Energy optimization method and system based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based energy optimization method and system. The method comprises the steps of collecting energy operation data when an energy management system adopts a current energy parameter configuration scheme; according to the energy operation data, utilizing a pre-trained artificial intelligence-based energy state evaluation model to evaluate the operation state of the energy management system, and calculating the operation stability index of the energy management system; and optimizing an energy parameter configuration scheme of the energy management system according to the operation state and the operation stability index. According to the embodiment of the invention, the operation stability and energy efficiency of the energy management system can be effectively improved, and powerful support is provided for sustainable development.

Description

Technical Field

[0001] The present invention belongs to the field of energy technology, and in particular to an energy optimization method and system based on artificial intelligence. Background Art

[0002] Traditional energy management methods often rely on experience and static data analysis, making them difficult to adapt to the rapidly changing energy environment and complex user needs. Therefore, how to improve the intelligence and dynamism of energy management has become a technical challenge that needs to be solved urgently. Summary of the Invention

[0003] The purpose of this invention is to provide an energy optimization method and system based on artificial intelligence to address the deficiencies in the existing technology, effectively improve the operational stability and energy efficiency of the energy management system, and provide strong support for sustainable development.

[0004] An embodiment of the present application provides an artificial intelligence-based energy optimization method, the method comprising: Collect energy operation data of the energy management system when using the current energy parameter configuration plan; Based on the energy operation data, using a pre-trained artificial intelligence-based energy status assessment model, the operating status of the energy management system is assessed, and an operating stability index of the energy management system is calculated; An energy parameter configuration scheme of the energy management system is optimized according to the operating status and the operating stability index.

[0005] Optionally, the calculation formula of the operation stability index is:

[0006] Among them, the is the operation stability index, is the energy consumption rate at the tth collection time point, is the energy consumption fluctuation frequency at the tth collection time point, is the environmental disturbance index at the tth acquisition time point, is the system redundancy at the tth acquisition time point, 、 、 is the corresponding weight coefficient, is the attenuation factor.

[0007] Optionally, the energy consumption rate is calculated as follows:

[0008]

[0009] Wherein, the E(t) is the total energy consumption at the t-th collection time point, and the L(t) is the total load at the t-th collection time point.

[0010] Optionally, the calculation formula for the energy consumption fluctuation frequency is:

[0011] Wherein, k is the preset number of previous collection time points, and k is less than t.

[0012] Optionally, the calculation formula of the environmental disturbance index is:

[0013] Among them, the is the measured value of the jth environmental indicator at the tth collection time point, is the historical average value of the jth environmental indicator, is the weight factor of the jth environmental indicator, and n is the number of environmental indicators.

[0014] Optionally, the calculation formula of the system redundancy is:

[0015] Among them, the is the connectivity of the mth device in the energy management system, where M is the number of devices.

[0016] Optionally, optimizing the energy parameter configuration scheme of the energy management system according to the operating state and the operating stability index includes: If the operating state is abnormal and / or the operating stability index exceeds a preset threshold, the energy parameter configuration plan of the energy management system is adjusted so that the operating state is normal and the operating stability index does not exceed the preset threshold.

[0017] Another embodiment of the present application provides an artificial intelligence-based energy optimization system, the system comprising: The collection module is used to collect energy operation data of the energy management system when the current energy parameter configuration scheme is adopted; An evaluation module is used to evaluate the operating status of the energy management system and calculate the operating stability index of the energy management system based on the energy operation data using a pre-trained energy status evaluation model based on artificial intelligence; The optimization module is used to optimize the energy parameter configuration scheme of the energy management system according to the operating status and the operating stability index.

[0018] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when run.

[0019] Yet another embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above methods.

[0020] Compared with the existing technology, the present invention provides an artificial intelligence-based energy optimization method, which collects energy operation data of the energy management system when adopting the current energy parameter configuration scheme; based on the energy operation data, a pre-trained artificial intelligence-based energy status assessment model is used to evaluate the operating status of the energy management system and calculate the operating stability index of the energy management system; based on the operating status and the operating stability index, the energy parameter configuration scheme of the energy management system is optimized, thereby effectively improving the operating stability and energy efficiency of the energy management system and providing strong support for sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A hardware structure block diagram of a computer terminal for an energy optimization method based on artificial intelligence provided by an embodiment of the present invention; Figure 2 A schematic diagram of a process flow of an artificial intelligence-based energy optimization method provided in an embodiment of the present invention; Figure 3 A schematic structural diagram of an artificial intelligence-based energy optimization system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention.

[0023] The embodiment of the present invention first provides an energy optimization method based on artificial intelligence, which can be applied to electronic devices such as computer terminals, specifically ordinary computers.

[0024] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for an energy optimization method based on artificial intelligence provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0025] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the artificial intelligence-based energy optimization method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0026] Transmission device 106 is used to receive or transmit data via a network. A specific example of such a network may include a wireless network provided by a computer terminal's communications provider. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0027] See also Figure 2 , an embodiment of the present invention provides an energy optimization method based on artificial intelligence, which may include the following steps: S201, collecting energy operation data of the energy management system when adopting the current energy parameter configuration solution; This step involves collecting energy operation data of the energy management system under a specific energy parameter configuration scheme. The core of this process is to systematically record and monitor the real-time operating indicators of the energy management system through a variety of sensors and data acquisition equipment, including but not limited to energy consumption, load, equipment status and external environmental factors. The accurate collection of this data is an important foundation for subsequent analysis and optimization, ensuring that the evaluation model can make scientific and reasonable judgments based on real data. 1. Data-driven decision-making basis: Reliable energy operation data sources make the energy management decision-making process more transparent and efficient, avoiding subjective judgments based on experience or speculation. 2. Real-time response capability: By continuously collecting real-time data, the system can identify and respond to instantaneous changes in energy demand, improving the system's flexibility and responsiveness. 3. Comprehensively evaluate system performance: Detailed operational data helps identify potential inefficiencies and failures in the energy management system and supports the development of improvement measures. One implementation approach may include: Step 1: System Architecture Design Design a multi-layer data acquisition system, divided into data acquisition layer, data transmission layer, and data processing layer. Each layer adopts a modular design to facilitate expansion and maintenance. Step 2: Select sensors and data acquisition equipment. Select sensors with high precision and high sensitivity that can monitor energy consumption, load, environmental factors, etc. in real time. For example, power sensors, temperature sensors, humidity sensors, etc., and install them on key equipment and energy transmission channels. Step 3: Set the frequency of data collection. Determine a reasonable frequency for data collection. Based on actual usage scenarios, it is recommended to set it to collect data once every minute to ensure real-time performance and data integrity. Step 4: Intelligent Data Integration: At the data transmission layer, edge computing technology is used to initially process and integrate the collected data, calculating local energy consumption and load indicators. For example, by calculating the real-time rate of change of energy consumption, immediate feedback is provided for subsequent data analysis. Step 5: Build a data protocol. Design an effective data transmission protocol to ensure that the collected data can be seamlessly transmitted between different devices and systems. Use low-latency network technologies (such as LoRa, NB-IoT, etc.) to improve the reliability and security of data transmission. Step 6: Status Monitoring and Alarm Mechanism: Implement a real-time monitoring system, set energy consumption and load thresholds, and establish an alarm mechanism. When collected data exceeds or falls below the set thresholds, the system must immediately issue an alarm, facilitating timely inspection and maintenance by technicians. Step 7: Data storage and backup strategies use a combination of cloud storage and local storage to ensure high data availability and security. At the same time, data is backed up regularly to prevent system failures or data loss. Step 8: Data visualization platform Create a centralized data visualization platform to display the operating status and historical data of the energy management system through real-time data charts and dashboards, so that managers can make intuitive judgments and decisions. Through the above steps, the energy management system can efficiently and stably collect energy operation data, providing an accurate basis for subsequent status assessment and optimization decision-making. The implementation of this method not only improves the intelligence level of the system, but also creates conditions for enhancing the flexibility and adaptability of energy management.

[0028] S202, based on the energy operation data, using a pre-trained artificial intelligence-based energy status assessment model to assess the operating status of the energy management system and calculate an operating stability index of the energy management system; The first step is to use a pre-trained AI-based energy status assessment model to analyze and evaluate the collected energy operation data. The purpose of this process is to accurately assess the status of the energy management system through comprehensive analysis of various influencing factors, so as to effectively control and optimize the system. Specifically, the model inputs multi-dimensional energy operation data, processes complex nonlinear relationships, and outputs the system's operating status and operating stability index (ESI). Function and significance: 1. Intelligent Assessment: Using AI models instead of traditional rule-based algorithms can more intelligently process complex data sets, be more adaptable, and help assess system status in real time. 2. Improved accuracy: By training the model, the system can identify key factors affecting operating status based on historical data, improve the accuracy of evaluation results, and reduce human errors. 3. Dynamic adjustment: Through dynamic evaluation of operating status and stability index, the system can adjust strategies in a timely manner to respond to changing environments and load demands, thereby improving operational efficiency. 4. Decision support: The calculation of the stability index provides a clear basis for decision-making in subsequent energy parameter optimization, enabling managers to make adjustments and improvements based on scientific evaluation results. One implementation method may include: Step 1: Data Preprocessing: Before inputting into the AI ​​model, the collected energy operation data is preprocessed, including removing outliers, filling in missing data, and normalizing. Using the Z-score normalization method, all data are converted to a standard normal distribution to eliminate the influence of different dimensions on the model. Step 2: Feature engineering extracts useful features from the raw data to enhance the model's accuracy and robustness. For example, a more representative feature vector can be constructed based on energy consumption rates, historical load trends, and environmental disturbances. These features include, but are not limited to, the sliding mean of energy consumption, the standard deviation of energy consumption fluctuations, and the frequency of equipment operating states. Step 3: Select and Optimize Models. Perform preliminary training and cross-validation using a variety of AI algorithms (such as decision trees, random forests, support vector machines, or deep learning models) to select the optimal model. During model training, evaluate model performance using K-fold cross-validation and continuously optimize model performance through hyperparameter adjustments (such as learning rate and tree depth). Step 4: Model Training: The processed training data is fed into the selected AI model for training. During training, a labeled dataset is used, including both normal and abnormal system states (e.g., downtime, overload, etc.). The training dataset is used for model learning, generating a generalizable state assessment model. Step 5: Real-time Evaluation: During system operation, new energy operation data is fed into the trained model in real time for status evaluation. The model generates a prediction of the operating status based on the real-time data. The evaluation output should include the current operating status classification (e.g., normal, abnormal, etc.) and the corresponding operating stability index (ESI). Step 6: Stability Index Calculation Based on the state assessment output by the model and a specific calculation formula, the Operational Stability Index (ESI) is calculated. The ESI calculation can combine multiple input factors, such as energy consumption rate, fluctuation frequency, and environmental disturbances, using a weighted average method to generate a comprehensive stability index. Specifically, a calculation formula for the operation stability index is:

[0029] This formula is designed to comprehensively evaluate the operational stability of energy management systems. The ESI is a key metric used to quantify system performance and stability. By combining key factors such as energy consumption rate, fluctuation frequency, and environmental disturbances, it comprehensively reflects the system's overall stability over a specific time period.

[0030] Among them, the is the operation stability index, The energy consumption rate at the tth collection time point is used to measure the energy efficiency of the system. When the energy consumption is high, it may indicate that the system is under great pressure and has a high operating intensity, and has a high potential instability. The energy consumption fluctuation frequency at the tth acquisition time point indicates the stability of energy consumption. The greater the fluctuation, the greater the instability of the operation. is the environmental disturbance index at the tth acquisition time point, reflecting the impact of the external environment on the system. The greater the disturbance of environmental factors, the lower the stability may be. is the system redundancy at the tth acquisition time point, which describes the fault tolerance of the system. The higher the redundancy, the better the system stability. 、 、 The corresponding weight coefficients ensure that the contribution of each factor to the stability index is reasonably reflected. Expert evaluation settings or feature importance analysis based on machine learning may be needed to optimize these coefficients. To control the speed of the redundancy effect on the stability index and ensure the real-time and dynamic response of the system, we can optimize it through experiments and analyze the impact of different proportions of redundancy on the system stability to set the optimal value.

[0031] Specifically, a calculation formula for energy consumption rate is:

[0032]

[0033] Here, E(t) is the total energy consumption at the tth collection time point, reflecting the actual energy consumption of the energy management system at that specific moment. L(t) is the total load at the tth collection time point, representing the total burden borne by all devices and tasks at that moment. This formula is used to calculate the energy consumption rate at a specific moment and is a basic indicator for evaluating energy management efficiency. Its purpose is to quantify energy consumption per unit load to track changes in energy efficiency.

[0034] Specifically, a calculation formula for energy consumption fluctuation frequency is:

[0035] Here, k is the preset number of previous collection time points, and k is less than t. This formula measures the degree of energy consumption fluctuation and is another key indicator for assessing system stability. A higher frequency of fluctuation indicates unstable system energy consumption, which may affect management decisions. The number of previous collection time points, k, determines the width of the fluctuation band and affects the sensitivity of energy consumption changes.

[0036] Specifically, a calculation formula for the environmental disturbance index is:

[0037] Among them, the is the measured value of the jth environmental indicator at the tth collection time point, and the environmental factors that affect the operation of the system (such as temperature, humidity, etc.). is the historical average value of the jth environmental indicator, providing a benchmark to judge the changes in the current environment. is the weight factor of the jth environmental indicator, defining the contribution of each indicator to the overall disturbance effect. n is the number of environmental indicators.

[0038] This formula is designed to comprehensively consider the impact of the external environment on the operation of the energy management system and help evaluate the stability and reliability of the system under different environmental conditions.

[0039] Specifically, a calculation formula for system redundancy is:

[0040] Among them, the The connectivity of the mth device in the energy management system measures the availability and redundancy of that device within the entire system. M represents the number of devices. This formula is used to assess the redundancy of devices in the system and is an important indicator for evaluating system reliability. Higher redundancy increases system fault tolerance, contributing to stable operation. Device connectivity can be calculated using network topology analysis tools or manually verified based on a logical design diagram and actual connectivity.

[0041] Through these steps, the AI-based energy status assessment model can effectively process complex data from the energy management system, providing accurate operational status assessments and stability index calculations. This approach not only improves the system's intelligent management capabilities but also provides a solid technical foundation for efficient energy optimization.

[0042] S203: Optimize the energy parameter configuration scheme of the energy management system according to the operating status and the operating stability index.

[0043] In an energy management system, the operating status refers to the working conditions of the system at a specific moment, including normal operation and abnormal status; while the operating stability index (ESI) is an important indicator reflecting the stability of the system operation. Through the comprehensive analysis of these two, more accurate energy management can be achieved, thereby optimizing the system's energy parameter configuration plan, improving overall operating efficiency, saving energy consumption, and reducing operating costs. - Improve system reliability: By timely adjusting energy management parameters, the system is kept in a normal state, avoiding equipment failures caused by overload or improper operation, and extending system life. - Optimize energy utilization: Dynamically adjust energy allocation according to changes in ESI values ​​to optimize resource utilization and improve overall operating efficiency. - Enhanced anti-interference capability: When the environmental disturbance is strong, timely adjust the parameters to maintain the stability and reliability of the system. - Save energy costs: reduce unnecessary energy consumption, reduce operating costs and improve economic benefits.

[0044] Specifically, if the operating state is abnormal and / or the operating stability index exceeds a preset threshold, the energy parameter configuration scheme of the energy management system is adjusted so that the operating state is normal and the operating stability index does not exceed the preset threshold. One implementation method may include: An adaptive genetic algorithm (GA) generates a set of energy parameter adjustment strategies based on the current operating status and stability index. The key to this algorithm lies in developing a fitness function that considers the operating status, ESI value, and the user-defined target sustainable energy efficiency. In each generation of the GA, multiple candidate solutions are generated, and the optimal energy parameter configuration is continuously optimized through selection, crossover, and mutation mechanisms.

[0045] For the optimal parameter configuration generated, you can use system dynamic simulation tools (such as MATLAB / Simulink) to conduct pre-implementation simulations to evaluate expected performance under different disturbance conditions and load scenarios. By inputting different environmental disturbances and load fluctuations, you can verify the system stability and energy consumption performance under the new parameter configuration.

[0046] During implementation, a feedback loop mechanism was established to monitor operational status and ESI changes in real time, generating data feedback. If the current system operational status or ESI falls short of requirements, the genetic algorithm's fitness function weights were adjusted through analysis of the feedback data, and a new parameter optimization solution was generated and implemented again.

[0047] Design a decision support system that leverages artificial intelligence algorithms (such as reinforcement learning) and combines current operating conditions with historical data to provide real-time optimization recommendations. This system can coordinately adjust system operation strategies based on variables such as market energy price fluctuations, real-time load demand, and environmental conditions, achieving dual optimization of economic and ecological benefits.

[0048] Through the above steps, a real-time dynamic optimization system with intelligent algorithms as the core is built, which can flexibly adapt to the ever-changing energy usage environment and ensure the efficiency and stability of the energy management system under various operating conditions.

[0049] It can be seen that the energy operation data of the energy management system when adopting the current energy parameter configuration scheme is collected; based on the energy operation data, a pre-trained energy status assessment model based on artificial intelligence is used to evaluate the operation status of the energy management system and calculate the operation stability index of the energy management system; based on the operation status and the operation stability index, the energy parameter configuration scheme of the energy management system is optimized, thereby effectively improving the operation stability and energy efficiency of the energy management system and providing strong support for sustainable development.

[0050] Another embodiment of the present invention provides an energy optimization system based on artificial intelligence, see Figure 3 , the system may include: The collection module 301 is used to collect energy operation data of the energy management system when the current energy parameter configuration scheme is adopted; An evaluation module 302 is configured to evaluate the operating status of the energy management system and calculate an operating stability index of the energy management system based on the energy operating data using a pre-trained energy status evaluation model based on artificial intelligence; The optimization module 303 is configured to optimize the energy parameter configuration scheme of the energy management system according to the operation status and the operation stability index.

[0051] It can be seen that the energy operation data of the energy management system when adopting the current energy parameter configuration scheme is collected; based on the energy operation data, a pre-trained energy status assessment model based on artificial intelligence is used to evaluate the operation status of the energy management system and calculate the operation stability index of the energy management system; based on the operation status and the operation stability index, the energy parameter configuration scheme of the energy management system is optimized, thereby effectively improving the operation stability and energy efficiency of the energy management system and providing strong support for sustainable development.

[0052] An embodiment of the present invention further provides a storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0053] Specifically, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps: S201, collecting energy operation data of the energy management system when adopting the current energy parameter configuration solution; S202, based on the energy operation data, using a pre-trained artificial intelligence-based energy status assessment model to assess the operating status of the energy management system and calculate an operating stability index of the energy management system; S203: Optimize the energy parameter configuration scheme of the energy management system according to the operating status and the operating stability index.

[0054] It can be seen that the energy operation data of the energy management system when adopting the current energy parameter configuration scheme is collected; based on the energy operation data, a pre-trained energy status assessment model based on artificial intelligence is used to evaluate the operation status of the energy management system and calculate the operation stability index of the energy management system; based on the operation status and the operation stability index, the energy parameter configuration scheme of the energy management system is optimized, thereby effectively improving the operation stability and energy efficiency of the energy management system and providing strong support for sustainable development.

[0055] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0056] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0057] Specifically, in this embodiment, the processor may be configured to execute the following steps through a computer program: S201, collecting energy operation data of the energy management system when adopting the current energy parameter configuration solution; S202, based on the energy operation data, using a pre-trained artificial intelligence-based energy status assessment model to assess the operating status of the energy management system and calculate an operating stability index of the energy management system; S203: Optimize the energy parameter configuration scheme of the energy management system according to the operating status and the operating stability index.

[0058] It can be seen that the energy operation data of the energy management system when adopting the current energy parameter configuration scheme is collected; based on the energy operation data, a pre-trained energy status assessment model based on artificial intelligence is used to evaluate the operation status of the energy management system and calculate the operation stability index of the energy management system; based on the operation status and the operation stability index, the energy parameter configuration scheme of the energy management system is optimized, thereby effectively improving the operation stability and energy efficiency of the energy management system and providing strong support for sustainable development.

[0059] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the scope of implementation of the present invention is not limited to what is shown in the drawings. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which do not exceed the spirit covered by the description and drawings, should be within the scope of protection of the present invention.

Claims

1. An energy optimization method based on artificial intelligence, characterized in that: The method comprises: Collect energy operation data of the energy management system when using the current energy parameter configuration solution; According to the energy operation data, using a pre-trained energy status assessment model based on artificial intelligence, the operation status of the energy management system is assessed, and an operation stability index of the energy management system is calculated; An energy parameter configuration scheme of an energy management system is optimized according to the operating status and the operating stability index.

2. The method according to claim 1, characterized in that The calculation formula of the operation stability index is: Among them, the is the operation stability index, is the energy consumption rate at the tth collection time point, is the energy consumption fluctuation frequency at the tth collection time point, is the environmental disturbance index at the tth acquisition time point, is the system redundancy at the tth acquisition time point, , , is the corresponding weight coefficient, is the attenuation factor.

3. The method according to claim 2, characterized in that The calculation formula of the energy consumption rate is: Wherein, the E(t) is the total energy consumption at the t-th collection time point, and the L(t) is the total load at the t-th collection time point.

4. The method according to claim 2, characterized in that: The calculation formula of the energy consumption fluctuation frequency is: Wherein, k is the preset number of previous collection time points, and k is less than t.

5. The method according to claim 2, characterized in that: The calculation formula of the environmental disturbance index is: Among them, the is the measured value of the jth environmental indicator at the tth collection time point, is the historical average value of the jth environmental indicator, is the weight factor of the jth environmental indicator, and n is the number of environmental indicators.

6. The method according to claim 2, characterized in that The calculation formula of the system redundancy is: Among them, the is the connectivity of the mth device in the energy management system, where M is the number of devices.

7. The method according to any one of claims 3 to 6, characterized in that: The step of optimizing the energy parameter configuration scheme of the energy management system according to the operating state and the operating stability index includes: If the operating state is in an abnormal state and / or the operating stability index exceeds a preset threshold, the energy parameter configuration scheme of the energy management system is adjusted so that the operating state is in a normal state and the operating stability index does not exceed the preset threshold.

8. An energy optimization system based on artificial intelligence, characterized in that: The system comprises: A collection module is used to collect energy operation data of the energy management system when the current energy parameter configuration scheme is adopted; An evaluation module, for evaluating the operation status of the energy management system and calculating the operation stability index of the energy management system based on the energy operation data by using a pre-trained energy status evaluation model based on artificial intelligence; The optimization module is used to optimize the energy parameter configuration scheme of the energy management system according to the operating state and the operating stability index.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 7.

Images