Comprehensive energy service power transaction method and system

Abstract

The invention relates to the technical field of electric power data transaction, in particular to an integrated energy service electric power transaction method and system. The method comprises the following steps: acquiring power use data; performing consumer behavior pattern graph construction on the power use data to generate a consumer energy use behavior pattern graph; performing comprehensive energy demand prediction on the standard power use data through the consumer energy use behavior mode map to generate consumer comprehensive energy demand prediction data; and building a block chain energy transaction platform based on the comprehensive energy demand prediction data of the consumer, and generating a block chain energy transaction contract. According to the invention, through personalized energy demand prediction, block chain transaction platform construction, electric energy type analysis, fluctuation response strategy, automatic transaction monitoring and data visualization, the flexibility and efficiency of electric power transaction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power data trading, and in particular to an integrated energy service power trading method and system. Background Art

[0002] With the rapid development of information technology, the application of big data, artificial intelligence and blockchain technology has provided strong support for power trading. Big data technology can achieve accurate prediction and demand response of the energy market, and improve the accuracy and efficiency of power trading. Artificial intelligence technology can realize the automated operation and intelligent management of the power market through algorithm optimization and intelligent decision-making. The application of blockchain technology ensures the security and transparency of power trading, realizes a decentralized trading model, and reduces transaction costs. However, at present, people often only focus on the total amount of electricity, ignoring the impact of different types of power generation on the environment and economy. At the same time, the pricing of power trading is relatively fixed and cannot flexibly respond to market fluctuations, resulting in low flexibility and efficiency of power trading. Summary of the invention

[0003] Based on this, it is necessary to provide an integrated energy service electricity trading method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, a comprehensive energy service power trading method is provided, the method comprising the following steps:

[0005] Step S1: Acquire electricity usage data; construct a consumer behavior pattern map for the electricity usage data to generate a consumer energy usage behavior pattern map;

[0006] Step S2: Comprehensive energy demand forecasting is performed on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer comprehensive energy demand forecasting data; blockchain energy trading platform is constructed based on consumer comprehensive energy demand forecasting data to generate blockchain energy trading contracts;

[0007] Step S3: Based on the blockchain energy trading contract, the standard power usage data is analyzed for the type of trading energy generation, and direct power data and indirect power conversion data are generated; the direct power data and indirect power conversion data are priced for fluctuation trading, and a power fluctuation trading response speed adjustment strategy is generated;

[0008] Step S4: Automatically monitor the power transaction of the blockchain energy trading contract according to the power fluctuation transaction response speed adjustment strategy to generate power transaction security monitoring data; visualize the power transaction security monitoring data to generate a power transaction security monitoring report.

[0009] The present invention can more accurately predict consumers' comprehensive energy needs, improve the matching degree of energy supply and demand, and reduce energy waste through the consumer energy use behavior pattern map. The construction of a blockchain energy trading platform realizes the decentralization and transparency of transactions, and enhances the security and trust of transactions. By analyzing the transaction energy generation type, the accuracy of energy identification is improved. Formulate a strategy for adjusting the response speed of power fluctuation transactions, and through automatic power transaction monitoring, realize the automated operation of power transactions, improve the efficiency and accuracy of transactions, and reduce the possibility of human errors. Visualize and report the power transaction security monitoring data, provide participants with intuitive data analysis and decision-making basis, and enhance the transparency and credibility of transactions. Therefore, the present invention improves the flexibility and efficiency of power transactions through personalized energy demand forecasting, blockchain transaction platform construction, power type analysis, fluctuation pricing strategy, automatic transaction monitoring and data visualization.

[0010] In this specification, a comprehensive energy service power trading system is provided, which is used to execute the above-mentioned comprehensive energy service power trading method. The comprehensive energy service power trading system includes:

[0011] A behavior analysis module is used to obtain power usage data; construct a consumer behavior pattern map based on the power usage data to generate a consumer energy usage behavior pattern map;

[0012] The energy demand prediction module is used to make comprehensive energy demand predictions on standard electricity usage data through consumer energy usage behavior pattern maps, and generate consumer comprehensive energy demand prediction data; construct a blockchain energy trading platform based on consumer comprehensive energy demand prediction data, and generate blockchain energy trading contracts;

[0013] The transaction pricing module is used to analyze the transaction energy generation type of standard power usage data based on the blockchain energy transaction contract, generate direct power data and indirect power conversion data; perform fluctuation transaction pricing on direct power data and indirect power conversion data, and generate a power fluctuation transaction response speed adjustment strategy;

[0014] The transaction monitoring module is used to automatically monitor the power transaction of the blockchain energy trading contract according to the power fluctuation transaction response speed adjustment strategy, generate power transaction security monitoring data; visualize the power transaction security monitoring data, and generate a power transaction security monitoring report.

[0015] The beneficial effect of the present invention is that through the consumer energy use behavior pattern map and comprehensive energy demand forecast data, the energy demand of consumers can be predicted more accurately. Based on the blockchain energy trading contract and the volatility trading pricing strategy, the automated monitoring and adjustment of power trading can be realized, which can improve the efficiency and transparency of energy trading. Through the generation and visualization report of power trading security monitoring data, potential security risks and abnormal trading behaviors can be discovered and responded to in a timely manner, the security and stability of energy trading can be improved, and the continuity of energy supply can be guaranteed. Through the analysis of trading energy generation type and the generation of direct power data and indirect power conversion data, the utilization of different energy sources can be deeply understood. Integrating blockchain technology, data analysis and visualization technology to establish an efficient, transparent and secure energy trading platform will help improve the flexibility and efficiency of power trading. Therefore, the present invention improves the flexibility and efficiency of power trading through personalized energy demand forecasting, blockchain trading platform construction, power type analysis, volatility pricing strategy, automatic transaction monitoring and data visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of steps of a comprehensive energy service power trading method;

[0017] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0018] Figure 3 for Figure 2 Detailed implementation steps of step S24;

[0019] Figure 4 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0023] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0024] To achieve this, please refer to Figures 1 to 4 , a comprehensive energy service electricity trading method, the method comprising the following steps:

[0025] Step S1: Acquire electricity usage data; construct a consumer behavior pattern map for the electricity usage data to generate a consumer energy usage behavior pattern map;

[0026] Step S2: Comprehensive energy demand forecasting is performed on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer comprehensive energy demand forecasting data; blockchain energy trading platform is constructed based on consumer comprehensive energy demand forecasting data to generate blockchain energy trading contracts;

[0027] Step S3: Based on the blockchain energy trading contract, the standard power usage data is analyzed for the type of trading energy generation, and direct power data and indirect power conversion data are generated; the direct power data and indirect power conversion data are priced for fluctuation trading, and a power fluctuation trading response speed adjustment strategy is generated;

[0028] Step S4: Automatically monitor the power transaction of the blockchain energy trading contract according to the power fluctuation transaction response speed adjustment strategy to generate power transaction security monitoring data; visualize the power transaction security monitoring data to generate a power transaction security monitoring report.

[0029] The present invention can more accurately predict consumers' comprehensive energy needs and improve the matching degree of energy supply and demand through the consumer energy usage behavior pattern map. The construction of a blockchain energy trading platform realizes the decentralization and transparency of transactions, and enhances the security and trust of transactions. By analyzing the transaction energy power generation type, the accuracy of energy identification is improved. Formulate a strategy for adjusting the response speed of power fluctuation transactions, and through automatic power transaction monitoring, realize the automated operation of power transactions, improve the efficiency and accuracy of transactions, and reduce the possibility of human errors. Visualize and report the power transaction security monitoring data, provide participants with intuitive data analysis and decision-making basis, and enhance the transparency and credibility of transactions. Therefore, the present invention improves the flexibility and efficiency of power transactions through personalized energy demand forecasting, blockchain transaction platform construction, power type analysis, fluctuation pricing strategy, automatic transaction monitoring and data visualization. In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a comprehensive energy service power trading method of the present invention. In this example, the comprehensive energy service power trading method includes the following steps:

[0030] Step S1: Acquire electricity usage data; construct a consumer behavior pattern map for the electricity usage data to generate a consumer energy usage behavior pattern map;

[0031] In an embodiment of the present invention, by obtaining the power usage data of consumers from power suppliers or relevant institutions, these data may include information such as the power consumption, power usage time, and power usage method of each consumer. These data may be real-time data, historical data, or regularly collected data. The acquired power usage data is analyzed and processed using data mining and machine learning techniques to identify the behavior patterns and characteristics of different consumers. Using cluster analysis, association rule mining and other techniques, consumers are classified according to their power usage behaviors or the association rules between different consumer behaviors are discovered. The consumer behavior patterns and characteristics are presented in the form of a graph, which may be a network graph, a heat map, etc., to show the relationships, similarities, and differences between different consumers in an intuitive way. The graph includes information such as the characteristics of consumer groups, power usage habits, peak hours, and the interactive relationships and influencing factors between consumers.

[0032] Step S2: Comprehensive energy demand forecasting is performed on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer comprehensive energy demand forecasting data; blockchain energy trading platform is constructed based on consumer comprehensive energy demand forecasting data to generate blockchain energy trading contracts;

[0033] In an embodiment of the present invention, by utilizing the consumer energy usage behavior pattern map generated in step S1, combined with standard electricity usage data, a prediction model is used to predict comprehensive energy demand. Specifically, methods such as time series analysis, machine learning algorithms (such as neural networks, decision trees, etc.), and statistical models are used to predict consumers' future energy demand. The prediction data includes information such as power consumption, power consumption patterns, and energy consumption trends in different time periods to support subsequent energy supply and trading decisions. Based on the consumer's comprehensive energy demand prediction data, a blockchain energy trading platform is built, and existing blockchain technology platforms such as Ethereum and Hyperledger can be used. Design and implement smart contracts for automatically executing energy trading rules to ensure the security, transparency and credibility of transactions. Build a user interface to provide functions such as consumer registration, energy demand prediction query, and energy trading order submission. Generate a blockchain energy trading contract based on the consumer's comprehensive energy demand prediction data and trading rules. The contract includes information such as energy suppliers, consumers, energy transaction quantities, prices, and transaction times to ensure the legality and accuracy of the transaction. Smart contract technology is used to encode and deploy contracts on the blockchain to realize the automated energy trading process. The specific blockchain energy trading contract is a smart contract implemented by blockchain technology, which is used to manage and execute energy transactions. The contract is based on the blockchain platform and uses the decentralized, transparent and tamper-proof characteristics to ensure the security, efficiency and traceability of energy transactions. The blockchain energy trading contract contains the following important elements: Participant identity information: The contract will record the identity information of all parties involved in the energy transaction to ensure the legality and security of the transaction. Transaction terms: The contract will clearly specify the specific terms of the energy transaction, including energy type, quantity, price, delivery method, etc. Smart execution logic: Blockchain energy trading contracts are usually smart contracts, which have automatic execution functions. Once the conditions of the transaction are met, the contract will automatically execute the transaction without the intervention of the intermediary. Payment and settlement mechanism: The contract will specify the payment and settlement methods to ensure the security and timely arrival of transaction funds. Transaction history: The immutability of blockchain ensures the transparency and traceability of transaction history. All transaction details will be permanently recorded on the blockchain. The more specific blockchain energy trading contract construction process includes determining the functions and characteristics of the blockchain energy trading platform, including determining the roles and permissions of the participants (consumers, power generators, energy suppliers, etc.), transaction types (purchase, sale, exchange, etc.), and transaction implementation details (such as settlement method, payment method, etc.). Choose a suitable blockchain platform such as Ethereum, Hyperledger, EOS, etc. Use smart contract languages ​​(such as Solidity, Go, etc.) to write blockchain energy trading contracts. Smart contracts are responsible for managing and executing various operations of energy transactions, including energy purchase, sale, settlement, etc. The contract needs to take into account the rights and obligations of all parties, as well as the security and reliability of the transaction.Deploy the written smart contract to the selected blockchain platform and conduct tests. The tests need to ensure that the functions and logic of the contract are correct and can run stably in the actual environment, thereby generating a blockchain energy trading contract.

[0034] Step S3: Based on the blockchain energy trading contract, the standard power usage data is analyzed for the type of trading energy generation, and direct power data and indirect power conversion data are generated; the direct power data and indirect power conversion data are priced for fluctuation trading, and a power fluctuation trading response speed adjustment strategy is generated;

[0035] In the embodiment of the present invention, the information on energy generation types involved in energy trading is recorded and tracked by using blockchain technology, which is specifically implemented through smart contracts to ensure the transparency and immutability of energy trading. According to the energy generation type information in the transaction data, statistics and analysis are performed to understand the proportion and trend of different energy types in the transaction, as well as their impact on the power market. The information on energy generation types involved in energy trading is recorded and tracked by using blockchain technology, which is specifically implemented through smart contracts to ensure the transparency and immutability of energy trading. According to the energy generation type information in the transaction data, statistics and analysis are performed to understand the proportion and trend of different energy types in the transaction, as well as their impact on the power market. The fluctuation of direct power data and indirect power conversion data is analyzed, including factors such as supply, demand, and price changes. A power fluctuation transaction response speed adjustment strategy is formulated based on the fluctuation, which involves formulating a dynamic pricing model, considering the market supply and demand relationship, and using machine learning algorithms for prediction. The adjustment strategy includes adjusting the power price according to the supply and demand situation, optimizing the energy configuration to cope with price fluctuations, formulating flexible trading rules, etc., such as monitoring the supply and demand situation in the power market and adjusting the power price according to real-time data and prediction models. When the power supply is tight, the price of electricity can be moderately increased to encourage electricity conservation and increase supply. On the contrary, when the supply is oversupplied, the price of electricity can be reduced to promote consumption and reduce the demand for energy storage. Using data analysis tools and techniques, the direct power data and indirect power conversion data are thoroughly analyzed to find out the laws and trends. A model of energy price fluctuations is established, taking into account various factors such as seasonal changes, weather effects, market supply and demand, etc., to predict future price trends. Specifically, the transaction data of solar and wind energy, including information such as power generation and price, are obtained from blockchain energy trading contracts. Then, these data are analyzed to identify the characteristics of different energy types, such as the volatility of power generation, price change trends, energy conversion methods, etc., where the volatility of power generation can be represented by calculating the standard deviation of power generation over time. Indirect power (such as solar and wind energy) usually shows greater volatility, while direct power (power converted from fossil energy) is relatively stable. The price trend can be represented by calculating the moving average of the price. The data price of direct power usually fluctuates greatly, while the data price of indirect power is relatively stable. Direct electricity (such as fossil energy) is electricity directly converted from natural resources, while indirect electricity is electricity indirectly converted through solar energy and wind energy. This can be determined by the identification of the energy source. The extracted features are standardized and the data is divided into two categories: direct electricity and indirect electricity using the KMeans clustering algorithm. According to the analysis results of energy types, the transaction data is divided into direct electricity data and indirect electricity conversion data. The part of solar energy and wind energy directly converted into electricity belongs to indirect electricity data, while the part converted into electricity through fossil energy and other means belongs to direct electricity conversion data.Based on direct power data and indirect power conversion data, a volatility trading pricing strategy is formulated, taking into account factors such as energy supply and demand, market fluctuations, and costs. According to the volatility trading pricing results, a power volatility trading response speed adjustment strategy is formulated, which involves how to adjust the operating status of solar and wind power generation equipment to meet market demand. Taking solar energy in renewable energy as an example, for example, solar power generation data is obtained from blockchain energy trading contracts, including daily power generation, power generation costs, transaction prices and other information. These data are uploaded to the blockchain in real time through smart meters, smart gateways and other devices. The acquired data is analyzed to identify the characteristics of solar power generation, such as day and night changes, seasonal changes, etc. It can then be classified as a type of solar power generation in renewable energy. According to the characteristics of solar power generation and market demand, a volatility trading pricing strategy for solar power generation is formulated. For example, during the day when solar energy is sufficient, the price of solar power generation is lower; while at night or when the weather is bad, the price is higher. Based on the volatility trading pricing results, a response speed adjustment strategy for solar power generation is formulated. For example, when market demand increases, the operating status of solar power generation equipment is specifically adjusted to increase power generation; when market demand decreases, the power generation is specifically reduced or part of the energy is stored for emergency use.

[0036] Step S4: Automatically monitor the power transaction of the blockchain energy trading contract according to the power fluctuation transaction response speed adjustment strategy to generate power transaction security monitoring data; visualize the power transaction security monitoring data to generate a power transaction security monitoring report.

[0037] In the embodiment of the present invention, by developing a monitoring system, the automatic monitoring of blockchain energy trading contracts is realized through smart contract technology. A monitoring algorithm is designed to adjust the strategy according to the response speed of power fluctuation transactions, and the execution of power trading contracts is monitored in real time. The monitoring content includes whether the transaction execution conforms to the expected price fluctuation strategy, whether there is abnormal trading behavior, etc. The data collected by the monitoring system includes transaction execution, price fluctuation, abnormal trading behavior, etc. The collected data is sorted and analyzed to generate power trading security monitoring data. The security monitoring data should include real-time data and historical data for subsequent analysis and visualization. The power trading security monitoring data is converted into visual charts, tables, etc. by using data visualization tools or technologies. The visualization content specifically includes price fluctuation trend charts, transaction execution statistics, abnormal trading behavior identification charts, etc. Ensure that the visualization results are clear and intuitive, and are easy for users to understand and analyze. Integrate the visualized monitoring data into a power trading security monitoring report. The report should include an explanation and analysis of the monitoring data, an assessment and suggestions on the safety of power trading. The report is specifically generated regularly to monitor changes and trends in the safety of power trading.

[0038] Preferably, step S1 comprises the following steps:

[0039] Step S11: Obtaining power usage data;

[0040] Step S12: performing data standardization on the power usage data to generate standard power usage data, wherein data standardization includes data cleaning, data specification and data standardization;

[0041] Step S13: Conduct consumer energy consumption trend analysis on the standard electricity usage data to generate consumer energy trend consumption analysis data; construct a consumer behavior pattern map based on the consumer energy trend analysis data to generate a consumer energy usage behavior pattern map.

[0042] The present invention can obtain the actual situation and trend of energy use by collecting electricity usage data. Remove outliers, missing values ​​or erroneous values ​​in the data to ensure data quality. Process the data to reduce the complexity and redundancy of the data to improve analysis efficiency. Scaling, translation and normalization of the data are performed so that the data has a uniform scale and distribution. By analyzing standard electricity usage data, trends and patterns of consumer energy consumption can be identified, such as peak hours, energy-saving hours, etc. Generating consumer energy trend consumption analysis data helps to understand consumers' energy usage habits and behaviors. Based on consumer energy trend analysis data, a consumer energy usage behavior pattern map is constructed to reveal consumers' behavior patterns, preferences and changes.

[0043] In an embodiment of the present invention, power usage data is obtained in real time by using devices such as sensors or smart meters. Historical power usage data is obtained from power companies or related institutions. Duplicate, missing or abnormal data is removed to ensure data quality. Appropriate data features and dimensions are selected to reduce data redundancy and complexity. The data is normalized, standardized or discretized so that the data has a unified scale and format. The standardized power usage data is analyzed using statistical analysis, data mining or machine learning techniques. Consumers' energy consumption trends are determined, such as daily, weekly or monthly peaks and troughs in electricity consumption. Consumer energy trend consumption analysis data is generated, such as energy consumption patterns, energy saving potential, etc. A graph of consumer energy usage behavior patterns is constructed using graph analysis or network analysis techniques. Based on consumer energy consumption trends and patterns, the consumer's energy usage behavior is depicted, including information on electricity usage habits, energy-saving awareness, etc.

[0044] Preferably, step S13 includes the following steps:

[0045] Step S131: Analyze the power consumption characteristics of the standard power consumption data to obtain the consumer power consumption data;

[0046] Step S132: constructing a time period electricity consumption curve based on the consumer electricity consumption data to generate the consumer time period electricity consumption curve; performing electricity consumption peak-valley difference analysis on the consumer time period electricity consumption curve to generate the consumer daily electricity consumption peak-valley difference data;

[0047] Step S133: dividing the consumer's time period power consumption curve into consumer power consumption cycles according to the consumer's daily power consumption peak-valley difference data to generate consumer power consumption cycle data; reading the power factor of the consumer's power equipment through the consumer's power consumption cycle data to obtain the power factor of the consumer's power equipment;

[0048] Step S134: using the power factor of the consumer's electrical equipment to perform a time period power load analysis on the consumer's power consumption data to generate the consumer's time period power load data; performing a consumer energy consumption trend analysis based on the consumer's time period power load data to generate the consumer energy trend consumption analysis data;

[0049] Step S135: dividing the consumer power consumption data into power consumption patterns according to the consumer energy trend consumption analysis data, and generating peak power consumption consumer data and valley power consumption consumer data;

[0050] Step S136: Perform similarity analysis on the peak electricity consumption consumer data and the valley electricity consumption consumer data to generate similar consumer group data; perform difference analysis on the peak electricity consumption consumer data and the valley electricity consumption consumer data to generate difference consumer group data; perform graph edge connection based on the similar consumer group data and the difference consumer group data to generate consumer behavior pattern graph edge data; perform graph node association on the consumer electricity consumption data based on the consumer behavior pattern graph edge data to generate a consumer energy usage behavior pattern graph.

[0051] By analyzing the characteristics of electricity consumption, the present invention can better understand the electricity consumption of consumers, including the distribution and changing trends of electricity consumption, and is helpful to discover the regularity and abnormalities of electricity consumption behavior. Generating consumer time period electricity consumption curves and daily electricity peak-to-valley difference data can help determine the peak and trough periods of electricity consumption. Dividing the consumer's electricity consumption cycle helps to understand the electricity consumption patterns in different time periods and provide a basis for formulating targeted energy management strategies. By analyzing the energy consumption trend through time period electricity load data, the energy consumption behavior patterns of consumers can be discovered. By dividing the consumer electricity consumption data into electricity consumption patterns, it is possible to identify consumers with peak and trough electricity consumption, providing a basis for differentiated energy management. Through similarity and difference analysis, consumers can be divided into different groups to better understand electricity consumption characteristics and behavior patterns, thereby providing personalized energy solutions.

[0052] In the embodiment of the present invention, standard power usage data including information such as power consumption and power consumption time of consumers are collected. Statistical methods or machine learning algorithms are used to analyze the data to identify the power consumption characteristics of consumers, such as peak hours, valley hours, daily power consumption patterns, etc. Based on the power consumption data of consumers, a time period power consumption curve is constructed to show the power consumption of consumers in different time periods. Power consumption peak-valley difference analysis is performed to determine the peak and valley periods of power consumption, and the daily power consumption peak-valley difference data of consumers is generated. According to the daily power consumption peak-valley difference data of consumers, the time period power consumption curve is divided into periods to determine the power consumption cycle of consumers. Through the period data, the power factor of the consumer's power equipment is read to obtain more detailed power consumption information. Using the power factor of the consumer's power equipment, the power consumption data is analyzed for the period power load to obtain the consumer's period power load data. Based on the power load data, an energy consumption trend analysis is performed to reveal the energy consumption pattern of consumers. According to the energy consumption trend analysis data, the power consumption of consumers is divided into power consumption patterns, and consumers are divided into peak power consumption and valley power consumption consumers. Conduct similarity and difference analysis on peak and valley power consumption consumer data to generate similarity and difference consumer group data. Based on similarity and difference consumer group data, construct a consumer behavior pattern map to show the association and behavior patterns between consumers.

[0053] Preferably, step S135 includes the following steps:

[0054] Step S1351: collecting consumer equipment power consumption signals according to consumer energy trend consumption analysis data to obtain consumer power consumption equipment signals; performing equipment power consumption intensity analysis on consumer power consumption data according to consumer power consumption equipment identification signals to generate consumer equipment power consumption intensity data;

[0055] Step S1352: based on the power intensity data of the consumer device, the signal source of the consumer power device signal is tracked to generate the movement trajectory of the consumer power device; the consumer power consumption active period is analyzed by the consumer power consumption data through the movement trajectory of the consumer power device, and the consumer power consumption active period data is generated;

[0056] Step S1353: Overlap the consumer's electricity consumption active time period data with the preset standard electricity consumption active time period to generate consumer's electricity consumption active overlapping time period and consumer's electricity consumption active non-overlapping time period, and mark the consumer's electricity consumption active overlapping time period as peak electricity consumption consumer data, and mark the consumer's electricity consumption active non-overlapping time period as valley electricity consumption consumer data.

[0057] The present invention collects consumer power equipment signals according to consumer energy trend consumption analysis data. The consumer power equipment signals are analyzed to determine the power intensity of each device and generate corresponding consumer equipment power intensity data. Based on the consumer equipment power intensity data, the signal source is tracked to determine the location and activity trajectory of each power device. The active time period of the consumer power equipment is analyzed by tracking the mobile trajectory to generate the consumer power active time period data. The consumer power active time period data is compared with the preset standard power active time period to determine the overlap and non-overlap of the active time period. The consumer power active overlap period is marked as the peak power consumption consumer data, and the non-overlap period is marked as the trough power consumption consumer data. By analyzing the consumer power equipment signals and active time periods, the consumer's power consumption habits and behavior patterns can be better understood. By identifying the peak and trough power consumption periods, the peak power consumption can be avoided and the data redundancy can be reduced. According to the consumer's active power consumption period, the energy use cycle characteristics can be more clearly obtained, making the subsequent processing more accurate.

[0058] In an embodiment of the present invention, by collecting consumer energy trend consumption analysis data, such as consumption patterns, seasonal changes, etc. Based on these data, the signals of consumer power equipment are collected, which is implemented through smart meters, sensors and other devices. The collected consumer power equipment signals are analyzed, including the time series data and frequency distribution of power consumption, as well as the characteristics of the power equipment, such as power and power consumption. According to the equipment signals and power consumption data, the power intensity of the equipment is analyzed to determine the power intensity of each device and generate the corresponding consumer equipment power intensity data. Using the power intensity data of the consumer equipment, the signal source of the consumer power equipment signal is tracked, that is, the source device of each signal is determined. By tracking the signal source, the movement trajectory of the consumer power equipment is generated, that is, the activity and position changes of different devices at different times. According to the movement trajectory and power consumption data of the consumer power equipment, the consumer power consumption active time period is analyzed to determine which time periods the consumer power consumption is more active. The consumer power consumption active time period data is compared with the preset standard power consumption active time period to find out the overlapping and non-overlapping time periods. The overlapping time periods are marked as peak power consumption consumer data, indicating that these time periods are the peak periods of consumer power consumption. The non-overlapping time periods are marked as low-consumption consumer data, indicating that consumers are less active in electricity consumption during these periods.

[0059] Preferably, step S2 comprises the following steps:

[0060] Step S21: performing consumer electricity usage behavior pattern recognition on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer electricity usage behavior pattern recognition data; dividing the consumer electricity usage behavior pattern recognition data into data sets to generate model training sets and model test sets;

[0061] Step S22: using a recurrent neural network algorithm to perform model training on the model training set to generate a comprehensive energy demand training model; using a model test set to perform model testing on the comprehensive energy demand training model to generate a comprehensive energy demand prediction model;

[0062] Step S23: importing the consumer electricity consumption behavior pattern recognition data into the comprehensive energy demand prediction model to perform comprehensive energy demand prediction, and generate consumer comprehensive energy demand prediction data;

[0063] Step S24: Conduct power supply and demand balance analysis based on consumer comprehensive energy demand forecast data to generate energy service power supply and demand balance data; construct a blockchain energy trading platform based on the energy service power supply and demand balance data to generate a blockchain energy trading contract.

[0064] The present invention analyzes and identifies standard electricity usage data through consumer energy usage behavior pattern maps, and can more accurately understand consumers' electricity usage behaviors, including electricity usage habits, periodic changes, etc. Dividing consumer electricity usage behavior pattern recognition data into training sets and test sets is helpful to establish a reliable model for subsequent energy demand forecasting. Using algorithms such as recurrent neural networks to train and test the model, an efficient and accurate comprehensive energy demand forecasting model can be established to predict future consumer energy demand trends. The forecasting model can help energy suppliers and managers make reasonable resource allocation and adjustment decisions. Power supply and demand balance analysis based on consumer comprehensive energy demand forecasting data can better understand the supply and demand of electricity. By analyzing energy service power supply and demand balance data, power supply chain management can be optimized to avoid oversupply or undersupply, and improve the efficiency and reliability of data resource use. Building a blockchain energy trading platform based on energy service power supply and demand balance data can achieve more transparent, secure and efficient energy trading. The application of blockchain technology can ensure the traceability and security of energy transactions, while reducing transaction costs and improving the security and reliability of power services.

[0065] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0066] Step S21: performing consumer electricity usage behavior pattern recognition on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer electricity usage behavior pattern recognition data; dividing the consumer electricity usage behavior pattern recognition data into data sets to generate model training sets and model test sets;

[0067] In the embodiment of the present invention, by using machine learning and data mining technology, the collected standard electricity usage data is analyzed and modeled to construct a consumer energy usage behavior pattern map, which involves data preprocessing, feature extraction, cluster analysis and other methods. According to the constructed consumer energy usage behavior pattern map, the standard electricity usage data is mapped to the corresponding consumer electricity usage behavior pattern, thereby generating consumer electricity usage behavior pattern recognition data. The generated consumer electricity usage behavior pattern recognition data is divided into a model training set and a model test set. The commonly used division methods include random division, time series division, etc., to ensure that there is no overlap between the training set and the test set. The training set is used to train the consumer electricity usage behavior pattern recognition model. Specifically, a machine learning algorithm such as a convolutional neural algorithm is selected, and the model parameters are tuned by cross-validation and other technologies. The trained consumer electricity usage behavior pattern recognition model is tested and evaluated using a test set. Evaluation indicators include accuracy, recall rate, F1-score, etc., and methods such as drawing confusion matrices are used to analyze model performance. The model is optimized and adjusted according to the test results, and steps such as model structure, feature selection, and parameter adjustment need to be adjusted to improve the generalization ability and accuracy of the model. Deploy the optimized consumer electricity behavior pattern recognition model to the production environment for actual use. During the deployment process, factors such as model performance, scalability, and real-time performance need to be considered, and the stability and security of the model must be ensured.

[0068] Step S22: using a recurrent neural network algorithm to perform model training on the model training set to generate a comprehensive energy demand training model; using a model test set to perform model testing on the comprehensive energy demand training model to generate a comprehensive energy demand prediction model;

[0069] In an embodiment of the present invention, the model training set and model test set generated by step S21 are used as input data. RNN is a deep learning algorithm suitable for sequence data, suitable for processing time series data, such as energy demand time series. Select RNN variants, such as long short-term memory network (LSTM) or gated recurrent unit (GRU), to deal with problems such as long-term dependence and gradient disappearance. Construct the network structure of the RNN model, including input layer, recurrent layer (LSTM or GRU), output layer, etc. Determine the hyperparameters of the model, such as the number of hidden units, learning rate, optimizer (such as Adam, SGD, etc.). Use the model training set to train the constructed RNN model. In each training cycle, the model is input into the time series of training data, and the model parameters are updated by the back propagation algorithm to optimize the prediction performance of the model. Use the model test set to test the trained RNN model. Input the model into the time series of test data, and compare the difference between the model prediction results and the actual values ​​to evaluate the prediction accuracy and generalization ability of the model. Analyze the performance of the model on the test set, evaluate the model's performance indicators (such as mean square error, mean absolute error, etc.), and adjust the model parameters and optimize the hyperparameters as needed to improve the model's prediction accuracy and stability. After multiple training and testing iterations, determine the final RNN model as the comprehensive energy demand forecasting model for future energy demand forecasting tasks.

[0070] Step S23: importing the consumer electricity consumption behavior pattern recognition data into the comprehensive energy demand prediction model to perform comprehensive energy demand prediction, and generate consumer comprehensive energy demand prediction data;

[0071] In the embodiment of the present invention, by ensuring that the consumer's electricity consumption behavior pattern data has been collected, these data specifically include characteristic information such as the consumer's electricity consumption time series, historical electricity consumption, holidays, etc. The consumer's electricity consumption behavior pattern recognition data is preprocessed, including data cleaning, feature selection, feature scaling and other operations. Ensure the quality and consistency of the data for subsequent modeling and prediction. Use the comprehensive energy demand prediction model trained in step S22 to import the consumer's electricity consumption behavior pattern recognition data into the model for prediction, which is specifically implemented through the model interface or programming. Input the consumer's electricity consumption behavior pattern recognition data into the comprehensive energy demand prediction model, and the model will predict the comprehensive energy demand in the future period based on the consumer's electricity consumption characteristics and historical data. The prediction results are specifically electricity consumption, energy type demand, etc. According to the model prediction results, the consumer's comprehensive energy demand prediction data is generated. These data include information such as the electricity consumption forecast value and energy type demand forecast value of each consumer in the future time period. The generated consumer comprehensive energy demand prediction data is analyzed and verified to evaluate the accuracy and reliability of the prediction results. Specifically, historical data is used to compare with the prediction results to perform error analysis and model improvement.

[0072] Step S24: Conduct power supply and demand balance analysis based on consumer comprehensive energy demand forecast data to generate energy service power supply and demand balance data; construct a blockchain energy trading platform based on the energy service power supply and demand balance data to generate a blockchain energy trading contract.

[0073] In an embodiment of the present invention, by using the consumer's comprehensive energy demand forecast data, combined with other relevant data (such as power generation, storage, etc.), power supply and demand balance analysis is performed, which is specifically achieved by establishing a model or algorithm. The consumer's comprehensive energy demand forecast data and the energy output of the supply side (power generation, energy storage, etc.) are analyzed to determine the balance between supply and demand, that is, whether the consumer's energy demand can be met in a specific time period, or whether there is a surplus or shortage of energy. According to the results of the power supply and demand balance analysis, energy service power supply and demand balance data are generated. These data specifically include information such as power demand, power supply, energy reserves, and energy regulation requirements in each time period. The energy service power supply and demand balance data is specifically used to guide decisions such as the operation of the power market, energy scheduling, and power trading to ensure the balance and stability between energy supply and demand. Based on the generated energy service power supply and demand balance data, a blockchain energy trading platform is constructed. This platform is specifically a decentralized platform that realizes energy trading and settlement through blockchain technology. Design and implement smart contracts for automatically executing energy trading rules, managing capital flows during transactions, and supervising the transparency and security of the energy supply chain. Build a user interface and trading system so that users can easily conduct energy transactions and monitor energy prices and market conditions. Generate corresponding blockchain energy trading contracts based on the design and requirements of the blockchain energy trading platform. These contracts stipulate the conditions for energy transactions, the rights and obligations of the participants, the execution process of the transaction, etc. The generation of contracts is specifically implemented through smart contract programming languages ​​(such as Solidity) to ensure the security, reliability and automatic execution of the contracts.

[0074] Preferably, step S24 includes the following steps:

[0075] Step S241: performing energy demand power evaluation on the consumer comprehensive energy demand forecast data to generate energy demand power evaluation data; dividing the energy demand power evaluation data into power influencing factors to generate power influencing external factors and power influencing internal factors;

[0076] Step S242: Performing power transportation impact loss analysis on external factors affecting power, generating power transportation impact loss data, wherein the power transportation impact loss data includes weather impact data and seasonal impact data; performing power supply impact loss analysis on internal factors affecting power, generating power supply impact loss data;

[0077] Step S243: adjusting the power supply demand of the power supply loss data according to the weather impact data and the season impact data to generate actual power supply demand adjustment data; balancing the power supply demand gap based on the actual power supply demand adjustment data to generate energy service power supply and demand balance data;

[0078] Step S244: Write an electric power transaction smart contract for the energy service electric power supply and demand balance data through the blockchain platform to generate an electric power transaction smart contract, wherein the writing of the electric power transaction smart contract includes the identification of the participants, electric power transaction details, electric power supply and demand data and electric power transaction time; deploy the electric power transaction smart contract to the preset blockchain network for transaction security and privacy protection, thereby generating a blockchain energy transaction contract.

[0079] By evaluating the consumer's comprehensive energy demand forecast data, the present invention can more accurately understand the energy demand situation and provide a basis for subsequent energy planning. The power influencing factors are divided into external factors and internal factors, and the power transportation impact loss data is analyzed, which helps to more comprehensively consider the various factors affecting energy supply and demand and improve the accuracy of decision-making. According to the weather and seasonal impact data, the power supply impact loss data is adjusted to generate actual power supply and demand adjustment data, which can improve energy utilization efficiency. Based on the actual power supply and demand adjustment data, step S243 performs power supply and demand balance gaps to generate energy service power supply and demand balance data. This helps to ensure the balance between energy supply and demand. Writing a power transaction smart contract on the blockchain platform and deploying it to the preset blockchain network for transactions can achieve transaction security and privacy protection, which helps to establish a safe and reliable energy trading platform.

[0080] As an example of the present invention, refer to Figure 3 As shown, in this example, step S24 includes:

[0081] Step S241: performing energy demand power evaluation on the consumer comprehensive energy demand forecast data to generate energy demand power evaluation data; dividing the energy demand power evaluation data into power influencing factors to generate power influencing external factors and power influencing internal factors;

[0082] In an embodiment of the present invention, various available data sources are collected, such as historical energy usage data, demographic data, economic development data, industrial activity data, etc., to predict future energy demand. The collected data is cleaned and preprocessed, including processing missing values, outliers and noise data to ensure the quality and accuracy of the data. Based on the consumer's comprehensive energy demand forecast data, a suitable model and algorithm are used to perform an electricity assessment of energy demand to predict future electricity demand and generate corresponding energy demand electricity assessment data. The energy demand electricity assessment data is divided into external factors and internal factors according to influencing factors. External factors include external factors that affect energy demand, such as weather, season, and economic environment; internal factors include internal factors that affect energy demand, such as technological development, energy policy, and population structure. According to the divided influencing factors, the corresponding electricity impact external factor data and electricity impact internal factor data are generated for subsequent analysis and decision-making.

[0083] Step S242: Performing power transportation impact loss analysis on external factors affecting power, generating power transportation impact loss data, wherein the power transportation impact loss data includes weather impact data and seasonal impact data; performing power supply impact loss analysis on internal factors affecting power, generating power supply impact loss data;

[0084] In an embodiment of the present invention, relevant weather data including temperature, humidity, precipitation, etc. are obtained, which have a great impact on power transportation. Data of different seasons are collected, for example, summer and winter have different impacts on power demand and transportation. The collected weather data is used to analyze the impact of power transportation under different weather conditions, such as power transmission loss under extreme weather conditions. The power demand and supply under different seasons are analyzed to understand the impact of seasonal effects on the power system. The weather impact data and the seasonal impact data are integrated to form power transportation impact loss data, including power transportation loss under different weather conditions and seasons. Specifically, the analysis results are modeled using statistical models or machine learning models for subsequent prediction and optimization. Data related to power supply are obtained, such as the status of power supply facilities, supply chain information, etc. The impact of internal factors on power supply is analyzed, such as supply chain delays, equipment failures, and other factors. Power supply impact loss data is generated based on the analysis results to describe the impact and loss caused by internal factors on power supply.

[0085] Step S243: adjusting the power supply demand of the power supply loss data according to the weather impact data and the season impact data to generate actual power supply demand adjustment data; balancing the power supply demand gap based on the actual power supply demand adjustment data to generate energy service power supply and demand balance data;

[0086] In an embodiment of the present invention, by comprehensively considering the impact of weather and season on power supply, the relationship between it and power supply and demand is analyzed. Based on the analysis results, a corresponding power supply and demand adjustment strategy is formulated to cope with changes in power supply and demand under different weather and seasonal conditions. According to the formulated strategy, the power supply and demand are adjusted accordingly, taking into account weather conditions and seasonal changes to obtain more accurate actual power supply and demand data. Based on the actual power supply and demand adjustment data, the gap and difference between power supply and demand are analyzed. According to the analysis results, a power supply and demand balance strategy is formulated to fill the supply and demand gap and ensure the balance between power supply and demand. According to the formulated strategy, the power supply or demand is adjusted accordingly to achieve supply and demand balance. The adjusted power supply and demand data are integrated to form energy service power supply and demand balance data. The generated data is verified and checked to ensure data accuracy and reliability. The energy service power supply and demand balance data is recorded, and corresponding reports or visualization results are generated for subsequent analysis and decision-making.

[0087] Step S244: Write an electric power transaction smart contract for the energy service electric power supply and demand balance data through the blockchain platform to generate an electric power transaction smart contract, wherein the writing of the electric power transaction smart contract includes the identification of the participants, electric power transaction details, electric power supply and demand data and electric power transaction time; deploy the electric power transaction smart contract to the preset blockchain network for transaction security and privacy protection, thereby generating a blockchain energy transaction contract.

[0088] In the embodiment of the present invention, by determining the identities of the parties involved in the power transaction, including energy suppliers, consumers, trading platforms, etc., a unique identity is assigned to each participant. The details of the power transaction are determined, including the transaction method (such as fixed price, market auction, etc.), transaction conditions (such as minimum transaction volume, maximum transaction volume, transaction period, etc.) and related compliance requirements. The energy service power supply and demand balance data is integrated into the smart contract to ensure that the basic data of the transaction is accurate, including information such as supply, demand, price, etc. The time schedule of the power transaction is determined, including the transaction start time, end time and possible periodic transaction arrangements. According to the needs, a suitable blockchain platform is selected, such as Ethereum, Hyperledger Fabric, etc., considering its performance, security, cost and other factors. Using the development tools and interfaces provided by the blockchain platform, the written power transaction smart contract is deployed to the preset blockchain network. Take corresponding security measures to protect the security and privacy of the transaction, such as data encryption, identity authentication, permission management, etc., to ensure that the transaction information is not tampered with or leaked. Verify the smart contract deployed in the blockchain network to ensure the correctness of its functions and logic. The participants execute the electricity transaction according to the rules set in the smart contract, and the transaction information will be recorded on the blockchain, making the transaction transparent and tamper-proof. As the transaction proceeds, blockchain energy transaction contracts will continue to be generated, recording the transaction behavior and related information of the participants.

[0089] Preferably, step S3 comprises the following steps:

[0090] Step S31: Analyze the transaction energy generation type of the standard power usage data based on the blockchain energy transaction contract to generate direct power data and indirect power conversion data, where the indirect power conversion data includes wind power conversion data and solar power conversion data, and mark the direct power data with a first power source to generate first power source data;

[0091] Step S32: integrating cross-border conversion data through wind power conversion data and solar power conversion data to generate cross-border power source data, and marking the cross-border power source data as a second power source to generate second power source data;

[0092] Step S33: performing power energy efficiency analysis on the first power source data and the second power source data to generate first power energy efficiency data and second power energy efficiency data;

[0093] Step S34: performing fluctuation trading pricing according to the first power energy efficiency data and the second power energy efficiency data, and generating a power fluctuation trading response speed adjustment strategy.

[0094] By analyzing the standard electricity usage data, the present invention can understand the type of energy generation, including direct electricity and indirect electricity conversion data (such as wind power conversion and solar power conversion). This helps to identify the proportion of energy and its impact on energy trading. The direct electricity data is marked as the first power source data, which provides a basis for subsequent power energy efficiency analysis. Integrate wind power conversion data and solar power conversion data to generate cross-border power source data and mark it as second power source data. This helps to comprehensively consider the impact of different energy types and provide more comprehensive data for power energy efficiency analysis. Energy efficiency analysis of the first power source data and the second power source data can evaluate the efficiency of various energy conversion processes and provide basic data for volatility trading pricing, which helps to improve energy utilization efficiency. According to the first power energy efficiency data and the second power energy efficiency data, a power fluctuation transaction response speed adjustment strategy is formulated. The strategy can adjust the transaction pricing according to the volatility of different energy types to make the transaction more flexible and efficient.

[0095] As an example of the present invention, refer to Figure 4 As shown, in this example, step S3 includes:

[0096] Step S31: Analyze the transaction energy generation type of the standard power usage data based on the blockchain energy transaction contract to generate direct power data and indirect power conversion data, where the indirect power conversion data includes wind power conversion data and solar power conversion data, and mark the direct power data with a first power source to generate first power source data;

[0097] In an embodiment of the present invention, standard electricity usage data is obtained, which includes energy usage of consumers, production capacity data of power plants, etc. These data are specifically collected through smart meters, sensors, energy monitoring systems and other devices. The collected data is transmitted to the blockchain energy trading contract for storage. Blockchain technology can ensure the security and immutability of data and provide traceability. Energy generation type analysis is performed in the blockchain energy trading contract to identify direct power data and indirect power conversion data, involving the use of data mining, machine learning or other analysis techniques to identify energy sources. Direct power data is marked as first power source data, and a first power source data set is generated. At the same time, the indirect power conversion data is subdivided, including wind power conversion data and solar power conversion data, and they are stored as corresponding data sets. Smart contracts are executed to automate the data marking and generation process, which is specifically achieved by writing smart contract code and deploying it on the blockchain network.

[0098] Step S32: integrating cross-border conversion data through wind power conversion data and solar power conversion data to generate cross-border power source data, and marking the cross-border power source data as a second power source to generate second power source data;

[0099] In an embodiment of the present invention, wind power conversion data and solar power conversion data are collected and integrated. These data come from facilities such as wind power stations and solar photovoltaic panels, including their power generation, production capacity and other information. The integrated wind power conversion data and solar power conversion data are cross-border integrated to generate cross-border power source data, which involves unified unit conversion and data format standardization of data of different energy types for subsequent processing and analysis. The cross-border power source data is marked as a second power source, which involves determining the secondary source of the energy or its secondary position in energy trading. The marking method is specifically to add corresponding tags or metadata to the data set to indicate that it is a second power source. Based on the marked cross-border power source data, a second power source data set is generated. This data set will contain cross-border power source data and corresponding second power source tags for subsequent energy trading and analysis.

[0100] Step S33: performing power energy efficiency analysis on the first power source data and the second power source data to generate first power energy efficiency data and second power energy efficiency data;

[0101] In an embodiment of the present invention, the first power source data and the second power source data are prepared. These data include information such as output, energy consumption, efficiency, etc. of various power production methods. Determine indicators for evaluating power energy efficiency, such as unit energy output, energy utilization rate, carbon emissions, etc. Use statistical analysis and modeling techniques to perform power energy efficiency analysis on the first power source data and the second power source data, involving the use of tools such as Python, R or MATLAB for data processing and analysis, calculation and evaluation of energy efficiency indicators. According to the selected energy efficiency indicators, the first power source data and the second power source data are energy efficiency calculated, including calculating the efficiency, energy utilization rate, emissions and other indicators of various energy conversion processes, and integrating the results into the corresponding energy efficiency data set. Explain and report the results of the energy efficiency analysis, including comparison and evaluation of the first power energy efficiency data and the second power energy efficiency data. The explanation includes comparative analysis of the energy efficiency performance of different energy sources to identify potential improvement space and optimization strategies.

[0102] Step S34: performing fluctuation trading pricing according to the first power energy efficiency data and the second power energy efficiency data, and generating a power fluctuation trading response speed adjustment strategy.

[0103] In an embodiment of the present invention, by determining the first and second power energy efficiency data to be collected, this includes information such as energy output, consumption, and storage. Deploy sensors or data acquisition equipment to monitor and collect power energy efficiency data in real time. Preprocess and clean the collected power energy efficiency data to ensure the accuracy and consistency of the data. Including operations such as removing outliers, filling missing values, and data smoothing. Based on the collected first and second power energy efficiency data, a volatility trading pricing model is established. Specifically, machine learning, time series analysis, or other modeling methods are used to predict future power price fluctuations based on historical data and characteristic variables. Combined with the output of the volatility trading pricing model, a power fluctuation trading response speed adjustment strategy is formulated. The strategy includes adjusting the transaction response speed according to the predicted price fluctuations to maximize returns or reduce risks. Use historical data or simulation data to verify the effectiveness and feasibility of the power fluctuation trading response speed adjustment strategy. According to the verification results, the strategy is tuned and improved to improve its adaptability and robustness. The generated power fluctuation trading response speed adjustment strategy is applied to the actual trading environment. A real-time monitoring system is established to monitor power price fluctuations and transaction execution so as to adjust power strategies in a timely manner. The specific response speed adjustment can be determined based on the amplitude of price fluctuations and the uncertainty of the forecast. For example, if the predicted price fluctuation amplitude is large, the response is fast, and if the predicted price fluctuation amplitude is small, the response is slow. When the price fluctuation amplitude exceeds 1.5, the transaction response speed is quickly adjusted to 10. At this time, the system quickly adjusts power supply and prices to respond to market changes. When the price fluctuation amplitude is between 1.0 and 1.5, the transaction response speed is adjusted to 7. At this time, the system is moderately adjusted to balance the response speed and market stability. When the price fluctuation amplitude is between 0.5 and 1.0, the transaction response speed is adjusted to 5. At this time, the system adjusts slowly to reduce the fluctuations caused by frequent adjustments. When the price fluctuation amplitude is less than 0.5, the response speed is adjusted to 2. At this time, the system responds slowly to maintain the smooth operation of the market.

[0104] Preferably, the volatility trading pricing in step S34 includes the following steps:

[0105] Divide the transaction phases based on the blockchain energy transaction contract to generate the transaction window period and the transaction active period; analyze the power market share based on the first power energy efficiency data and the second power energy efficiency data to generate the first power market share data and the second power market share data;

[0106] The power market response is judged on the first power market share ratio data and the second power market share ratio data. When the first power market share ratio data is greater than the second power market share ratio data, a high power transaction demand phase is generated; when the first power market share ratio data is less than the second power market share ratio data, a low power transaction demand phase is generated;

[0107] Price fluctuation adjustment is judged through the trading window period and the trading active period, as well as the high demand stage and the low demand stage of electricity trading. When the trading stage is in the trading window period and the power market response is judged to be the high demand stage of electricity trading, the power trading response speed of the blockchain energy trading contract remains unchanged; when the trading stage is in the trading window period and the power market response is judged to be the low demand stage of electricity trading, the power trading response speed of the blockchain energy trading contract decreases;

[0108] When the transaction stage is in an active trading period and the power market response is judged to be a high-demand stage for power trading, the power trading response speed of the blockchain energy trading contract is improved; when the transaction stage is in an active trading period and the power market response is judged to be a low-demand stage for power trading, the power trading response of the blockchain energy trading contract is suspended.

[0109] The present invention can improve the flexibility and reaction speed of the trading system by adjusting the power transaction response speed of the blockchain energy trading contract according to the transaction stage and the power market response. During the high demand stage and active trading period, by improving the response speed, user needs can be met faster and transaction efficiency can be increased. According to the discrimination conditions of the transaction window period and the low demand stage, when the market demand is low, reducing the response speed of power trading can reduce the risk of excessive trading. This can avoid executing transactions too quickly, resulting in oversupply in the market or increased price fluctuations. By calculating the power market share ratio based on the first and second power energy efficiency data and using it as a discrimination condition, the share distribution of the power market can be analyzed and adjusted. This helps to understand the changing trend of the market share of electricity. Through reasonable transaction stage division and price fluctuation adjustment discrimination, the transaction response speed can be reduced during the transaction window period and the low demand stage, invalid or excessive transaction activities can be avoided, and the utilization rate of data resources can be reduced.

[0110] In an embodiment of the present invention, the transaction phase is divided into a transaction window period and a transaction active period based on a blockchain energy trading contract. The transaction window period refers to a period when market demand is low, and the transaction active period refers to a period when market demand is high. The first power energy efficiency data and the second power energy efficiency data are used to calculate the market share data of each power provider, and the market share of each provider is determined by comparing the size of the power energy efficiency data. According to the comparison of the first and second power market share data, it is determined whether the current transaction phase is a high demand phase or a low demand phase. If the first power market share data is greater than the second power market share data, it is determined to be a high demand phase; if the first power market share data is less than the second power market share data, it is determined to be a low demand phase. According to the transaction phase and the power market response judgment result, the price fluctuation adjustment is judged. When the transaction is in the trading window period and the power market responds to the high demand stage, the power transaction response speed of the blockchain energy trading contract will not be changed; when the transaction is in the trading window period and the power market responds to the low demand stage, the power transaction response speed of the blockchain energy trading contract will be reduced; when the transaction is in the active trading period and the power market responds to the high demand stage, the power transaction response speed of the blockchain energy trading contract will be increased; when the transaction is in the active trading period and the power market responds to the low demand stage, the power transaction response of the blockchain energy trading contract will be suspended.

[0111] Preferably, step S4 comprises the following steps:

[0112] Step S41: Automatically conduct power trading on the blockchain energy trading contract according to the power fluctuation trading response speed adjustment strategy to generate power trading data; monitor the transaction security of the power trading data to generate power trading security monitoring data;

[0113] Step S42: Visualize the power transaction security monitoring data and generate a power transaction security monitoring report.

[0114] The present invention automatically conducts electricity trading on blockchain energy trading contracts through an electricity fluctuation transaction response speed adjustment strategy, and generates electricity trading data. Subsequently, the transaction security of these electricity trading data is monitored to generate electricity trading security monitoring data. Such operations can ensure the security and compliance in the electricity trading process, and provide data support for further analysis and decision-making. For the electricity trading security monitoring data, data visualization processing is performed to generate an electricity trading security monitoring report. The beneficial effect of this step is that through the visualization report, the security status of electricity trading can be intuitively displayed, which helps relevant personnel quickly understand the transaction situation and promptly discover potential security risks or abnormal situations, which can strengthen the supervision and management of electricity trading security and help improve the stability and reliability of the overall trading system.

[0115] In an embodiment of the present invention, an energy trading contract is automatically adjusted according to the fluctuation of the power market through an adjustment strategy for the response speed of power fluctuation trading, involving the use of historical data, market forecasting models and real-time data to determine the best trading strategy. Blockchain smart contracts are designed and implemented to ensure the transparency, security and automated execution of energy trading. Automated power trading is performed through smart contracts, and corresponding transaction data is generated when the transaction occurs, including information such as the time, participants, energy quantity, price, etc. of the transaction. A monitoring system is developed to monitor the security of power trading in real time, including detecting abnormal trading behavior, preventing potential fraudulent activities and ensuring the compliance of transactions. Based on the data collected by the monitoring system, power trading security monitoring data is generated, including abnormal trading conditions, security incident reports, transaction compliance analysis, etc. Suitable data visualization tools or platforms, such as Tableau, Power BI, etc., are selected for processing and presenting monitoring data. The layout and content of the power trading security monitoring report are designed, including charts, tables, indicators, etc., so as to clearly show the security of the transaction. The monitoring data is converted into a visual report using the selected data visualization tool, and the timely update and accessibility of the report are ensured.

[0116] In this specification, a comprehensive energy service power trading system is provided, which is used to execute the above-mentioned comprehensive energy service power trading method. The comprehensive energy service power trading system includes:

[0117] A behavior analysis module is used to obtain power usage data; construct a consumer behavior pattern map based on the power usage data to generate a consumer energy usage behavior pattern map;

[0118] The energy demand prediction module is used to make comprehensive energy demand predictions on standard electricity usage data through consumer energy usage behavior pattern maps, and generate consumer comprehensive energy demand prediction data; construct a blockchain energy trading platform based on consumer comprehensive energy demand prediction data, and generate blockchain energy trading contracts;

[0119] The transaction pricing module is used to analyze the transaction energy generation type of standard power usage data based on the blockchain energy transaction contract, generate direct power data and indirect power conversion data; perform fluctuation transaction pricing on direct power data and indirect power conversion data, and generate a power fluctuation transaction response speed adjustment strategy;

[0120] The transaction monitoring module is used to automatically monitor the power transaction of the blockchain energy trading contract according to the power fluctuation transaction response speed adjustment strategy, generate power transaction security monitoring data; visualize the power transaction security monitoring data, and generate a power transaction security monitoring report.

[0121] The beneficial effect of the present invention is that through the consumer energy use behavior pattern map and comprehensive energy demand forecast data, the energy demand of consumers can be predicted more accurately. Based on the blockchain energy trading contract and the volatility trading pricing strategy, the automated monitoring and adjustment of power trading can be realized, which can improve the efficiency and transparency of energy trading. Through the generation and visualization report of power trading security monitoring data, potential security risks and abnormal trading behaviors can be discovered and responded to in a timely manner, the security and stability of energy trading can be improved, and the continuity of energy supply can be guaranteed. Through the analysis of trading energy generation type and the generation of direct power data and indirect power conversion data, the utilization of different energy sources can be deeply understood. Integrating blockchain technology, data analysis and visualization technology to establish an efficient, transparent and secure energy trading platform will help improve the flexibility and efficiency of power trading. Therefore, the present invention improves the flexibility and efficiency of power trading through personalized energy demand forecasting, blockchain trading platform construction, power type analysis, volatility pricing strategy, automatic transaction monitoring and data visualization.

[0122] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0123] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A comprehensive energy service power trading method, characterized in that: The following steps are involved: Step S1: Acquire electricity usage data; construct a consumer behavior pattern map for the electricity usage data to generate a consumer energy usage behavior pattern map; Step S2: Perform comprehensive energy demand forecasting on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer comprehensive energy demand forecasting data; Build a blockchain energy trading platform based on consumer comprehensive energy demand forecast data and generate blockchain energy trading contracts; Step S3: Based on the blockchain energy trading contract, the standard power usage data is analyzed for the type of trading energy generation, and direct power data and indirect power conversion data are generated; the direct power data and indirect power conversion data are priced for fluctuation trading, and a power fluctuation trading response speed adjustment strategy is generated; Step S4: Automatically monitor the power transaction of the blockchain energy transaction contract according to the power fluctuation transaction response speed adjustment strategy to generate power transaction security monitoring data; Visualize the power trading security monitoring data and generate a power trading security monitoring report.

2. The integrated energy service electricity trading method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Obtaining power usage data; Step S12: performing data standardization on the power usage data to generate standard power usage data, wherein data standardization includes data cleaning, data specification and data standardization; Step S13: Conduct consumer energy consumption trend analysis on the standard electricity usage data to generate consumer energy trend consumption analysis data; construct a consumer behavior pattern map based on the consumer energy trend analysis data to generate a consumer energy usage behavior pattern map.

3. The integrated energy service electricity trading method according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: Analyze the power consumption characteristics of the standard power consumption data to obtain the consumer power consumption data; Step S132: constructing a time period electricity consumption curve based on the consumer electricity consumption data to generate the consumer time period electricity consumption curve; performing electricity consumption peak-valley difference analysis on the consumer time period electricity consumption curve to generate the consumer daily electricity consumption peak-valley difference data; Step S133: dividing the consumer's time period power consumption curve into consumer power consumption cycles according to the consumer's daily power consumption peak-valley difference data to generate consumer power consumption cycle data; reading the power factor of the consumer's power equipment through the consumer's power consumption cycle data to obtain the power factor of the consumer's power equipment; Step S134: using the power factor of the consumer's electrical equipment to perform a time period power load analysis on the consumer's power consumption data to generate the consumer's time period power load data; performing a consumer energy consumption trend analysis based on the consumer's time period power load data to generate the consumer energy trend consumption analysis data; Step S135: dividing the consumer power consumption data into power consumption patterns according to the consumer energy trend consumption analysis data, and generating peak power consumption consumer data and valley power consumption consumer data; Step S136: Perform similarity analysis on the peak electricity consumption consumer data and the valley electricity consumption consumer data to generate similar consumer group data; perform difference analysis on the peak electricity consumption consumer data and the valley electricity consumption consumer data to generate difference consumer group data; perform graph edge connection based on the similar consumer group data and the difference consumer group data to generate consumer behavior pattern graph edge data; perform graph node association on the consumer electricity consumption data based on the consumer behavior pattern graph edge data to generate a consumer energy usage behavior pattern graph.

4. The integrated energy service electricity trading method according to claim 3, characterized in that: Step S135 includes the following steps: Step S1351: collecting consumer equipment power consumption signals according to consumer energy trend consumption analysis data to obtain consumer power consumption equipment signals; performing equipment power consumption intensity analysis on consumer power consumption data according to consumer power consumption equipment identification signals to generate consumer equipment power consumption intensity data; Step S1352: based on the power intensity data of the consumer device, the signal source of the consumer power device signal is tracked to generate the movement trajectory of the consumer power device; the consumer power consumption active period is analyzed by the consumer power consumption data through the movement trajectory of the consumer power device, and the consumer power consumption active period data is generated; Step S1353: Overlap the consumer's electricity consumption active time period data with the preset standard electricity consumption active time period to generate consumer's electricity consumption active overlapping time period and consumer's electricity consumption active non-overlapping time period, and mark the consumer's electricity consumption active overlapping time period as peak electricity consumption consumer data, and mark the consumer's electricity consumption active non-overlapping time period as valley electricity consumption consumer data.

5. The integrated energy service electricity trading method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing consumer electricity usage behavior pattern recognition on standard electricity usage data through consumer energy usage behavior pattern maps to generate consumer electricity usage behavior pattern recognition data; dividing the consumer electricity usage behavior pattern recognition data into data sets to generate model training sets and model test sets; Step S22: using a recurrent neural network algorithm to perform model training on the model training set to generate a comprehensive energy demand training model; using a model test set to perform model testing on the comprehensive energy demand training model to generate a comprehensive energy demand prediction model; Step S23: importing the consumer electricity consumption behavior pattern recognition data into the comprehensive energy demand prediction model to perform comprehensive energy demand prediction and generate consumer comprehensive energy demand prediction data; Step S24: Conduct power supply and demand balance analysis based on consumer comprehensive energy demand forecast data to generate energy service power supply and demand balance data; construct a blockchain energy trading platform based on the energy service power supply and demand balance data to generate a blockchain energy trading contract.

6. The integrated energy service electricity trading method according to claim 5, characterized in that: Step S24 includes the following steps: Step S241: performing energy demand power evaluation on the consumer comprehensive energy demand forecast data to generate energy demand power evaluation data; dividing the energy demand power evaluation data into power influencing factors to generate power influencing external factors and power influencing internal factors; Step S242: Performing power transportation impact loss analysis on external factors affecting power, generating power transportation impact loss data, wherein the power transportation impact loss data includes weather impact data and seasonal impact data; performing power supply impact loss analysis on internal factors affecting power, generating power supply impact loss data; Step S243: adjusting the power supply demand of the power supply loss data according to the weather impact data and the season impact data to generate actual power supply demand adjustment data; balancing the power supply demand gap based on the actual power supply demand adjustment data to generate energy service power supply and demand balance data; Step S244: Write an electric power transaction smart contract for the energy service electric power supply and demand balance data through the blockchain platform to generate an electric power transaction smart contract, wherein the writing of the electric power transaction smart contract includes the identification of the participants, electric power transaction details, electric power supply and demand data and electric power transaction time; deploy the electric power transaction smart contract to the preset blockchain network for transaction security and privacy protection, thereby generating a blockchain energy transaction contract.

7. The integrated energy service electricity trading method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Analyze the transaction energy generation type of the standard power usage data based on the blockchain energy transaction contract to generate direct power data and indirect power conversion data, where the indirect power conversion data includes wind power conversion data and solar power conversion data, and mark the direct power data with a first power source to generate first power source data; Step S32: integrating cross-border conversion data through wind power conversion data and solar power conversion data to generate cross-border power source data, and marking the cross-border power source data as a second power source to generate second power source data; Step S33: performing power energy efficiency analysis on the first power source data and the second power source data to generate first power energy efficiency data and second power energy efficiency data; Step S34: adjusting the fluctuation transaction response speed according to the first power energy efficiency data and the second power energy efficiency data, and generating a power fluctuation transaction response speed adjustment strategy.

8. The integrated energy service electricity trading method according to claim 7, characterized in that: The volatility trading pricing of step S34 includes the following steps: Divide the transaction phases based on the blockchain energy transaction contract to generate the transaction window period and the transaction active period; analyze the power market share based on the first power energy efficiency data and the second power energy efficiency data to generate the first power market share data and the second power market share data; The power market response is judged on the first power market share ratio data and the second power market share ratio data. When the first power market share ratio data is greater than the second power market share ratio data, a high power transaction demand phase is generated; when the first power market share ratio data is less than the second power market share ratio data, a low power transaction demand phase is generated; Price fluctuation adjustment is judged through the trading window period and the trading active period, as well as the high demand stage and the low demand stage of electricity trading. When the trading stage is in the trading window period and the power market response is judged to be the high demand stage of electricity trading, the power trading response speed of the blockchain energy trading contract remains unchanged; when the trading stage is in the trading window period and the power market response is judged to be the low demand stage of electricity trading, the power trading response speed of the blockchain energy trading contract decreases; When the transaction stage is in an active trading period and the power market response is judged to be a high-demand stage for power trading, the power trading response speed of the blockchain energy trading contract is improved; when the transaction stage is in an active trading period and the power market response is judged to be a low-demand stage for power trading, the power trading response of the blockchain energy trading contract is suspended.

9. The integrated energy service electricity trading method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Automatically conduct power trading on the blockchain energy trading contract according to the power fluctuation trading response speed adjustment strategy to generate power trading data; monitor the transaction security of the power trading data to generate power trading security monitoring data; Step S42: Visualize the power transaction security monitoring data and generate a power transaction security monitoring report.

10. An integrated energy service power trading system, characterized in that: For executing the integrated energy service power trading method according to claim 1, the integrated energy service power trading system comprises: A behavior analysis module is used to obtain power usage data; construct a consumer behavior pattern map based on the power usage data to generate a consumer energy usage behavior pattern map; The energy demand prediction module is used to make comprehensive energy demand predictions on standard electricity usage data through consumer energy usage behavior pattern maps, and generate consumer comprehensive energy demand prediction data; construct a blockchain energy trading platform based on consumer comprehensive energy demand prediction data, and generate blockchain energy trading contracts; The transaction pricing module is used to analyze the transaction energy generation type of standard power usage data based on the blockchain energy transaction contract, generate direct power data and indirect power conversion data; perform fluctuation transaction pricing on direct power data and indirect power conversion data, and generate a power fluctuation transaction response speed adjustment strategy; The transaction monitoring module is used to automatically monitor the power transaction of the blockchain energy trading contract according to the power fluctuation transaction response speed adjustment strategy, generate power transaction security monitoring data; visualize the power transaction security monitoring data, and generate a power transaction security monitoring report.

Images