) and a data integration unit (33). The abnormal data detection unit (31) uses the K-means algorithm to detect abnormal data, and the abnormal data processing unit (32) uses linear interpolation to repair missing data.

5. The multi-source electricity market trading and settlement management system based on artificial intelligence according to claim 1, characterized in that: The smart contract management module (5) includes a smart contract deployment unit (51) and a smart contract invocation unit (52).

6. The multi-source electricity market trading and settlement management system based on artificial intelligence according to claim 1, characterized in that: The real-time settlement execution module (6) includes a data acquisition unit (61), a settlement calculation unit (62), and a fund transfer and recording unit (63).

7. A method for conducting multi-source electricity market transactions and settlements using the management system described in any one of claims 1-6, characterized in that, Includes the following steps: Step 1: Data Collection; Step 2: Data preprocessing; Step 3: Determine the dynamic settlement rules; Step 4: Real-time settlement; In step one, the data acquisition module (1) is used to collect data from new energy power generation equipment and electricity meter data, and store them in the data storage module (2). In step two, the data preprocessing module (3) is used to preprocess the data collected in step one, detect and remove abnormal data, supplement missing data, and finally normalize the data and store it in the data storage module (2). In step three, the dynamic settlement rule determination module (4) predicts the new energy power generation and power demand based on the preprocessed data in step two, and selects the settlement rule accordingly. In step four, the smart contract management module (5) calls the corresponding smart contract based on the settlement rules selected in step three. When the preset settlement conditions are met, the real-time settlement execution module (6) automatically triggers the execution of the smart contract to complete the automatic settlement.

8. The multi-source electricity market trading and settlement method based on artificial intelligence according to claim 7, characterized in that: In step one, the data on new energy power generation equipment includes data on wind power generation equipment and data on solar power generation equipment.

9. The multi-source electricity market trading and settlement method based on artificial intelligence according to claim 7, characterized in that: In step three, the process of predicting renewable energy power generation is as follows: Let the renewable energy power generation predicted by the autoregressive integral moving average algorithm be... The new energy power generation predicted by the Long Short-Term Memory Network algorithm is The formula for the weighted fusion prediction result is as follows: ； in, and These are the weights of the prediction results from the autoregressive integral moving average algorithm and the long short-term memory network algorithm, respectively, and they satisfy... The weights can be optimized based on historical prediction errors. Specifically, let the mean square error of the autoregressive integral moving average algorithm be... The mean square error of the Long Short-Term Memory (LSTM) network algorithm is The weight calculation formula is as follows: ； 。

Images