Intelligent electrical load management method based on big data analysis

Abstract

The invention relates to the technical field of big data analysis and data processing, and provides an intelligent power utilization load management method based on big data analysis, which constructs an accurate power utilization load prediction model by integrating historical power utilization data, climate data, a power grid equipment state and user behavior data. According to the method, the security and traceability of prediction data are improved by adopting a block chain technology, and automation of an electrical load management process is realized by means of an intelligent contract. The method comprises the specific steps of data acquisition and preprocessing, load prediction model construction and verification, prediction data storage and hash value generation, intelligent contract writing and execution, and process node data processing and evaluation. The method effectively solves the problems of load data abnormity and model errors, and improves the stability and management efficiency of a power grid system.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis and data processing, and in particular to an intelligent power load management method based on big data analysis. Background Art

[0002] The application of big data analysis in intelligent power load management is mainly reflected in the following aspects: power grid companies can integrate various data resources, such as historical power consumption data, climate data, etc., to build complex prediction models and achieve accurate prediction of future power load. This prediction helps power grid companies to reasonably arrange power generation plans, reduce operating costs, and improve power quality. Big data analysis can monitor the operating status of power grid equipment in real time, and timely discover potential failure risks and perform preventive maintenance by mining the massive data collected by sensors and monitoring points. This can effectively avoid the occurrence of 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 the best allocation of resources, including optimization of transmission line capacity, transformation and upgrading of substations, etc. This helps to improve the overall operating efficiency of the power grid and promote energy conservation and emission reduction.

[0003] Although big data analysis has shown significant advantages in intelligent power load management, there are the following technical pain points: Although big data analysis can monitor the operating status of power grid equipment in real time, power grid power load management depends on the accuracy and timeliness of big data analysis. In actual applications, due to abnormal power load data of the power grid and errors in the data analysis model, errors occur in intelligent power load management based on big data analysis. If errors in power load management are not discovered in time, the normal operation of the power grid system will be affected. For example, power load data of the power grid may be abnormal in actual applications, such as missing data, wrong records or inaccurate values. Missing data, wrong records or inaccurate values ​​will directly affect the accuracy of load forecasting. At the same time, there may also be errors in the data analysis model, causing the prediction results to deviate from the actual power load situation. If the above errors are not discovered and corrected in time, the intelligent power load management decision based on big data analysis will be biased, which will in turn affect the normal operation of the power grid system. Incorrect load forecasting may cause insufficient power supply during peak hours or excessive power generation during trough hours, thereby wasting resources and possibly damaging the life of power grid equipment. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an intelligent power load management method based on big data analysis. Through data preprocessing steps, such as data cleaning and outlier removal, the quality of input data is improved, and the impact of data anomalies on the prediction model is reduced, thereby solving the problem of inaccurate prediction caused by abnormal power load data of the power grid. By comparing the predicted data with the actual power load data, the cause of the prediction error is analyzed, and the model parameters are adjusted according to the cause of the error, and the prediction model is continuously optimized, thereby improving the accuracy and credibility of the prediction results. Blockchain technology is used to store power load prediction data and generate hash values, which improves the time traceability, security and non-tamperability of the data, and solves the security and traceability problems of power grid operation management data. The present invention realizes the automatic allocation, monitoring and recording of power load management process nodes through smart contract technology, reduces human intervention, improves management efficiency, and solves the problems of inefficiency and error-proneness caused by the traditional power load management process relying on manual operation.

[0005] Continuously compare the forecast data with the actual load data, analyze the forecast error, and adjust the model parameters to achieve continuous optimization of the forecast model and improve the accuracy of long-term forecasts. Integrate historical electricity consumption data, climate data, power grid equipment status and user behavior data to build an accurate power load forecast model, and obtain and process power grid operation management data in real time, achieve real-time data processing, and improve timely response to changes in power grid operation.

[0006] The present invention improves the accuracy of power load forecasting and introduces automated management processes, significantly improves the stability and management efficiency of the power grid system, provides strong support for the intelligent management of power grid enterprises, and solves the problems of low stability and management efficiency of the power grid system.

[0007] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0008] The present invention provides an intelligent power load management method based on big data analysis, comprising:

[0009] Step S101, acquiring power grid operation management data, the power grid operation management data including historical power consumption data, climate data, power grid equipment operation status data and user behavior data;

[0010] Step S102, building a power load forecasting model based on historical power consumption data, climate data, power grid equipment operating status data, and user behavior data, acquiring real-time power grid operation management data, substituting the real-time power grid operation management data into the power load forecasting model, and obtaining power load forecasting data;

[0011] Step S103, creating a timestamp for the power load forecast data at the time when the data was generated, and storing it in the blockchain to generate a hash value corresponding to the power load forecast data;

[0012] Step S104, obtaining the power load management process node and process node management rules, storing the power load management process node and process node management rules in the blockchain to generate a hash value corresponding to the power load forecast data, and constructing a power load process node smart contract;

[0013] Step S105, establish a data matching tag for the power load process node smart contract, match the power grid operation management data with the data matching tag, transmit the power grid operation management data to the corresponding power load process node smart contract according to the matching result, obtain the data processing result of the first process node smart contract, randomly sort the power load process node smart contract, obtain the randomly sorted power load process node smart contract, match the randomly sorted power load process node smart contract with the power load forecast data, obtain the data processing result of the second process node smart contract, match the randomly sorted power load process node smart contract with the power grid operation management data, obtain the data processing result of the third process node smart contract, perform data analysis on the data processing results of the first process node smart contract, the second process node smart contract and the third process node smart contract, and obtain the completion degree of each process node of the power load management.

[0014] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S101 includes:

[0015] Obtain historical electricity consumption data from the data center or database of the power grid company. The historical electricity consumption data includes electricity consumption, peak load, and valley load in different time periods.

[0016] Obtain climate data for the corresponding time period from the meteorological department database, including temperature, humidity, wind speed, and sunshine time;

[0017] By using sensors and monitoring systems deployed on power grid equipment, the operating status data of power grid equipment is obtained in real time. The operating status data of power grid equipment includes power grid equipment voltage, power grid equipment current, power grid equipment power factor and power grid equipment temperature.

[0018] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S101 includes:

[0019] Preprocessing the acquired power grid operation management data, cleaning the power grid operation management data, removing abnormal power grid operation management data, and obtaining preprocessed power grid operation management data;

[0020] The preprocessed power grid operation management data is stored, the stored preprocessed power grid operation management data is classified according to the type of data, and a retrieval tag is established for the classified preprocessed power grid operation management data.

[0021] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S102 includes:

[0022] Correlation analysis is performed on historical electricity consumption data, climate data, grid equipment operating status data, and user behavior data to obtain highly correlated features of electricity load, which include historical load features, temperature features, and humidity features.

[0023] Construct a load forecasting model based on historical load characteristics, temperature characteristics, and humidity characteristics;

[0024] Acquire real-time grid operation and management data, which includes real-time power load, climate conditions, grid equipment status, and user behavior information. Substitute the real-time data into the constructed power load forecasting model to perform power load forecasting. The power load forecasting data is calculated by the power load forecasting model.

[0025] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S102 includes:

[0026] Obtain actual power load data, compare the predicted data with the actual power load data, obtain the error data between the predicted data and the actual power load, match the predicted data with the actual power load error data in the knowledge base, and obtain information on the cause of the error, which includes data quality issues, unreasonable models, and external factors;

[0027] According to the information on the cause of the error, the parameters of the power load forecasting model are adjusted, and the adjusted power load forecasting model is used for re-forecasting. The prediction effect of the adjusted power load forecasting model is verified by comparing it with the actual data.

[0028] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S103 includes:

[0029] According to the time when each piece of power load forecast data is generated, a timestamp corresponding to each piece of power load forecast data is created, and the timestamp is used to identify the generation time of the data;

[0030] Write the power load forecast data with timestamp into the blockchain, and use the hash function to calculate the hash value of each power load forecast data stored in the blockchain;

[0031] The generated hash value is stored together with the original data on the blockchain, recording each piece of data and its corresponding hash value.

[0032] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S104 includes:

[0033] Obtain information about each node of the power load management process from the power management system or document. The information about each node of the power load management process includes power application, approval, allocation, and monitoring.

[0034] Obtain management rules corresponding to each node information of the power load management process, which define the operation specifications, authority settings and data processing methods of each process node;

[0035] Generate hash values ​​based on power load management process nodes and process node management rules:

[0036] The acquired power load management process node information and the corresponding management rules are used as input data to generate a hash value.

[0037] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S104 includes:

[0038] The generated hash value and the related power load management process node information and management rules are stored on the blockchain;

[0039] Utilize the smart contract function of the blockchain platform to write smart contract code based on the power load management process nodes and management rules;

[0040] Smart contracts will automatically execute the management rules of process nodes. Smart contracts will automatically distribute, monitor and record electricity loads based on the management rules of automatically executed process nodes.

[0041] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S105 includes:

[0042] According to the functions and requirements of each smart contract, data matching tags are established and grid operation management data is pre-processed;

[0043] Use the established data matching tags to match the power grid operation management data to obtain the data of the smart contract of each power load process node;

[0044] According to the matching results, the power grid operation management data is transmitted to the corresponding power load process node smart contract:

[0045] The successfully matched power grid operation management data is classified according to the corresponding power load process node smart contract;

[0046] The classified data are transmitted to the corresponding smart contracts respectively. Each power load process node smart contract processes the received power grid operation management data, generates corresponding data processing results, and randomly sorts the power load process node smart contracts to obtain a randomly sorted smart contract list.

[0047] Furthermore, the intelligent power load management method based on big data analysis provided by the present invention, step S105 includes:

[0048] Collect the first process node smart contract data processing results, the second process node smart contract data processing results, and the third process node smart contract data processing results;

[0049] A cluster analysis is performed on the smart contract completion degree in the first process node data analysis of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node, and an evaluation is performed based on the cluster analysis results to obtain the completion degree of each process node of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node. If the completion degree of each process node of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node contains data that is lower than a preset completion value, the data that is lower than the preset completion value is reviewed, and if the review result is a data error, a data error warning message is generated.

[0050] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0051] The present invention integrates historical electricity consumption data, climate data, grid equipment operating status data and user behavior data, and uses correlation analysis to build a load forecasting model, which significantly improves the accuracy of power load forecasting. This not only helps grid companies to reasonably arrange power generation plans, but also effectively reduces operating costs and improves power quality.

[0052] By storing the power load forecast data in the blockchain and generating a hash value, the time traceability, security and immutability of the data are improved. Blockchain technology provides a distributed ledger, and any data modification will be recorded on the chain, thereby preventing the data from being maliciously tampered with and enhancing the trust and security of the data.

[0053] Smart contract technology is used to realize the automatic allocation, monitoring and recording of power load management process nodes. Smart contracts are automatically executed according to preset management rules, which reduces human intervention, improves the transparency and efficiency of the process, and reduces the risk of human error.

[0054] By preprocessing the power grid operation management data, including data cleaning and outlier removal, the quality of input data is improved, and the accuracy and reliability of the prediction model are further enhanced. Through data analysis, the completion of each process node is evaluated to timely discover and deal with potential problems. If data errors or inefficient processing are found, the system will generate early warning information to notify relevant personnel to deal with it in time, thereby ensuring the normal operation of the power grid system. By continuously comparing the predicted data with the actual load data, analyzing the causes of the prediction error, and adjusting the model parameters, the continuous optimization of the prediction model is achieved, and the accuracy and effectiveness of long-term predictions are improved.

[0055] In summary, the present invention significantly improves the accuracy and efficiency of power grid load management, enhances the security and stability of the system, and provides strong support for the intelligent management of power grid enterprises by introducing big data analysis, blockchain technology and smart contracts. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 A schematic flow chart of an intelligent power load management method based on big data analysis provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0059] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0060] See also Figure 1 The present invention provides an intelligent power load management method based on big data analysis, comprising:

[0061] Step S101, acquiring power grid operation management data, the power grid operation management data including historical power consumption data, climate data, power grid equipment operation status data and user behavior data;

[0062] Step S101 mainly involves obtaining power grid operation management data. These data are an indispensable basis for subsequent power load forecasting and management. Specifically, the following types of data need to be obtained:

[0063] Historical electricity consumption data: including electricity consumption in different time periods, peak load, valley load and other information. Provides reference for subsequent load forecasting.

[0064] Climate data: obtained through the meteorological department database, mainly including temperature, humidity, wind speed, sunshine time, etc. Climate factors have a significant impact on power load, especially temperature and humidity, so climate data is crucial to improve the accuracy of load forecasting.

[0065] Grid equipment operation status data: Grid equipment operation status data is obtained in real time through sensors and monitoring systems deployed on grid equipment, reflecting the voltage, current, power factor, equipment temperature and other status of grid equipment. Understanding the equipment status helps to timely predict and maintain the stable operation of the grid.

[0066] User behavior data: including users’ electricity usage habits, electricity consumption patterns, etc. User behavior data can help us more accurately predict future electricity loads, thereby optimizing electricity distribution and management.

[0067] After obtaining these data, preprocessing steps are required, such as data cleaning, removing outliers, and categorizing and storing them. These preprocessing operations can improve the quality and accuracy of the data and lay a solid foundation for subsequent analysis and prediction.

[0068] Step S102, building a power load forecasting model based on historical power consumption data, climate data, power grid equipment operating status data, and user behavior data, acquiring real-time power grid operation management data, substituting the real-time power grid operation management data into the power load forecasting model, and obtaining power load forecasting data;

[0069] The historical electricity consumption data includes electricity consumption, peak load and valley load in each time period.

[0070] Obtain climate data such as temperature, humidity, wind speed, and sunshine hours from the meteorological department database.

[0071] By using sensors and monitoring systems deployed on power grid equipment, real-time data on the operating status of power grid equipment can be obtained, including voltage, current, power factor, etc. At the same time, user behavior data can be considered, which helps to predict power load more accurately.

[0072] Conduct correlation analysis on various types of collected data, identify features that are highly correlated with power load, and build a load forecasting model. Obtain real-time power grid operation and management data, including current power load, climate conditions, power grid equipment status, and user behavior information. Input these real-time data into the constructed forecasting model and calculate the forecast data of power load.

[0073] Obtain actual power load data and compare the forecast results with the actual data to evaluate the accuracy of the model. Analyze the causes of forecast errors and adjust the model parameters based on these causes to improve the accuracy of the forecast.

[0074] Step S103, creating a timestamp for the power load forecast data at the time when the data was generated, and storing it in the blockchain to generate a hash value corresponding to the power load forecast data;

[0075] The process of processing the power load forecast data in step S103 mainly includes the following steps:

[0076] Create timestamp: Create a corresponding timestamp for each piece of power load forecast data based on the time it was generated. The timestamp is used to uniquely identify the time when the data was generated, which improves the timeliness and traceability of the data.

[0077] Store to blockchain: Write the power load forecast data with timestamp to blockchain. As a decentralized and tamper-proof distributed ledger technology, blockchain improves the security and immutability of data.

[0078] Generate hash value: For each piece of power load forecast data stored on the blockchain, use the hash function to calculate its hash value. The hash value is a digital fingerprint of fixed length that can uniquely represent the original data. Any slight change in the original data will result in a significant change in the hash value, thereby ensuring the integrity of the data.

[0079] Record hash value: Store the generated hash value together with the original data on the blockchain, and record each piece of data and its corresponding hash value. This can verify the integrity and non-tampering of the data without directly exposing the original data.

[0080] In summary, step S103 improves the time traceability, security and data integrity of the power load forecast data through the combined application of timestamps, blockchains and hash values, and provides a reliable data basis for subsequent power load management.

[0081] Step S104, obtaining the power load management process node and process node management rules, storing the power load management process node and process node management rules in the blockchain to generate a hash value corresponding to the power load forecast data, and constructing a power load process node smart contract;

[0082] Step S104 describes how to obtain the power load management process node and process node management rules, and build a power load process node smart contract based on this information and the hash value of the power load forecast data stored on the blockchain. The specific steps are as follows:

[0083] Obtaining power load management process nodes: Collecting information on each node of the power load management process from the power management system or related documents. These nodes usually include power application, approval, allocation, monitoring and other links.

[0084] Get process node management rules: Management rules define the operation specifications, permission settings, and data processing methods for each process node. These rules improve the orderly and compliant execution of process nodes.

[0085] Combine hash values ​​to build smart contracts: The power load management process node information, process node management rules, and hash values ​​corresponding to the power load forecast data stored on the blockchain are used as input to build smart contracts. The hash value is used as a unique identifier for the power load forecast data, which improves the integrity and traceability of the data.

[0086] Use blockchain platform to write smart contracts: Use the smart contract function provided by the blockchain platform to write smart contract code according to process nodes and management rules. Smart contracts will automatically execute the management rules of process nodes and automatically distribute, monitor and record power loads.

[0087] Automatic execution of smart contracts: Once deployed on the blockchain, smart contracts will automatically execute the electricity load management process according to preset rules. This reduces human intervention and improves the transparency and efficiency of the process.

[0088] In this way, step S104 improves the standardization, automation and traceability of the power load management process, thereby improving the efficiency and accuracy of power grid operation management.

[0089] Step S105, establish a data matching tag for the power load process node smart contract, match the power grid operation management data with the data matching tag, transmit the power grid operation management data to the corresponding power load process node smart contract according to the matching result, obtain the data processing result of the first process node smart contract, randomly sort the power load process node smart contract, obtain the randomly sorted power load process node smart contract, match the randomly sorted power load process node smart contract with the power load forecast data, obtain the data processing result of the second process node smart contract, match the randomly sorted power load process node smart contract with the power grid operation management data, obtain the data processing result of the third process node smart contract, perform data analysis on the data processing results of the first process node smart contract, the second process node smart contract and the third process node smart contract, and obtain the completion degree of each process node of the power load management.

[0090] Step S105 describes in detail a key step in the intelligent power load management method based on big data analysis, which mainly involves the data processing process of the power load process node smart contract. The following is the specific content and process of this step:

[0091] Establish data matching tags: For each power load process node smart contract, establish corresponding data matching tags according to its functions and requirements. Tags are used to identify and distinguish different types of power grid operation management data.

[0092] Data matching and transmission: Match the grid operation management data with these matching tags so that the data can be accurately transmitted to the corresponding power load process node smart contract. According to the matching results, the grid operation management data is transmitted to the corresponding smart contract for subsequent processing.

[0093] First process node smart contract data processing: Each power load process node smart contract receives and processes the transmitted power grid operation management data, and generates the data processing results of the first process node smart contract.

[0094] Smart contract random sorting: Randomly sort all the power load process node smart contracts to generate a randomly sorted list of power load process node smart contracts. This step is intended to increase the robustness of the system and avoid potential prediction bias.

[0095] Second process node smart contract data processing: Match the randomly sorted electric load process node smart contract with the electric load forecast data to generate the data processing result of the second process node smart contract. This step is used to verify the applicability and accuracy of the forecast data in the actual process node.

[0096] Third process node smart contract data processing: The randomly sorted load process node smart contract is matched with the original power grid operation management data again to generate the data processing result of the third process node smart contract. This step is used to further confirm the consistency and accuracy of the data at different processing stages.

[0097] Data analysis and evaluation: Comprehensively analyze the data processing results of the first, second, and third process node smart contracts to evaluate the completion of each process node. Through data analysis, determine whether there is data below the preset completion value. If so, review the data and generate data error warning information after confirming the data error.

[0098] This step realizes the automatic processing and analysis of power grid operation management data through the application of smart contracts, improving the accuracy and efficiency of power load management. At the same time, through random sorting and multiple matching verifications, the stability and reliability of the system are enhanced.

[0099] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S101 includes:

[0100] Obtain historical electricity consumption data from the data center or database of the power grid company. The historical electricity consumption data includes electricity consumption, peak load, and valley load in different time periods.

[0101] Obtain climate data for the corresponding time period from the meteorological department database, including temperature, humidity, wind speed, and sunshine time;

[0102] By using sensors and monitoring systems deployed on power grid equipment, the operating status data of power grid equipment is obtained in real time. The operating status data of power grid equipment includes power grid equipment voltage, power grid equipment current, power grid equipment power factor and power grid equipment temperature.

[0103] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S101 includes:

[0104] Preprocessing the acquired power grid operation management data, cleaning the power grid operation management data, removing abnormal power grid operation management data, and obtaining preprocessed power grid operation management data;

[0105] The preprocessed power grid operation management data is stored, the stored preprocessed power grid operation management data is classified according to the type of data, and a retrieval tag is established for the classified preprocessed power grid operation management data.

[0106] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S102 includes:

[0107] Correlation analysis is performed on historical electricity consumption data, climate data, grid equipment operating status data, and user behavior data to obtain highly correlated features of electricity load, which include historical load features, temperature features, and humidity features.

[0108] Construct a load forecasting model based on historical load characteristics, temperature characteristics, and humidity characteristics;

[0109] Acquire real-time grid operation and management data, which includes real-time power load, climate conditions, grid equipment status, and user behavior information. Substitute the real-time data into the constructed power load forecasting model to perform power load forecasting. The power load forecasting data is calculated by the power load forecasting model.

[0110] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S102 includes:

[0111] Obtain actual power load data, compare the predicted data with the actual power load data, obtain the error data between the predicted data and the actual power load, match the predicted data with the actual power load error data in the knowledge base, and obtain information on the cause of the error, which includes data quality issues, unreasonable models, and external factors;

[0112] According to the information on the cause of the error, the parameters of the power load forecasting model are adjusted, and the adjusted power load forecasting model is used for re-forecasting. The prediction effect of the adjusted power load forecasting model is verified by comparing it with the actual data.

[0113] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S103 includes:

[0114] According to the time when each piece of power load forecast data is generated, a timestamp corresponding to each piece of power load forecast data is created, and the timestamp is used to identify the generation time of the data;

[0115] Write the power load forecast data with timestamp into the blockchain, and use the hash function to calculate the hash value of each power load forecast data stored in the blockchain;

[0116] The generated hash value is stored together with the original data on the blockchain, recording each piece of data and its corresponding hash value.

[0117] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S104 includes:

[0118] Obtain information about each node of the power load management process from the power management system or document. The information about each node of the power load management process includes power application, approval, allocation, and monitoring.

[0119] Obtain management rules corresponding to each node information of the power load management process, which define the operation specifications, authority settings and data processing methods of each process node;

[0120] Generate hash values ​​based on power load management process nodes and process node management rules:

[0121] The acquired power load management process node information and the corresponding management rules are used as input data to generate a hash value.

[0122] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S104 includes:

[0123] The generated hash value and the related power load management process node information and management rules are stored on the blockchain;

[0124] Utilize the smart contract function of the blockchain platform to write smart contract code based on the power load management process nodes and management rules;

[0125] Smart contracts will automatically execute the management rules of process nodes. Smart contracts will automatically distribute, monitor and record electricity loads based on the management rules of automatically executed process nodes.

[0126] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S105 includes:

[0127] According to the functions and requirements of each smart contract, data matching tags are established and grid operation management data is pre-processed;

[0128] Use the established data matching tags to match the power grid operation management data to obtain the data of the smart contract of each power load process node;

[0129] According to the matching results, the power grid operation management data is transmitted to the corresponding power load process node smart contract:

[0130] The successfully matched power grid operation management data is classified according to the corresponding power load process node smart contract;

[0131] The classified data are transmitted to the corresponding smart contracts respectively. Each power load process node smart contract processes the received power grid operation management data, generates corresponding data processing results, and randomly sorts the power load process node smart contracts to obtain a randomly sorted smart contract list.

[0132] First, according to the functions and requirements of the smart contract of each power load process node, the corresponding data matching tags are established, and the collected power grid operation management data is preprocessed to improve the accuracy and availability of the data.

[0133] Next, these established data matching tags are used to match the power grid operation management data, with the aim of finding the data corresponding to the smart contracts of each power load process node.

[0134] Then, based on the matching results, we accurately transmit the grid operation management data to the corresponding power load process node smart contract, and classify the successfully matched grid operation management data according to its corresponding power load process node smart contract. After the classification is completed, each type of data is sent to the corresponding smart contract. After receiving this data, each power load process node smart contract performs independent data processing and generates corresponding data processing results.

[0135] In addition, in order to enhance the flexibility and robustness of the system, the power load process node smart contracts will be randomly sorted to obtain a randomly sorted smart contract list.

[0136] Specifically, the intelligent power load management method based on big data analysis provided by the present invention, step S105 includes:

[0137] Collect the first process node smart contract data processing results, the second process node smart contract data processing results, and the third process node smart contract data processing results;

[0138] A cluster analysis is performed on the smart contract completion degree in the first process node data analysis of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node, and an evaluation is performed based on the cluster analysis results to obtain the completion degree of each process node of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node. If the completion degree of each process node of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node contains data that is lower than a preset completion value, the data that is lower than the preset completion value is reviewed, and if the review result is a data error, a data error warning message is generated.

[0139] First, the data processing results of the first process node smart contract, the second process node smart contract, and the third process node smart contract are collected. These data are key information generated during the execution of each process node smart contract, reflecting the actual situation of power load management.

[0140] 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, so that the data similarity within the same group is high, while the data similarity between different groups is low.

[0141] During this process, the system pays special attention to the completion of smart contracts and the power load data of each node. Through cluster analysis of these data, the efficiency and performance differences of different process nodes in processing power load can be revealed.

[0142] Evaluation and judgment: Based on the results of cluster analysis, the system evaluates the data processing completion of the first, second, and third process node smart contracts. The purpose of the evaluation is to determine the actual effect of each process node in processing power load and whether there are areas that need improvement or optimization.

[0143] The system sets a preset completion value as the judgment standard. If the completion of a process node is lower than this preset value, it means that the node has problems or is inefficient in handling power load.

[0144] Data review and early warning: For process nodes whose completion rate is lower than the preset value, the system will conduct further data review. The purpose of the review is to confirm whether there are errors or anomalies in the data to improve the accuracy of the evaluation results.

[0145] If the review results confirm that there are errors in the data, the system will immediately generate data error warning information. These warning messages will promptly notify relevant personnel so that they can quickly take measures to correct the errors and ensure the normal operation of power load management.

[0146] Through the above steps, the present invention realizes a comprehensive analysis and evaluation of the data processing results of the smart contract of the power load management process node in step S105, and timely discovers and handles potential data problems, thereby improving the efficiency and reliability of power load management.

[0147] The technical solution of the present invention solves the problems caused by abnormal power load data of the power grid and errors in the data analysis model by the following methods:

[0148] Obtain historical electricity consumption data, climate data, etc. from the data center or database of the power grid company, and perform preprocessing, including cleaning and removing abnormal data, to improve the data quality of the input model. Based on correlation analysis, select highly correlated features such as historical load characteristics, temperature characteristics, humidity characteristics, etc. to build a load forecasting model to improve the accuracy of the forecast.

[0149] Real-time power grid operation and management data is substituted into the model for prediction, and the model is verified and adjusted based on actual power load data, and the model prediction effect is improved through repeated optimization.

[0150] Generate a timestamp for the power load forecast data and store it on the blockchain, generating a hash value to improve the integrity and immutability of the data. Through blockchain technology, every step of the data operation can be traced, improving the transparency and security of data processing. Build smart contracts based on the power load management process nodes and management rules, automatically execute management rules, and reduce human errors. Smart contracts are responsible for the automatic allocation, monitoring and recording of power loads, improving management efficiency and accuracy.

[0151] Classify the power grid operation management data, establish search tags, and match them through smart contracts to improve the accuracy of data transmission to the corresponding process nodes. Perform data analysis on the smart contract processing results, evaluate the completion of each process node, and promptly identify and review problems.

[0152] By comparing the forecast data with the actual load data, the forecast error is found, and the cause of the error is matched in the knowledge base to adjust the model parameters. The forecast effect of the adjusted model is verified, and the model is continuously optimized to improve the forecast accuracy.

[0153] Through the above measures, the technical solution of the present invention not only improves the accuracy of power grid power 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.

[0154] The technical solution of the present invention is practical

[0155] The intelligent power load management method based on big data analysis provided by the present invention has significant practicality, which is mainly reflected in the following aspects:

[0156] Improve the accuracy of power load forecasting: By integrating historical power consumption data, climate data, power grid equipment status and user behavior data, and using correlation analysis to build a load forecasting model, the accuracy of power load forecasting has been significantly improved. This helps power grid companies to arrange power generation plans more accurately, reduce operating costs, and improve power quality.

[0157] Enhanced data security and traceability: Blockchain technology is used to store power load forecast data and generate hash values ​​to improve the time traceability, security and immutability of data. Blockchain technology provides a distributed ledger, and any data modification will be recorded on the chain to prevent data from being maliciously tampered with, thereby enhancing the trust and security of data.

[0158] Automating the power load management process: Using smart contract technology, the nodes of the power load management process can be automatically allocated, monitored and recorded. Smart contracts are automatically executed according to preset management rules, which reduces human intervention, improves the transparency and efficiency of the process, and reduces the risk of human error.

[0159] Improve the stability and management efficiency of the power grid system: By preprocessing and classifying the power grid operation management data, the quality of input data is improved. At the same time, data analysis is performed on the data processing results of the smart contract of the power load management process node to timely discover and deal with potential problems, thereby improving the stability and management efficiency of the power grid system.

[0160] Promoting intelligent management of power grid companies: The technical solution of the present invention provides strong support for the intelligent management of power grid companies by introducing big data analysis, blockchain technology and smart contracts. This not only helps to improve the management level of power grid companies, but also promotes the intelligent development of the entire power industry. Specific embodiments

[0162] The following is a specific embodiment based on the technical solution of the present invention:

[0163] Obtain historical electricity consumption data for the past year from the power grid company's data center, including electricity consumption, peak load, and valley load in different time periods. Obtain climate data for the corresponding time period from the meteorological department database, including temperature, humidity, wind speed, and sunshine time. Use sensors and monitoring systems deployed on power grid equipment to obtain real-time status data such as voltage, current, power factor, and equipment temperature of power grid equipment. Clean and preprocess the collected data to remove outliers and duplicate data and improve data quality.

[0164] Conduct correlation analysis on historical electricity consumption data, climate data, power grid equipment status data, and user behavior data to identify features that are highly correlated with power load (such as historical load features, temperature features, and humidity features). Build a load forecasting model based on these features, and verify the model using real-time power grid operation management data. Compare the forecast results with the actual power load data, analyze the causes of the forecast errors, and adjust the model parameters based on the causes of the errors to optimize the forecasting effect.

[0165] Generate a timestamp for the power load forecast data and store it on the blockchain. Use a hash function to calculate the hash value of each forecast data, and store the hash value together with the original data on the blockchain to improve the integrity and immutability of the data.

[0166] Obtain the process node information and management rules of power load management, such as the operation specifications, authority settings and data processing methods of power application, approval, allocation and monitoring. Write smart contract code based on the process node information, management rules and the hash value of the predicted data stored on the blockchain.

[0167] By deploying smart contracts on the blockchain platform, the smart contracts will automatically execute the management rules of the power load management process nodes to achieve automatic allocation, monitoring and recording of power loads.

[0168] Classify the grid operation management data and create search tags, and use data matching tags to transmit the data to the corresponding smart contract. Each smart contract processes the received data and generates corresponding data processing results. Perform data analysis on the processing results of the smart contract to evaluate the completion of each process node. If data errors or low processing efficiency are found, generate warning information and notify relevant personnel to handle it.

[0169] Through the above steps, the technical solution of the present invention can significantly improve the accuracy and efficiency of power grid power load management, enhance the security and stability of the system, and provide strong support for the intelligent management of power grid enterprises.

[0170] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. An intelligent power load management method based on big data analysis, characterized in that: include: Step S101, acquiring power grid operation management data, the power grid operation management data including historical power consumption data, climate data, power grid equipment operation status data and user behavior data; Step S102, building a power load forecasting model based on historical power consumption data, climate data, power grid equipment operating status data, and user behavior data, acquiring real-time power grid operation management data, substituting the real-time power grid operation management data into the power load forecasting model, and obtaining power load forecasting data; Step S103, creating a timestamp for the power load forecast data at the time when the data was generated, and storing it in the blockchain to generate a hash value corresponding to the power load forecast data; Step S104, obtaining the power load management process node and process node management rules, storing the power load management process node and process node management rules in the blockchain to generate a hash value corresponding to the power load forecast data, and constructing a power load process node smart contract; Step S105, establish a data matching tag for the power load process node smart contract, match the power grid operation management data with the data matching tag, transmit the power grid operation management data to the corresponding power load process node smart contract according to the matching result, obtain the data processing result of the first process node smart contract, randomly sort the power load process node smart contract, obtain the randomly sorted power load process node smart contract, match the randomly sorted power load process node smart contract with the power load forecast data, obtain the data processing result of the second process node smart contract, match the randomly sorted power load process node smart contract with the power grid operation management data, obtain the data processing result of the third process node smart contract, perform data analysis on the data processing results of the first process node smart contract, the second process node smart contract and the third process node smart contract, and obtain the completion degree of each process node of the power load management.

2. The intelligent power load management method based on big data analysis according to claim 1 is characterized in that: The step S101 includes: Obtain historical electricity consumption data from the data center or database of the power grid company. The historical electricity consumption data includes electricity consumption, peak load, and valley load in different time periods. Obtain climate data for the corresponding time period from the meteorological department database, including temperature, humidity, wind speed, and sunshine time; By using sensors and monitoring systems deployed on power grid equipment, the operating status data of power grid equipment is obtained in real time. The operating status data of power grid equipment includes power grid equipment voltage, power grid equipment current, power grid equipment power factor and power grid equipment temperature.

3. The intelligent power load management method based on big data analysis according to claim 2 is characterized in that: The step S101 includes: Preprocessing the acquired power grid operation management data, cleaning the power grid operation management data, removing abnormal power grid operation management data, and obtaining preprocessed power grid operation management data; The preprocessed power grid operation management data is stored, the stored preprocessed power grid operation management data is classified according to the type of data, and a retrieval tag is established for the classified preprocessed power grid operation management data.

4. The intelligent power load management method based on big data analysis according to claim 1 is characterized in that: The step S102 includes: Correlation analysis is performed on historical electricity consumption data, climate data, grid equipment operating status data, and user behavior data to obtain highly correlated features of electricity load, which include historical load features, temperature features, and humidity features. Construct a load forecasting model based on historical load characteristics, temperature characteristics, and humidity characteristics; Acquire real-time grid operation and management data, which includes real-time power load, climate conditions, grid equipment status, and user behavior information. Substitute the real-time data into the constructed power load forecasting model to perform power load forecasting. The power load forecasting data is calculated by the power load forecasting model.

5. The intelligent power load management method based on big data analysis according to claim 4 is characterized in that: The step S102 includes: Obtain actual power load data, compare the predicted data with the actual power load data, obtain the error data between the predicted data and the actual power load, match the predicted data with the actual power load error data in the knowledge base, and obtain information on the cause of the error, which includes data quality issues, unreasonable models, and external factors; According to the information on the cause of the error, the parameters of the power load forecasting model are adjusted, and the adjusted power load forecasting model is used for re-forecasting. The prediction effect of the adjusted power load forecasting model is verified by comparing it with the actual data.

6. The intelligent power load management method based on big data analysis according to claim 1 is characterized in that: The step S103 includes: According to the time when each piece of power load forecast data is generated, a timestamp corresponding to each piece of power load forecast data is created, and the timestamp is used to identify the generation time of the data; Write the power load forecast data with timestamp into the blockchain, and use the hash function to calculate the hash value of each power load forecast data stored in the blockchain; The generated hash value is stored together with the original data on the blockchain, recording each piece of data and its corresponding hash value.

7. The intelligent power load management method based on big data analysis according to claim 1 is characterized in that: The step S104 includes: Obtain information about each node of the power load management process from the power management system or document. The information about each node of the power load management process includes power application, approval, allocation, and monitoring. Obtain management rules corresponding to each node information of the power load management process, which define the operation specifications, authority settings and data processing methods of each process node; Generate hash values ​​based on power load management process nodes and process node management rules: The acquired power load management process node information and the corresponding management rules are used as input data to generate a hash value.

8. The intelligent power load management method based on big data analysis according to claim 7 is characterized in that: The step S104 includes: The generated hash value and the related power load management process node information and management rules are stored on the blockchain; Utilize the smart contract function of the blockchain platform to write smart contract code based on the power load management process nodes and management rules; Smart contracts will automatically execute the management rules of process nodes. Smart contracts will automatically distribute, monitor and record electricity loads based on the management rules of automatically executed process nodes.

9. The intelligent power load management method based on big data analysis according to claim 1, characterized in that: The step S105 includes: According to the functions and requirements of each smart contract, data matching tags are established and grid operation management data is pre-processed; Use the established data matching tags to match the power grid operation management data to obtain the data of the smart contract of each power load process node; According to the matching results, the power grid operation management data is transmitted to the corresponding power load process node smart contract: The successfully matched power grid operation management data is classified according to the corresponding power load process node smart contract; The classified data are transmitted to the corresponding smart contracts respectively. Each power load process node smart contract processes the received power grid operation management data, generates corresponding data processing results, and randomly sorts the power load process node smart contracts to obtain a randomly sorted smart contract list.

10. The intelligent power load management method based on big data analysis according to claim 9, characterized in that: The step S105 includes: Collect the first process node smart contract data processing results, the second process node smart contract data processing results, and the third process node smart contract data processing results; A cluster analysis is performed on the smart contract completion degree in the first process node data analysis of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node, and an evaluation is performed based on the cluster analysis results to obtain the completion degree of each process node of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node. If the completion degree of each process node of the smart contract data processing results of the first process node, the smart contract data processing results of the second process node, and the smart contract data processing results of the third process node contains data that is lower than a preset completion value, the data that is lower than the preset completion value is reviewed, and if the review result is a data error, a data error warning message is generated.

Images