Power market transaction and settlement system and method oriented to renewable energy sources

Abstract

The invention provides an electricity market transaction and settlement system and method oriented to renewable energy sources, and relates to the field of electricity market transaction. The renewable energy-oriented power market transaction and settlement system and method comprise hardware, software, a model and an algorithm, and aims to solve the problem of supply and demand matching complexity caused by intermittency and uncertainty of renewable energy power generation and improve the efficiency and accuracy of a settlement process. According to the technical scheme, the accuracy of supply and demand matching and price adjustment in the renewable energy power market is remarkably improved by combining multivariate data fusion and a reinforcement learning algorithm, and data such as the power generation amount, the user demand amount and the market price can be collected and processed in real time by adopting edge calculation and an intelligent electric meter.

Description

Technical Field

[0001] The present invention relates to the field of power market transaction technology, specifically to a power market transaction and settlement system and method for renewable energy. Background Art

[0002] A power market transaction and settlement system for renewable energy usually includes the following key parts: 1) Data acquisition module: Collecting power production and consumption data from renewable energy power generation facilities (such as solar panels, wind turbines, etc.) and power users; 2) Transaction matching module: Matching power producers and consumers according to real-time supply and demand conditions to ensure the rational distribution of power; 3) Settlement module: Based on the results of transaction matching, financial settlement of power transactions is carried out, usually using technologies such as blockchain to ensure transparency and immutability; 4) Forecasting and scheduling module: By analyzing meteorological data and historical power consumption data, predicting future power production and demand conditions, and performing scheduling optimization to improve system stability and efficiency.

[0003] In the electricity market trading and settlement system for renewable energy, the main defects are concentrated in the efficiency and accuracy of the trading and settlement process. Due to the intermittent and uncertain nature of renewable energy generation, the complexity of matching supply and demand in the electricity trading market increases. 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 the volatility of market prices and the randomness of renewable energy output, the accuracy and timeliness of settlement results face challenges. Once delays or errors occur in the data collection or transmission process, settlement delays or errors may occur. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a system and method for electricity market trading and settlement for renewable energy, which solves the problem that the intermittent and uncertain power generation of renewable energy leads to increased complexity in matching supply and demand in the electricity trading market; due to the volatility of market prices and the randomness of renewable energy output, the accuracy and timeliness of settlement results face challenges. Once delays or errors occur in the data collection or transmission process, settlement delays or errors may occur.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a power market transaction and settlement system for renewable energy, including hardware, software, models and algorithms, which aims to solve the complexity of supply and demand matching caused by the intermittent and uncertain nature of renewable energy generation, and improve the efficiency and accuracy of the settlement process, characterized in that: the hardware part includes: a distributed data acquisition module, a smart meter, a central processing unit, an edge computing unit, a communication module, a server cluster and a distributed storage unit, wherein: the distributed data acquisition module is composed of power generation equipment and user equipment located in different geographical locations, and is used to collect power data in different areas in real time;

[0006] Smart meters integrate two-way communication capabilities, which not only monitor users’ electricity usage, but also adjust users’ electricity usage behavior based on market price feedback;

[0007] Edge computing units are embedded in power plants and user-end devices, which can perform preliminary data processing locally and reduce data transmission delays;

[0008] The server cluster adopts a distributed architecture to handle complex computing tasks such as transactions, supply and demand balance, and settlement;

[0009] Distributed storage units ensure redundant backup of data in various locations, improving system reliability and security.

[0010] The software part includes: intelligent transaction matching system, dynamic prediction and scheduling system, intelligent contract settlement system, visual interface and user behavior analysis system, among which:

[0011] The intelligent trading matching system uses adaptive algorithms to dynamically adjust trading strategies based on supply and demand changes and historical trading data to ensure market stability;

[0012] The dynamic forecasting and dispatching system combines meteorological forecasts with real-time data and uses a hybrid neural network model to make ultra-short-term power generation and demand forecasts and optimize power distribution;

[0013] The smart contract settlement system is based on blockchain technology and automatically executes transaction contracts to ensure transparent and fair transactions;

[0014] The user behavior analysis system analyzes users' electricity usage patterns through big data and provides personalized electricity optimization suggestions;

[0015] The visualization interface uses augmented reality technology to display the operating status of power generation equipment, market price fluctuations and user electricity consumption in real time.

[0016] Models and algorithms include: supply and demand forecasting model based on multivariate data fusion, price adjustment model based on reinforcement learning algorithm, and settlement formula driven by smart contracts:

[0017] The supply and demand forecasting model combines multi-source data and uses multi-level time series analysis to improve the accuracy of supply and demand forecasting;

[0018] The price adjustment model uses a reinforcement learning algorithm to adaptively adjust electricity prices based on historical market fluctuations, reduce drastic price fluctuations, and optimize the stability of the electricity market;

[0019] The smart contract driven settlement formula is based on the formula:

[0020] P(t)=P_base+α * (D(t)-S(t))+β ★ f(t);

[0021] Where P(t) is the current electricity price, P_base is the basic electricity price, D(t) is the current demand, S(t) is the current supply, α is the supply and demand adjustment coefficient, β is the market fluctuation adjustment coefficient, and f(t) is the system's response function to market fluctuations.

[0022] Preferably, the edge computing unit is embedded in renewable energy power generation equipment and user equipment, and can pre-process data locally and realize automatic identification and adjustment of abnormal power generation or power consumption. The smart meter is integrated with a prediction algorithm to implement dynamic power consumption optimization suggestions based on market prices on the user side.

[0023] Preferably, the communication module supports multi-protocol integration, including LoRa, NB-I oT and 5G communication protocols, ensuring wide coverage and low latency of data transmission. The distributed storage unit adopts a two-way chain backup mechanism to ensure that data in different areas can be continuously used even in the event of a local failure, thereby increasing the robustness of the system.

[0024] Preferably, the intelligent transaction matching system optimizes the supply and demand matching between different power generators and users by introducing an auction mechanism, thereby improving the allocation efficiency of market resources. The intelligent contract settlement system automatically executes transactions between the supply and demand parties based on programmable intelligent contracts in the blockchain, ensuring that the transaction process cannot be tampered with and is transparent.

[0025] Preferably, the supply and demand forecasting model uses a large-scale data set, combined with neural networks and regression analysis, to achieve high-precision forecasting of electricity demand in different time periods. The reinforcement learning algorithm learns from historical price fluctuations and adaptively adjusts the price adjustment coefficient to minimize the impact of supply and demand imbalances on market prices.

[0026] A method for electricity market trading and settlement for renewable energy, comprising the following steps:

[0027] a. Data collection: Real-time collection of power data from different regions, including renewable energy generation, user power demand and market price information, is achieved through distributed data collection modules and smart meters. The smart meters have two-way communication capabilities and can adjust user power consumption behavior based on market price feedback;

[0028] b. Data preprocessing: The collected data is preliminarily processed in the edge computing unit, abnormal data in power generation and power consumption are identified through anomaly detection algorithms, and real-time adjustments are made to improve data accuracy;

[0029] c. Supply and demand forecasting based on multivariate data fusion: A supply and demand forecasting model based on multivariate data fusion is used to forecast future electricity demand and supply. The model combines meteorological data, historical power generation data, market price fluctuations and user behavior data, and uses the formula:

[0030] P forecast (t) = f(M weather ,D history ,U behavior ,P market );

[0031] Among them, P forecast (t) is the predicted supply and demand balance point at time t, M weather is the meteorological data, D history is the historical power generation and demand data, U behavior is user behavior data, P market is the market price;

[0032] d. Transaction matching: Based on the results of the supply and demand forecasting model, the intelligent transaction matching system uses adaptive algorithms and auction mechanisms to match supply and demand between power generators and power users, ensuring market supply and demand balance and optimizing resource allocation;

[0033] e. Price adjustment by reinforcement learning algorithm: In the process of transaction matching, the power price is dynamically adjusted by reinforcement learning algorithm. The reinforcement learning model learns and optimizes through historical price fluctuations and real-time supply and demand conditions. The price adjustment formula is:

[0034]

[0035] Among them, P(t) is the current electricity price, P base is the basic electricity price, D(t) is the current demand, S(t) is the current supply, α is the supply and demand adjustment coefficient, β is the historical fluctuation adjustment coefficient, γ i is the discount factor, ΔP history (i) is the i-th historical price fluctuation;

[0036] f. Settlement model: The smart contract settlement system is based on blockchain technology, automatically executes transaction contracts, and realizes efficient, secure and transparent transactions and fund settlement through programmable smart contracts. The following settlement formula is used:

[0037]

[0038] Among them, C is the settlement amount, P i is the electricity price of the ith transaction, E i is the amount of electricity in the ith transaction, and n is the number of transactions;

[0039] g. Real-time feedback and adjustment: After the transaction and settlement are completed, the user's electricity consumption behavior is fed back through the smart meter. The system can dynamically adjust the user's electricity consumption strategy based on user behavior analysis and market price fluctuations, and provide users with personalized electricity consumption suggestions;

[0040] h. System adaptive optimization: During market fluctuations, the system continuously optimizes the supply and demand forecasting model and price adjustment model through reinforcement learning algorithms to ensure supply and demand balance and price stability, and reduce the impact of drastic fluctuations on the market.

[0041] Preferably, the multivariate data fusion supply and demand forecasting model is further combined with environmental sensor data, including wind speed, temperature, and sunshine intensity, to improve the accuracy of supply and demand forecasting.

[0042] Preferably, the price adjustment model of the reinforcement learning algorithm introduces a penalty mechanism to limit excessive price fluctuations and ensure the stability of market prices.

[0043] Preferably, the price adjustment model uses historical data analysis based on reinforcement learning, combined with recent price fluctuation trends, to dynamically adjust price adjustment parameters α and β. The settlement model is based on blockchain technology, supports distributed ledgers to record each transaction and settlement, and ensures the immutability and transparency of transaction data.

[0044] Preferably, the supply and demand forecasting model is based on machine learning technology, which can learn users' electricity usage habits and changes in meteorological conditions, and dynamically adjust forecasting parameters to improve forecasting accuracy.

[0045] The present invention provides a system and method for electricity market trading and settlement for renewable energy, which has the following beneficial effects:

[0046] This technical solution significantly improves the accuracy of supply and demand matching and price adjustment in the renewable energy power market by combining multivariate data fusion and reinforcement learning algorithms. It uses edge computing and smart meters to collect and process data such as power generation, user demand and market prices in real time, and promptly identify and correct abnormal data to ensure the accuracy of the input data of the prediction model. The supply and demand prediction model combines meteorological, historical data and user behavior data to dynamically predict future electricity demand and supply, optimize the transaction matching mechanism, achieve efficient matching of supply and demand, and improve the stability of market operation.

[0047] The price adjustment model of the reinforcement learning algorithm automatically adjusts electricity prices by learning market fluctuations and historical price changes in real time, reducing market instability caused by drastic fluctuations. The smart contract settlement system combined with blockchain technology ensures the transparency of the transaction process and the non-tamperability of settlement data, thereby achieving efficient and secure settlement of transactions. This solution has the advantages of efficient data processing, high prediction accuracy, flexible price adjustment, transparent transactions and secure settlement, which significantly improves the overall operational efficiency and reliability of the renewable energy power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the internal structure of the present invention;

[0049] Figure 2 It is a schematic diagram of the process of the present invention; DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention are described clearly and completely. 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.

[0051] Embodiment 1:

[0052] like Figure 1-2As shown, an embodiment of the present invention provides an electricity market transaction and settlement system for renewable energy, including hardware, software, models and algorithms, aiming to solve the complexity of supply and demand matching caused by the intermittent and uncertain nature of renewable energy generation, and improve the efficiency and accuracy of the settlement process, characterized in that: the hardware part includes: a distributed data acquisition module, a smart meter, a central processing unit, an edge computing unit, a communication module, a server cluster and a distributed storage unit, wherein: the distributed data acquisition module is composed of power generation equipment and user equipment located in different geographical locations, and is used to collect power data from different regions in real time; the communication module supports multi-protocol integration, including LoRa, NB-I oT and 5G communication protocols, to ensure wide coverage and low latency of data transmission; the distributed storage unit adopts a two-way chain backup mechanism to ensure that data from different regions can be continuously used even in the event of a local failure, thereby increasing the robustness of the system.

[0053] Smart meters integrate two-way communication functions, which not only monitor users' electricity usage, but also adjust users' electricity usage behavior based on market price feedback.

[0054] Edge computing units are embedded in power stations and user-side devices, and can perform preliminary processing of data locally to reduce data transmission delays. Edge computing units are embedded in renewable energy power generation equipment and user devices, and can pre-process data locally and realize automatic identification and adjustment of abnormal power generation or power consumption. Smart meters are integrated with prediction algorithms to implement dynamic power consumption optimization recommendations based on market prices at the user end.

[0055] The server cluster adopts a distributed architecture to handle complex computing tasks such as transactions, supply and demand balance, and settlement.

[0056] Distributed storage units ensure redundant backup of data in various locations, improving system reliability and security.

[0057] The software part includes: intelligent transaction matching system, dynamic prediction and scheduling system, intelligent contract settlement system, visual interface and user behavior analysis system, among which:

[0058] The intelligent transaction matching system uses adaptive algorithms to dynamically adjust trading strategies based on changes in supply and demand and historical transaction data to ensure market stability. The intelligent transaction matching system optimizes the supply and demand matching between different power generators and users by introducing an auction mechanism, thereby improving the allocation efficiency of market resources. The smart contract settlement system is based on programmable smart contracts in the blockchain, which automatically executes transactions between supply and demand parties, ensuring that the transaction process cannot be tampered with and is transparent.

[0059] The dynamic prediction and dispatching system combines meteorological forecasts with real-time data and adopts a hybrid neural network model to make ultra-short-term power generation and demand forecasts and optimize power distribution. The supply and demand forecasting model uses a large-scale data set, combined with neural networks and regression analysis, to achieve high-precision forecasts of power demand in different time periods. The reinforcement learning algorithm learns from historical price fluctuations and adaptively adjusts the price adjustment coefficient to minimize the impact of supply and demand imbalances on market prices.

[0060] The smart contract settlement system is based on blockchain technology and automatically executes transaction contracts to ensure transparent and fair transactions.

[0061] The user behavior analysis system analyzes users’ electricity usage patterns through big data and provides personalized electricity optimization suggestions.

[0062] The visualization interface uses augmented reality technology to display the operating status of power generation equipment, market price fluctuations and user electricity consumption in real time.

[0063] Models and algorithms include: supply and demand forecasting model based on multivariate data fusion, price adjustment model based on reinforcement learning algorithm, and settlement formula driven by smart contracts:

[0064] The supply and demand forecasting model combines multi-source data and uses multi-level time series analysis to improve the accuracy of supply and demand forecasts.

[0065] The price regulation model uses a reinforcement learning algorithm to adaptively adjust electricity prices based on historical market fluctuations, reduce drastic price fluctuations, and optimize the stability of the electricity market.

[0066] The smart contract driven settlement formula is based on the formula:

[0067] *★

[0068] P(t)=P_base+α(D(t)-S(t))+βf(t);

[0069] Where P(t) is the current electricity price, P_base is the basic electricity price, D(t) is the current demand, S(t) is the current supply, α is the supply and demand adjustment coefficient, β is the market fluctuation adjustment coefficient, and f(t) is the system's response function to market fluctuations.

[0070] A method for electricity market trading and settlement for renewable energy, comprising the following steps:

[0071] a. Data collection: The distributed data collection module and smart meters collect power data from different regions in real time, including renewable energy generation, user power demand and market price information. Smart meters have two-way communication functions and can adjust user power consumption behavior based on market price feedback;

[0072] b. Data preprocessing: The collected data is preliminarily processed in the edge computing unit, abnormal data in power generation and consumption are identified through anomaly detection algorithms, and real-time adjustments are made to improve data accuracy.

[0073] c. Supply and demand forecasting based on multivariate data fusion: A supply and demand forecasting model based on multivariate data fusion is used to forecast future electricity demand and supply. The model combines meteorological data, historical power generation data, market price fluctuations and user behavior data, and uses the formula:

[0074] P forecast (t) = f(M weather ,D history ,U behavior ,P market );

[0075] Among them, P forecast (t) is the predicted supply and demand balance point at time t, M weather is the meteorological data, D history is the historical power generation and demand data, U behavior is user behavior data, P market For market prices, the supply and demand forecasting model based on multivariate data fusion is further combined with environmental sensor data, including wind speed, temperature, and sunshine intensity, to improve the accuracy of supply and demand forecasts.

[0076] d. Transaction matching: Based on the results of the supply and demand forecasting model, the intelligent transaction matching system uses adaptive algorithms and auction mechanisms to match supply and demand between power generators and power users, ensuring market supply and demand balance and optimizing resource allocation.

[0077] e. Price adjustment by reinforcement learning algorithm: In the process of transaction matching, the power price is dynamically adjusted by reinforcement learning algorithm. The reinforcement learning model learns and optimizes through historical price fluctuations and real-time supply and demand conditions. The price adjustment formula is:

[0078]

[0079] Among them, P(t) is the current electricity price, P base is the basic electricity price, D(t) is the current demand, S(t) is the current supply, α is the supply and demand adjustment coefficient, β is the historical fluctuation adjustment coefficient, γ i is the discount factor, ΔP history(i) is the i-th historical price fluctuation. The price adjustment model of the reinforcement learning algorithm introduces a penalty mechanism to limit excessive price fluctuations and ensure the stability of market prices. The price adjustment model uses historical data analysis based on reinforcement learning and combines recent price fluctuation trends to dynamically adjust price adjustment parameters α and β. The settlement model is based on blockchain technology and supports distributed ledgers to record each transaction and settlement, ensuring the immutability and transparency of transaction data.

[0080] f. Settlement model: The smart contract settlement system is based on blockchain technology, automatically executes transaction contracts, and realizes efficient, secure and transparent transactions and fund settlement through programmable smart contracts. The following settlement formula is used:

[0081]

[0082] Among them, C is the settlement amount, P i is the electricity price of the ith transaction, E i is the amount of electricity in the ith transaction, and n is the number of transactions.

[0083] g. Real-time feedback and adjustment: After the transaction and settlement are completed, the user's electricity usage behavior is fed back through the smart meter. The system can dynamically adjust the user's electricity usage strategy based on user behavior analysis and market price fluctuations, and provide users with personalized electricity usage recommendations.

[0084] h. System adaptive optimization: During market fluctuations, the system continuously optimizes the supply and demand forecasting model and price adjustment model through reinforcement learning algorithms to ensure supply and demand balance and price stability, and reduce the impact of drastic fluctuations on the market. The supply and demand forecasting model is based on machine learning technology, which can learn users' electricity usage habits and changes in meteorological conditions, and dynamically adjust forecasting parameters to improve forecasting accuracy.

[0085] Operation Example:

[0086] Assume that at a certain moment, the system needs to match and settle the renewable energy generation, user electricity demand and market price in a region. The region contains three users and two renewable energy power stations.

[0087] Initial conditions:

[0088] The real-time power demands of users A, B and C are:

[0089] User A: 5MWh

[0090] User B: 3MWh

[0091] User C: 2MWh

[0092] The real-time power generation of the two power stations is:

[0093] Power station 1: 7MWh

[0094] Power station 2: 4MWh

[0095] Current market basic electricity price (P base ): 60 yuan / MWh

[0096] Historical price fluctuation coefficient (ΔP history ) is 5 yuan / MWh based on the fluctuations of previous transactions. The adjustment coefficients α and β are 0.8 and 0.2 respectively, and the discount factor γ = 0.9.

[0097] Step 1: Supply and Demand Forecasting

[0098] Through the supply and demand forecasting model, the system predicts the supply and demand balance at future moments. Assuming that through meteorological data, historical power generation and user behavior data, the forecasting model concludes:

[0099] P forecast (t) = f(M weather ,D history ,U behavior ,P market )=9MWh;

[0100] The actual demand is 10MWh and the supply is 11MWh. The system finds that supply exceeds demand and needs to adjust the market price.

[0101] Step 2: Price Adjustment

[0102] Use reinforcement learning algorithm to dynamically adjust the price. According to the formula:

[0103]

[0104] in:

[0105] D(t)=10MWh(demand)

[0106] S(t)=11MWh(supply)

[0107] ΔP history =5 yuan / MWh

[0108] Substitute into the formula to calculate:

[0109] P(t)=60+0.8(10-11)+0.2×5

[0110] P(t)=60-0.8+1=60.2 yuan / MWh;

[0111] Therefore, the current market price is adjusted to 60.2 yuan / MWh.

[0112] Step 3: Transaction matching

[0113] Based on the current supply and demand forecasts and price adjustments, the intelligent transaction matching system begins to match power plants and users:

[0114] User A demands 5MWh, and power station 1 supplies 5MWh, so the match is successful.

[0115] User B demands 3MWh, power station 1 supplies another 2MWh, and the remaining 1MWh is obtained from power station 2.

[0116] User C demands 2MWh, which is fully supplied by power station 2.

[0117] Step 4: Settlement

[0118] According to the smart contract settlement system, the system settles according to the transaction volume and price. The settlement formula is:

[0119]

[0120] in:

[0121] User A: C A =60.2×5=301 yuan

[0122] User B: C B =60.2×3=180.6 yuan

[0123] User C: C C =60.2×2=120.4 yuan

[0124] Step 5: Real-time feedback and optimization

[0125] After the transaction is completed, the system obtains the user's actual electricity consumption feedback through the smart meter, and generates personalized electricity optimization suggestions for each user based on the user behavior analysis system. Assuming that user A has a certain energy-saving potential, the system recommends that he reduce the electricity load during the period with higher prices, thereby reducing future electricity costs.

[0126] Results: This example demonstrates how the system can efficiently trade electricity between different users and power plants through supply and demand forecasting, price adjustment, intelligent transaction matching and blockchain settlement, ensure market price stability, and further optimize electricity consumption behavior through real-time feedback and personalized recommendations.

[0127] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power market transaction and settlement system for renewable energy, characterized in that: It includes hardware, software, models and algorithms, and aims to solve the complexity of supply and demand matching caused by the intermittency and uncertainty of renewable energy generation, and improve the efficiency and accuracy of the settlement process. It is characterized by: the hardware part includes: distributed data acquisition module, smart meter, central processing unit, edge computing unit, communication module, server cluster and distributed storage unit, among which: the distributed data acquisition module is composed of power generation equipment and user equipment located in different geographical locations, and is used to collect power data in different areas in real time; Smart meters integrate two-way communication capabilities, which not only monitor users’ electricity usage, but also adjust users’ electricity usage behavior based on market price feedback; Edge computing units are embedded in power plants and user-end devices, which can perform preliminary data processing locally and reduce data transmission delays; The server cluster adopts a distributed architecture to handle complex computing tasks such as transactions, supply and demand balance, and settlement; Distributed storage units ensure redundant backup of data in various locations, improving system reliability and security; The software part includes: intelligent transaction matching system, dynamic prediction and scheduling system, intelligent contract settlement system, visual interface and user behavior analysis system, among which: The intelligent trading matching system uses adaptive algorithms to dynamically adjust trading strategies based on supply and demand changes and historical trading data to ensure market stability; The dynamic forecasting and dispatching system combines meteorological forecasts with real-time data and uses a hybrid neural network model to make ultra-short-term power generation and demand forecasts and optimize power distribution; The smart contract settlement system is based on blockchain technology and automatically executes transaction contracts to ensure transparent and fair transactions; The user behavior analysis system analyzes users' electricity usage patterns through big data and provides personalized electricity optimization suggestions; The visualization interface uses augmented reality technology to display the operating status of power generation equipment, market price fluctuations and user electricity consumption in real time; Models and algorithms include: supply and demand forecasting model based on multivariate data fusion, price adjustment model based on reinforcement learning algorithm, and settlement formula driven by smart contracts: The supply and demand forecasting model combines multi-source data and uses multi-level time series analysis to improve the accuracy of supply and demand forecasting; The price adjustment model uses a reinforcement learning algorithm to adaptively adjust electricity prices based on historical market fluctuations, reduce drastic price fluctuations, and optimize the stability of the electricity market; The smart contract driven settlement formula is based on the formula: P(t)=P_base+α ＊ (D(t)-S(t))+β ＊ f(t); Where P(t) is the current electricity price, P_base is the basic electricity price, D(t) is the current demand, S(t) is the current supply, α is the supply and demand adjustment coefficient, β is the market fluctuation adjustment coefficient, and f(t) is the system's response function to market fluctuations.

2. The renewable energy-oriented electricity market transaction and settlement system according to claim 1, characterized in that: The edge computing unit is embedded in renewable energy power generation equipment and user equipment, and can pre-process data locally and realize automatic identification and adjustment of abnormal power generation or power consumption. The smart meter is integrated with a prediction algorithm to implement dynamic power consumption optimization suggestions based on market prices on the user side.

3. The renewable energy-oriented electricity market transaction and settlement system according to claim 1, characterized in that: The communication module supports multi-protocol integration, including LoRa, NB-IoT and 5G communication protocols, ensuring wide coverage and low latency of data transmission. The distributed storage unit adopts a two-way chain backup mechanism to ensure that data in different areas can be continuously used even in the event of local failures, thereby increasing the robustness of the system.

4. The renewable energy-oriented electricity market transaction and settlement system according to claim 1, characterized in that: The intelligent transaction matching system optimizes the supply and demand matching between different power generators and users by introducing an auction mechanism, thereby improving the allocation efficiency of market resources. The intelligent contract settlement system automatically executes transactions between supply and demand parties based on programmable intelligent contracts in the blockchain, ensuring that the transaction process cannot be tampered with and is transparent.

5. The renewable energy-oriented electricity market transaction and settlement system according to claim 1, characterized in that: The supply and demand forecasting model uses a large-scale data set, combined with neural networks and regression analysis, to achieve high-precision forecasts of electricity demand in different time periods. The reinforcement learning algorithm learns from historical price fluctuations and adaptively adjusts the price adjustment coefficient to minimize the impact of supply and demand imbalances on market prices.

6. A method for electricity market trading and settlement for renewable energy, characterized in that: The following steps are involved: a. Data collection: Real-time collection of power data from different regions, including renewable energy generation, user power demand and market price information, is achieved through distributed data collection modules and smart meters. The smart meters have two-way communication capabilities and can adjust user power consumption behavior based on market price feedback; b. Data preprocessing: The collected data is preliminarily processed in the edge computing unit, abnormal data in power generation and power consumption are identified through anomaly detection algorithms, and real-time adjustments are made to improve data accuracy; c. Supply and demand forecasting based on multivariate data fusion: A supply and demand forecasting model based on multivariate data fusion is used to forecast future electricity demand and supply. The model combines meteorological data, historical power generation data, market price fluctuations and user behavior data, and uses the formula: P forecast (t)=f(M weather ,D history ,U behavior ,P market ); Among them, P forecast (t) is the predicted supply and demand balance point at time t, M weather is the meteorological data, D history is the historical power generation and demand data, U behavior is user behavior data, P market is the market price; d. Transaction matching: Based on the results of the supply and demand forecasting model, the intelligent transaction matching system uses adaptive algorithms and auction mechanisms to match supply and demand between power generators and power users, ensuring market supply and demand balance and optimizing resource allocation; e. Price adjustment by reinforcement learning algorithm: In the process of transaction matching, the power price is dynamically adjusted by reinforcement learning algorithm. The reinforcement learning model learns and optimizes through historical price fluctuations and real-time supply and demand conditions. The price adjustment formula is: Among them, P(t) is the current electricity price, P base is the basic electricity price, D(t) is the current demand, S(t) is the current supply, α is the supply and demand adjustment coefficient, β is the historical fluctuation adjustment coefficient, γ i is the discount factor, ΔP history (i) is the i-th historical price fluctuation; f. Settlement model: The smart contract settlement system is based on blockchain technology, automatically executes transaction contracts, and realizes efficient, secure and transparent transactions and fund settlement through programmable smart contracts. The following settlement formula is used: Among them, C is the settlement amount, P i is the electricity price of the ith transaction, E i is the amount of electricity in the i-th transaction, and n is the number of transactions; g. Real-time feedback and adjustment: After the transaction and settlement are completed, the user's electricity consumption behavior is fed back through the smart meter. The system can dynamically adjust the user's electricity consumption strategy based on user behavior analysis and market price fluctuations, and provide users with personalized electricity consumption suggestions; h. System adaptive optimization: During market fluctuations, the system continuously optimizes the supply and demand forecasting model and price adjustment model through reinforcement learning algorithms to ensure supply and demand balance and price stability, and reduce the impact of drastic fluctuations on the market.

7. The method for electricity market transaction and settlement for renewable energy according to claim 6, characterized in that: The multivariate data fusion supply and demand forecasting model is further combined with environmental sensor data, including wind speed, temperature, and sunshine intensity, to improve the accuracy of supply and demand forecasting.

8. The method for electricity market transaction and settlement for renewable energy according to claim 6, characterized in that: The price adjustment model of the reinforcement learning algorithm introduces a penalty mechanism to limit excessive price fluctuations and ensure the stability of market prices.

9. The method for electricity market transaction and settlement for renewable energy according to claim 6, characterized in that: The price adjustment model uses historical data analysis based on reinforcement learning and combines recent price fluctuation trends to dynamically adjust price adjustment parameters α and β. The settlement model is based on blockchain technology and supports distributed ledgers to record each transaction and settlement, ensuring the immutability and transparency of transaction data.

10. A method for electricity market transaction and settlement for renewable energy according to claim 6, characterized in that: The supply and demand forecasting model is based on machine learning technology, which can learn users' electricity usage habits and changes in meteorological conditions, and dynamically adjust forecasting parameters to improve forecasting accuracy.

Images