Multi-user comprehensive energy efficiency data monitoring, tracking and analyzing system and method thereof

Abstract

The invention relates to the technical field of energy efficiency management, in particular to a multi-user comprehensive energy efficiency data monitoring, tracking and analyzing system and method.The system comprises a multi-user application platform, and the output end of the multi-user application platform is connected with an automatic starting response module, a comprehensive energy efficiency monitoring and tracking module and a data analysis module; the input end of the comprehensive energy efficiency monitoring and tracking module is connected with the Internet and the IDC network, the input end of the Internet is connected with the area management module and the DMZ area, and the input end of the IDC network and the input end of the Internet are connected with the electric power private network. According to the system, energy consumption and energy cost of equipment of public energy consumption, manufacturing energy consumption and domestic energy consumption units are ranked through an electric quantity cost analysis module, ranked energy is divided into comprehensive energy, electric energy, water energy, gas energy, heat energy and carbon emission, ranking is divided into secondary energy consumption unit ranking and main energy consumption equipment ranking, and energy consumption and energy cost of energy consumption units are analyzed. And energy consumption analysis can be carried out from day, month, season and year.

Description

Technical Field

[0001] The present invention relates to the technical field of energy efficiency management, and in particular to a system and method for monitoring, tracking and analyzing comprehensive energy efficiency data of multiple users. Background Art

[0002] With the continuous development of social economy and science and technology, the multi-user integrated energy monitoring, tracking, analysis and data service platform has begun to appear in the power industry. Its application has not only promoted the rapid development of social economy, but also reduced the production costs of power companies and made operations simpler. On the basis of the existing architecture of the power demand side management platform, a multi-user integrated energy monitoring, tracking, analysis and data service platform is built to further improve the functions of the multi-user integrated energy monitoring, tracking, analysis and data service platform. On the one hand, it can provide users with safer and more reliable data information, and it can also drive the start-up cities to carry out pilot information push applications.

[0003] The patent specification with announcement number CN114034926A discloses a comprehensive energy monitoring, tracking and analysis system for multiple user sides, which includes an online monitoring system, a regional management model, an energy conversion model and an energy efficiency evaluation and diagnosis system. The regional management model includes key energy units, production energy units, life energy units and public and security energy units. The online monitoring system includes a data acquisition device, and each energy unit uploads actual energy usage data through the data acquisition device. It uses the organic combination of regional management models and energy conversion models to refine the energy consumption categories of each energy unit and provide targeted services. It also uses the energy conversion model to compensate for the impact of uneven energy distribution in the region on the power grid, optimize the comprehensive monitoring and control system, and thus achieve the efficiency of serving diversified side users.

[0004] However, in the implementation of relevant technologies, it was found that the above-designed integrated energy monitoring, tracking and analysis system for multiple users has the following problems: in the above-mentioned technical solution, by setting up an energy consumption data forecasting module, the energy usage data is transmitted to the energy-saving feedback function module, and the deviation between the planned and actual energy consumption data is analyzed, so as to monitor the energy consumption of multiple users and optimize the energy distribution of each energy-consuming unit in the area. However, in super-large buildings, there are often different equipment operation modes in different areas, resulting in engineering complexity, large deviations in prediction effects, and reduced accuracy in energy consumption prediction. In view of this, a multi-user integrated energy efficiency data monitoring, tracking and analysis system and method thereof are provided to overcome the above-mentioned defects. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a multi-user comprehensive energy efficiency data monitoring, tracking and analysis system and method.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a multi-user comprehensive energy efficiency data monitoring, tracking and analysis system, including a multi-user application platform, the output end of the multi-user application platform is respectively connected to an automatic start response module, a comprehensive energy efficiency monitoring and tracking module and a data analysis module, the input end of the comprehensive energy efficiency monitoring and tracking module is respectively connected to the Internet and an IDC network, the input end of the Internet is respectively connected to a regional management module and a DMZ area, the input ends of the IDC network and the Internet are both connected to a private power network, the output end of the data analysis module is connected to a data access management module, the output end of the data access management module is connected to a data analysis and evaluation module, the output end of the data analysis and evaluation module is connected to an energy efficiency prediction module, and the output end of the energy efficiency prediction module is connected to an electricity cost prediction module.

[0007] As a further description of the above technical solution: the regional management module includes public energy, manufacturing energy and living energy;

[0008] The public energy consumption is used to collect energy efficiency data of public and security unit electricity consumption;

[0009] The manufacturing energy is used to collect energy efficiency data of electricity used by manufacturing units;

[0010] The living energy is used to collect energy efficiency data of electricity consumption of living units, and is used to manage the electricity of public energy, manufacturing energy and living energy through the regional management module. Public energy, manufacturing energy and living energy can collect energy efficiency electricity consumption data.

[0011] As a further description of the above technical solution: the automatic start response module includes an information viewing module, an energy efficiency result module and an energy efficiency management module;

[0012] Wherein, the information viewing module is used by the user end to view the energy efficiency data;

[0013] The energy efficiency result module is used to check the users who use electricity normally;

[0014] The energy efficiency management module is used to manage and control users who use electricity abnormally. The automatic start response module is set up to provide demand response events, information viewing module, energy efficiency result module of power data and energy efficiency management module for power management and multi-dimensional statistical control of demand response customers.

[0015] As a further description of the above technical solution: the output end of the comprehensive energy efficiency monitoring and tracking module is connected to the comprehensive energy efficiency collection module, and the output end of the comprehensive energy efficiency collection module is connected to the online monitoring and tracking module. Through the comprehensive energy efficiency collection module, the collected energy efficiency and electricity consumption data can be stored, and the set online monitoring and tracking module can monitor the online power data.

[0016] As a further description of the above technical solution: the line monitoring and tracking module includes an online load detection module, an online power detection module and an online voltage detection module;

[0017] Wherein, the online load detection module is used to detect the energy load;

[0018] The online power detection module is used to detect the power output;

[0019] The online voltage detection module is used to detect the voltage of the cable, the online load detection module, the online power detection module and the online voltage detection module monitor the energy consumption of online users, and the comprehensive energy efficiency acquisition module further acquires and stores the monitoring data.

[0020] As a further description of the above technical solution: the output end of the online monitoring and tracking module is connected to an electricity cost analysis module, through which the energy consumption and energy cost of public energy, manufacturing energy and life energy unit equipment are ranked. The ranked energy is divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emissions. The ranking is divided into secondary energy unit ranking and main energy equipment ranking, and energy consumption analysis can be performed from day, month, season and year.

[0021] As a further description of the above technical solution: the data analysis and evaluation module includes an energy efficiency analysis module and a load analysis module;

[0022] Wherein, the energy efficiency analysis module is used to analyze the output energy efficiency data of the power equipment;

[0023] The load analysis module is used to analyze the load of the power equipment, the data access management module receives the collected and stored data and sends it to the data analysis and evaluation module, and the energy efficiency analysis module and the load analysis module evaluate the energy efficiency and load.

[0024] As a further description of the above technical solution: the energy efficiency prediction module includes a support vector machine module, a deep learning module and an energy efficiency prediction model;

[0025] Wherein, the support vector machine module is used to classify the collected multi-feature data;

[0026] The deep learning module is used to train the model and build a variety of prediction models that match it;

[0027] The energy efficiency prediction model is used to display the energy efficiency prediction data. The energy efficiency prediction module further receives the evaluated data, and the monthly daily electricity consumption prediction method of the support vector machine module and the deep learning module is used to first establish a fuzzy wavelet neural network monthly daily electricity consumption prediction model, and then use the chaotic hybrid bat algorithm to calculate and optimize the initialization of the fuzzy wavelet neural network parameters. Secondly, the support vector machine module and the deep learning module technology are integrated to train the fuzzy wavelet neural network, and then displayed through the energy efficiency prediction model.

[0028] As a further description of the above technical solution: the electricity cost prediction module includes a data cleaning module, a data screening module, a data clustering module and an electricity prediction model;

[0029] Wherein, the data cleaning module is used to clean the collected user data;

[0030] The data screening module is used to screen the cleaned user data;

[0031] The data clustering module is used to cluster the filtered user data;

[0032] The electricity prediction model is used to display the data of electricity cost prediction. The electricity cost prediction module receives the evaluated data. The data cleaning module performs data cleaning on the collected public energy consumption, manufacturing energy consumption and living energy consumption unit equipment data to obtain the cleaned user data. The cleaned user data is processed by the data screening module to obtain the screened user data. The screened user data is divided into preset categories as cluster centers and is processed by the data clustering module to obtain clustered user data. Feature construction is performed based on the clustered user data, and the feature structure is displayed by the electricity prediction model.

[0033] The method for monitoring, tracking and analyzing the comprehensive energy efficiency data of multiple users includes the following steps:

[0034] S1. The system software is deployed on the data servers of the IDC network and the Internet respectively. The hardware deployment framework is an important part of the construction of a comprehensive energy monitoring, tracking, analysis and data service platform for multiple users. The power private network, IDC network and the Internet are organically connected together, and the Internet is connected to the DMZ area to achieve effective connection between internal and external network data platforms.

[0035] S2, the regional management module manages electricity, public energy, manufacturing energy and living energy can collect energy efficiency and electricity consumption data, the online load detection module, online power detection module and online voltage detection module monitor online user energy consumption, and the comprehensive energy efficiency collection module further collects and stores the monitoring data;

[0036] S3. The energy consumption and energy cost of public energy, manufacturing energy and living energy unit equipment are ranked through the electricity cost analysis module. The energy ranked is divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emissions. The ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed from day, month, season and year.

[0037] S4, the energy efficiency prediction module receives the evaluated data, and uses the monthly daily electricity consumption prediction method of the support vector machine module and the deep learning module to first establish a fuzzy wavelet neural network monthly daily electricity consumption prediction model, and then use the chaotic hybrid bat algorithm to calculate and optimize the initialization of the fuzzy wavelet neural network parameters, and then integrate the support vector machine module and the deep learning module technology to train the fuzzy wavelet neural network, and then display it through the energy efficiency prediction model;

[0038] S5. The electricity cost prediction module receives the evaluated data, the data cleaning module performs data cleaning on the collected data to obtain the cleaned user data, the cleaned user data is processed by the data screening module to obtain the screened user data, the screened user data is divided into preset categories as cluster centers by the data clustering module to obtain clustered user data, feature construction is performed based on the clustered user data, and the feature structure is displayed by the electricity prediction model.

[0039] The present invention has the following beneficial effects:

[0040] The present invention organically links the IDC network and the Internet together through a power private network, and the Internet is connected to the DMZ area, which can realize the effective connection between the internal and external network data platforms. The prediction through the energy efficiency prediction module has the characteristics of scientific, accurate, fast and concise, reduces the prediction deviation and improves the accuracy; the regional management module is used to manage the electricity of public energy, manufacturing energy and daily energy, and the public energy, manufacturing energy and daily energy can collect energy efficiency electricity data; the online load detection module, the online power detection module and the online voltage detection module monitor the online user energy consumption, and the comprehensive energy efficiency acquisition module further collects and stores the monitoring data.

[0041] The present invention ranks the energy consumption and energy cost of public energy, manufacturing energy and life energy unit equipment through the electricity cost analysis module. The ranked energy is divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emission. The ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed from day, month, season and year; the data access management module receives the collected and stored data and sends it to the data analysis and evaluation module. The energy efficiency analysis module and the load analysis module evaluate the energy efficiency and load.

[0042] The energy efficiency prediction module designed by the present invention further receives the evaluated data, and uses the monthly daily electricity consumption prediction method of the support vector machine module and the deep learning module to first establish a fuzzy wavelet neural network monthly daily electricity consumption prediction model, and then use the chaotic hybrid bat algorithm to calculate and optimize the initialization fuzzy wavelet neural network parameters, and then integrate the support vector machine module and deep learning module technology to train the fuzzy wavelet neural network, and display it through the energy efficiency prediction model.

[0043] The electricity cost prediction module designed in the present invention receives the data after evaluation, and the data cleaning module performs data cleaning processing on the collected public energy consumption, manufacturing energy consumption and living energy consumption unit equipment data to obtain the cleaned user data, and processes the cleaned user data through the data screening module to obtain the screened user data, and the screened user data is divided into preset categories as clustering centers through the data clustering module to obtain clustered user data, and feature construction processing is performed based on the clustered user data, and the feature structure is displayed through the electricity prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the main structure of the present invention;

[0045] Figure 2 It is a schematic diagram of the structure of the system distribution of the present invention;

[0046] Figure 3 This is a schematic diagram of the structure of the automatic startup response module of the present invention;

[0047] Figure 4 It is a structural schematic diagram of the regional management module of the present invention;

[0048] Figure 5 It is a structural diagram of the online monitoring and tracking module of the present invention;

[0049] Figure 6 It is a structural schematic diagram of the energy efficiency prediction module of the present invention;

[0050] Figure 7 It is a structural schematic diagram of the electricity cost prediction module of the present invention;

[0051] Figure 8 It is a schematic diagram of the working method structure of the present invention.

[0052] Legend:

[0053] 1. Multi-user application platform; 2. Automatic start response module; 3. Comprehensive energy efficiency monitoring and tracking module; 4. Data analysis module; 5. Regional management module; 501. Public energy use; 502. Manufacturing energy use; 503. Life energy use; 6. IDC network; 7. Power private network; 8. DMZ area; 9. Internet; 10. Information viewing module; 11. Energy efficiency result module; 12. Energy efficiency management module; 13. Comprehensive energy efficiency collection module; 14. Online monitoring and tracking module; 15. Online load detection Module; 16. Online power detection module; 17. Online voltage detection module; 18. Electricity cost analysis module; 19. Data access management module; 20. Data analysis and evaluation module; 21. Energy efficiency analysis module; 22. Load analysis module; 23. Energy efficiency prediction module; 24. Support vector machine module; 25. Deep learning module; 26. Energy efficiency prediction model; 27. Electricity cost prediction module; 28. Data cleaning module; 29. ​​Data screening module; 30. Data clustering module; 31. Electricity prediction model. DETAILED DESCRIPTION

[0054] Reference Figure 1-Figure 8 The multi-user integrated energy efficiency data monitoring, tracking and analysis system provided by the present invention comprises a multi-user application platform 1, the output end of the multi-user application platform 1 is respectively connected to an automatic start response module 2, an integrated energy efficiency monitoring and tracking module 3 and a data analysis module 4, the input end of the integrated energy efficiency monitoring and tracking module 3 is respectively connected to the Internet 9 and the IDC network 6, the input end of the Internet 9 is respectively connected to a regional management module 5 and a DMZ area 8, the input ends of the IDC network 6 and the Internet 9 are both connected to a power private network 7, the output end of the data analysis module 4 is connected to a data access management module 9, and the output end of the data analysis module 4 is connected to a data access management module 9. Block 19, the output end of the data access management module 19 is connected to the data analysis and evaluation module 20, the output end of the data analysis and evaluation module 20 is connected to the energy efficiency prediction module 23, the output end of the energy efficiency prediction module 23 is connected to the electricity cost prediction module 27, through the power dedicated network 7, the IDC network 6 and the Internet 9 are organically linked together, and the Internet 9 is connected to the DMZ area 8, which can realize the effective connection between the internal and external network data platforms. The prediction through the energy efficiency prediction module 23 has the characteristics of scientific, accurate, fast, concise, etc., which reduces the prediction deviation and improves the accuracy.

[0055] As a further implementation scheme of the above technical scheme: the regional management module 5 includes public energy 501, manufacturing energy 502 and living energy 503;

[0056] Among them, public energy consumption 501 is used to collect energy efficiency data of public and security unit electricity consumption;

[0057] Manufacturing Energy 502 is used to collect energy efficiency data on electricity used by manufacturing units;

[0058] The living energy 503 is used to collect energy efficiency data of electricity consumption of living units. The regional management module 5 is used to manage the electricity of public energy 501, manufacturing energy 502 and living energy 503. Public energy 501, manufacturing energy 502 and living energy 503 can collect energy efficiency electricity consumption data.

[0059] As a further implementation scheme of the above technical scheme: the automatic start response module 2 includes an information viewing module 10, an energy efficiency result module 11 and an energy efficiency management module 12;

[0060] The information viewing module 10 is used by the user to view the energy efficiency data;

[0061] The energy efficiency result module 11 is used to check the users who use electricity normally;

[0062] The energy efficiency management module 12 is used to manage and control users who use electricity abnormally. The automatic start response module 2 is set up to provide demand response events, information viewing module 10, energy efficiency result module 11 of power data and energy efficiency management module 12 for power management and multi-dimensional statistical control of demand response customers.

[0063] As a further implementation plan of the above technical solution: the output end of the comprehensive energy efficiency monitoring and tracking module 3 is connected to the comprehensive energy efficiency collection module 13, and the output end of the comprehensive energy efficiency collection module 13 is connected to the online monitoring and tracking module 14. Through the comprehensive energy efficiency collection module 13, the collected energy efficiency and electricity consumption data can be stored, and the set online monitoring and tracking module 14 can monitor the online power data.

[0064] As a further implementation scheme of the above technical scheme: the online monitoring and tracking module 14 includes an online load detection module 15, an online power detection module 16 and an online voltage detection module 17;

[0065] Among them, the online load detection module 15 is used to detect the energy load;

[0066] The online power detection module 16 is used to detect the power output;

[0067] The online voltage detection module 17 is used to detect the voltage of the cable, the online load detection module 15, the online power detection module 16 and the online voltage detection module 17 monitor the energy consumption of online users, and the comprehensive energy efficiency acquisition module 13 further acquires and stores the monitoring data.

[0068] As a further implementation plan of the above technical solution: the output end of the online monitoring and tracking module 14 is connected to the electricity cost analysis module 18, and the energy consumption and energy cost of the public energy 501, manufacturing energy 502 and life energy 503 unit equipment are ranked by the electricity cost analysis module 18. The ranked energy is divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emissions. The ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed from day, month, season and year.

[0069] During specific implementation, the system software is arranged on the data servers of the IDC network 6 and the Internet 9 respectively. While providing diversified services for the multi-user application platform 1, the data service platform can also realize intelligence, digitization and interactivity, and promote the continuous improvement of the platform functions. The hardware deployment framework is an important link in the construction of the multi-user comprehensive energy monitoring, tracking, analysis and data service platform. Through the power private network 7, the IDC network 6 and the Internet 9 are organically linked together, and the Internet 9 is connected to the DMZ area 8, which can realize the effective connection between the internal and external network data platforms. The comprehensive energy efficiency monitoring and tracking module 3, the automatic start response module 2 is set, which is used to provide demand response events, including an information viewing module 10 that can view data, an energy efficiency result module 11 of power data, and an energy efficiency management module 12 for power management, as well as multi-dimensional statistics of demand response customers, and a set regional management module 5 It is used to manage the electricity of public energy 501, manufacturing energy 502 and domestic energy 503. The online monitoring and tracking module 14 includes an online load detection module 15, an online power detection module 16 and an online voltage detection module 17, which monitors the online user energy consumption. The comprehensive energy efficiency acquisition module 13 collects and stores the monitored data. The energy consumption and energy cost of unit equipment of public energy 501, manufacturing energy 502 and domestic energy 503 are ranked through the electricity cost analysis module 18. The energy consumption ranking is divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emission, and the ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed from day, month, season and year. The energy cost ranking is divided into comprehensive energy, electric energy, water energy, gas energy and thermal energy, and the ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed from day, month, season and year.

[0070] As a further implementation scheme of the above technical scheme: the data analysis and evaluation module 20 includes an energy efficiency analysis module 21 and a load analysis module 22;

[0071] The energy efficiency analysis module 21 is used to analyze the output energy efficiency data of the power equipment;

[0072] The load analysis module 22 is used to analyze the load of the power equipment. The data access management module 19 receives the collected and stored data and sends it to the data analysis and evaluation module 20. The energy efficiency analysis module 21 and the load analysis module 22 evaluate the energy efficiency and load.

[0073] As a further implementation scheme of the above technical scheme: the energy efficiency prediction module 23 includes a support vector machine module 24, a deep learning module 25 and an energy efficiency prediction model 26;

[0074] Among them, the support vector machine module 24 is used to classify the collected multi-feature data;

[0075] The deep learning module 25 is used to train the model and build a variety of prediction models that match it;

[0076] The energy efficiency prediction model 26 is used to display the energy efficiency prediction data. The energy efficiency prediction module 23 further receives the evaluated data, and the monthly daily electricity consumption prediction method of the support vector machine module 24 and the deep learning module 25 first establishes a fuzzy wavelet neural network monthly daily electricity consumption prediction model, and then uses the chaotic hybrid bat algorithm to calculate and optimize the initialization fuzzy wavelet neural network parameters. Secondly, the support vector machine module 24 and the deep learning module 25 technology are integrated to train the fuzzy wavelet neural network, and then displayed through the energy efficiency prediction model 26.

[0077] As a further implementation scheme of the above technical scheme: the electricity cost prediction module 27 includes a data cleaning module 28, a data screening module 29, a data clustering module 30 and an electricity prediction model 31;

[0078] Among them, the data cleaning module 28 is used to clean the collected user data;

[0079] The data screening module 29 is used to screen the cleaned user data;

[0080] The data clustering module 30 is used to cluster the filtered user data;

[0081] The electricity prediction model 31 is used to display the data of electricity cost prediction. The electricity cost prediction module 27 receives the evaluated data. The data cleaning module 28 performs data cleaning on the collected unit equipment data of public energy consumption 501, manufacturing energy consumption 502 and living energy consumption 503 to obtain the cleaned user data. The cleaned user data is processed by the data screening module 29 to obtain the screened user data. The screened user data is divided into preset categories as cluster centers and passed through the data clustering module 30 to obtain clustered user data. Feature construction is performed based on the clustered user data, and the feature structure is displayed by the electricity prediction model 31.

[0082] The method for monitoring, tracking and analyzing the comprehensive energy efficiency data of multiple users includes the following steps:

[0083] S1, the system software is arranged on the data servers of the IDC network 6 and the Internet 9 respectively. The hardware deployment framework is an important part of the construction of a multi-user integrated energy monitoring, tracking, analysis and data service platform. The power private network 7, the IDC network 6 and the Internet 9 are organically connected together, and the Internet 9 is connected to the DMZ area 8, which can realize the effective connection between the internal and external network data platforms;

[0084] S2, the regional management module 5 manages electricity, public energy 501, manufacturing energy 502 and living energy 503 can collect energy efficiency and electricity consumption data, the online load detection module 15, the online power detection module 16 and the online voltage detection module 17 monitor the online user energy consumption, and the comprehensive energy efficiency collection module 13 further collects and stores the monitoring data;

[0085] S3. The energy consumption and energy cost of the public energy 501, manufacturing energy 502 and living energy 503 unit equipment are ranked through the electricity cost analysis module 18. The energy ranked is divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emission. The ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed from day, month, season and year.

[0086] S4, the energy efficiency prediction module 23 receives the evaluated data, and uses the monthly daily power consumption prediction method of the support vector machine module 24 and the deep learning module 25 to first establish a fuzzy wavelet neural network monthly daily power consumption prediction model, and then use the chaotic hybrid bat algorithm to calculate and optimize the initialization fuzzy wavelet neural network parameters, and then integrate the support vector machine module 24 and the deep learning module 25 technology to train the fuzzy wavelet neural network, and display it through the energy efficiency prediction model 26;

[0087] S5. The electricity cost prediction module 27 receives the evaluated data, the data cleaning module 28 performs data cleaning on the collected data to obtain the cleaned user data, the cleaned user data is processed by the data screening module 29 to obtain the screened user data, the screened user data is divided into preset categories as cluster centers by the data clustering module 30 to obtain clustered user data, feature construction is performed based on the clustered user data, and the feature structure is displayed by the electricity prediction model 31.

[0088] In the specific implementation, the data analysis module 4 includes a data access management module 19 and a data analysis and evaluation module 20. The data access management module 19 receives the collected and stored data and sends it to the data analysis and evaluation module 20. The energy efficiency analysis module 21 and the load analysis module 22 evaluate the energy efficiency and load. The energy efficiency prediction module 23 further receives the evaluated data and uses the support vector machine module 24 and the deep learning module 25 to predict the monthly daily electricity consumption. First, a fuzzy wavelet neural network monthly daily electricity consumption prediction model is established, and then a chaotic hybrid bat algorithm is used to calculate and optimize the initialization fuzzy wavelet neural network parameters. Secondly, the support vector machine module 24 and the deep learning module 25 technology are integrated to train the fuzzy wavelet neural network. Through the network, it is displayed through the energy efficiency prediction model 26. This prediction method has the characteristics of scientific, accurate, fast and concise. The electricity cost prediction module 27 is set to receive the evaluated data. The data cleaning module 28 performs data cleaning processing on the collected public energy consumption 501, manufacturing energy consumption 502 and life energy consumption 503 unit equipment data to obtain the cleaned user data. The cleaned user data is processed by the data screening module 29 to obtain the screened user data. The screened user data is divided into preset categories as cluster centers through the data clustering module 30 to obtain clustered user data. Feature construction processing is performed based on the clustered user data, and the feature structure is displayed through the electricity prediction model 31.

[0089] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-user integrated energy efficiency data monitoring, tracking and analysis system, comprising a multi-user application platform (1), wherein the output end of the multi-user application platform (1) is respectively connected to an automatic start response module (2), an integrated energy efficiency monitoring and tracking module (3) and a data analysis module (4), characterized in that: The input end of the comprehensive energy efficiency monitoring and tracking module (3) is respectively connected to the Internet (9) and the IDC network (6), the input end of the Internet (9) is respectively connected to the regional management module (5) and the DMZ area (8), the input ends of the IDC network (6) and the Internet (9) are both connected to the power private network (7), the output end of the data analysis module (4) is connected to the data access management module (19), the output end of the data access management module (19) is connected to the data analysis and evaluation module (20), the output end of the data analysis and evaluation module (20) is connected to the energy efficiency prediction module (23), and the output end of the energy efficiency prediction module (23) is connected to the electricity cost prediction module (27).

2. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 1 is characterized by: The regional management module (5) includes public energy (501), manufacturing energy (502) and living energy (503); Wherein, the public energy consumption (501) is used to collect energy efficiency data of public and security unit electricity consumption; The manufacturing energy consumption (502) is used to collect energy efficiency data of electricity consumption of manufacturing units; The living energy (503) is used to collect energy efficiency data of electricity used by living units.

3. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 1 is characterized by: The automatic start response module (2) comprises an information viewing module (10), an energy efficiency result module (11) and an energy efficiency management module (12); Wherein, the information viewing module (10) is used for the user end to view the energy efficiency data; The energy efficiency result module (11) is used to check users who use electricity normally; The energy efficiency management module (12) is used to manage and control users who use electricity abnormally.

4. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 1 is characterized by: The output end of the comprehensive energy efficiency monitoring and tracking module (3) is connected to a comprehensive energy efficiency collection module (13), and the output end of the comprehensive energy efficiency collection module (13) is connected to an online monitoring and tracking module (14).

5. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 4 is characterized by: The online monitoring and tracking module (14) comprises an online load detection module (15), an online power detection module (16) and an online voltage detection module (17); Wherein, the online load detection module (15) is used to detect the energy load; The online power detection module (16) is used to detect the electric output power; The online voltage detection module (17) is used to detect the voltage of the cable.

6. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 4 is characterized by: The output end of the online monitoring and tracking module (14) is connected to an electricity cost analysis module (18).

7. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 1 is characterized by: The data analysis and evaluation module (20) comprises an energy efficiency analysis module (21) and a load analysis module (22); Wherein, the energy efficiency analysis module (21) is used to analyze the output energy efficiency data of the power equipment; The load analysis module (22) is used to analyze the load of the electric equipment.

8. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 1 is characterized by: The energy efficiency prediction module (23) includes a support vector machine module (24), a deep learning module (25) and an energy efficiency prediction model (26); Wherein, the support vector machine module (24) is used to classify the collected multi-feature data; The deep learning module (25) is used to train the model and construct a variety of prediction models that match it; The energy efficiency prediction model (26) is used to display energy efficiency prediction data.

9. The multi-user comprehensive energy efficiency data monitoring, tracking and analysis system according to claim 1 is characterized by: The electricity cost prediction module (27) includes a data cleaning module (28), a data screening module (29), a data clustering module (30) and an electricity prediction model (31); Wherein, the data cleaning module (28) is used to clean the collected user data; The data screening module (29) is used to screen the cleaned user data; The data clustering module (30) is used to cluster the filtered user data; The electricity quantity prediction model (31) is used to display data of electricity cost prediction.

10. A method for monitoring, tracking and analyzing comprehensive energy efficiency data of multiple users, characterized in that: The following steps are involved: S1, the system software is deployed on the data servers of the IDC network (6) and the Internet (9) respectively. The hardware deployment framework is an important part of the construction of a multi-user integrated energy monitoring, tracking, analysis and data service platform. The power private network (7), IDC network (6) and the Internet (9) are organically connected together, and the Internet (9) is connected to the DMZ area (8), which can realize the effective connection between the internal and external network data platforms; S2, the regional management module (5) manages electricity, public energy consumption (501), manufacturing energy consumption (502) and living energy consumption (503) can collect energy efficiency and electricity consumption data, the online load detection module (15), the online power detection module (16) and the online voltage detection module (17) monitor the online user energy consumption, and the comprehensive energy efficiency collection module (13) further collects and stores the monitoring data; S3. Rank the energy consumption and energy cost of public energy (501), manufacturing energy (502) and living energy (503) unit equipment through the electricity cost analysis module (18). The energy sources for ranking are divided into comprehensive energy, electric energy, water energy, gas energy, thermal energy and carbon emission. The ranking is divided into secondary energy unit ranking and main energy equipment ranking. Energy consumption analysis can be performed on a daily, monthly, seasonal and annual basis. S4, the energy efficiency prediction module (23) receives the evaluated data, and uses the monthly daily electricity consumption prediction method of the support vector machine module (24) and the deep learning module (25) to first establish a fuzzy wavelet neural network monthly daily electricity consumption prediction model, then use the chaotic hybrid bat algorithm to calculate and optimize the initialization fuzzy wavelet neural network parameters, and then integrate the support vector machine module (24) and the deep learning module (25) technology to train the fuzzy wavelet neural network, and display it through the energy efficiency prediction model (26); S5, the electricity cost prediction module (27) receives the evaluated data, the data cleaning module (28) performs data cleaning on the collected data to obtain cleaned user data, the cleaned user data is processed by the data screening module (29) to obtain screened user data, the screened user data is classified into preset categories as cluster centers by the data clustering module (30) to obtain clustered user data, feature construction is performed based on the clustered user data, and the feature structure is displayed by the electricity prediction model (31).

Images