An energy management method for green power tracing

Abstract

The present invention discloses an energy management method for green power traceability, which relates to the technical field of energy management. The invention includes the following steps: Step 1: Establish a database containing multiple energy attributes to store attribute information of different power sources; determine the types of energy attributes that the database needs to store, and establish a database containing multiple energy attributes, and combine blockchain technology to ensure the transparency and non-tamperability of power source information. This method of combining traditional databases with blockchain not only improves the efficiency of data management, but also enhances data security. Users can track the source and flow of electricity in real time, thereby increasing trust in the authenticity of green electricity. By automating the data input and verification process through smart contracts, the possibility of human errors and fraud is reduced, and a more reliable and trustworthy data management platform is provided for the power market.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to an energy management method for green power tracing. Background Art

[0002] With the growth of global energy demand and the improvement of environmental protection awareness, the promotion and application of green electricity has become increasingly important. Existing energy management technologies mainly focus on the monitoring of electricity generation, distribution and consumption, but there are obvious deficiencies in the tracking and verification of electricity sources. Especially in the field of green electricity, there is a lack of effective technical means to ensure the authenticity of the source and green attributes of electricity, which not only affects consumers' trust in green electricity, but also restricts the healthy development of the renewable energy market. In addition, when processing and analyzing large-scale power data, existing data management systems often face problems of data silos, security and real-time performance, and cannot meet the requirements of modern energy management for data transparency and accuracy.

[0003] Blockchain technology, with its unique data immutability and decentralization characteristics, provides new possibilities for solving the above problems. Through blockchain, the record of each electricity transaction can be securely stored in a distributed ledger, ensuring the transparency and traceability of electricity source information. However, the application of blockchain technology to energy management, especially green electricity traceability, requires overcoming a series of technical challenges including data collection, real-time processing, smart contract design and user-friendly interface. In addition, how to ensure the high performance, high availability and cost-effectiveness of the blockchain system is also a key factor in achieving its widespread application in the field of energy management.

[0004] Big data analysis technology plays a vital role in the identification and management of electricity sources. By analyzing a large amount of electricity usage data, the source and flow of electricity can be identified, thereby providing decision support for participants in the electricity market. However, existing data analysis methods often rely on complex models and algorithms, require a lot of computing resources, and have limitations in real-time and accuracy. Therefore, developing an efficient and accurate method for identifying electricity sources is of great significance to improving the efficiency and transparency of energy management. In addition, how to present the results of big data analysis to users in an intuitive and easy-to-understand way is also the key to improving user experience and satisfaction.

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] The purpose of the present invention is to solve the deficiencies of existing energy management technologies in power source tracking, data security and real-time performance, and user interaction, and to propose an energy management method for green power tracing.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An energy management method for green power tracing includes the following steps:

[0009] S1: Establish a database containing multiple energy attributes to store attribute information of different power sources. The specific process is as follows:

[0010] Identify the energy attributes that need to be stored, including power generation methods, time, location, environmental impact and carbon footprint, obtain relevant data from power companies and weather stations, and design the database structure according to the needs, including data tables, fields and relationships, to optimize data storage and query;

[0011] Clean and standardize data, including unit conversion, before importing into the database, checking data for accuracy and completeness, and creating indexes in the database to speed up queries;

[0012] Establish processes to regularly update databases to ensure that information is up to date, select and optimize databases, and design storage and query optimization strategies for data;

[0013] Configure database high availability, including master-slave replication and develop disaster recovery plans;

[0014] S2: collects power usage data through sensors and uploads it to the database established by S1 in real time;

[0015] S3: Use big data analysis technology to process the collected data and determine the source of electricity;

[0016] S4: Use blockchain technology to record the source and flow of each unit of electricity to ensure that the data cannot be tampered with;

[0017] S5: Provide a user interface for the user to display the source information of the electricity and the green attribute verification result.

[0018] Furthermore, the specific steps of selecting and optimizing the database in S1 are as follows:

[0019] Determine data storage requirements, including data volume, data growth rate, query frequency, and data access mode, and select the corresponding database type based on the requirements, including relational database, NoSQL database, or time series database;

[0020] Design database architecture, including data model, table structure and index strategy;

[0021] Based on read / write capability, concurrent processing capability, and data throughput, the selected database is evaluated to obtain a comprehensive score.

[0022] The obtained comprehensive score is compared with the preset comprehensive score threshold. When the comprehensive score is greater than the preset comprehensive score threshold, it is determined that the performance of the database meets the standard;

[0023] Otherwise, it is judged that the performance of the database does not meet the standard. When the performance of the database does not meet the standard, the database is tested in a test environment, including load testing and stress testing. The reasons why the database performance does not meet the standard are analyzed based on the test results, and targeted optimization is performed according to the reasons until the database performance meets the standard.

[0024] Furthermore, the specific operation steps of performing performance evaluation on the selected database to obtain a comprehensive score in S1 are as follows:

[0025] By monitoring the reading and writing speed, the average reading and writing speed of the preset time period is obtained, and the reading and writing speeds at different times of the preset time period are formed into a group of values. The variance of the group of values ​​is calculated and recorded as the stability evaluation value. This stability evaluation value is used as a standard to measure the reading and writing stability. Then, the concurrent processing capability and data throughput are assigned scores of 1-20 respectively, and recorded as the evaluation value and processing value respectively;

[0026] The average read / write speed, stability evaluation value, transmission evaluation value and treatment evaluation value are calibrated as p, w, f and c respectively, and after normalization, they are entered into the following formula: To get the comprehensive score ZFZ, where They are the preset weight coefficients for average reading and writing speed, stability evaluation value, issuance evaluation value and disposal evaluation value, and the obtained comprehensive score is used as the performance standard for measuring the database.

[0027] Furthermore, the specific operation steps of S2 are as follows:

[0028] Select sensors that match the data type required and deploy them in the power system to collect data;

[0029] Read data from sensors and perform preprocessing, including filtering, calibration, and unit conversion, and select the corresponding communication protocol to ensure efficient and secure data transmission;

[0030] Upload the pre-processed data to the database in real time through the selected communication protocol, build a network architecture to ensure communication between sensors and servers, and implement redundancy and failover mechanisms;

[0031] Deploy a system on the server side to receive, store and process uploaded data, implement monitoring mechanisms to ensure the continuity and integrity of data uploads, and regularly maintain sensors and data transmission links;

[0032] An anomaly detection mechanism is implemented during the data upload process. When a problem is found, an alarm is immediately triggered and corrective measures are taken.

[0033] Furthermore, the process of the anomaly detection mechanism in S2 is as follows:

[0034] First, define the criteria for abnormal situations, including data outside the normal range, data loss, and transmission delay exceeding the threshold, and integrate anomaly detection algorithms to analyze data streams in real time and identify abnormal patterns;

[0035] Continuously track the status and quality of data uploads, design data integrity check mechanisms to ensure that uploaded data has not been tampered with or damaged during transmission, and use fault diagnosis tools to identify and locate problems in the data transmission process;

[0036] Design an alert process to notify relevant personnel via email, SMS, or app push when an anomaly is detected; develop an automated response strategy to automatically take action when an anomaly is detected, including retrying data transmission and switching to an alternate network connection;

[0037] Implement logging to record all data upload activities and abnormal events for post-analysis and auditing;

[0038] Test the anomaly detection mechanism.

[0039] Furthermore, the specific operation steps of S3 are as follows:

[0040] Integrate information from multiple sensors and data sources into a single data platform and cleanse it to ensure data quality;

[0041] Extract key features from the data, including timestamps, power changes, and frequency fluctuations;

[0042] Use statistical and machine learning techniques, including decision trees, random forests, support vector machines, and neural networks, to build and train models;

[0043] Evaluate the contribution of different features to power source identification and optimize model performance;

[0044] Validate the model using a test dataset, assess accuracy, and make adjustments based on the results to optimize model performance;

[0045] Explain the model's predictions and present the analysis results in charts and dashboards for easy understanding by users.

[0046] Furthermore, the specific steps of evaluating the contribution of different features to the identification of power sources and optimizing the model performance in S3 are as follows:

[0047] First, the extracted key features are combined in various forms, and the features of each combination are divided into training sets and test sets. The training set data is used to train the machine learning model, and then the contribution of each feature to the prediction result is evaluated through the feature importance score within the model.

[0048] Use the test set data to evaluate the performance of the model. Specifically, the performance parameters are standardized based on the accuracy, recall, F1 score, and ROC-AUC. The performance parameters are assigned scores of 1-100 respectively. After normalization, the comprehensive score is obtained by weighted summation.

[0049] Test different combinations of features to obtain comprehensive scores of model performance established by different combinations of features. Sort all comprehensive scores by size, and select the combination feature with the largest comprehensive score as the optimal combination feature.

[0050] The importance score of each feature in the optimal combination of features is analyzed, and the features with importance scores below the preset threshold are screened out, and other candidate features are selected for replacement, where the importance scores of other candidate features are all greater than the preset threshold, to obtain the final feature combination, and this feature combination is used as the optimal feature combination.

[0051] Furthermore, the specific operation steps of S4 are as follows:

[0052] Choose the appropriate blockchain based on needs, security, performance, and cost, specifically a public chain, consortium chain, or private chain;

[0053] Formulate rules to automate the input, verification, storage and update of power data through smart contracts, and design blockchain data structures to ensure the storage of information on the source and flow process of each unit of electricity;

[0054] Deploy nodes in the blockchain network to verify transactions, maintain ledgers, and execute smart contracts;

[0055] Select a matching consensus mechanism to ensure the security and efficiency of the network, encrypt data, and implement permission management to ensure that only authorized users or nodes can access or modify data;

[0056] Verify newly uploaded data through blockchain network nodes to ensure data authenticity and compliance; provide an interface for users to query power data on the blockchain to verify the source and flow of power;

[0057] Integrate blockchain query functionality into the user interface, enabling users to access and verify data.

[0058] Furthermore, the specific operation steps of S5 are as follows:

[0059] Determine the information that needs to be displayed in the user interface, including the source of electricity, time, location, and green attributes, obtain user requirements, design the user interface, including layout, color, and fonts, and use charts, maps, and timeline tools for data visualization;

[0060] Use HTML, CSS, and JavaScript technologies to build front-end interfaces and integrate with back-end databases, analysis platforms, and blockchain interfaces;

[0061] Implement data query, filtering, and sorting functions, and ensure that the user interface is adaptively displayed on different devices;

[0062] Integrate energy consumption monitoring, efficiency analysis and reporting dashboards into the user interface, providing real-time and historical energy data to assist users in saving energy;

[0063] Conduct user testing, collect feedback, optimize interface performance, and establish feedback mechanisms to continuously improve the user experience.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] The present invention ensures the transparency and immutability of power source information by establishing a database containing multiple energy attributes and combining blockchain technology. This method of combining traditional databases with blockchain not only improves the efficiency of data management, but also enhances data security. Users can track the source and flow of electricity in real time, thereby increasing trust in the authenticity of green electricity. The data input and verification process is automated through smart contracts, reducing the possibility of human errors and fraud, and providing a more reliable and trustworthy data management platform for the power market.

[0066] The present invention uses big data analysis technology to deeply process the collected power usage data, accurately identify and predict the source of electricity, not only improves the accuracy of power source identification, but also optimizes the model performance by evaluating the contribution of different features to power source identification, and provides users with better decision support tools by displaying the analysis results in the form of intuitive charts and dashboards. Functions such as energy consumption monitoring, efficiency analysis and reporting dashboards enable users to more effectively monitor and manage energy use, thereby achieving energy saving and cost control;

[0067] The present invention provides a user-friendly interface, allowing users to easily access and understand complex power data. By realizing practical functions such as data query, screening, and sorting, and ensuring the adaptive display of the interface on different devices, the user experience is greatly improved. At the same time, through continuous user testing and feedback collection, the interface performance and response speed are continuously optimized to ensure the high availability and user satisfaction of the system. By integrating the blockchain query function, users can directly verify the green attributes of electricity on the interface, further improving the convenience and practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0069] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0070] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0072] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0073] like Figure 1 As shown, a green power source tracing energy management method includes the following steps:

[0074] Step 1:

[0075] Establish a database containing multiple energy attributes to store attribute information of different electricity sources; determine the types of energy attributes that need to be stored in the database, including power generation methods (wind, solar, hydropower, etc.), power generation time, geographic location, environmental impact assessment, carbon footprint, etc.; collect data from various sources, including power companies, weather stations, environmental monitoring agencies, etc., and design the structure of the database according to user needs, including data tables, fields, data types, associations, etc., to ensure that the organization and storage of data can meet subsequent query and analysis needs;

[0076] Unify the collected data for storage and processing, including unit conversion and data cleaning steps, and automatically import the standardized data into the database through scripts or using database management tools; verify the imported data to ensure the accuracy and completeness of the data, and create indexes in the database, especially for frequently queried fields to improve query efficiency; establish a data update process to ensure that the information in the database can reflect the latest energy attribute data, and set different data access permissions according to the user's role and needs;

[0077] Design a data storage solution for the subsequent real-time monitoring of power usage data, including the selection and optimization of databases to support the storage and fast query of large amounts of data, specifically:

[0078] Determine data storage requirements, including data volume, data growth rate, query frequency, and data access mode, and select appropriate database types according to requirements, such as relational databases (MySQL, PostgreSQL), NoSQL databases (MongoDB, Cassandra), time series databases (InfluxDB), etc.; design database architecture, including data model, table structure, index strategy, etc., to optimize data storage and query performance; perform performance evaluation on the selected database, based on read and write capabilities, concurrent processing capabilities, and data throughput, obtain the average read and write speed of the preset time period by monitoring the read and write speed, form a set of values ​​for the read and write speeds at different times of the preset time period, calculate the variance of the set of values, and record it as the stability evaluation value, use this stability evaluation value as the standard for measuring read and write stability, and then assign scores of 1-20 to the concurrent processing capability and data throughput, and record them as the evaluation value and processing value respectively;

[0079] The average read / write speed, stability evaluation value, transmission evaluation value and treatment evaluation value are calibrated as p, w, f and c respectively, and after normalization, they are entered into the following formula: To get the comprehensive score ZFZ, where The preset weight coefficients are respectively the average read and write speed, stability evaluation value, issuance evaluation value and disposal evaluation value, and the obtained comprehensive score is used as the performance standard for measuring the database;

[0080] The obtained comprehensive score is compared with the preset comprehensive score threshold. When the comprehensive score is greater than the preset comprehensive score threshold, the database performance is judged to be up to standard. Otherwise, the database performance is judged to be not up to standard. When the database performance is not up to standard, the database is tested in a test environment, including load testing, stress testing, etc. The reasons why the database performance is not up to standard are analyzed according to the test results, and targeted optimization is carried out according to the reasons until the database performance meets the standard.

[0081] Design data partitioning and sharding strategies based on data volume and query requirements to improve query efficiency and data management flexibility, and implement high availability configuration of the database, such as master-slave replication, cluster deployment, etc., as well as disaster recovery plans.

[0082] Step 2:

[0083] Collect power usage data through sensors and upload it to the database established in step 1 in real time;

[0084] According to the type of data that needs to be collected (such as current, voltage, power, frequency, etc.), select sensor devices corresponding to the data type and deploy these sensors in the power system to ensure that the required power usage data can be accurately collected; design a data acquisition module that can interface with the sensor, read the data collected by the sensor, and perform necessary preprocessing on the raw data collected by the sensor, such as filtering, calibration, unit conversion, etc., to improve data quality;

[0085] Determine the communication protocol for data upload, such as Modbus, MQTT, CoAP, etc., to ensure that data can be transmitted efficiently and securely, and upload the pre-processed data to the database established in step 1 in real time through the determined communication protocol; design the network architecture to ensure stable and reliable communication between the sensor and the central server, including considering the redundancy and failover mechanism of the network, and deploy a data processing system on the server side to receive, store and preliminarily process the uploaded data; implement a data monitoring mechanism to ensure the continuity and integrity of data upload, and at the same time, regularly maintain the sensors and data transmission system;

[0086] An abnormality detection mechanism is implemented during the data upload process. Once data abnormality or transmission failure is found, an alarm is immediately issued and corresponding measures are taken. The specific process is as follows:

[0087] First, define the criteria for abnormal situations, such as data outside the normal range, data loss, transmission delay exceeding the threshold, etc., integrate anomaly detection algorithms that can analyze data streams in real time and identify abnormal patterns; continuously track the status and quality of data uploads, design data integrity check mechanisms to ensure that uploaded data has not been tampered with or damaged during transmission, and use fault diagnosis tools to quickly identify and locate problems in the data transmission process; design an alarm system that can notify relevant personnel through email, SMS, application push, etc. when an anomaly is detected, and formulate an automated response strategy. Once an anomaly is detected, the system can automatically take action, such as retrying data transmission, switching to an alternate network connection, etc.; implement logging to record all data upload activities and abnormal events for subsequent analysis and auditing; thoroughly test the anomaly detection mechanism to ensure that it works reliably in various situations.

[0088] Step 3:

[0089] Using big data analysis technology, the collected data is processed to determine the source of electricity;

[0090] Integrate data from different sensors and data sources into a unified data platform or data warehouse, clean the integrated data, and remove invalid, erroneous or incomplete data records; extract and construct features that are helpful for power source analysis, such as timestamps, power changes, frequency fluctuations, etc., use statistics, machine learning or deep learning technology to build models for predicting or identifying the source of electricity, and select appropriate algorithms for training, such as decision trees, random forests, support vector machines, neural networks, etc.;

[0091] Evaluate the contribution of different features to power source identification and optimize model performance. The specific process is as follows:

[0092] First, the extracted features are combined in various forms, and the features of each combination are divided into training sets and test sets. The training set data is used to train different machine learning models, and then the contribution of each feature to the prediction result is evaluated through the feature importance score within the model; the performance of the model is evaluated using the test set data, specifically based on performance parameters, which include: accuracy, recall rate, F1 score, ROC-AUC, and the performance parameters are standardized and assigned scores of 1-100 respectively. After normalization, the comprehensive score is obtained by weighted summation;

[0093] Different combinations of features are tested to obtain comprehensive scores of model performance established by different combinations of features. All comprehensive scores are sorted by size, and the combination features with the largest comprehensive score are selected as the optimal combination features. The importance score of each feature in the optimal combination of features is analyzed, and features with importance scores below the preset threshold are screened out, and other alternative features are selected for replacement, where the importance scores of other alternative features are all greater than the preset threshold, so as to obtain the final feature combination, and use this feature combination as the optimal feature combination.

[0094] Use the test data set to verify the model, evaluate the accuracy and generalization ability of the model, adjust and optimize the model based on the verification results to improve the recognition accuracy; explain the model's prediction results to ensure that users can understand the basis for judging the source of electricity, and visualize the analysis results in the form of charts, dashboards, etc. for users to intuitively understand.

[0095] Step 4:

[0096] The source and flow process of each unit of electricity is recorded through blockchain technology to ensure that the data cannot be tampered with;

[0097] Determine whether to use a public chain, consortium chain or private chain, and make the selection based on application requirements, security, performance and cost. Use smart contracts to define the recording rules of power data, including the data input, verification, storage and update process. Design the data structure on the blockchain to determine how to store the source, flow process and other related information of each unit of electricity, and upload the power source information and flow data determined by big data analysis to the chain to ensure the integrity and consistency of the data.

[0098] Deploy nodes in the blockchain network to verify transactions, maintain ledgers, and execute smart contracts. Select appropriate consensus mechanisms, such as Proof of Work (PoW), Proof of Stake (PoS), Delegated Proof of Stake (DPoS), etc., to ensure the security and efficiency of the network. Encrypt the data on the chain to ensure the privacy and security of the data, implement a permission management mechanism, and ensure that only authorized users or nodes can access or modify the data on the blockchain.

[0099] Newly uploaded data is verified through the nodes of the blockchain network to ensure the authenticity and compliance of the data; a query interface is provided to allow users to query electricity data on the blockchain and verify the source and flow of electricity; the blockchain query function is integrated into the user interface to enable users to easily access and verify data.

[0100] Step 5:

[0101] Provide users with a user interface to display the source information of electricity and the green attribute verification results;

[0102] Determine the type of information that needs to be displayed in the user interface, including electricity source, time, location, green attributes, etc., and obtain the needs and preferences of the target user group, including non-technical users and professionals; design an intuitive and easy-to-use user interface, including layout, color scheme, font selection, etc., and use visualization tools such as charts, maps, and timelines to display complex data; use front-end technologies such as HTML, CSS, and JavaScript to implement the user interface, and integrate the user interface with back-end systems (such as databases, big data analysis platforms, and blockchain interfaces);

[0103] Implement various functions on the user interface, such as data query, filtering, sorting, etc., to ensure that the user interface can be well displayed on different devices (such as mobile phones, tablets, computers); establish energy management functions, including energy consumption monitoring, energy efficiency analysis, and energy reports and dashboards. Energy consumption monitoring enables users to monitor energy usage by providing real-time and historical energy consumption data; energy efficiency analysis is used to assist users in identifying energy-saving opportunities by comparing energy consumption in different time periods or on different devices; energy reports and dashboards display key performance indicators and energy usage overviews through preset reports and dashboards; conduct user testing, collect feedback, understand user satisfaction with the interface and difficulties in use, optimize the loading speed and response time of the user interface, establish a user feedback mechanism, and continuously collect user opinions for improving the interface.

[0104] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A green power source tracing energy management method, characterized in that: The following steps are involved: S1: Establish a database containing multiple energy attributes to store attribute information of different power sources. The specific process is as follows: Identify the energy attributes that need to be stored, including power generation methods, time, location, environmental impact and carbon footprint, obtain relevant data from power companies and weather stations, and design the database structure according to the needs, including data tables, fields and relationships, to optimize data storage and query; Clean and standardize data, including unit conversion, before importing into the database, checking data for accuracy and completeness, and creating indexes in the database to speed up queries; Establish a process to regularly update the database to ensure the latest information, select and optimize the database, and design storage and query optimization strategies for the data; the specific process is as follows: Determine data storage requirements, including data volume, data growth rate, query frequency, and data access mode, and select the corresponding database type based on the requirements, including relational database, NoSQL database, or time series database; Design database architecture, including data model, table structure and index strategy; Based on read / write capability, concurrent processing capability, and data throughput, the selected database is evaluated to obtain a comprehensive score. The obtained comprehensive score is compared with the preset comprehensive score threshold. When the comprehensive score is greater than the preset comprehensive score threshold, it is determined that the performance of the database meets the standard; Otherwise, it is judged that the performance of the database does not meet the standard. When the performance of the database does not meet the standard, the database is tested in the test environment, including load testing and stress testing. The reasons why the database performance does not meet the standard are analyzed according to the test results, and targeted optimization is carried out according to the reasons until the performance of the database meets the standard; The process of evaluating the performance of the selected database to obtain the comprehensive score is as follows: By monitoring the reading and writing speed, the average reading and writing speed of the preset time period is obtained, and the reading and writing speeds at different times of the preset time period are formed into a group of values. The variance of the group of values ​​is calculated and recorded as the stability evaluation value. This stability evaluation value is used as a standard to measure the reading and writing stability. Then, the concurrent processing capability and data throughput are assigned scores of 1-20 respectively, and recorded as the evaluation value and processing value respectively; The average read / write speed, stability evaluation value, release evaluation value and treatment evaluation value are calibrated as p, w, f and c respectively, and after normalization, they are entered into the following formula: To get the comprehensive score ZFZ, where The preset weight coefficients are respectively the average read and write speed, stability evaluation value, issuance evaluation value and disposal evaluation value, and the obtained comprehensive score is used as the performance standard for measuring the database; Configure database high availability, including master-slave replication and develop disaster recovery plans; S2: collects power usage data through sensors and uploads it to the database established by S1 in real time; S3: Use big data analysis technology to process the collected data and determine the source of electricity; the specific steps are as follows: Integrate information from multiple sensors and data sources into a single data platform and cleanse it to ensure data quality; Extract key features from the data, including timestamps, power changes, and frequency fluctuations; Use statistical and machine learning techniques, including decision trees, random forests, support vector machines, and neural networks, to build and train models; Evaluate the contribution of different features to power source identification and optimize model performance; Validate the model using a test dataset, assess accuracy, and make adjustments based on the results to optimize model performance; Explain the model's predictions and present the analysis results in charts and dashboards for easy understanding by users; The specific steps to evaluate the contribution of different features to power source identification and optimize model performance are as follows: First, the extracted key features are combined in various forms, and the features of each combination are divided into training sets and test sets. The training set data is used to train the machine learning model, and then the contribution of each feature to the prediction result is evaluated through the feature importance score within the model. Use the test set data to evaluate the performance of the model. Specifically, the performance parameters are standardized based on the accuracy, recall, F1 score, and ROC-AUC. The performance parameters are assigned scores of 1-100 respectively. After normalization, the comprehensive score is obtained by weighted summation. Test different combinations of features to obtain comprehensive scores of model performance established by different combinations of features. Sort all comprehensive scores by size, and select the combination feature with the largest comprehensive score as the optimal combination feature. Analyze the importance score of each feature in the optimal combination of features, screen out features with importance scores below a preset threshold, and select other candidate features for replacement, where the importance scores of other candidate features are all greater than the preset threshold, to obtain the final feature combination, and use this feature combination as the optimal feature combination; S4: Use blockchain technology to record the source and flow of each unit of electricity to ensure that the data cannot be tampered with; S5: Provide a user interface for the user to display the source information of the electricity and the green attribute verification result.

2. The energy management method for green power tracing according to claim 1 is characterized in that: The specific operation steps of S2 are as follows: Select sensors that match the data type required and deploy them in the power system to collect data; Read data from sensors and perform preprocessing, including filtering, calibration, and unit conversion, and select the corresponding communication protocol to ensure efficient and secure data transmission; Upload the pre-processed data to the database in real time through the selected communication protocol, build a network architecture to ensure communication between sensors and servers, and implement redundancy and failover mechanisms; Deploy a system on the server side to receive, store and process uploaded data, implement monitoring mechanisms to ensure the continuity and integrity of data uploads, and regularly maintain sensors and data transmission links; An anomaly detection mechanism is implemented during the data upload process. When a problem is found, an alarm is immediately triggered and corrective measures are taken.

3. The energy management method for green power tracing according to claim 2 is characterized in that: The process of the anomaly detection mechanism in S2 is as follows: First, define the criteria for abnormal situations, including data outside the normal range, data loss, and transmission delay exceeding the threshold, and integrate anomaly detection algorithms to analyze data streams in real time and identify abnormal patterns; Continuously track the status and quality of data uploads, design data integrity check mechanisms to ensure that uploaded data has not been tampered with or damaged during transmission, and use fault diagnosis tools to identify and locate problems in the data transmission process; Design an alert process to notify relevant personnel via email, SMS, or app push when an anomaly is detected; develop an automated response strategy to automatically take action when an anomaly is detected, including retrying data transmission and switching to an alternate network connection; Implement logging to record all data upload activities and abnormal events for post-analysis and auditing; Test the anomaly detection mechanism.

4. The energy management method for green power tracing according to claim 1 is characterized in that: The specific operation steps of S4 are as follows: Choose the appropriate blockchain based on needs, security, performance, and cost, specifically a public chain, consortium chain, or private chain; Formulate rules to automate the input, verification, storage and update of power data through smart contracts, and design blockchain data structures to ensure the storage of information on the source and flow process of each unit of electricity; Deploy nodes in the blockchain network to verify transactions, maintain ledgers, and execute smart contracts; Select a matching consensus mechanism to ensure the security and efficiency of the network, encrypt data, and implement permission management to ensure that only authorized users or nodes can access or modify data; Verify newly uploaded data through blockchain network nodes to ensure data authenticity and compliance; provide an interface for users to query power data on the blockchain to verify the source and flow of power; Integrate blockchain query functionality into the user interface, enabling users to access and verify data.

5. The energy management method for green power tracing according to claim 1 is characterized in that: The specific operation steps of S5 are as follows: Determine the information that needs to be displayed in the user interface, including the source of electricity, time, location, and green attributes, obtain user requirements, design the user interface, including layout, color, and fonts, and use charts, maps, and timeline tools for data visualization; Use HTML, CSS, and JavaScript technologies to build front-end interfaces and integrate with back-end databases, analysis platforms, and blockchain interfaces; Implement data query, filtering, and sorting functions, and ensure that the user interface is adaptively displayed on different devices; Integrate energy consumption monitoring, efficiency analysis and reporting dashboards into the user interface, providing real-time and historical energy data to assist users in saving energy; Conduct user testing, collect feedback, optimize interface performance, and establish feedback mechanisms to continuously improve the user experience.

Images