Energy consumption grading metering loss analysis method and system based on energy consumption trend recursive algorithm

Through the energy consumption grading measurement loss analysis method based on the energy consumption trend recursive algorithm, the problem of lack of in-depth analysis and grading processing of energy consumption metering methods in the existing technology is solved, and the accurate classification and early warning of energy consumption at all levels is achieved, which improves the Efficiency and effectiveness of energy management.

CN119048285APending Publication Date: 2024-11-29SHENZHEN SIBIYUN TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411550674.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-01
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing energy consumption measurement methods lack in-depth analysis and hierarchical processing, making it difficult to accurately grasp the changing trends of energy consumption and the specific energy consumption situation, and are unable to position the specific links and reasons of energy consumption in a timely manner, and it is difficult to achieve adaptability to energy consumption at all levels. Accurate grading.

Method used

The energy consumption hierarchical measurement loss analysis method based on the energy consumption trend recursive algorithm is adopted. The energy consumption data is carried out through real-time acquisition and trend analysis of energy consumption data at each level, combined with the preset energy consumption model structure and energy consumption change trend data. Grade processing, calculate stability and sustainability, and formulate early warning plans.

Benefits of technology

Accurate classification of adaptability to energy consumption at all levels is achieved, timely detection of energy consumption abnormalities, improving the efficiency and effectiveness of energy management, and avoiding further deterioration of energy waste and equipment failure.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048285A_ABST
    Figure CN119048285A_ABST
Patent Text Reader

Abstract

The invention provides an energy consumption grading metering loss analysis method and system based on an energy consumption trend recursive algorithm, and the method comprises the steps: carrying out the real-time collection of all levels of energy consumption data, and obtaining initial energy consumption data; performing trend analysis on the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; performing grading processing on the initial energy consumption data according to a preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different grades; performing energy consumption metering on the energy consumption data of each level to obtain an energy consumption metering value of each level; comparing each level of energy consumption metering value with a corresponding preset standard value, and if the energy consumption metering value exceeds a preset standard value range, analyzing the stability and continuity of each level of energy consumption change in combination with the energy consumption change trend data; and making a corresponding early warning scheme according to the analyzed stability and continuity. According to the invention, the defect that adaptive accurate grading cannot be carried out on each level of energy consumption at present is overcome.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an energy consumption classification metering loss analysis method and system based on an energy consumption trend recursive algorithm. Background Art

[0002] In various fields such as industrial production, commercial operations and residents' lives, accurate measurement and analysis of energy consumption is crucial to reducing energy costs and achieving sustainable development.

[0003] Traditional energy consumption measurement methods are often relatively simple and lack in-depth analysis and hierarchical processing of energy consumption data. Usually, they simply record the amount of energy used, but cannot accurately grasp the changing trend of energy consumption and the specific situation of energy consumption at different levels. Moreover, when faced with complex energy consumption systems, it is difficult to quickly locate the specific links and causes of energy consumption loss, resulting in the inability to take effective prevention and improvement measures in a timely manner.

[0004] In addition, existing energy consumption management technologies find it difficult to accurately predict energy consumption trends when analyzing energy consumption, and when performing graded metering, they usually only use a general structure for graded processing, which cannot reflect the current actual changes, and therefore cannot adaptively and accurately grade energy consumption at each level. Summary of the invention

[0005] The main purpose of the present invention is to provide an energy consumption classification metering loss analysis method and system based on an energy consumption trend recursive algorithm, aiming to overcome the current defect that it is impossible to adaptively and accurately classify each level of energy consumption.

[0006] To achieve the above object, the present invention provides an energy consumption classification metering loss analysis method based on energy consumption trend recursive algorithm, comprising the following steps: Collect energy consumption data at all levels in real time to obtain initial energy consumption data; perform trend analysis on the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; The initial energy consumption data is graded according to a preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the classification criteria for each level; Energy consumption data at each level is measured separately to obtain energy consumption measurement values ​​at each level; Compare the energy consumption measurement values ​​at each level with the corresponding preset standard values. If they exceed the preset standard value range, analyze the stability and sustainability of the energy consumption changes at each level in combination with the energy consumption change trend data; Make corresponding early warning plans based on the analyzed stability and sustainability.

[0007] Furthermore, the corresponding early warning plan is made according to the analyzed stability and sustainability, including: If the energy consumption trend is increasing and the loss exceeds the preset range, an in-depth analysis of the equipment operating parameters is performed to determine whether there is equipment aging; If the equipment is not aged, the energy usage behavior data is analyzed to determine whether there are unreasonable energy usage factors and obtain loss analysis results; When the loss analysis result exceeds a preset threshold range, an early warning prompt is issued.

[0008] Furthermore, the initial energy consumption data is graded according to the preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels, including: Analyze various parameters in the preset energy consumption model structure to obtain basic classification standards; Performing statistical analysis on the energy consumption change trend data to determine trend influencing factors; The basic classification standard is combined with the trend influencing factor, and the initial energy consumption data is classified to obtain energy consumption data corresponding to different levels.

[0009] Furthermore, the statistical analysis of the energy consumption change trend data to determine the trend influencing factors includes: Calculate the mean and standard deviation of the energy consumption change trend data to obtain statistical characteristics of the trend data; The statistical features of the trend data are input into a pre-trained neural network model for calculation, and the trend influencing factors are output.

[0010] Furthermore, the analysis of the stability and sustainability of energy consumption changes at all levels in combination with the energy consumption change trend data includes: Calculate the variance of energy consumption trend data, and determine the stability of energy consumption changes at all levels based on the variance calculation results; The slope changes of the energy consumption change trend data at multiple consecutive time points are analyzed, and the continuity of the energy consumption changes at each level is determined based on the slope changes.

[0011] Furthermore, after making the corresponding early warning plan, it also includes: Add the initial energy consumption data, energy consumption change trend data, and energy consumption measurement values ​​at all levels to a data table to obtain an energy consumption data table; Generate an identification value based on the energy consumption change trend data and the energy consumption measurement values ​​at each level, and identify the energy consumption data table based on the identification value; generating a transmission key based on the initial energy consumption data and the identification value; After the energy consumption data table is encrypted based on the transmission key, it is transmitted to the energy consumption management terminal.

[0012] Further, the generating a transmission key based on the initial energy consumption data and the identification value includes: Performing character cleaning on the initial energy consumption data to obtain a cleaned data string; wherein the character cleaning includes removing specified characters from the initial energy consumption data; Obtain a standard binary tree template pre-stored in a database, and add the characters in the cleaned data string to each node of the standard binary tree template in sequence to obtain a character binary tree; The identification value is segmented to obtain a plurality of digits; wherein the identification value includes a plurality of numeric characters; Based on the multiple numbers, a graphic is generated according to a preset rule; superimposing the graphic onto a designated position of the character binary tree, and performing geometric stretching or scaling on the graphic so that the graphic and the character binary tree satisfy a preset positional relationship; After the graphic is stretched or scaled proportionally, a character located in the graphic is obtained in the character binary tree as a target character; Based on the target character, the transmission key is generated using a preset rule.

[0013] The present invention also provides an energy consumption classification metering loss analysis system based on an energy consumption trend recursive algorithm, comprising: An analysis unit is used to collect energy consumption data at all levels in real time to obtain initial energy consumption data; perform trend analysis on the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; A grading unit, used to grade the initial energy consumption data according to a preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the classification criteria for each level; The metering unit is used to measure the energy consumption data of each level and obtain the energy consumption measurement value of each level; A comparison unit is used to compare the energy consumption measurement values ​​at each level with the corresponding preset standard values. If the preset standard value range is exceeded, the stability and sustainability of the energy consumption changes at each level are analyzed in combination with the energy consumption change trend data; The early warning unit is used to make corresponding early warning plans based on the analyzed stability and continuity.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0016] The energy consumption hierarchical metering loss analysis method and system based on the energy consumption trend recursive algorithm provided by the present invention include: real-time collection of energy consumption data at all levels to obtain initial energy consumption data; trend analysis of the initial energy consumption data based on the energy consumption trend recursive algorithm to obtain energy consumption change trend data; hierarchical processing of the initial energy consumption data according to the preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the division standards of each level; energy consumption metering of the energy consumption data of each level is performed respectively to obtain energy consumption metering values ​​at each level; comparing the energy consumption metering values ​​at each level with the corresponding preset standard values, if they exceed the preset standard value range, then combining the energy consumption change trend data to analyze the stability and continuity of energy consumption changes at each level; making corresponding early warning plans according to the analyzed stability and continuity. In the present invention, by analyzing the energy consumption change trend data and hierarchical processing of the initial energy consumption data in combination with the preset energy consumption model structure, the grading is made more reasonable and in line with the current energy consumption data changes; it is convenient for subsequent hierarchical metering and then early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of an energy consumption classification measurement loss analysis method based on an energy consumption trend recursive algorithm in one embodiment of the present invention; Figure 2 It is a structural block diagram of an energy consumption classification metering loss analysis system based on an energy consumption trend recursive algorithm in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The implementation, functional features and advantages of the present invention will be further described in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] Reference Figure 1 In one embodiment of the present invention, a method for analyzing energy consumption loss by level measurement based on an energy consumption trend recursive algorithm is provided, comprising the following steps: Step S1, real-time collection of energy consumption data at all levels to obtain initial energy consumption data; trend analysis of the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; Step S2, performing classification processing on the initial energy consumption data according to the preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the classification criteria for each level; Step S3, respectively measuring the energy consumption data at each level to obtain energy consumption measurement values ​​at each level; Step S4, comparing the energy consumption measurement values ​​at each level with the corresponding preset standard values. If the values ​​exceed the preset standard value range, the stability and sustainability of the energy consumption changes at each level are analyzed in combination with the energy consumption change trend data; Step S5, making a corresponding early warning plan based on the analyzed stability and continuity.

[0021] In this embodiment, as described in step S1 above, sensors and data acquisition systems are first used to conduct all-round, real-time monitoring and data collection of energy usage at different levels. For example, in industrial production scenarios, the energy consumption of electricity, water, heat, and other energy in each production workshop and equipment is monitored; in commercial buildings, the power consumption and air conditioning energy consumption of different floors and functional areas are collected; in home environments, the energy consumption of various electrical appliances is recorded in real time. The collected data should include detailed information such as the type of energy, usage time, and usage amount, so that accurate analysis and processing can be performed later. Through real-time collection, the dynamic changes in energy use can be grasped in a timely manner, providing the latest data support for subsequent trend analysis and management decisions.

[0022] The above energy consumption trend recursive algorithm is a powerful algorithm specifically used to analyze time series data. It can accurately predict the trend of future energy consumption changes by continuously iterating and analyzing historical energy consumption data. The algorithm takes into account the impact of multiple factors on energy consumption, such as seasonal changes, changes in equipment operating status, fluctuations in production activities, etc. For example, in terms of seasonal changes, air conditioning power consumption usually increases significantly in summer. The algorithm predicts the energy consumption trend of the current summer based on the changing pattern of historical summer energy consumption data. In terms of equipment operating status, if a certain device fails or ages, energy consumption will change abnormally. The algorithm can capture this change trend in time and issue an early warning. Through the trend analysis of the initial energy consumption data, the energy consumption change trend data obtained can provide an important reference for subsequent hierarchical processing and decision-making.

[0023] As described in step S2 above, the preset energy consumption model structure is pre-designed according to different application scenarios and requirements. For example, in industrial production, it can be graded according to different production workshops, production lines, equipment types, etc.; in commercial buildings, it can be graded according to floors, functional areas, tenants, etc.; in urban energy management, it can be graded according to different regions, industries, etc. The above energy consumption change trend data plays a key role in assisting in determining the classification standards of each level in the hierarchical processing. If the energy consumption change trend of a certain area or equipment shows a rapid growth, it means that its energy consumption may have changed significantly, and it needs to be divided into a higher energy consumption level for stricter monitoring and management. For example, if the energy consumption of a production workshop continues to rise in the near future, and the rising trend is significantly higher than that of other workshops, then the energy consumption level of the workshop can be increased so that managers can pay more attention to the energy use of the workshop and take corresponding energy-saving measures. Through hierarchical processing, complex energy consumption data can be classified and managed, making energy management more refined and efficient.

[0024] As described in step S3 above, for energy consumption data of different levels, corresponding metering equipment and methods are used to accurately measure energy consumption. For example, for the measurement of electric energy, a high-precision electric energy meter can be used; for the measurement of water energy, a water meter or flow meter can be used; for the measurement of thermal energy, a calorimeter can be used. During the metering process, the accuracy and reliability of the metering equipment must be ensured, and calibration and maintenance must be performed regularly. At the same time, the metering data can also be calibrated and corrected in combination with data analysis technology to improve the accuracy of the measurement. For example, if it is found that the reading of a certain metering device is significantly different from the reading of other related devices, the possible reasons can be found through data analysis and corresponding adjustments can be made. After measuring the energy consumption data at each level, the energy consumption measurement values ​​obtained at each level can intuitively reflect the specific situation of energy consumption at each level, and provide quantitative data support for subsequent comparative analysis and management decisions.

[0025] As described in step S4 above, the preset standard value is set according to historical data, industry standards or energy-saving targets, and is used to determine whether the energy consumption is within a reasonable range. For example, in industrial production, the preset standard value can be set according to the average energy consumption level of enterprises of the same type or relevant national standards; in commercial buildings, reasonable energy consumption standards can be set according to factors such as the type, area, and use function of the building. By comparing the energy consumption metering values ​​at all levels with the corresponding preset standard values, abnormal energy consumption can be discovered in time. If the energy consumption metering value of a certain level exceeds the preset standard value range, it means that there may be problems such as energy waste, equipment failure or unreasonable energy use at this level. At this time, combined with the energy consumption change trend data for analysis, the stability and sustainability of energy consumption changes can be further understood. If the energy consumption change trend is unstable, such as large fluctuations and frequent changes, it means that there may be problems such as unstable equipment operation and irregular energy use behavior; if the energy consumption change trend is continuously rising or falling, it means that there may be long-term influencing factors such as equipment aging and production process changes. For example, if the energy consumption measurement value of a production workshop exceeds the preset standard value range for several consecutive months, and the energy consumption trend shows a continuous upward trend, then through further analysis of equipment operation data, production plans and other factors, the specific reasons for the increase in energy consumption can be found out, and corresponding measures can be taken to improve it.

[0026] As described in step S5 above, according to the analysis results of the stability and continuity of energy consumption changes at all levels, a corresponding early warning plan is formulated. The early warning plan can be customized according to different situations to ensure that relevant personnel can be reminded to take measures in a timely and effective manner. For example, if the energy consumption change at a certain level is unstable and exceeds the preset standard value range by a large margin, the management personnel can be notified immediately by SMS, email, sound and light alarm, etc., so that they can take timely measures to make adjustments; if the energy consumption change at a certain level shows a continuous upward trend, but has not exceeded the preset standard value range by a large margin, the management personnel can be reminded to pay attention to the energy usage at this level through regular reports, early warning prompts, etc., and take preventive measures in advance. The above early warning plan can also provide corresponding solutions and suggestions in combination with historical data and experience. For example, if the energy consumption of a certain device continues to rise, it can be recommended to overhaul, replace or optimize the operating parameters of the device; if the energy consumption behavior in a certain area is irregular, it can be recommended to strengthen energy management and carry out energy-saving training. In this embodiment, by analyzing the energy consumption change trend data and combining the preset energy consumption model structure to perform hierarchical processing on the initial energy consumption data, the classification is more reasonable and in line with the current energy consumption data changes; it is convenient for subsequent hierarchical measurement and then early warning. Through timely and effective early warning plans, further deterioration of energy waste and equipment failure can be avoided, and the efficiency and effectiveness of energy management can be improved.

[0027] In one embodiment, making a corresponding early warning plan based on the analyzed stability and continuity includes: If the energy consumption trend is increasing and the loss exceeds the preset range, an in-depth analysis of the equipment operating parameters is performed to determine whether there is equipment aging; If the equipment is not aged, the energy usage behavior data is analyzed to determine whether there are unreasonable energy usage factors and obtain loss analysis results; When the loss analysis result exceeds a preset threshold range, an early warning prompt is issued.

[0028] In this embodiment, first, the changes in the energy consumption metering values ​​at all levels are continuously monitored. When it is found that the energy consumption change trend is in an upward state, it means that the energy consumption is showing a trend of continuous increase over a period of time. At the same time, the actual energy consumption is compared with the preset standard energy consumption to calculate the loss value. If the loss exceeds the preset range, it means that there may be a problem with the energy utilization efficiency, and the cause needs to be further analyzed. At this time, various operating parameters of the equipment are collected, such as the operating time, operating temperature, pressure, speed, etc. of the equipment. The above parameters can reflect the working status and performance of the equipment. Analyze the change trend of the equipment operating parameters. For example, if the operating temperature of the equipment continues to rise, it may mean that there is a problem with the cooling system of the equipment, or that there is wear and tear on the internal components of the equipment, resulting in increased heat. Compare the operating parameters of the equipment in different time periods to determine whether there are abnormal changes. If the operating parameters of the equipment have changed significantly compared with the historical data, it may indicate that the equipment has aged or failed. Through in-depth analysis of the equipment operating parameters, it can be preliminarily determined whether the equipment has aged. If the operating parameters of the equipment show characteristics related to aging, such as performance degradation, increased failure rate, etc., it can be determined that equipment aging is a possible cause of increased energy consumption and loss exceeding the preset range.

[0029] When it is determined through in-depth analysis of the equipment operating parameters that the equipment is not aging, it is necessary to turn to analyzing the energy consumption behavior data to find other reasons that may cause energy consumption to rise and loss to exceed the preset range. Specifically, energy consumption behavior data can be collected, including the equipment's usage time, usage frequency, usage mode, etc. For example, some equipment is still turned on during non-working hours, or the equipment has unreasonable behaviors such as excessive use, frequent start and stop during use, etc.

[0030] Then, analyze the relationship between energy consumption behavior data and energy consumption changes. For example, if the energy consumption of a certain area suddenly increases during a specific time period, by analyzing the energy consumption behavior data, it is found that a large number of devices are running at the same time during this period, which may be caused by unreasonable energy consumption.

[0031] Then, determine whether there are unreasonable energy usage factors. By analyzing the energy usage behavior data, determine whether there are factors such as energy waste and unreasonable equipment usage. For example, if it is found that some equipment is still running at high power under low load conditions, or the power of the equipment is not turned off in time after use, these are all unreasonable energy usage factors.

[0032] Finally, the loss analysis results are obtained. The specific reasons for the increase in energy consumption and the loss exceeding the preset range are determined by combining the analysis results of the equipment operating parameters and energy consumption behavior data, and the loss analysis results are obtained. The warning threshold range of the loss analysis results is pre-set. This threshold range can be adjusted according to actual conditions, such as according to industry standards, the company's energy-saving goals or historical data.

[0033] When the loss analysis results exceed the preset threshold range, it means that the energy consumption problem is serious and timely intervention measures are needed. Early warnings can be provided in a variety of ways, such as sending text messages or emails to notify relevant management personnel, displaying early warning information in the energy management system, or triggering sound and light alarms. Early warnings should contain key information, such as the level of abnormal energy consumption, specific problem descriptions (such as equipment aging, unreasonable energy use, etc.), and recommended measures. This allows relevant personnel to quickly understand the severity and specific circumstances of the problem and take appropriate measures to deal with it in a timely manner.

[0034] In one embodiment, the initial energy consumption data is graded according to the preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels, including: Analyze various parameters in the preset energy consumption model structure to obtain basic classification standards; Performing statistical analysis on the energy consumption change trend data to determine trend influencing factors; The basic classification standard is combined with the trend influencing factor, and the initial energy consumption data is classified to obtain energy consumption data corresponding to different levels.

[0035] In this embodiment, the above-mentioned preset energy consumption model structure is designed according to specific application scenarios and requirements, and it includes multiple parameters that can reflect different aspects of energy consumption. For example, in an industrial production scenario, the energy consumption model structure may include parameters such as equipment type, production process, and working hours; in a commercial building, it may include parameters such as floor, functional area, and equipment power. Different combinations of the above parameters can be used to distinguish different energy consumption levels.

[0036] Conduct in-depth analysis of each parameter in the energy consumption model structure to determine the degree of influence of each parameter on energy consumption. For example, you can use historical data to statistically analyze the energy consumption differences of different types of equipment, or analyze the influence of different working hours on energy consumption. According to the degree of influence of the parameters, formulate basic classification standards. The basic classification standard can be a numerical range or a classification rule to preliminarily divide the initial energy consumption data into different levels. For example, energy consumption can be divided into three levels: high, medium, and low according to the power size of the equipment.

[0037] The above energy consumption change trend data is obtained by performing trend analysis on the initial energy consumption data, and reflects the change of energy consumption over time. For example, the energy consumption change trend data may include information such as the growth rate and fluctuation range of energy consumption.

[0038] Perform statistical analysis on the energy consumption trend data to extract key features. For example, you can calculate the mean, standard deviation, median and other statistics of the energy consumption trend data to understand the central trend and dispersion of energy consumption changes.

[0039] According to the statistical analysis results, the trend impact factor is determined. The trend impact factor is a value or an indicator used to measure the impact of the energy consumption trend on the classification process. For example, if the energy consumption trend shows a rapid growth, the trend impact factor can be set to a larger value to increase the sensitivity of the classification.

[0040] The basic classification standard and the trend influencing factor are combined to obtain a comprehensive classification standard. The combination method can be weighted summation, multiplication operation or other appropriate mathematical methods. For example, the equipment power parameter and the trend influencing factor in the basic classification standard can be weighted summed to obtain a new classification index for more accurate classification of the initial energy consumption data.

[0041] Finally, the initial energy consumption data is graded using a comprehensive grading standard. Specifically, each initial energy consumption data point is compared with the grading standard to determine its level. After grading, energy consumption data corresponding to different levels are obtained. These data can be used for subsequent energy consumption measurement, analysis, and early warning. For example, statistical analysis can be performed on energy consumption data of different levels to understand the characteristics and problems of energy consumption at different levels so as to take targeted energy-saving measures.

[0042] In one embodiment, the statistical analysis of the energy consumption change trend data to determine the trend influencing factor includes: Calculate the mean and standard deviation of the energy consumption change trend data to obtain statistical characteristics of the trend data; The statistical features of the trend data are input into a pre-trained neural network model for calculation, and the trend influencing factors are output.

[0043] In this embodiment, the energy consumption change trend data is obtained by performing trend analysis on the initial energy consumption data, which reflects the change of energy consumption over time. For example, the energy consumption change trend data may include information such as the growth rate and fluctuation range of energy consumption. These data are time series data, which record the change of energy consumption at different time points.

[0044] The mean is the arithmetic average of a set of data, which reflects the central tendency of the data. For energy consumption trend data, the mean is calculated by adding up the values ​​of all data points and then dividing by the total number of data points. The standard deviation is a measure of the degree of dispersion of a set of data, which reflects the degree of deviation of the data from the mean. For energy consumption trend data, the standard deviation is calculated by first calculating the difference between each data point and the mean, then adding up the squares of these differences, dividing by the total number of data points, and finally taking the square root.

[0045] The above neural network model is a machine learning tool that can establish a complex relationship between input and output by learning a large amount of data. In this embodiment, the neural network model is used to calculate the trend impact factor based on the statistical characteristics of the trend data. The trend impact factor is a numerical value that reflects the degree of influence of the energy consumption change trend on the energy consumption classification process. Through the calculation of the neural network model, the trend impact factor can be determined more accurately, thereby improving the accuracy of the energy consumption classification.

[0046] The above neural network model needs to be trained before use. The training process usually includes the following steps: Collect a large number of labeled energy consumption change trend data samples, which include trend data statistical features and corresponding trend influencing factors. Input the sample data into the neural network model, and adjust the parameters of the model so that the output of the model is as close to the labeled value in the sample as possible. Repeat this process until the performance of the model meets the expected requirements. The trained neural network model can accurately calculate the trend influencing factor based on the new trend data statistical features.

[0047] In one embodiment, the combining of the energy consumption change trend data to analyze the stability and sustainability of energy consumption changes at each level includes: Calculate the variance of energy consumption trend data, and determine the stability of energy consumption changes at all levels based on the variance calculation results; The slope changes of the energy consumption change trend data at multiple consecutive time points are analyzed, and the continuity of the energy consumption changes at each level is determined based on the slope changes.

[0048] In this embodiment, the variance is a measure of the degree of dispersion of a set of data, which reflects the average of the squares of the degree of deviation of the data from the mean. For the energy consumption change trend data, the method of calculating the variance is to first calculate the difference between each data point and the mean, then add the squares of these differences, and then divide by the total number of data points. The smaller the variance, the smaller the degree of deviation of the energy consumption change trend data from the mean, that is, the more stable the energy consumption change. Conversely, the larger the variance, the more unstable the energy consumption change. For example, if the variance is close to zero, it means that the energy consumption change trend data is very close to the mean, and the energy consumption changes at all levels are relatively stable; if the variance is large, it means that the energy consumption change trend data fluctuates greatly, and the energy consumption changes at all levels are unstable.

[0049] For energy consumption change trend data at multiple consecutive time points, the trend of energy consumption change can be analyzed by calculating the slope between two adjacent time points. The slope calculation formula is: slope = (energy consumption value at the next time point - energy consumption value at the previous time point) / (next time point - previous time point).

[0050] By analyzing the changes in the slope at multiple consecutive time points, we can understand whether the trend of energy consumption changes is continuous. If the slope changes slightly and tends to be stable, it means that the energy consumption change is continuous; if the slope changes greatly, it means that the energy consumption change is not continuous. For example, if the slopes at multiple consecutive time points fluctuate within a small range, it means that the energy consumption changes at all levels are continuous; if the slopes change greatly between different time points, it means that the energy consumption changes at all levels are not continuous.

[0051] In one embodiment, after making a corresponding early warning plan, the method further includes: Add the initial energy consumption data, energy consumption change trend data, and energy consumption measurement values ​​at all levels to a data table to obtain an energy consumption data table; Generate an identification value based on the energy consumption change trend data and the energy consumption measurement values ​​at each level, and identify the energy consumption data table based on the identification value; generating a transmission key based on the initial energy consumption data and the identification value; After the energy consumption data table is encrypted based on the transmission key, it is transmitted to the energy consumption management terminal.

[0052] In this embodiment, a data table structure is constructed to store and manage energy consumption related data. The above data table may contain multiple fields, corresponding to different types of data such as initial energy consumption data, energy consumption change trend data, energy consumption measurement values ​​at various levels, etc. The sorted initial energy consumption data, energy consumption change trend data, and energy consumption measurement values ​​at various levels are filled into the corresponding fields of the data table one by one. Ensure the accuracy and completeness of the data for subsequent analysis and processing. For example, the initial energy consumption value at a certain point in time, the corresponding energy consumption change trend analysis results, and the energy consumption measurement values ​​at this level are filled into the corresponding positions of the data table respectively.

[0053] Then, a unique identification value is generated by combining the energy consumption trend data and the energy consumption measurement values ​​at all levels through a preset algorithm. This identification value can reflect the characteristics and status of the current energy consumption data. For example, some key characteristics of the energy consumption trend data (such as trend direction, change amplitude, etc.) and statistical information of the energy consumption measurement values ​​at all levels (such as sum, average value, etc.) can be combined to generate an identification value through a hash algorithm or other encryption algorithm.

[0054] The energy consumption data table is identified using the generated identification value. The identification can be used as a unique label for the data table to facilitate identification and management during subsequent processing and transmission. For example, the identification value can be recorded in a specific field of the energy consumption data table, or the identification value can be used as part of the file name of the data table.

[0055] Furthermore, some key parts of the initial energy consumption data, such as the peak value and average value of energy consumption in a specific time period, and the previously generated identification value are selected as basic data for generating the transmission key.

[0056] A specific encryption algorithm is used to process the selected initial energy consumption data and identification value to generate a key for data transmission encryption. This key should have sufficient complexity and security to ensure the confidentiality of the energy consumption data during transmission. For example, a symmetric encryption algorithm can be used to mix and transform the initial energy consumption data and identification value to generate an encryption key.

[0057] Finally, the energy consumption data table is encrypted using the generated transmission key. Encryption can be done using symmetric encryption or asymmetric encryption to ensure that the data is not illegally stolen or tampered with during transmission. For example, using the AES symmetric encryption algorithm, each data field in the energy consumption data table is encrypted so that only the recipient with the correct key can decrypt and read the data.

[0058] The encrypted energy consumption data sheet is transmitted to the energy consumption management terminal through a secure communication channel. The above communication channel can be a dedicated network connection, an encrypted file transfer protocol, etc. to ensure the security and reliability of data transmission. For example, the encrypted energy consumption data sheet can be transmitted from the data acquisition device to the remote energy consumption management server using the HTTPS protocol.

[0059] After receiving the encrypted energy consumption data table, the energy consumption management terminal uses the corresponding transmission key to decrypt it and restore the original energy consumption data. Then the data can be further analyzed, processed and managed.

[0060] In one embodiment, the generating a transmission key based on the initial energy consumption data and the identification value includes: Performing character cleaning on the initial energy consumption data to obtain a cleaned data string; wherein the character cleaning includes removing specified characters from the initial energy consumption data; Obtain a standard binary tree template pre-stored in a database, and add the characters in the cleaned data string to each node of the standard binary tree template in sequence to obtain a character binary tree; The identification value is segmented to obtain a plurality of digits; wherein the identification value includes a plurality of numeric characters; Based on the multiple numbers, a graphic is generated according to a preset rule; superimposing the graphic onto a designated position of the character binary tree, and performing geometric stretching or scaling on the graphic so that the graphic and the character binary tree satisfy a preset positional relationship; After the graphic is stretched or scaled proportionally, a character located in the graphic is obtained in the character binary tree as a target character; Based on the target character, the transmission key is generated using a preset rule.

[0061] In this embodiment, the above initial energy consumption data is obtained by real-time collection of energy consumption data at all levels, and contains various types of character information, including Chinese characters, numbers, letters, symbols, etc. However, in the process of generating the transmission key, there are some specified characters that will interfere with the generation of the key or reduce the security of the key.

[0062] Determine the specified characters that need to be cleared. The specified characters can be some special symbols, spaces, line breaks, etc., which are determined according to the actual situation. For example, symbols such as commas, semicolons, brackets, etc. can be set as specified characters for clearing. Check the initial energy consumption data character by character, and when the specified characters are found, delete them from the data. After cleaning, a cleaned data string containing only valid characters is obtained.

[0063] The standard binary tree template pre-stored in the above database is a tree data structure with a specific structure, which is used to organize and store character information, and can provide an orderly way to process and manage the cleaned data string.

[0064] Starting from the first character of the clean data string, each character is added to the node of the standard binary tree template in turn. The characters can be assigned to different nodes of the binary tree one by one in a specific order, such as from left to right, from top to bottom, etc. For example, if the clean data string is "ABCDE", first add "A" to the root node of the binary tree, then add "B" to the left child node or right child node of the root node, and so on, until all characters are added to the binary tree to form a character binary tree.

[0065] The above identification value is generated based on the energy consumption trend data and the energy consumption measurement values ​​at all levels, and contains multiple numeric characters. Extract the numeric characters in the identification value and split them. You can split them according to specific rules, such as fixed digits, separators, etc. For example, if the identification value is "123456789", you can split it according to every two digits to get multiple numbers, such as [12, 34, 56, 78, 9].

[0066] Multiple numbers can be used as input parameters to generate a specific shape according to preset rules. The above rules can be based on mathematical formulas, algorithms or specific shape generation algorithms. It should be noted that the shape is usually composed of a closed curve, such as an ellipse, a circle, a polygon, etc.

[0067] For example, the numeric characters in the above identification value can be divided into 4 groups of numbers, and the preset rules can be used to obtain 3 coordinate points in the coordinate system based on these 4 groups of numbers. For example, the 4 groups of numbers are 13, 24, 38, and 16, then three coordinate points (13, 24), (24, 38), and (38, 16) can be generated, and then a triangle can be generated based on the 3 coordinate points. No further details will be given here.

[0068] Then, the graphic is superimposed on the designated position of the character binary tree, and the graphic is stretched or scaled proportionally so that it satisfies the preset position relationship with the character binary tree. First, the designated position of the character binary tree is determined, and the generated graphic is superimposed on this position. The designated position can be a node, a branch, or the surrounding of the entire binary tree.

[0069] The graphic is stretched or scaled proportionally so that it meets the preset position relationship with the character binary tree. This position relationship can be that the graphic completely covers a node, the size ratio with the binary tree is appropriate, etc. For example, if the graphic is too large, it can be scaled down proportionally to match the size of the character binary tree; if the graphic is too small, it can be scaled up proportionally to better combine with the binary tree.

[0070] After the graph is proportionally stretched or scaled and combined with the character binary tree, the characters within the graph range are determined. The above characters are regarded as target characters and will be used to generate the transmission key. Each node of the character binary tree is checked to determine whether it is within the graph range. If so, the character is extracted as the target character. For example, if the graph covers some nodes of the binary tree, the characters on these nodes are determined as target characters.

[0071] The target characters are determined by the interaction between the graphics and the character binary tree, and these characters can be used as the basis for generating the transmission key. The target characters are processed using preset rules to generate the transmission key. This rule can be an encryption algorithm, a hash function, or other specific key generation method. For example, the target characters can be combined, transformed, encrypted, etc. to generate a transmission key with sufficient complexity and security for encrypted transmission of the energy consumption data table.

[0072] In one embodiment, the generating of identification values ​​based on the energy consumption change trend data and the energy consumption measurement values ​​at each level includes: Extracting the energy consumption change trend data and the digital characters in the energy consumption measurement values ​​at each level to obtain the corresponding first character string and second character string; According to a preset rule, the numeric characters in the first string are sequentially added to a first matrix, and the numeric characters in the second string are sequentially added to a second matrix; wherein the rows and columns of the first matrix and the second matrix are the same; Calculate the product of the first matrix and the second matrix to obtain a product matrix; The product matrix is ​​subjected to digital character screening to screen out a plurality of target digital characters, which are combined to obtain the identification value.

[0073] In this embodiment, the energy consumption trend data and the energy consumption measurement values ​​at each level are obtained through the previous steps, which contain numeric characters and other non-numeric characters. For example, the energy consumption trend data may be a descriptive text containing numbers and letters, and the energy consumption measurement values ​​at each level may be numerical values ​​composed of numbers and units. All numeric characters are extracted from the energy consumption trend data, and these numeric characters are combined into a string, which is called the first string. Similarly, numeric characters are extracted from the energy consumption measurement values ​​at each level to form a second string. For example, if the energy consumption trend data is "the trend has increased by 10%", the number "10" is extracted to form the first string. If the energy consumption measurement values ​​at each level are "50 kWh", the number "50" is extracted to form the second string.

[0074] Furthermore, the size of the first matrix and the second matrix is ​​determined. The number of rows and columns can be set according to actual needs, but the rows and columns of the two matrices must be the same. For example, it can be set to a 3x3 matrix.

[0075] For the numeric characters in the first string, they are added to the elements of the first matrix in order from left to right and from top to bottom. If the number of numeric characters in the first string is less than the number of elements in the matrix, they can be added repeatedly or a specific filling process can be performed. Similarly, for the numeric characters in the second string, they are added to the second matrix according to the same rules.

[0076] The above matrix multiplication is a mathematical operation used to calculate the product of two matrices. In this step, the first matrix and the second matrix are subjected to matrix multiplication. The calculation rule of matrix multiplication is that for two matrices A and B, each element of their product C is equal to the sum of the products of the corresponding elements of the i-th row of A and the j-th column of B.

[0077] Through the matrix multiplication operation, a new matrix is ​​obtained, which is called the product matrix. The size of this product matrix is ​​the same as the size of the first matrix and the second matrix. Each element in the product matrix is ​​checked to filter out the digital characters that meet specific rules. The screening rules can be to select only the numbers in a specific position, to select only the numbers greater than a certain threshold, etc. For example, the unit digit of each element in the product matrix can be selected as the target digital character.

[0078] Combine the selected target numeric characters in a certain order to obtain a string, which is the identification value. For example, if the selected target numeric characters are [1, 2, 3, 4], they can be combined into "1234" as the identification value.

[0079] Reference Figure 2In one embodiment of the present invention, there is also provided an energy consumption classification metering loss analysis system based on an energy consumption trend recursive algorithm, comprising: An analysis unit is used to collect energy consumption data at all levels in real time to obtain initial energy consumption data; perform trend analysis on the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; A grading unit, used to grade the initial energy consumption data according to a preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the classification criteria for each level; The metering unit is used to measure the energy consumption data of each level and obtain the energy consumption measurement value of each level; A comparison unit is used to compare the energy consumption measurement values ​​at each level with the corresponding preset standard values. If the preset standard value range is exceeded, the stability and sustainability of the energy consumption changes at each level are analyzed in combination with the energy consumption change trend data; The early warning unit is used to make corresponding early warning plans based on the analyzed stability and continuity.

[0080] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0081] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0082] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0083] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0084] In summary, the energy consumption hierarchical metering loss analysis method and system based on the energy consumption trend recursive algorithm provided in the embodiment of the present invention include: real-time collection of energy consumption data at all levels to obtain initial energy consumption data; trend analysis of the initial energy consumption data based on the energy consumption trend recursive algorithm to obtain energy consumption change trend data; hierarchical processing of the initial energy consumption data according to the preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the division standards of each level; energy consumption measurement of each level of energy consumption data is performed separately to obtain energy consumption measurement values ​​at each level; the energy consumption measurement values ​​at each level are compared with the corresponding preset standard values. If the preset standard value range is exceeded, the stability and continuity of energy consumption changes at each level are analyzed in combination with the energy consumption change trend data; and corresponding early warning schemes are made according to the analyzed stability and continuity. In the present invention, by analyzing the energy consumption change trend data and hierarchical processing of the initial energy consumption data in combination with the preset energy consumption model structure, the classification is more reasonable and in line with the current energy consumption data changes; it is convenient for subsequent hierarchical metering and then early warning.

[0085] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0086] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0087] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for analyzing energy consumption loss by level measurement based on energy consumption trend recursive algorithm, characterized in that: The following steps are involved: Collect energy consumption data at all levels in real time to obtain initial energy consumption data; Performing trend analysis on the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; The initial energy consumption data is graded according to a preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the classification criteria for each level; Energy consumption data at each level is measured separately to obtain energy consumption measurement values ​​at each level; Compare the energy consumption measurement values ​​at each level with the corresponding preset standard values. If they exceed the preset standard value range, analyze the stability and sustainability of the energy consumption changes at each level in combination with the energy consumption change trend data; Make corresponding early warning plans based on the analyzed stability and sustainability.

2. The energy consumption classification measurement loss analysis method based on energy consumption trend recursive algorithm according to claim 1 is characterized in that: According to the analyzed stability and sustainability, a corresponding early warning plan is made, including: If the energy consumption trend is increasing and the loss exceeds the preset range, an in-depth analysis of the equipment operating parameters is performed to determine whether there is equipment aging; If the equipment is not aged, the energy usage behavior data is analyzed to determine whether there are unreasonable energy usage factors and obtain loss analysis results; When the loss analysis result exceeds a preset threshold range, an early warning prompt is issued.

3. The energy consumption classification measurement loss analysis method based on energy consumption trend recursive algorithm according to claim 1 is characterized in that: The step of performing hierarchical processing on the initial energy consumption data according to the preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels includes: Analyze various parameters in the preset energy consumption model structure to obtain basic classification standards; Performing statistical analysis on the energy consumption change trend data to determine trend influencing factors; The basic classification standard is combined with the trend influencing factor, and the initial energy consumption data is classified to obtain energy consumption data corresponding to different levels.

4. The energy consumption classification measurement loss analysis method based on energy consumption trend recursive algorithm according to claim 3 is characterized in that: The statistical analysis of the energy consumption change trend data to determine the trend influencing factors includes: Calculate the mean and standard deviation of the energy consumption change trend data to obtain statistical characteristics of the trend data; The statistical features of the trend data are input into a pre-trained neural network model for calculation, and the trend influencing factors are output.

5. The energy consumption classification measurement loss analysis method based on energy consumption trend recursive algorithm according to claim 1 is characterized in that: The above mentioned energy consumption change trend data is combined to analyze the stability and sustainability of energy consumption changes at all levels, including: Calculate the variance of energy consumption trend data, and determine the stability of energy consumption changes at all levels based on the variance calculation results; The slope changes of the energy consumption change trend data at multiple consecutive time points are analyzed, and the continuity of the energy consumption changes at each level is determined based on the slope changes.

6. The energy consumption classification measurement loss analysis method based on energy consumption trend recursive algorithm according to claim 1 is characterized in that: After making the corresponding early warning plan, it also includes: Add the initial energy consumption data, energy consumption change trend data, and energy consumption measurement values ​​at all levels to a data table to obtain an energy consumption data table; Generate an identification value based on the energy consumption change trend data and the energy consumption measurement values ​​at each level, and identify the energy consumption data table based on the identification value; generating a transmission key based on the initial energy consumption data and the identification value; After the energy consumption data table is encrypted based on the transmission key, it is transmitted to the energy consumption management terminal.

7. The energy consumption classification measurement loss analysis method based on energy consumption trend recursive algorithm according to claim 6 is characterized in that: The generating a transmission key based on the initial energy consumption data and the identification value includes: Performing character cleaning on the initial energy consumption data to obtain a cleaned data string; wherein the character cleaning includes removing specified characters from the initial energy consumption data; Obtain a standard binary tree template pre-stored in a database, and add the characters in the cleaned data string to each node of the standard binary tree template in sequence to obtain a character binary tree; split the identification value to obtain multiple numbers; wherein the identification value includes multiple numeric characters; Based on the multiple numbers, a graphic is generated according to a preset rule; the graphic is superimposed on a specified position of the character binary tree, and the graphic is stretched or scaled proportionally so that the graphic satisfies a preset positional relationship with the character binary tree; After the graphic is stretched or scaled proportionally, the character located in the graphic is obtained in the character binary tree as the target character; based on the target character, the transmission key is generated using a preset rule.

8. An energy consumption classification metering loss analysis system based on energy consumption trend recursive algorithm, characterized in that: include: The analysis unit is used to collect energy consumption data at all levels in real time to obtain initial energy consumption data; Performing trend analysis on the initial energy consumption data based on an energy consumption trend recursive algorithm to obtain energy consumption change trend data; A grading unit, used to grade the initial energy consumption data according to a preset energy consumption model structure and the energy consumption change trend data to obtain energy consumption data corresponding to different levels; wherein the energy consumption change trend data is used to assist in determining the classification criteria for each level; The metering unit is used to measure the energy consumption data of each level and obtain the energy consumption measurement value of each level; A comparison unit is used to compare the energy consumption measurement values ​​at each level with the corresponding preset standard values. If the preset standard value range is exceeded, the stability and sustainability of the energy consumption changes at each level are analyzed in combination with the energy consumption change trend data; The early warning unit is used to make corresponding early warning plans based on the analyzed stability and continuity.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Electric power energy monitoring method and system, terminal equipment and storage medium

    CN117349624A

  • Energy-saving energy integrated management system and method for optimizing energy scheduling

    CN118378834A

  • Method and apparatus for predicting a fault condition

    US5950147A