Ultrahigh voltage equipment energy efficiency intelligent control system based on big data analysis

Abstract

The invention provides an ultrahigh pressure equipment energy efficiency intelligent control system based on big data analysis, and relates to the technical field of big data analysis. Comprising an energy efficiency data integration module, an energy efficiency characteristic analysis module, an energy efficiency diagnosis and evaluation module and an energy efficiency strategy design module. The method comprises the following steps: collecting multi-source heterogeneous energy efficiency data of an ultrahigh-pressure equipment data source, performing preprocessing operation on the multi-source heterogeneous energy efficiency data, performing deep analysis on the preprocessed data, and mining potential factors influencing the energy efficiency of the equipment; then, the energy efficiency problem causing low energy efficiency of the ultrahigh-voltage equipment is identified, and a quantitative value evaluation report is generated from energy-saving potential, economic benefits and environmental benefits through comparison with a set datum line; and designing an energy efficiency control strategy according to the identified energy efficiency bottleneck and the value evaluation report in combination with an artificial intelligence optimization algorithm to achieve intelligent energy efficiency control of the ultrahigh-pressure equipment.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, and in particular to an intelligent energy efficiency control system for ultra-high voltage equipment based on big data analytics. Background Technology

[0002] As the main artery of energy supply, the efficiency and cleanliness of the power system directly affect national energy security and sustainable development. The State Grid Corporation of China and major power companies are actively promoting energy structure optimization and grid intelligent upgrading, committed to building a clean, low-carbon, safe, and efficient energy system. Among these, ultra-high voltage (UHV) equipment, as the core hub for inter-regional power transmission, directly impacts the economy, reliability, and environmental friendliness of power transmission. Therefore, improving the precision and intelligence of UHV equipment energy efficiency management has become a key link in the power industry's cost reduction, efficiency improvement, and green development.

[0003] During long-term operation, the energy consumption characteristics of ultra-high voltage (UHV) equipment dynamically change due to complex factors such as equipment aging, environmental changes, load fluctuations, and maintenance conditions. Accurately grasping the real-time energy efficiency status of UHV equipment, identifying key factors affecting energy efficiency, and extracting the value of energy efficiency data to design energy efficiency adjustment and control strategies can provide precise support for energy efficiency optimization, load scheduling, and fault prediction. This has significant practical implications for reducing losses, decreasing carbon emissions, and improving the utilization rate of power grid assets.

[0004] With the accelerated construction of smart grids and the deep application of IoT and sensor technologies, ultra-high voltage (UHV) equipment has formed a multi-dimensional energy efficiency data collection system covering operating parameters, energy consumption data, environmental data, and maintenance data, providing abundant "raw materials" for UHV equipment energy efficiency data management. However, UHV equipment energy efficiency data is scattered across multiple heterogeneous information platforms such as SCADA systems and EMS systems, and suffers from problems such as inconsistent data formats, non-uniform data standards, and varying data quality. Existing UHV equipment energy efficiency data analysis methods struggle to reveal the coupled impact of multiple factors such as load fluctuations, environmental changes, and equipment aging on energy efficiency from such complex, dynamic, and multi-source heterogeneous data. Moreover, existing UHV equipment energy efficiency data management mechanisms mainly focus on post-event traceability, lacking capabilities in real-time analysis and application.

[0005] Against this backdrop, effectively integrating the multi-source, heterogeneous big data generated during the operation of ultra-high voltage (UHV) equipment, constructing a unified, high-quality data foundation, and utilizing advanced big data analytics to deeply explore the potential value hidden behind the energy efficiency data of UHV equipment, and providing energy efficiency control strategies for UHV equipment, has become a key issue that urgently needs to be addressed in the current energy efficiency data management of UHV equipment. Only by fully releasing the value of this energy efficiency data can we achieve a paradigm shift from experience-driven to data-driven energy efficiency management, promote the transformation of UHV equipment energy efficiency management from "passive response" to "proactive optimization," provide a scientific basis for the refined operation and maintenance, intelligent scheduling, and full life-cycle energy efficiency optimization of UHV equipment, and provide core technological support for the energy efficiency improvement and low-carbon development of new power systems. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this paper proposes an intelligent energy efficiency control system for ultra-high voltage (UHV) equipment based on big data analytics. Through data acquisition, energy efficiency analysis, value assessment, and strategy design, the system performs real-time analysis and utilization of the energy efficiency of multi-source heterogeneous UHV equipment, thereby improving the economy, reliability, and low-carbon performance of UHV equipment and achieving cost reduction and efficiency improvement.

[0007] On one hand, this invention provides an intelligent energy efficiency control system for ultra-high voltage (UHV) equipment based on big data analysis, comprising: an energy efficiency data integration module, an energy efficiency feature analysis module, an energy efficiency diagnosis and evaluation module, and an energy efficiency strategy design module. The energy efficiency data integration module collects multi-source heterogeneous energy efficiency data from UHV equipment, and cleans, denoises, standardizes the format, and handles missing values ​​in the collected multi-source heterogeneous energy efficiency data to obtain a preprocessed dataset. The energy efficiency feature analysis module extracts key energy efficiency features from the preprocessed dataset and analyzes the correlation between the energy efficiency of UHV equipment and various factors. The energy efficiency diagnosis and evaluation module evaluates the potential improvement value of identified energy efficiency bottlenecks. The energy efficiency strategy design module designs energy efficiency control strategies and applies them to the operation and management of UHV equipment.

[0008] The energy efficiency data integration module is used to collect multi-source heterogeneous energy efficiency data from ultra-high voltage equipment data sources, preprocess the multi-source heterogeneous energy efficiency data, output the data in a unified format, and output the preprocessed data to the energy efficiency characteristic analysis module.

[0009] The energy efficiency feature analysis module uses big data analysis technology to perform in-depth analysis on the pre-processed data and extract key features that can reflect the energy efficiency of ultra-high voltage equipment. Combining existing metering models and artificial intelligence models, it analyzes the correlation between equipment energy efficiency and operating conditions, environmental factors, equipment aging degree, and maintenance history, and uncovers potential factors that affect equipment energy efficiency.

[0010] The energy efficiency feature analysis module comprises two parts: feature extraction and correlation analysis. Specifically, feature extraction involves extracting unit-time energy consumption and energy consumption fluctuation coefficient from power and operating time; extracting equipment load rate and efficiency from equipment operating parameters; and mining the temporal evolution trend, periodic characteristics, and convergence laws of unit-time energy consumption, energy consumption fluctuation coefficient, load rate, and efficiency based on existing long short-term memory neural network models, XGBoost models, and convergence models. The correlation analysis involves using a multiple linear regression model to analyze the linear impact of operating conditions, environmental factors, equipment aging, and maintenance history on the energy efficiency of ultra-high voltage equipment, identifying linear factors based on significance test results, and using support vector machines and random forest models to capture the nonlinear relationship between other nonlinear factors and the energy efficiency of ultra-high voltage equipment.

[0011] The energy efficiency diagnosis and evaluation module identifies potential factors derived from the energy efficiency characteristic analysis module, and identifies energy efficiency problems that lead to low energy efficiency of ultra-high voltage equipment. Energy efficiency problems are the energy efficiency bottlenecks of ultra-high voltage equipment, specifically including key links, specific equipment and operating modes in the operation of ultra-high voltage equipment. For the identified energy efficiency problems, a quantitative value assessment report is generated based on the energy-saving potential, economic benefits and environmental benefits by comparing them with the set baseline.

[0012] The energy efficiency diagnosis and assessment module comprises two parts: bottleneck identification and value assessment. Bottleneck identification specifically involves: based on the time evolution trend, periodic characteristics, and convergence patterns derived from the energy efficiency characteristic analysis module, comparative analysis and anomaly detection methods are used to identify energy efficiency bottlenecks leading to low energy efficiency in ultra-high voltage equipment, starting from key links, specific equipment, and operating modes. When the energy consumption of a certain operating link, operating equipment, or operating mode is found to be higher than the corresponding set baseline and mismatched with the corresponding load, the corresponding link is identified as an energy efficiency bottleneck. Value assessment specifically involves: for the identified energy efficiency bottlenecks, simulations are performed based on operating data such as load rate, voltage, current, and operating time, as well as environmental data such as temperature, humidity, and air pressure, to calculate the energy-saving potential of the ultra-high voltage equipment; combined with the equipment's operating costs, energy prices, and environmental policies, the economic benefits of the equipment are calculated; and based on the ultra-high voltage equipment's emission factors, emission standards, and energy-saving potential, the environmental benefits of the equipment are estimated, thereby generating a value assessment report.

[0013] The energy efficiency strategy design module designs an energy efficiency control strategy based on the identified energy efficiency bottlenecks and value assessment reports, combined with artificial intelligence optimization algorithms, to achieve intelligent energy efficiency control of ultra-high voltage equipment. The energy efficiency control strategy, based on the control strategy proposed by the energy efficiency strategy design module, solves the energy efficiency bottleneck problem and optimizes the operating status of the equipment.

[0014] The energy efficiency strategy design module comprises two parts: algorithm selection and strategy generation. Algorithm selection specifically involves choosing a suitable optimization algorithm based on the characteristics of the energy efficiency bottleneck and the optimization objective: for continuous optimization problems, particle swarm optimization and genetic algorithms are used; for discrete decision problems, simulated annealing and tabu search algorithms are used. Simultaneously, the parameters of the selected algorithm are set and optimized. Strategy generation specifically involves determining strategy design constraints based on the energy efficiency bottleneck identification results, clarifying the optimization objective based on the value of energy efficiency data, using the constraints and optimization objective as strategy input elements, and designing an energy efficiency control strategy including adjustment measures, implementation steps, and expected effects using the selected optimization algorithm. For energy efficiency bottlenecks caused by unreasonable load allocation, a load allocation strategy is designed to adjust the load ratio of each device; for energy efficiency bottlenecks caused by improper operating parameter settings, a parameter optimization strategy is designed to determine the optimal operating parameter values.

[0015] Secondly, this application proposes a computer-readable storage medium storing executable instructions that, when executed, cause a processor to execute the intelligent energy efficiency control system for ultra-high voltage equipment.

[0016] Thirdly, this application proposes a computer program product, including a computer program or instructions, which, when executed by a processor, implements the intelligent energy efficiency control system for the ultra-high voltage equipment.

[0017] The beneficial effects of adopting the above technical solution are as follows:

[0018] This invention provides an intelligent energy efficiency control system for ultra-high voltage (UHV) equipment based on big data analytics. Employing big data analytics, it effectively processes massive amounts of energy efficiency data from UHV equipment. Through in-depth data mining and value application, it achieves intelligent energy efficiency control of UHV equipment. The energy efficiency data integration module ensures data quality, providing a reliable foundation for subsequent analysis; the energy efficiency characteristic analysis module identifies key factors affecting energy efficiency, guiding energy efficiency control; the energy efficiency diagnosis and evaluation module clarifies the problems to be solved and their value, providing a basis for decision-making; and the energy efficiency strategy design module formulates specific strategies that can effectively improve the energy efficiency of UHV equipment, bringing significant energy-saving potential, economic benefits, and environmental benefits, while simultaneously improving the stability and reliability of equipment operation. Attached Figure Description

[0019] Figure 1 Overall structural diagram of the intelligent energy efficiency control system for ultra-high voltage equipment according to an embodiment of the present invention;

[0020] Figure 2 Flowchart of energy efficiency data analysis for ultra-high voltage equipment according to an embodiment of the present invention;

[0021] Figure 3The present invention provides a reference example diagram for the design of energy efficiency control strategies for ultra-high voltage equipment. Detailed Implementation

[0022] The specific implementation methods of this application will be further described in detail below with reference to the accompanying drawings and embodiments.

[0023] Example 1:

[0024] On the one hand, this invention provides an intelligent energy efficiency control system for ultra-high voltage equipment based on big data analysis, such as... Figure 1 As shown, it includes: an energy efficiency data integration module, an energy efficiency feature analysis module, an energy efficiency diagnosis and evaluation module, and an energy efficiency strategy design module. The energy efficiency data integration module collects multi-source heterogeneous energy efficiency data from ultra-high voltage (UHV) equipment, and cleans, denoises, standardizes the format, and handles missing values ​​to obtain a preprocessed dataset. The energy efficiency feature analysis module extracts key energy efficiency features from the preprocessed dataset and analyzes the correlation between the energy efficiency of UHV equipment and various factors. The energy efficiency diagnosis and evaluation module evaluates the potential improvement value of identified energy efficiency bottlenecks. The energy efficiency strategy design module designs energy efficiency control strategies and applies them to the operation and management of UHV equipment.

[0025] The energy efficiency data integration module is the starting point of the system's data flow, responsible for the centralized collection and preprocessing of multi-source heterogeneous energy efficiency data. This module collects multi-source heterogeneous energy efficiency data from ultra-high voltage equipment data sources, preprocesses the data to remove incomplete, inaccurate, and noisy useless data, and outputs the data in a unified format. This solves the problems of inconsistent energy efficiency data formats, inconsistent data standards, and uneven data quality from ultra-high voltage equipment, achieving one of the innovations of this invention. The preprocessed data is then output to the energy efficiency characteristic analysis module in a unified format, laying a solid data foundation for the entire intelligent energy efficiency control system and improving the accuracy and reliability of subsequent analysis.

[0026] The energy efficiency characteristic analysis module is the core analysis engine of the system, responsible for extracting energy efficiency insights from massive amounts of data. This module utilizes big data analytics to perform in-depth analysis of pre-processed data, extracting key characteristics reflecting the energy efficiency of ultra-high voltage equipment. Combining existing metrology models and artificial intelligence models, it analyzes the correlation between equipment energy efficiency and operating conditions, environmental factors, equipment aging, and maintenance history, uncovering potential factors affecting equipment energy efficiency. This reveals the underlying causes and potential patterns affecting the energy efficiency of ultra-high voltage equipment, providing a scientific basis for accurately identifying energy efficiency bottlenecks.

[0027] The energy efficiency diagnosis and assessment module is the system's decision support center, responsible for locating and quantifying the value of energy efficiency bottlenecks. Based on the potential factors identified by the energy efficiency characteristic analysis module, this module identifies energy efficiency problems leading to low energy efficiency in ultra-high voltage equipment. These energy efficiency problems are the energy efficiency bottlenecks of the ultra-high voltage equipment, specifically including key links, specific equipment, and operating modes in the operation of the equipment. For the identified energy efficiency problems, a quantitative value assessment report is generated by comparing them with a set baseline, considering energy-saving potential, economic benefits, and environmental benefits. This provides clear value guidance and reference for management decisions and strategy formulation, achieving the second innovation of this invention.

[0028] The energy efficiency strategy design module is the final output for realizing the system's value, responsible for transforming data analysis results into practical action plans. Based on identified energy efficiency bottlenecks and value assessment reports, this module, combined with artificial intelligence optimization algorithms, designs energy efficiency control strategies, thereby realizing the value of energy efficiency data and guiding operation and management departments to make precise adjustments and optimizations. This achieves intelligent energy efficiency control of ultra-high voltage equipment, realizing the third innovation of this invention.

[0029] The energy efficiency control strategy, based on the control strategy proposed by the energy efficiency strategy design module, solves the energy efficiency bottleneck problem, optimizes the operating status of the equipment, fully leverages the value of energy efficiency data, and achieves the core objectives of improving the energy efficiency of ultra-high voltage equipment, tapping energy-saving potential, and creating comprehensive benefits.

[0030] Example 2:

[0031] This embodiment specifically proposes an energy efficiency data integration module. In this embodiment, the module mainly includes data acquisition and data preprocessing, wherein the overall data analysis process is as follows: Figure 2 As shown.

[0032] Data acquisition in this embodiment involves directly collecting data from sensors and interfacing with data interfaces of various modules. Raw data related to equipment energy efficiency is collected from sensors, operation monitoring systems, environmental monitoring systems, equipment ledgers, maintenance records, and energy consumption metering systems within the ultra-high voltage equipment. Data acquisition supports both real-time and timed acquisition modes. Real-time acquisition provides timely dynamic energy efficiency data during equipment operation, while timed acquisition collects data at set time intervals. The collected data includes equipment voltage, current, power, temperature, humidity, operating time, maintenance records, and energy consumption.

[0033] Data preprocessing in this embodiment: A series of processing operations are performed on the collected multi-source heterogeneous energy efficiency data to obtain high-quality data. The main steps of this module are as follows:

[0034] Step S1: Data cleaning stage, remove noise and duplicate data from the data, delete invalid data, perform validity checks on the data, and report data quality issues.

[0035] Step S2, the format unification stage, uses ETL, Python tools, as well as natural language processing, computer vision, and convolutional neural network technologies to convert multi-source heterogeneous and unstructured data into structured data in a unified format, unifying the units and expression forms of the data.

[0036] Step S3: Missing Value Handling Stage. For missing values ​​in the data, appropriate methods are used based on the data characteristics, such as mean imputation, median imputation, or imputation based on adjacent data interpolation. Data with excessive missing values ​​and low importance are deleted. The processed data is then stored in the cloud to prepare for subsequent analysis.

[0037] This embodiment specifically proposes an energy efficiency feature analysis module. This module mainly includes feature extraction and correlation analysis.

[0038] Feature extraction in this embodiment involves extracting energy consumption per unit time and energy consumption fluctuation coefficient from power and operating time; and extracting load rate and efficiency from equipment operating parameters. These key features concisely and effectively reflect the energy efficiency of ultra-high voltage equipment. Based on a long short-term memory neural network model, an XGBoost model, and a convergence model, the temporal evolution trend, periodic characteristics, and convergence patterns of ultra-high voltage equipment energy efficiency data, such as energy consumption per unit time, energy consumption fluctuation coefficient, load rate, and efficiency, are analyzed.

[0039] The correlation analysis in this embodiment employs a multiple linear regression model to analyze the linear impact of operating conditions (such as load size and operating frequency), environmental factors (such as ambient temperature, humidity, and air pressure), equipment aging (such as equipment service life and cumulative operating time), and maintenance history (such as maintenance frequency, maintenance content, and last maintenance time) on the energy efficiency of ultra-high voltage equipment. Based on the significance test results, linear factors are identified. Support vector machines and random forest models are then used to capture the nonlinear relationships between other nonlinear factors and the energy efficiency of ultra-high voltage equipment.

[0040] This embodiment specifically proposes an energy efficiency diagnosis and evaluation module, which mainly includes bottleneck identification and value assessment.

[0041] Bottleneck identification in this embodiment: Based on the time evolution trend, periodicity characteristics, and convergence law obtained from the energy efficiency characteristic analysis module, comparative analysis and anomaly detection methods are adopted to identify the energy efficiency bottlenecks that lead to low energy efficiency of ultra-high voltage equipment, starting from key links, specific equipment, and operating modes. When it is found that the energy consumption of a certain operating link, operating equipment, or operating mode is significantly higher than its baseline and does not match its load, it can be identified as an energy efficiency bottleneck.

[0042] The value assessment in this embodiment is as follows: For the identified energy efficiency bottlenecks, based on operating data such as load rate, voltage, current, and operating time, as well as environmental data such as temperature, humidity, and air pressure, an energy efficiency model is used to conduct simulations to calculate the energy-saving potential of the ultra-high voltage equipment (such as the expected reduction in energy consumption); combined with the equipment's operating costs, energy prices, and environmental policies, its economic benefits (such as annual energy cost savings) are calculated; based on the ultra-high voltage equipment's emission factors, emission standards, and energy-saving potential, its environmental benefits (such as the reduction in carbon dioxide emissions) are estimated, thereby forming a value assessment report.

[0043] This embodiment proposes an energy efficiency strategy design module, which mainly includes algorithm selection and strategy generation.

[0044] In this embodiment, the algorithm selection is as follows: Based on the characteristics of the energy efficiency bottleneck and the optimization objective, a suitable optimization algorithm is chosen. For continuous optimization problems, particle swarm optimization and genetic algorithms are selected; for discrete decision problems, simulated annealing and tabu search algorithms are selected. Simultaneously, the parameters of the selected algorithms are set and optimized to improve their performance and solution accuracy.

[0045] The strategy generation in this embodiment is as follows: Figure 3 As shown: Based on the energy efficiency bottleneck identification results (such as key links, specific equipment, and operational stages), strategy design constraints (such as equipment safe operating range and load limits) are determined. Based on the value of energy efficiency data (such as energy-saving potential, economic benefits, and environmental benefits), optimization objectives (such as minimizing energy consumption and maximizing efficiency) are clarified. Using the constraints and optimization objectives as strategy input elements, and employing the selected optimization algorithm, an energy efficiency control strategy is designed, encompassing adjustment measures, implementation steps, and expected effects. For energy efficiency bottlenecks caused by unreasonable load allocation, a load allocation strategy is designed to adjust the load ratio of each piece of equipment; for energy efficiency bottlenecks caused by improper operating parameter settings, a parameter optimization strategy is designed to determine the optimal operating parameter values. This improves the energy-saving potential, economic benefits, and environmental benefits of ultra-high voltage equipment, providing a reference for ultra-high voltage equipment operation and management departments.

[0046] Example 3:

[0047] This embodiment proposes a computer-readable storage medium that stores executable instructions. When these instructions are executed, if they are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0048] The computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the various embodiments of this application.

[0049] The aforementioned storage media include: flash memory, hard disk, multimedia card, card-type memory (e.g., SD (Secure Digital Memory Card) or DX (Memory Data Register, MDR) memory, random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, APP (Application) application store, and other media capable of storing program verification codes, on which computer programs are stored. When the computer programs are executed by a processor, they can implement the various steps of the embodiments.

[0050] Example 4:

[0051] This embodiment proposes a computer program product, including a computer program or instructions, which, when executed by a processor, implement the method of the embodiment.

[0052] Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a computer program product.

[0053] The various embodiments in this application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0054] The scope of protection of this application is not limited to the embodiments described above. Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from the scope and spirit of this disclosure. If such modifications and variations fall within the scope of the methods disclosed herein and their equivalents, then the intent of this disclosure also includes such modifications and variations.

Claims

1. An intelligent energy efficiency control system for ultra-high voltage equipment based on big data analysis, characterized in that, include: Energy efficiency data integration module, energy efficiency characteristic analysis module, energy efficiency diagnosis and evaluation module, and energy efficiency strategy design module; The energy efficiency data integration module is used to collect multi-source heterogeneous energy efficiency data from ultra-high voltage equipment data sources, preprocess the multi-source heterogeneous energy efficiency data, output the data in a unified format, and output the preprocessed data to the energy efficiency characteristic analysis module. The energy efficiency feature analysis module uses big data analysis technology to perform in-depth analysis on the pre-processed data and extract key features that can reflect the energy efficiency of ultra-high voltage equipment. Combining existing metering models and artificial intelligence models, it analyzes the correlation between equipment energy efficiency and operating conditions, environmental factors, equipment aging degree, and maintenance history, and uncovers potential factors that affect equipment energy efficiency. The energy efficiency diagnosis and evaluation module identifies potential factors derived from the energy efficiency characteristic analysis module, and identifies energy efficiency problems that lead to low energy efficiency of ultra-high voltage equipment. Energy efficiency problems are the energy efficiency bottlenecks of ultra-high voltage equipment, specifically including key links, specific equipment and operating modes in the operation of ultra-high voltage equipment. For the identified energy efficiency problems, a quantitative value assessment report is generated based on the energy-saving potential, economic benefits and environmental benefits by comparing them with the set baseline. The energy efficiency strategy design module designs an energy efficiency control strategy based on the identified energy efficiency bottlenecks and value assessment reports, combined with artificial intelligence optimization algorithms, to achieve intelligent energy efficiency control of ultra-high voltage equipment. The energy efficiency control strategy, based on the control strategy proposed by the energy efficiency strategy design module, solves the energy efficiency bottleneck problem and optimizes the operating status of the equipment.

2. The intelligent energy efficiency control system for ultra-high voltage equipment based on big data analysis according to claim 1, characterized in that, The energy efficiency data integration module collects multi-source heterogeneous energy efficiency data from ultra-high voltage equipment, and cleans, denoises, standardizes the format, and handles missing values ​​in the collected multi-source heterogeneous energy efficiency data to obtain a preprocessed dataset. The energy efficiency feature analysis module extracts key energy efficiency features from the preprocessed dataset and analyzes the correlation between the energy efficiency of ultra-high voltage equipment and various factors. The energy efficiency diagnosis and evaluation module evaluates the potential improvement value based on the identified energy efficiency bottlenecks. The energy efficiency strategy design module designs energy efficiency control strategies and applies them to the operation and management of ultra-high voltage equipment.

3. The intelligent energy efficiency control system for ultra-high voltage equipment based on big data analysis according to claim 1, characterized in that, The energy efficiency feature analysis module comprises two parts: feature extraction and correlation analysis. Specifically, feature extraction involves extracting unit-time energy consumption and energy consumption fluctuation coefficient from power and operating time; extracting equipment load rate and efficiency from equipment operating parameters; and mining the temporal evolution trend, periodic characteristics, and convergence laws of unit-time energy consumption, energy consumption fluctuation coefficient, load rate, and efficiency based on existing long short-term memory neural network models, XGBoost models, and convergence models. The correlation analysis involves using a multiple linear regression model to analyze the linear impact of operating conditions, environmental factors, equipment aging, and maintenance history on the energy efficiency of ultra-high voltage equipment, identifying linear factors based on significance test results, and using support vector machines and random forest models to capture the nonlinear relationship between other nonlinear factors and the energy efficiency of ultra-high voltage equipment.

4. The intelligent energy efficiency control system for ultra-high voltage equipment based on big data analysis according to claim 1, characterized in that, The energy efficiency diagnosis and assessment module comprises two parts: bottleneck identification and value assessment. Bottleneck identification specifically involves: based on the time evolution trend, periodic characteristics, and convergence patterns derived from the energy efficiency characteristic analysis module, comparative analysis and anomaly detection methods are used to identify energy efficiency bottlenecks leading to low energy efficiency in ultra-high voltage equipment, starting from key links, specific equipment, and operating modes. When the energy consumption of a certain operating link, operating equipment, or operating mode is found to be higher than the corresponding set baseline and mismatched with the corresponding load, the corresponding link is identified as an energy efficiency bottleneck. Value assessment specifically involves: for the identified energy efficiency bottlenecks, simulations are performed based on operating data such as load rate, voltage, current, and operating time, as well as environmental data such as temperature, humidity, and air pressure, to calculate the energy-saving potential of the ultra-high voltage equipment; combined with the equipment's operating costs, energy prices, and environmental policies, the economic benefits of the equipment are calculated; and based on the ultra-high voltage equipment's emission factors, emission standards, and energy-saving potential, the environmental benefits of the equipment are estimated, thereby generating a value assessment report.

5. The intelligent energy efficiency control system for ultra-high voltage equipment based on big data analysis according to claim 1, characterized in that, The energy efficiency strategy design module comprises two parts: algorithm selection and strategy generation. Algorithm selection specifically involves choosing a suitable optimization algorithm based on the characteristics of the energy efficiency bottleneck and the optimization objective: for continuous optimization problems, particle swarm optimization and genetic algorithms are used; for discrete decision problems, simulated annealing and tabu search algorithms are used. Simultaneously, the parameters of the selected algorithm are set and optimized. Strategy generation specifically involves determining strategy design constraints based on the energy efficiency bottleneck identification results, clarifying the optimization objective based on the value of energy efficiency data, using the constraints and optimization objective as strategy input elements, and designing an energy efficiency control strategy including adjustment measures, implementation steps, and expected effects using the selected optimization algorithm. For energy efficiency bottlenecks caused by unreasonable load allocation, design load allocation strategies and adjust the load ratio of each device; For energy efficiency bottlenecks caused by improper operating parameter settings, design parameter optimization strategies to determine the optimal operating parameter values.

6. A computer-readable storage medium, characterized in that, The device stores executable instructions that, when executed, cause the processor to perform the intelligent energy efficiency control system for ultra-high voltage equipment as described in any one of claims 1-5.

7. A computer program product, characterized in that, Includes a computer program or instructions, which are executed by a processor as described in any one of claims 1-5, for the intelligent energy efficiency control system for ultra-high voltage equipment.

Images