Novel energy management system

Abstract

The embodiment of the invention provides a novel energy management system, and relates to the field. The novel energy management system comprises a data acquisition module; the intelligent analysis module is connected with the data acquisition module and is used for performing dynamic calculation and predictive analysis on the real-time data; the self-adaptive scheduling module is connected with the intelligent analysis module and is used for carrying out automatic switching and load balancing among various energy supply paths according to the optimization strategy output by the analysis module; the user interaction module communicates with the self-adaptive scheduling module and the intelligent analysis module; and the remote connection module is connected with the user interaction module. According to the method, high-precision prediction can be carried out on energy fluctuation in a complex energy utilization environment, and potential energy consumption fluctuation can be identified in advance. In this way, the system can carry out more accurate energy supply optimization under the condition that the energy demand fluctuates or is uncertain, and energy waste or shortage caused by surplus or insufficient demand is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to a novel energy management system. Background Art

[0002] As society's demand for energy continues to grow, energy management is becoming increasingly important in various industries. Traditional energy management systems usually manage a single energy form or a single energy scenario, which makes it difficult to fully cope with the increasingly complex problems of multi-energy coordinated use and dynamic load changes. Due to the lack of real-time collection and fusion analysis capabilities of multi-dimensional energy consumption data in existing technologies, managers often need to rely on experience or regular manual statistical data to adjust energy supply strategies, which is inefficient and prone to decision-making delays or resource waste.

[0003] In scenarios such as industrial production, commercial complexes, and smart cities, as the complexity of new energy applications (such as photovoltaics, energy storage batteries, etc.) and traditional energy (such as electricity, thermal energy, etc.) continues to increase, it is difficult to balance the supply and demand of multiple types of energy in different load periods if only static or linear scheduling methods are relied upon. In addition, although some energy management systems in the existing technology have certain data monitoring capabilities, they lack intelligent analysis and adaptive scheduling mechanisms, making it difficult to respond to environmental parameter fluctuations or emergencies during peak load periods in a timely manner, resulting in insufficient energy utilization efficiency or unreasonable scheduling.

[0004] On the other hand, remote management and operation and maintenance methods have gradually become one of the key requirements of energy management. Traditional remote monitoring solutions are mostly based on one-way data collection, lacking the function of in-depth analysis and self-learning optimization of the system. At the same time, there are also deficiencies in the transmission security of data and control instructions. The existing security protection mechanism is often limited to simple encryption or access control, which is difficult to effectively resist unauthorized operations or malicious attacks. Summary of the invention

[0005] According to an embodiment of the present invention, a new energy management system is provided to solve the problems raised by the above background technology.

[0006] In a first aspect of the present invention, a novel energy management system is provided.

[0007] The novel energy management system includes: a data acquisition module for collecting real-time data including energy consumption, temperature, humidity and environmental parameters from sensors distributed in at least two energy use scenarios;

[0008] An intelligent analysis module, connected to the data acquisition module, for dynamically calculating and predicting the real-time data, and optimizing the energy supply strategy based on the energy consumption trend recognition and prediction model;

[0009] An adaptive scheduling module, connected to the intelligent analysis module, is used to automatically switch and balance loads among multiple energy supply paths according to the optimization strategy output by the analysis module, so as to realize dynamic scheduling and allocation of electrical energy, thermal energy or other forms of energy;

[0010] A user interaction module, communicating with the adaptive scheduling module and the intelligent analysis module, for providing a visual energy consumption monitoring interface and decision-making auxiliary information, and allowing the user to perform manual intervention or strategy adjustment when necessary;

[0011] A remote connection module is connected to the user interaction module.

[0012] Preferably, it also includes a multi-dimensional feature association module, which performs multi-layer association processing on different types of energy consumption parameters based on dynamic morphological mapping during data collection and analysis, and transmits the association results to the intelligent analysis module in real time, so as to improve the accuracy of energy scheduling decisions in complex energy consumption environments.

[0013] Preferably, the remote connection module is used to connect the energy management system to a remote server or cloud platform via a wired or wireless network to support remote monitoring, operation and maintenance, and data analysis services.

[0014] Preferably, the adaptive scheduling module is configured with a multi-stage energy storage and conversion unit, which is used to store excess energy in multiple forms when the load is low, and automatically trigger the internal multi-phase conversion mechanism during the load peak stage to supply the excess energy back to the system's priority load units, thereby achieving full utilization of energy in the time dimension.

[0015] Preferably, it also includes a security protection module for protecting the control instructions and key data inside the system and when connected to the outside; the security protection module includes an internal instruction nested verification device, which automatically identifies and blocks any unauthorized or abnormal control requests by embedding a verification identifier matching the current operating status in the instructions transmitted between the modules of the system, thereby ensuring the integrity and security of the system's internal data and scheduling logic.

[0016] Preferably, the intelligent analysis module includes:

[0017] High-dimensional data integration submodule, used to preliminarily screen and denoise the real-time data from different types of sensors and integrate them into a unified format;

[0018] The dynamic trend identification submodule performs multi-level trend analysis and potential fluctuation warning on the integrated data based on multi-factor association rules;

[0019] The composite load assessment submodule evaluates the suitability of the current energy supply strategy and outputs correction suggestions when load fluctuations or abnormal operating conditions are detected;

[0020] The self-feedback optimization submodule updates the key parameters in the energy scheduling model in real time according to the correction suggestions output by the composite load evaluation submodule, and iterates the scheduling strategy in the next cycle, thereby improving the ability to adapt to changes in energy consumption.

[0021] Preferably, the user interaction module further includes a flexible interface configuration unit, which is used to adjust the interface layout and information presentation priority in real time based on the system operating load and the user's current operating preferences, automatically highlight key monitoring indicators and emergency operation options during energy consumption peaks or emergency conditions, and restore to a complete information display mode under normal conditions.

[0022] Preferably, the multi-stage energy storage and conversion unit is also provided with an online energy diagnosis submodule for continuously monitoring key parameters such as voltage, current and temperature during the energy charging, discharging and conversion process, and actively triggering a safety warning or switching to a backup energy storage path when abnormal changes are detected to avoid energy loss or system failure.

[0023] Preferably, the dynamic trend identification submodule iteratively calculates key parameters such as ambient temperature, humidity, and real-time energy consumption through customized multidimensional weighted factors, and forms differentiated prediction models for different industry load scenarios based on the multidimensional weighted factors, thereby achieving more accurate prediction of energy consumption fluctuations in complex or nonlinear energy consumption environments.

[0024] Preferably, it also includes a self-learning energy efficiency evaluation module, which communicates with the intelligent analysis module and the adaptive scheduling module, and dynamically updates the system's scheduling algorithm by periodically recording the scheduling strategy execution results and energy efficiency performance in each scenario, so as to continuously improve energy utilization and optimize overall operating costs.

[0025] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0026] Through the multi-dimensional weighted factors and differentiated prediction models of the dynamic trend identification submodule, it is possible to make high-precision predictions of energy fluctuations in complex energy use environments and identify potential energy consumption fluctuations in advance. This enables the system to optimize energy supply more accurately in situations of fluctuating or uncertain energy demand, avoiding energy waste or shortages caused by excess or insufficient demand.

[0027] The adaptive scheduling module in the present invention can automatically switch between multiple energy supply paths according to the real-time analysis results, ensuring that the system achieves load balancing and dynamic scheduling of energy under different load conditions. This flexible scheduling mechanism can not only effectively improve energy efficiency, but also reduce operating costs and improve the overall efficiency of the system.

[0028] The flexible interface configuration unit of the user interaction module can adjust the interface layout in real time according to the system load and user preferences, ensuring that in an emergency, users can quickly view key monitoring data and perform emergency operations, while providing complete information display in a normal state. This design significantly improves the convenience of user operation, reduces operational risks, and enhances the user's decision-making ability.

[0029] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0031] Figure 1 A system block diagram of a novel energy management system according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0034] like Figure 1 As shown, in a first aspect of the present invention, a new energy management system is provided.

[0035] The system includes a data acquisition module, an intelligent analysis module, an adaptive scheduling module, a user interaction module and a remote connection module.

[0036] The data acquisition module is used to collect real-time data from sensor devices distributed in at least two energy usage scenarios. The collected data includes but is not limited to energy consumption, temperature, humidity and other environmental parameters. Sensors can be deployed in different energy usage scenarios, such as industrial production lines, office areas or residential areas, to monitor the energy usage and environmental changes of each scenario in real time. The data acquisition module transmits the collected data to the intelligent analysis module through wired or wireless communication to ensure the timeliness and accuracy of the data.

[0037] The intelligent analysis module is connected to the data acquisition module and is used to perform dynamic calculation and predictive analysis on the collected real-time data. Based on the energy consumption trend identification and prediction model, this module predicts future energy demand and optimizes the energy supply strategy accordingly. The intelligent analysis module further includes a multi-dimensional feature association module, which performs multi-layer association processing based on dynamic morphological mapping on different types of energy consumption parameters during data collection and analysis, and transmits the association results to the intelligent analysis module in real time to improve the accuracy of energy scheduling decisions in complex energy consumption environments.

[0038] The adaptive scheduling module is connected to the intelligent analysis module. According to the optimization strategy output by the intelligent analysis module, it automatically switches and balances the load between various energy supply paths to achieve dynamic scheduling and allocation of electrical energy, thermal energy or other forms of energy. In addition, the adaptive scheduling module is equipped with a multi-stage energy storage and conversion unit, which is used to store excess energy in various forms at low loads, and automatically trigger the internal multi-phase conversion mechanism at the peak load stage to supply excess energy back to the system's priority load unit, so as to fully utilize energy in the time dimension.

[0039] The user interaction module communicates with the adaptive scheduling module and the intelligent analysis module to provide a visual energy consumption monitoring interface and decision-making support information, and allows users to manually intervene or adjust strategies when necessary. The user interaction interface is intuitively designed to display real-time data, historical trends, and forecast results, helping users make scientific energy management decisions. In addition, the user interaction module also has a self-learning function. By recording the user's modifications to the system scheduling strategy, it continuously optimizes the energy management interface and strategy recommendation accuracy, thereby improving user experience and operational efficiency.

[0040] The remote connection module is connected to the user interaction module and is used to connect the energy management system to a remote server or cloud platform via a wired or wireless network, supporting remote monitoring, operation and maintenance, and data analysis services. This module ensures that the system can be monitored and managed anytime and anywhere, while realizing centralized management and in-depth analysis of large-scale data through the data storage and processing capabilities of the cloud platform. The remote connection module also has a dynamic load routing function, which can flexibly switch communication channels or data compression strategies according to the data communication status between the system and the external platform, so as to ensure efficient remote monitoring and management of the system even when the network environment fluctuates or the bandwidth is limited.

[0041] In this embodiment, a multi-dimensional feature association module is also included. In the process of data collection and analysis, the multi-dimensional feature association module performs in-depth analysis and association of different types of energy consumption parameters through multi-layer association processing based on dynamic morphological mapping. This module can find the potential relationship between various energy consumption parameters in the multi-dimensional data space by performing association processing across time, space and energy types on various energy consumption parameters (such as electric energy, thermal energy, cold energy, ambient temperature, humidity, etc.), and optimize the interpretation and prediction of data in real time.

[0042] Specifically, the multi-dimensional feature association module first cleans, normalizes and preprocesses the various energy consumption parameters collected to ensure the quality and comparability of the data. Then, based on the dynamic morphological mapping algorithm, the module dynamically adjusts the data mapping method to adaptively handle energy consumption fluctuations in different time periods and under different load conditions, thereby forming a multi-level association model that matches the current system state. In this process, the module not only processes single-dimensional data, but also reveals the complex interactive relationship between different parameters through multi-dimensional association analysis, thereby improving the accuracy of predicting changes in energy supply and demand.

[0043] The processed correlation results are passed to the intelligent analysis module in real time, so that the module can make more accurate energy scheduling decisions based on multi-dimensional data support. Based on the information transmitted from the multi-dimensional feature correlation module, the intelligent analysis module performs more efficient dynamic prediction and optimization of the energy consumption trend in the system, thereby improving the accuracy and timeliness of energy scheduling decisions in a complex and changeable energy environment. Through real-time multi-dimensional correlation analysis, the energy management system of the present invention can better cope with changing environmental factors and changes in energy demand, and achieve more accurate energy supply and distribution.

[0044] In this embodiment, the user interaction module communicates with the adaptive scheduling module and the intelligent analysis module to provide a visual energy consumption monitoring interface and decision-making support information. The adaptive scheduling module can display real-time energy consumption data, predictive analysis results, and optimized scheduling strategies to users, and supports users to manually adjust energy management strategies when necessary. In addition, users can also set parameters and adjust loads on the system through the interface. The remote connection module is connected to the user interaction module, and the energy management system is connected to a remote server or cloud platform through a wired or wireless network to support remote monitoring, operation and maintenance, and data analysis services. With this function, system administrators can remotely manage and adjust the energy system anytime and anywhere to ensure efficient energy scheduling and supply under changing environmental conditions.

[0045] In this embodiment, a security protection module is also included, which is used to provide all-round security protection for each module within the system and the control instructions and key data when the system is connected to external devices or networks. The core function of the security protection module is to prevent unauthorized operations, data tampering and potential security attacks, and ensure the normal operation of the system and the security of data.

[0046] The security protection module includes an internal command nesting verification device, which embeds a verification mark that matches the current system operation status in the control command transmitted between the modules of the system. Each command must go through the nesting verification process before being sent. Only when the verification mark is consistent with the current operation status can the command be successfully executed. The verification mark includes but is not limited to timestamps, status codes, encrypted signatures, etc., which are used to ensure the legitimacy and integrity of the command.

[0047] Through this nested verification mechanism, the internal command nested verification device can automatically identify and block any unauthorized or abnormal control requests. If it is detected that the command from the outside or inside the system does not match the current operating status, the system will automatically trigger protective measures, including but not limited to refusing to execute the command, alarming, recording security logs, etc., to prevent illegal operations from affecting the system.

[0048] In addition, the security protection module is also equipped with a real-time data monitoring and anomaly detection submodule, which monitors the operating status of the system in real time and dynamically detects abnormal behaviors that may occur during data transmission (such as data tampering, malicious attacks, etc.). Once any abnormality is detected, the system will immediately take corresponding security response measures, such as data encryption, command revocation or re-verification, etc., to ensure the overall security and reliability of the energy management system.

[0049] Through the above technical solutions, the security protection module can effectively ensure the security of the energy management system in the internal and external environment, prevent unauthorized operations, data leakage and system failures, thereby improving the stability, integrity and security of the system.

[0050] In this embodiment, the intelligent analysis module includes:

[0051] The high-dimensional data integration submodule is used to preliminarily screen and denoise the real-time data from different types of sensors and integrate them in a unified format. This submodule standardizes the real-time data from different energy scenarios and different energy types, such as electricity, heat, temperature, humidity, etc., to eliminate noise and redundant information in the data, so as to ensure the accuracy of subsequent analysis. At the same time, this submodule ensures that data from different sources can be effectively compared and integrated on the same platform through data normalization and calibration.

[0052] The dynamic trend identification submodule performs multi-level trend analysis and potential fluctuation warning on the integrated data based on multi-factor association rules. This submodule uses deep learning algorithms and statistical methods to monitor and analyze various energy consumption data and their changing trends in real time. By identifying patterns such as periodic fluctuations, trend changes, and abnormal fluctuations in historical data, combined with environmental variables (such as temperature changes, equipment load, etc.), predictive analysis can be performed to timely warn of possible energy supply shortages or waste. This module can conduct refined analysis of energy demand based on different time scales and provide important decision support for subsequent energy scheduling.

[0053] The composite load assessment submodule evaluates the applicability of the current energy supply strategy and outputs correction suggestions when load fluctuations or abnormal operating conditions are detected. This submodule monitors the real-time changes in energy demand and load, and combines the prediction results to timely evaluate the current energy supply strategy. When abnormal fluctuations in energy load (such as a surge or drop in load) are detected, the composite load assessment submodule automatically analyzes whether the existing strategy is still applicable, identifies possible problems in the energy supply system, and outputs correction suggestions based on historical experience and intelligent algorithms to help the system make adjustments to ensure the stability and efficiency of energy supply.

[0054] The self-feedback optimization submodule updates the key parameters in the energy scheduling model in real time according to the correction suggestions output by the composite load evaluation submodule, and iterates the scheduling strategy in the next cycle, thereby improving the ability to adapt to changes in energy consumption. This submodule can automatically adjust the relevant parameters in the scheduling model based on real-time monitoring of the load and energy supply situation, combined with changes in the external environment (such as climate change, equipment status, etc.). For example, adjust the charging and discharging strategy of the energy storage device, switch the energy supply path, etc., to better cope with fluctuations in energy demand. Through adaptive adjustment, the system can achieve accurate prediction and efficient scheduling of future demand to ensure the optimization of energy use.

[0055] In this embodiment, the user interaction module further includes a flexible interface configuration unit for adjusting the interface layout and information presentation priority in real time based on the system operating load and the user's current operating preferences. During peak energy consumption or emergency conditions, the system automatically highlights key monitoring indicators and emergency operation options so that users can respond quickly and make necessary controls or adjustments. Specifically, when the system enters a high load or emergency condition, the interface configuration unit automatically adjusts the interface according to the real-time load conditions, so that key indicators such as energy consumption data, early warning information, load scheduling, etc. related to the current state are more prominent, making it easier for users to concentrate and respond in a timely manner. At the same time, under normal operating conditions, the interface will return to a complete information display mode to ensure that users can fully and intuitively view the system's various operating parameters and historical data, which is convenient for daily monitoring and management.

[0056] In this embodiment, the multi-stage energy storage and conversion unit is also provided with an online energy diagnosis submodule, which is used to continuously monitor key parameters such as voltage, current, temperature, etc. during the energy charging, discharging and conversion process. By monitoring these key parameters in real time, the online energy diagnosis submodule can promptly detect abnormal changes in the system, such as voltage fluctuations, current overloads or temperature anomalies. When any abnormal fluctuations are detected, the submodule will immediately trigger the safety warning mechanism, and remind the user or system administrator to take corresponding safety measures by alarming or sending a warning message to the user interface. In addition, the online energy diagnosis submodule can also automatically switch to the backup energy storage path or adjust the working mode of the energy storage unit when an abnormal situation occurs, so as to avoid energy loss or system failure, thereby ensuring the stable operation of the system and the reliability of energy supply.

[0057] In this embodiment, the dynamic trend identification submodule iteratively calculates key parameters such as ambient temperature, humidity, and real-time energy consumption by customizing multidimensional weighting factors. This submodule uses multidimensional weighting factors to weight different types of energy consumption data, and forms differentiated prediction models for different industry load scenarios based on the weighted results. Specifically, this submodule customizes and adjusts multidimensional weighting factors according to the specific needs and dynamic changes of each industry or energy usage scenario to more accurately reflect the impact of ambient temperature, humidity, and energy consumption fluctuations on energy efficiency. Through iterative calculation and optimization of these key parameters, the dynamic trend identification submodule can improve the prediction accuracy of energy consumption fluctuations in complex or nonlinear energy usage environments, accurately identify potential fluctuation trends, and timely adjust energy supply strategies in future cycles to avoid problems such as energy waste or insufficient supply.

[0058] In this embodiment, a self-learning energy efficiency evaluation module is also included, which communicates with the intelligent analysis module and the adaptive scheduling module. The self-learning energy efficiency evaluation module dynamically updates the system's scheduling algorithm by periodically recording the execution results of the scheduling strategy and the energy efficiency performance in each scenario. During operation, the module will evaluate the performance of the current scheduling strategy in different load scenarios based on real-time execution results and historical energy efficiency data. By continuously feeding back the execution effect and energy efficiency performance of the scheduling strategy, the system can self-adjust and optimize the scheduling algorithm, thereby continuously improving energy utilization and effectively reducing overall operating costs. The self-learning ability of this module enables the system to gradually improve the efficiency and accuracy of energy management based on long-term accumulated data and experience, and realize intelligent energy scheduling and optimization.

[0059] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A new type of energy management system, characterized in that: include: A data acquisition module, used to collect real-time data including energy consumption, temperature, humidity and environmental parameters from sensors distributed in at least two energy use scenarios; An intelligent analysis module, connected to the data acquisition module, for performing dynamic calculation and predictive analysis on the real-time data; An adaptive scheduling module, connected to the intelligent analysis module, for automatically switching and load balancing between multiple energy supply paths according to the optimization strategy output by the analysis module; A user interaction module, communicating with the adaptive scheduling module and the intelligent analysis module, for providing a visual energy consumption monitoring interface and decision-making auxiliary information, and allowing the user to perform manual intervention or strategy adjustment when necessary; A remote connection module is connected to the user interaction module.

2. The new energy management system according to claim 1 is characterized in that: It also includes a multi-dimensional feature association module, which performs multi-layer association processing on different types of energy consumption parameters based on dynamic morphological mapping during data collection and analysis, and transmits the association results to the intelligent analysis module in real time.

3. The new energy management system according to claim 1 is characterized in that: The remote connection module is used to connect the energy management system to a remote server or cloud platform via a wired or wireless network to support remote monitoring, operation and maintenance, and data analysis services.

4. The new energy management system according to claim 1 is characterized in that: The adaptive scheduling module is configured with a multi-stage energy storage and conversion unit, which is used to store excess energy in multiple forms when the load is low, and automatically trigger an internal multi-phase conversion mechanism during the load peak stage to supply the excess energy back to the system's priority load unit.

5. The new energy management system according to claim 1 is characterized in that: It also includes a security protection module for providing security protection for control instructions and key data within the system and when connected to the outside; the security protection module includes an internal instruction nesting verification device.

6. The new energy management system according to claim 1 is characterized in that: The intelligent analysis module includes: High-dimensional data integration submodule, used to preliminarily screen and denoise the real-time data from different types of sensors and integrate them into a unified format; The dynamic trend identification submodule performs multi-level trend analysis and potential fluctuation warning on the integrated data based on multi-factor association rules; The composite load assessment submodule evaluates the suitability of the current energy supply strategy and outputs correction suggestions when load fluctuations or abnormal operating conditions are detected; The self-feedback optimization submodule updates the key parameters in the energy scheduling model in real time according to the correction suggestions output by the composite load evaluation submodule, and iterates the scheduling strategy in the next cycle, thereby improving the ability to adapt to changes in energy consumption.

7. The new energy management system according to claim 1 is characterized in that: The user interaction module further includes a flexible interface configuration unit, which is used to adjust the interface layout and information presentation priority in real time based on the system operation load and the user's current operation preferences, automatically highlight key monitoring indicators and emergency operation options during energy consumption peaks or emergency conditions, and restore to a complete information display mode under normal conditions.

8. The new energy management system according to claim 4 is characterized in that: The multi-stage energy storage and conversion unit is also provided with an online energy diagnosis submodule for continuously monitoring the voltage, current and temperature during the energy charging, discharging and conversion process, and actively triggering a safety warning or switching to a backup energy storage path when abnormal changes are detected.

9. The novel energy management system according to claim 6 is characterized in that: The dynamic trend identification submodule iteratively calculates the ambient temperature, humidity and real-time energy consumption by customizing multi-dimensional weighting factors, and forms a differentiated prediction model for different industry load scenarios based on the multi-dimensional weighting factors.

10. The novel energy management system according to claim 1 is characterized in that: It also includes a self-learning energy efficiency evaluation module, which communicates with the intelligent analysis module and the adaptive scheduling module, and dynamically updates the system's scheduling algorithm by periodically recording the scheduling strategy execution results and energy efficiency performance in each scenario.

Images