Intelligent power load management method based on big data analysis

Abstract

An intelligent power load management method based on big data analysis, which relates to the technical field of big data analysis and data processing, wherein an accurate power load forecasting model is constructed by means of integrating historical power consumption data, climate data, power grid device status data and user behavior data. In the method, blockchain technology is employed to improve the security and traceability of forecast data, and the automation of a power load management process is realized by means of smart contracts. The specific steps include data acquisition and preprocessing, load forecasting model construction and verification, forecast data storage and hash value generation, smart contract writing and execution, and process node data processing and evaluation. The method effectively solves the problems of load data anomalies and model errors, thereby improving the stability and management efficiency of a power grid system.

Description

A Smart Electricity Load Management Method Based on Big Data Analytics

[0001] This application claims priority to Chinese Patent Application No. 202411509047.0, filed on October 28, 2024, entitled "A Smart Electricity Load Management Method Based on Big Data Analysis", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This invention relates to the field of big data analysis and data processing technology, and in particular to an intelligent power load management method based on big data analysis. Background Technology

[0003] The application of big data analytics in intelligent electricity load management is mainly reflected in the following aspects: Power grid companies can integrate various data resources, such as historical electricity consumption data and climate data, to build complex predictive models and achieve accurate predictions of future electricity load. This prediction helps power grid companies rationally arrange power generation plans, reduce operating costs, and improve power quality. Big data analytics can monitor the operating status of power grid equipment in real time. By mining the massive amounts of data collected by sensors and monitoring points, potential fault risks can be identified in a timely manner, and preventative maintenance can be carried out. This can effectively avoid large-scale power outages and improve the reliability of the power grid. By analyzing the operating data of various links in the power grid, big data technology can assist managers in achieving optimal resource allocation, including optimizing transmission line capacity and upgrading substations. This helps improve the overall operating efficiency of the power grid and promotes energy conservation and emission reduction.

[0004] While big data analytics has demonstrated significant advantages in intelligent load management, it also presents several technical challenges: Although big data analytics can monitor the real-time operating status of power grid equipment, power grid load management relies heavily on the accuracy and timeliness of this analytics. In practical applications, errors in intelligent load management based on big data analytics can occur due to anomalies in power grid load data and errors in data analysis models. Failure to promptly identify these errors will impact the normal operation of the power grid system. For example, power grid load data may exhibit anomalies in practice, such as missing data, incorrect recordings, or inaccurate values. These directly affect the accuracy of load forecasting. Simultaneously, data analysis models may also contain errors, causing forecasts to deviate from actual load conditions. If these errors are not detected and corrected in a timely manner, they will lead to biased decisions in intelligent load management based on big data analytics, thereby affecting the normal operation of the power grid system. Incorrect load forecasting may result in insufficient power supply during peak hours or excessive power generation during off-peak hours, wasting resources and potentially damaging the lifespan of power grid equipment. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent electricity load management method based on big data analytics. Through data preprocessing steps, such as data cleaning and outlier removal, the quality of input data is improved, reducing the impact of data anomalies on the prediction model. This solves the problem of inaccurate predictions caused by abnormal power grid load data. Furthermore, by comparing predicted data with actual electricity load data, the causes of prediction errors are analyzed, and model parameters are adjusted based on these causes to continuously optimize the prediction model, improving the accuracy and reliability of the prediction results. Blockchain technology is used to store the electricity load prediction data and generate hash values, enhancing the data's time traceability, security, and immutability, thus solving the security and traceability issues of power grid operation management data. This invention uses smart contract technology to automate the allocation, monitoring, and recording of nodes in the electricity load management process, reducing human intervention, improving management efficiency, and solving the problems of inefficiency and error susceptibility caused by traditional electricity load management processes relying on manual operation.

[0006] By continuously comparing predicted data with actual load data, analyzing prediction errors, and adjusting model parameters, the prediction model was continuously optimized, improving the accuracy of long-term predictions. By integrating historical electricity consumption data, climate data, power grid equipment status, and user behavior data, an accurate electricity load prediction model was constructed. Real-time acquisition and processing of power grid operation and management data enabled real-time data processing and improved timely response to changes in power grid operation.

[0007] This invention improves the accuracy of electricity load forecasting and introduces automated management processes, significantly enhancing the stability and management efficiency of the power grid system. It provides strong support for the intelligent management of power grid enterprises and solves the problems of low stability and management efficiency in the power grid system.

[0008] To solve the above-mentioned technical problems, the specific technical solution of the present invention is as follows:

[0009] This invention provides a smart electricity load management method based on big data analysis, comprising:

[0010] Step S101: Obtain power grid operation and management data, which includes historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data.

[0011] Step S102: Construct an electricity load prediction model based on historical electricity consumption data, climate data, power grid equipment operation status data and user behavior data, obtain real-time power grid operation management data, and substitute the real-time power grid operation management data into the electricity load prediction model to obtain electricity load prediction data.

[0012] Step S103: Establish a timestamp for the electricity load forecast data based on the time of data generation, and store it in the blockchain to generate the hash value corresponding to the electricity load forecast data;

[0013] Step S104: Obtain the power load management process nodes and process node management rules. Based on the power load management process nodes, process node management rules, and the hash values ​​corresponding to the power load prediction data stored in the blockchain, construct a smart contract for the power load process nodes.

[0014] Step S105: Establish data matching tags for smart contracts of electricity load process nodes, match the power grid operation management data with the data matching tags, and transmit the power grid operation management data to the corresponding smart contracts of electricity load process nodes according to the matching results to obtain the data processing results of the first process node smart contracts. Randomly sort the smart contracts of electricity load process nodes to obtain randomly sorted smart contracts of electricity load process nodes. Match the randomly sorted smart contracts of electricity load process nodes with the electricity load forecast data to obtain the data processing results of the second process node smart contracts. Match the randomly sorted smart contracts of electricity load process nodes with the power grid operation management data to obtain the data processing results of the third process node smart contracts. Perform data analysis on the data processing results of the first, second, and third process node smart contracts to obtain the completion degree of each process node of electricity load management.

[0015] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S101 includes:

[0016] Historical electricity consumption data is obtained from the data center or database of the power grid company. The historical electricity consumption data includes electricity consumption, peak load and valley load for different time periods.

[0017] Climate data for the corresponding time period is obtained from the meteorological department's database. The climate data includes temperature, humidity, wind speed, and sunshine duration.

[0018] By utilizing sensors and monitoring systems deployed on power grid equipment, real-time operational status data of the power grid equipment can be acquired. This operational status data includes power grid equipment voltage, power grid equipment current, power grid equipment power factor, and power grid equipment temperature.

[0019] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S101 includes:

[0020] The acquired power grid operation and management data is preprocessed and cleaned to remove abnormal power grid operation and management data, resulting in preprocessed power grid operation and management data.

[0021] The preprocessed power grid operation and management data is stored, classified according to data type, and search tags are established for the classified preprocessed power grid operation and management data.

[0022] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S102 includes:

[0023] Correlation analysis was performed on historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data to obtain highly correlated characteristics of electricity load. These highly correlated characteristics include historical load characteristics, temperature characteristics, and humidity characteristics.

[0024] A load forecasting model is constructed based on historical load characteristics, temperature characteristics, and humidity characteristics;

[0025] Real-time power grid operation and management data is acquired, including real-time electricity load, weather conditions, power grid equipment status, and user behavior information. This real-time data is then substituted into the constructed electricity load prediction model to predict the electricity load. The predicted electricity load data is then calculated using the electricity load prediction model.

[0026] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S102 includes:

[0027] Obtain actual electricity load data, compare the predicted data with the actual electricity load data to obtain the error data between the predicted data and the actual electricity load, match the predicted data with the actual electricity load error data in the knowledge base to obtain the error cause information, which includes data quality problems, unreasonable models and the influence of external factors.

[0028] Based on the information on the causes of the errors, the parameters of the electricity load prediction model were adjusted, and the adjusted electricity load prediction model was used to make predictions again. By comparing with the actual data, the prediction effect of the adjusted electricity load prediction model was verified.

[0029] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S103 includes:

[0030] Based on the time when each electricity load forecast data is generated, a timestamp is created for each electricity load forecast data. The timestamp is used to identify the time when the data was generated.

[0031] The electricity load forecast data with timestamps is written into the blockchain, and for each piece of electricity load forecast data stored on the blockchain, its hash value is calculated using a hash function.

[0032] The generated hash value is stored on the blockchain along with the original data, recording each piece of data and its corresponding hash value.

[0033] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S104 includes:

[0034] Obtain information on each node of the electricity load management process from the power management system or documents. This information includes the electricity application, approval, allocation, and monitoring stages.

[0035] Obtain the management rules corresponding to each node of the electricity load management process. The management rules define the operation specifications, permission settings and data processing methods for each process node.

[0036] Generate hash values ​​based on the electricity load management process nodes and process node management rules:

[0037] The obtained electricity load management process node information and corresponding management rules are used as input data to generate hash values.

[0038] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S104 includes:

[0039] The generated hash value, along with related electricity load management process node information and management rules, will be stored on the blockchain.

[0040] Utilize the smart contract functionality of the blockchain platform to write smart contract code based on the electricity load management process nodes and management rules;

[0041] The smart contract will automatically execute the management rules of the process nodes, and automatically allocate, monitor and record the power load according to the management rules of the automatically executed process nodes.

[0042] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S105 includes:

[0043] Based on the function and requirements of each smart contract, data matching tags are established, and power grid operation and management data are preprocessed.

[0044] The established data matching tags are used to match the power grid operation and management data to obtain data with the smart contracts of each power load process node;

[0045] Based on the matching results, the power grid operation management data will be transmitted to the corresponding power load process node smart contract:

[0046] The successfully matched power grid operation and management data are categorized according to the corresponding smart contracts for the power load process nodes;

[0047] The categorized data is transmitted to the corresponding smart contracts. Each power load process node smart contract processes the received power grid operation and management data, generates corresponding data processing results, and randomly sorts the power load process node smart contracts to obtain a randomly sorted list of smart contracts.

[0048] Furthermore, in the intelligent electricity load management method based on big data analysis provided by the present invention, step S105 includes:

[0049] Collect the data processing results of the smart contracts at the first process node, the second process node, and the third process node;

[0050] Cluster analysis is performed on the smart contract data processing results of the first, second, and third process nodes, along with the smart contract completion rates and electricity load data of each node. Based on the cluster analysis results, an evaluation is conducted to obtain the completion rates of each process node in the data processing results of the first, second, and third process nodes. If any of these process nodes has a completion rate lower than a preset value, the data with a lower completion rate is reviewed. If the review results indicate a data error, a data error warning is generated.

[0051] The beneficial effects of this invention are mainly reflected in the following aspects:

[0052] This invention significantly improves the accuracy of electricity load forecasting by integrating historical electricity consumption data, climate data, power grid equipment operating status data, and user behavior data, and by using correlation analysis to construct a load forecasting model. This not only helps power grid companies to rationally plan power generation, but also effectively reduces operating costs and improves power quality.

[0053] By storing electricity load forecast data on the blockchain and generating hash values, the data's time traceability, security, and immutability are improved. Blockchain technology provides a distributed ledger where any data modification is recorded on the chain, preventing malicious data tampering and enhancing data trust and security.

[0054] By leveraging smart contract technology, the allocation, monitoring, and recording of nodes in the electricity load management process have been automated. Smart contracts execute automatically according to preset management rules, reducing human intervention, improving process transparency and efficiency, and lowering the risk of human error.

[0055] By preprocessing power grid operation and management data, including data cleaning and outlier removal, the quality of input data is improved, further enhancing the accuracy and reliability of the prediction model. Data analysis is used to evaluate the completion rate of each process node, promptly identifying and addressing potential problems. If data errors or processing inefficiencies are detected, the system generates early warning messages to notify relevant personnel for timely handling, thus ensuring the normal operation of the power grid system. By continuously comparing predicted data with actual load data, the causes of prediction errors are analyzed, and model parameters are adjusted, achieving continuous optimization of the prediction model and improving the accuracy and effectiveness of long-term predictions.

[0056] In summary, by introducing big data analytics, blockchain technology, and smart contracts, this invention significantly improves the accuracy and efficiency of power grid load management, enhances system security and stability, and provides strong support for the intelligent management of power grid enterprises. Attached Figure Description

[0057] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0058] Figure 1 is a schematic diagram of the intelligent power load management method based on big data analysis provided in an embodiment of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. The technical solutions provided by various embodiments of this invention will be described in detail below with reference to the accompanying drawings.

[0060] To better understand the purpose of this invention, the invention will now be described in further detail.

[0061] Please refer to Figure 1. This invention provides a smart electricity load management method based on big data analysis, comprising:

[0062] Step S101: Obtain power grid operation and management data, which includes historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data.

[0063] Step S101 mainly involves acquiring power grid operation and management data. This data is an indispensable foundation for subsequent electricity load forecasting and management. Specifically, the following types of data need to be acquired:

[0064] Historical electricity consumption data includes information such as electricity consumption, peak load, and valley load for different time periods. This data serves as a reference for subsequent load forecasting.

[0065] Climate data: Obtained from meteorological databases, mainly including temperature, humidity, wind speed, and sunshine duration. Climate factors have a significant impact on electricity load, especially temperature and humidity; therefore, climate data is crucial for improving the accuracy of load forecasting.

[0066] Power grid equipment operating status data: This data is acquired in real time through sensors and monitoring systems deployed on power grid equipment. It reflects the voltage, current, power factor, and temperature of the equipment. Understanding the equipment status helps in timely prediction and maintenance of stable power grid operation.

[0067] User behavior data includes users' electricity usage habits and power consumption patterns. This data helps us more accurately predict future electricity load, thereby optimizing power allocation and management.

[0068] After acquiring this data, preprocessing steps are required, such as data cleaning, outlier removal, and categorized storage. These preprocessing operations improve the quality and accuracy of the data, laying a solid foundation for subsequent analysis and prediction.

[0069] Step S102: Construct an electricity load prediction model based on historical electricity consumption data, climate data, power grid equipment operation status data and user behavior data, obtain real-time power grid operation management data, and substitute the real-time power grid operation management data into the electricity load prediction model to obtain electricity load prediction data.

[0070] Historical electricity consumption data includes electricity consumption, peak load, and valley load for each time period.

[0071] Climate data, such as temperature, humidity, wind speed, and sunshine duration, are obtained from meteorological databases.

[0072] By utilizing sensors and monitoring systems deployed on power grid equipment, real-time operational status data, including voltage, current, and power factor, can be acquired. Simultaneously, considering user behavior data helps in more accurately predicting electricity load.

[0073] Correlation analysis is performed on the collected data to identify characteristics highly correlated with electricity load, and a load forecasting model is constructed. Real-time power grid operation and management data are acquired, including current electricity load, weather conditions, power grid equipment status, and user behavior information. This real-time data is input into the constructed forecasting model to calculate the predicted electricity load.

[0074] Obtain actual electricity load data and compare the predicted results with the actual data to evaluate the accuracy of the model. Analyze the causes of prediction errors and adjust the model parameters accordingly to improve prediction accuracy.

[0075] Step S103: Establish a timestamp for the electricity load forecast data based on the time of data generation, and store it in the blockchain to generate the hash value corresponding to the electricity load forecast data;

[0076] The processing flow of electricity load forecast data in step S103 mainly includes the following steps:

[0077] Establish timestamps: Create a corresponding timestamp for each piece of electricity load forecast data based on the time it was generated. Timestamps are used to uniquely identify when the data was generated, improving the timeliness and traceability of the data.

[0078] Storing to the Blockchain: Timestamped electricity load forecast data is written to the blockchain. As a decentralized, tamper-proof distributed ledger technology, blockchain enhances data security and immutability.

[0079] Hash value generation: For each piece of electricity load forecast data stored on the blockchain, a hash function is used to calculate its hash value. The hash value is a fixed-length digital fingerprint that uniquely represents the original data. Any small change to the original data will result in a significant change in the hash value, thus ensuring data integrity.

[0080] Record hash values: The generated hash values ​​are stored on the blockchain along with the original data, recording each piece of data and its corresponding hash value. This allows verification of data integrity and tamper-proofing without directly exposing the original data.

[0081] In summary, step S103 improves the time traceability, security, and data integrity of electricity load forecasting data through the combined application of timestamps, blockchain, and hash values, providing a reliable data foundation for subsequent electricity load management.

[0082] Step S104: Obtain the power load management process nodes and process node management rules. Based on the power load management process nodes, process node management rules, and the hash values ​​corresponding to the power load prediction data stored in the blockchain, construct a smart contract for the power load process nodes.

[0083] Step S104 describes how to obtain the electricity load management process nodes and process node management rules, and how to construct the electricity load process node smart contract based on this information and the hash value of the electricity load prediction data stored on the blockchain. The specific steps are as follows:

[0084] Obtain the nodes of the electricity load management process: Collect information on each node of the electricity load management process from the power management system or related documents. These nodes usually include electricity application, approval, allocation, monitoring and other links.

[0085] Obtain process node management rules: Management rules define the operational specifications, permission settings, and data processing methods for each process node. These rules improve the orderly and compliant execution of process nodes.

[0086] Smart contracts are constructed using hash values: The hash values ​​corresponding to the electricity load management process node information, process node management rules, and electricity load forecast data stored on the blockchain are used as inputs to construct smart contracts. The hash value serves as a unique identifier for the electricity load forecast data, improving data integrity and traceability.

[0087] Using a blockchain platform to write smart contracts: Utilize the smart contract functionality provided by the blockchain platform to write smart contract code based on process nodes and management rules. The smart contract will automatically execute the management rules of the process nodes, automatically allocating, monitoring, and recording electricity load.

[0088] Automated execution of smart contracts: Once deployed on the blockchain, smart contracts will automatically execute electricity load management processes according to preset rules. This reduces human intervention and improves the transparency and efficiency of the process.

[0089] In this way, step S104 improves the standardization, automation, and traceability of the electricity load management process, thereby improving the efficiency and accuracy of power grid operation management.

[0090] Step S105: Establish data matching tags for smart contracts of electricity load process nodes, match the power grid operation management data with the data matching tags, and transmit the power grid operation management data to the corresponding smart contracts of electricity load process nodes according to the matching results to obtain the data processing results of the first process node smart contracts. Randomly sort the smart contracts of electricity load process nodes to obtain randomly sorted smart contracts of electricity load process nodes. Match the randomly sorted smart contracts of electricity load process nodes with the electricity load forecast data to obtain the data processing results of the second process node smart contracts. Match the randomly sorted smart contracts of electricity load process nodes with the power grid operation management data to obtain the data processing results of the third process node smart contracts. Perform data analysis on the data processing results of the first, second, and third process node smart contracts to obtain the completion degree of each process node of electricity load management.

[0091] Step S105 details a key step in the intelligent electricity load management method based on big data analytics, primarily involving the data processing flow of the smart contracts for the electricity load process nodes. The specific content and flow of this step are as follows:

[0092] Establish data matching tags: For each smart contract in the electricity load process node, establish corresponding data matching tags based on its function and requirements. Tags are used to identify and distinguish different types of power grid operation and management data.

[0093] Data Matching and Transmission: Power grid operation and management data is matched against these tags to ensure accurate transmission to the corresponding power load process node smart contracts. Based on the matching results, the power grid operation and management data is transmitted to the appropriate smart contracts for further processing.

[0094] First-stage process node smart contract data processing: Each power load process node smart contract receives and processes the transmitted power grid operation and management data, generating the data processing results of the first-stage process node smart contract.

[0095] Random sorting of smart contracts: All smart contracts for the electricity load process nodes are randomly sorted to generate a randomly sorted list of smart contracts for the electricity load process nodes. This step aims to increase the robustness of the system and avoid potential prediction biases.

[0096] Second-stage process node smart contract data processing: The randomly sorted electricity load process node smart contracts are matched with the electricity load forecast data to generate the data processing results of the second-stage process node smart contracts. This step is used to verify the applicability and accuracy of the forecast data in the actual process nodes.

[0097] Third-stage process node smart contract data processing: The randomly sorted power load process node smart contracts are again matched with the original power grid operation and management data to generate the data processing results of the third-stage process node smart contracts. This step is used to further confirm the consistency and accuracy of the data at different processing stages.

[0098] Data Analysis and Evaluation: A comprehensive analysis of the data processing results from the smart contracts of the first, second, and third process nodes is conducted to evaluate the completion rate of each process node. Through data analysis, it is determined whether any data falls below a preset completion rate. If so, this data is reviewed, and a data error warning is generated upon confirmation of the error.

[0099] This step, through the application of smart contracts, automates the processing and analysis of power grid operation management data, improving the accuracy and efficiency of electricity load management. Simultaneously, random sorting and multiple matching verifications enhance the system's stability and reliability.

[0100] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S101, which includes:

[0101] Historical electricity consumption data is obtained from the data center or database of the power grid company. The historical electricity consumption data includes electricity consumption, peak load and valley load for different time periods.

[0102] Climate data for the corresponding time period is obtained from the meteorological department's database. The climate data includes temperature, humidity, wind speed, and sunshine duration.

[0103] By utilizing sensors and monitoring systems deployed on power grid equipment, real-time operational status data of the power grid equipment can be acquired. This operational status data includes power grid equipment voltage, power grid equipment current, power grid equipment power factor, and power grid equipment temperature.

[0104] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S101, which includes:

[0105] The acquired power grid operation and management data is preprocessed and cleaned to remove abnormal power grid operation and management data, resulting in preprocessed power grid operation and management data.

[0106] The preprocessed power grid operation and management data is stored, classified according to data type, and search tags are established for the classified preprocessed power grid operation and management data.

[0107] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S102, which includes:

[0108] Correlation analysis was performed on historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data to obtain highly correlated characteristics of electricity load. These highly correlated characteristics include historical load characteristics, temperature characteristics, and humidity characteristics.

[0109] A load forecasting model is constructed based on historical load characteristics, temperature characteristics, and humidity characteristics;

[0110] Real-time power grid operation and management data is acquired, including real-time electricity load, weather conditions, power grid equipment status, and user behavior information. This real-time data is then substituted into the constructed electricity load prediction model to predict the electricity load. The predicted electricity load data is then calculated using the electricity load prediction model.

[0111] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S102, which includes:

[0112] Obtain actual electricity load data, compare the predicted data with the actual electricity load data to obtain the error data between the predicted data and the actual electricity load, match the predicted data with the actual electricity load error data in the knowledge base to obtain the error cause information, which includes data quality problems, unreasonable models and the influence of external factors.

[0113] Based on the information on the causes of the errors, the parameters of the electricity load prediction model were adjusted, and the adjusted electricity load prediction model was used to make predictions again. By comparing with the actual data, the prediction effect of the adjusted electricity load prediction model was verified.

[0114] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S103, which includes:

[0115] Based on the time when each electricity load forecast data is generated, a timestamp is created for each electricity load forecast data. The timestamp is used to identify the time when the data was generated.

[0116] The electricity load forecast data with timestamps is written into the blockchain, and for each piece of electricity load forecast data stored on the blockchain, its hash value is calculated using a hash function.

[0117] The generated hash value is stored on the blockchain along with the original data, recording each piece of data and its corresponding hash value.

[0118] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S104, which includes:

[0119] Obtain information on each node of the electricity load management process from the power management system or documents. This information includes the electricity application, approval, allocation, and monitoring stages.

[0120] Obtain the management rules corresponding to each node of the electricity load management process. The management rules define the operation specifications, permission settings and data processing methods for each process node.

[0121] Generate hash values ​​based on the electricity load management process nodes and process node management rules:

[0122] The obtained electricity load management process node information and corresponding management rules are used as input data to generate hash values.

[0123] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S104, which includes:

[0124] The generated hash value, along with related electricity load management process node information and management rules, will be stored on the blockchain.

[0125] Utilize the smart contract functionality of the blockchain platform to write smart contract code based on the electricity load management process nodes and management rules;

[0126] The smart contract will automatically execute the management rules of the process nodes, and automatically allocate, monitor and record the power load according to the management rules of the automatically executed process nodes.

[0127] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S105, which includes:

[0128] Based on the function and requirements of each smart contract, data matching tags are established, and power grid operation and management data are preprocessed.

[0129] The established data matching tags are used to match the power grid operation and management data to obtain data with the smart contracts of each power load process node;

[0130] Based on the matching results, the power grid operation management data will be transmitted to the corresponding power load process node smart contract:

[0131] The successfully matched power grid operation and management data are categorized according to the corresponding smart contracts for the power load process nodes;

[0132] The categorized data is transmitted to the corresponding smart contracts. Each power load process node smart contract processes the received power grid operation and management data, generates corresponding data processing results, and randomly sorts the power load process node smart contracts to obtain a randomly sorted list of smart contracts.

[0133] First, based on the functions and requirements of the smart contracts at each electricity load process node, corresponding data matching tags are established, and the collected power grid operation and management data are preprocessed to improve the accuracy and usability of the data.

[0134] Next, these established data matching tags are used to match the power grid operation and management data in order to find the data corresponding to the smart contracts of each power load process node.

[0135] Then, based on the matching results, we accurately transmit the power grid operation and management data to the corresponding power load process node smart contracts, and categorize the successfully matched power grid operation and management data according to their corresponding power load process node smart contracts. After categorization, each type of data is sent to its corresponding smart contract. Each power load process node smart contract, upon receiving this data, performs independent data processing and generates the corresponding data processing results.

[0136] In addition, to enhance the system's flexibility and robustness, the smart contracts of the electricity load process nodes will be randomly sorted to obtain a randomly sorted list of smart contracts.

[0137] Specifically, the intelligent electricity load management method based on big data analysis provided by the present invention includes step S105, which includes:

[0138] Collect the data processing results of the smart contracts at the first process node, the second process node, and the third process node;

[0139] Cluster analysis is performed on the smart contract data processing results of the first, second, and third process nodes, along with the smart contract completion rates and electricity load data of each node. Based on the cluster analysis results, an evaluation is conducted to obtain the completion rates of each process node in the data processing results of the first, second, and third process nodes. If any of these process nodes has a completion rate lower than a preset value, the data with a lower completion rate is reviewed. If the review results indicate a data error, a data error warning is generated.

[0140] First, the data processing results of the smart contracts at the first, second, and third process nodes are collected. This data contains key information generated by the smart contracts at each process node during execution, reflecting the actual situation of electricity load management.

[0141] Cluster analysis: Cluster analysis is performed on the data processing results of the first, second, and third process node smart contracts. Cluster analysis is an unsupervised learning method used to divide data into several groups or clusters, such that data within the same group has high similarity, while data between different groups has low similarity.

[0142] During this process, the system pays particular attention to the completion status of smart contracts and the power load data of each node. Through cluster analysis of this data, the efficiency and performance differences of different process nodes in handling power load can be revealed.

[0143] Evaluation and Judgment: Based on the results of cluster analysis, the system evaluates the data processing completion rate of the smart contracts at the first, second, and third process nodes. The purpose of the evaluation is to determine the actual effectiveness of each process node in handling electricity load and whether there are any areas that need improvement or optimization.

[0144] The system sets a preset completion rate as the judgment standard. If the completion rate of a certain process node is lower than this preset value, it indicates that there is a problem or inefficiency in handling the power load at that node.

[0145] Data Review and Early Warning: For process nodes with a completion rate lower than the preset value, the system will conduct further data review. The purpose of the review is to confirm whether there are any errors or anomalies in the data, so as to improve the accuracy of the evaluation results.

[0146] If the review confirms that the data contains errors, the system will immediately generate a data error warning. These warnings will be promptly communicated to relevant personnel so that they can take swift action to correct the errors and ensure the normal operation of electrical load management.

[0147] Through the above steps, in step S105, the present invention achieves a comprehensive analysis and evaluation of the data processing results of smart contracts for the power load management process nodes, promptly identifies and addresses potential data problems, thereby improving the efficiency and reliability of power load management.

[0148] The technical solution of this invention solves the problems caused by abnormal power grid load data and errors in data analysis models in the following ways:

[0149] Historical electricity consumption data and climate data are obtained from the data centers or databases of power grid companies and preprocessed, including cleaning and removing outliers, to improve the data quality input to the model. Based on correlation analysis, highly correlated features such as historical load characteristics, temperature characteristics, and humidity characteristics are selected to construct a load forecasting model to improve forecast accuracy.

[0150] Real-time power grid operation and management data are substituted into the model for prediction, and the model is verified and adjusted based on actual power load data. The prediction effect of the model is improved through repeated optimization.

[0151] Timestamps are generated for electricity load forecast data and stored on the blockchain, with hash values ​​generated to enhance data integrity and immutability. Blockchain technology ensures traceability of every step of data processing, improving transparency and security. Smart contracts are built based on electricity load management process nodes and rules to automatically execute management rules, reducing human error. These smart contracts are responsible for the automatic allocation, monitoring, and recording of electricity load, improving management efficiency and accuracy.

[0152] The system categorizes and tags power grid operation and management data, and uses smart contracts for matching to improve the accuracy of data transmission to the corresponding process nodes. It then analyzes the results of the smart contract processing to assess the completion rate of each process node, promptly identify problems, and conduct follow-up reviews.

[0153] By comparing predicted data with actual load data, prediction errors were identified, and the causes of these errors were matched against the knowledge base to adjust the model parameters. The effectiveness of the adjusted model was then verified, leading to continuous model optimization and improved prediction accuracy.

[0154] Through the above measures, the technical solution of the present invention not only improves the accuracy of power grid load data, but also reduces the risk of human error through automated and intelligent management methods, thereby improving the normal operation of the power grid system.

[0155] The technical solution of this invention has practicality:

[0156] The intelligent electricity load management method based on big data analysis provided by this invention has significant practical value, mainly reflected in the following aspects:

[0157] Improving the accuracy of electricity load forecasting: By integrating historical electricity consumption data, climate data, grid equipment status, and user behavior data, and utilizing correlation analysis to construct load forecasting models, the accuracy of electricity load forecasting has been significantly improved. This helps grid companies to more accurately plan power generation, reduce operating costs, and improve power quality.

[0158] Enhancing data security and traceability: Utilizing blockchain technology to store electricity load forecast data and generate hash values ​​improves the data's time traceability, security, and immutability. Blockchain technology provides a distributed ledger, ensuring that any data modification is recorded on the chain, preventing malicious tampering and enhancing data trust and security.

[0159] Automating the electricity load management process: Utilizing smart contract technology, the allocation, monitoring, and recording of nodes in the electricity load management process are automated. Smart contracts execute automatically according to preset management rules, reducing human intervention, improving process transparency and efficiency, and lowering the risk of human error.

[0160] Improving the stability and management efficiency of the power grid system: By preprocessing and classifying power grid operation and management data, the quality of input data is improved. Simultaneously, data analysis of the data processing results from smart contracts at the electricity load management process nodes allows for the timely identification and resolution of potential problems, thereby enhancing the stability and management efficiency of the power grid system.

[0161] Promoting Intelligent Management of Power Grid Enterprises: The technical solution of this invention provides strong support for the intelligent management of power grid enterprises by introducing big data analysis, blockchain technology, and smart contracts. This not only helps improve the management level of power grid enterprises but also promotes the intelligent development of the entire power industry.

[0162] Specific implementation examples:

[0163] The following is a specific embodiment based on the technical solution of the present invention:

[0164] Historical electricity consumption data from the past year is obtained from the power grid company's data center, including electricity consumption, peak load, and off-peak load for different time periods. Climate data for the corresponding time periods, including temperature, humidity, wind speed, and sunshine duration, is obtained from meteorological databases. Real-time status data such as voltage, current, power factor, and equipment temperature are acquired using sensors and monitoring systems deployed on power grid equipment. The collected data is then cleaned and preprocessed to remove outliers and duplicate data, improving data quality.

[0165] Correlation analysis was performed on historical electricity consumption data, climate data, power grid equipment status data, and user behavior data to identify characteristics highly correlated with electricity load (such as historical load characteristics, temperature characteristics, and humidity characteristics). A load forecasting model was constructed based on these characteristics and validated using real-time power grid operation and management data. The forecast results were compared with actual electricity load data to analyze the causes of forecast errors. Based on these errors, model parameters were adjusted to optimize the forecasting performance.

[0166] Timestamps are generated for electricity load forecast data and stored on the blockchain. A hash function is used to calculate the hash value of each forecast data point, and the hash value is stored on the blockchain along with the original data, improving data integrity and immutability.

[0167] Obtain information on key nodes and management rules for electricity load management processes, such as operational procedures, permission settings, and data processing methods for electricity application, approval, allocation, and monitoring. Based on the process node information, management rules, and predicted data hash values ​​stored on the blockchain, write smart contract code.

[0168] By deploying smart contracts on a blockchain platform, the smart contracts will automatically execute the management rules of the electricity load management process nodes, realizing the automatic allocation, monitoring and recording of electricity load.

[0169] The power grid operation and management data are categorized and tagged, and then transmitted to the corresponding smart contracts using data matching tags. Each smart contract processes the received data and generates corresponding processing results. The processing results of the smart contracts are analyzed to evaluate the completion rate of each process node. If data errors or low processing efficiency are detected, an early warning message is generated and relevant personnel are notified for further action.

[0170] Through the above steps, the technical solution of the present invention can significantly improve the accuracy and efficiency of power grid load management, enhance the security and stability of the system, and provide strong support for the intelligent management of power grid enterprises.

[0171] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations. The above-described embodiments of this invention do not constitute a limitation on the scope of protection of this invention.

Claims

1. A smart electricity load management method based on big data analysis, characterized in that, include: Step S101: Obtain power grid operation and management data, which includes historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data. Step S102: Construct an electricity load prediction model based on historical electricity consumption data, climate data, power grid equipment operation status data and user behavior data, obtain real-time power grid operation management data, and substitute the real-time power grid operation management data into the electricity load prediction model to obtain electricity load prediction data. Step S103: Establish a timestamp for the electricity load forecast data based on the time of data generation, and store it in the blockchain to generate the hash value corresponding to the electricity load forecast data; Step S104: Obtain the power load management process nodes and process node management rules. Based on the power load management process nodes, process node management rules, and the hash values ​​corresponding to the power load prediction data stored in the blockchain, construct a smart contract for the power load process nodes. Step S105: Establish data matching tags for smart contracts of electricity load process nodes, match the power grid operation management data with the data matching tags, and transmit the power grid operation management data to the corresponding smart contracts of electricity load process nodes according to the matching results to obtain the data processing results of the first process node smart contracts. Randomly sort the smart contracts of electricity load process nodes to obtain randomly sorted smart contracts of electricity load process nodes. Match the randomly sorted smart contracts of electricity load process nodes with the electricity load forecast data to obtain the data processing results of the second process node smart contracts. Match the randomly sorted smart contracts of electricity load process nodes with the power grid operation management data to obtain the data processing results of the third process node smart contracts. Perform data analysis on the data processing results of the first, second, and third process node smart contracts to obtain the completion degree of each process node of electricity load management.

2. The intelligent electricity load management method based on big data analysis as described in claim 1, characterized in that, Step S101 includes: Historical electricity consumption data is obtained from the data center or database of the power grid company. The historical electricity consumption data includes electricity consumption, peak load and valley load for different time periods. Climate data for the corresponding time period is obtained from the meteorological department's database. The climate data includes temperature, humidity, wind speed, and sunshine duration. By utilizing sensors and monitoring systems deployed on power grid equipment, real-time operational status data of the power grid equipment can be acquired. This operational status data includes power grid equipment voltage, power grid equipment current, power grid equipment power factor, and power grid equipment temperature.

3. The intelligent electricity load management method based on big data analysis as described in claim 2, characterized in that, Step S101 includes: The acquired power grid operation and management data is preprocessed and cleaned to remove abnormal power grid operation and management data, resulting in preprocessed power grid operation and management data. The preprocessed power grid operation and management data is stored, classified according to data type, and search tags are established for the classified preprocessed power grid operation and management data.

4. The intelligent electricity load management method based on big data analysis as described in claim 1, characterized in that, Step S102 includes: Correlation analysis was performed on historical electricity consumption data, climate data, power grid equipment operation status data, and user behavior data to obtain highly correlated characteristics of electricity load. These highly correlated characteristics include historical load characteristics, temperature characteristics, and humidity characteristics. A load forecasting model is constructed based on historical load characteristics, temperature characteristics, and humidity characteristics; Real-time power grid operation and management data is acquired, including real-time electricity load, weather conditions, power grid equipment status, and user behavior information. This real-time data is then substituted into the constructed electricity load prediction model to predict the electricity load. The predicted electricity load data is then calculated using the electricity load prediction model.

5. The intelligent electricity load management method based on big data analysis as described in claim 4, characterized in that, Step S102 includes: Obtain actual electricity load data, compare the predicted data with the actual electricity load data to obtain the error data between the predicted data and the actual electricity load, match the predicted data with the actual electricity load error data in the knowledge base to obtain the error cause information, which includes data quality problems, unreasonable models and the influence of external factors. Based on the information on the causes of the errors, the parameters of the electricity load prediction model were adjusted, and the adjusted electricity load prediction model was used to make predictions again. By comparing with the actual data, the prediction effect of the adjusted electricity load prediction model was verified.

6. The intelligent electricity load management method based on big data analysis as described in claim 1, characterized in that, Step S103 includes: Based on the time when each electricity load forecast data is generated, a timestamp is created for each electricity load forecast data. The timestamp is used to identify the time when the data was generated. The electricity load forecast data with timestamps is written into the blockchain, and for each piece of electricity load forecast data stored on the blockchain, its hash value is calculated using a hash function. The generated hash value is stored on the blockchain along with the original data, recording each piece of data and its corresponding hash value.

7. The intelligent electricity load management method based on big data analysis as described in claim 1, characterized in that, Step S104 includes: Obtain information on each node of the electricity load management process from the power management system or documents. This information includes the electricity application, approval, allocation, and monitoring stages. Obtain the management rules corresponding to each node of the electricity load management process. The management rules define the operation specifications, permission settings and data processing methods for each process node. Generate hash values ​​based on the electricity load management process nodes and process node management rules: The obtained electricity load management process node information and corresponding management rules are used as input data to generate hash values.

8. The intelligent electricity load management method based on big data analysis as described in claim 7, characterized in that, Step S104 includes: The generated hash value, along with related electricity load management process node information and management rules, will be stored on the blockchain. Utilize the smart contract functionality of the blockchain platform to write smart contract code based on the electricity load management process nodes and management rules; The smart contract will automatically execute the management rules of the process nodes, and automatically allocate, monitor and record the power load according to the management rules of the automatically executed process nodes.

9. The intelligent electricity load management method based on big data analysis as described in claim 1, characterized in that, Step S105 includes: Based on the function and requirements of each smart contract, data matching tags are established, and power grid operation and management data are preprocessed. The established data matching tags are used to match the power grid operation and management data to obtain data with the smart contracts of each power load process node; Based on the matching results, the power grid operation management data will be transmitted to the corresponding power load process node smart contract: The successfully matched power grid operation and management data are categorized according to the corresponding smart contracts for the power load process nodes; The categorized data is transmitted to the corresponding smart contracts. Each power load process node smart contract processes the received power grid operation and management data, generates corresponding data processing results, and randomly sorts the power load process node smart contracts to obtain a randomly sorted list of smart contracts.

10. The intelligent electricity load management method based on big data analysis as described in claim 9, characterized in that, Step S105 includes: Collect the data processing results of the smart contracts at the first process node, the second process node, and the third process node; Cluster analysis is performed on the smart contract data processing results of the first, second, and third process nodes, along with the smart contract completion rates and electricity load data of each node. Based on the cluster analysis results, an evaluation is conducted to obtain the completion rates of each process node in the data processing results of the first, second, and third process nodes. If any of these process nodes has a completion rate lower than a preset value, the data with a lower completion rate is reviewed. If the review results indicate a data error, a data error warning is generated.

Images