AI-based intelligent energy management method and system for air conditioning equipment

Abstract

The invention discloses an AI-based intelligent energy management method and system for air conditioning equipment. The method comprises the following steps that indoor environment data are collected in real time through a sensor on the air conditioning equipment; cleaning, de-noising and normalizing the acquired environment data; collecting air conditioner setting preference data of the user; based on the collected data, reasoning and result output are conducted on operation of the air conditioner through an AI model in the edge computing device; according to the result output, an air conditioner control strategy adapting to the current environment and user requirements is generated; dynamically adjusting the operation mode of the air conditioner based on the real-time load and the power grid condition; the air conditioner control strategy is adjusted according to feedback data in the air conditioner operation process; according to the AI-based intelligent energy management method and system for the air conditioning equipment, a comfortable environment can be provided, efficient energy management can be achieved, the overall energy consumption is reduced, and the pressure on a power grid is reduced.

Description

Technical Field

[0001] The present invention specifically relates to an AI-based intelligent energy management method and system for air-conditioning equipment. Background Art

[0002] With the continuous increase in global energy consumption and increasingly severe environmental problems, how to effectively manage and optimize energy use has become a technical problem that needs to be solved in all walks of life. In homes, commercial and industrial buildings, air conditioning equipment is one of the main energy-consuming equipment, and its energy consumption accounts for an important proportion of the total energy consumption. The control method of traditional air conditioning equipment mainly relies on simple temperature sensors and user-preset control strategies. This method usually cannot be flexibly adjusted according to environmental changes and user needs, resulting in energy waste, insufficient user comfort and excessive burden on the power grid.

[0003] Existing air-conditioning systems usually rely on a single temperature sensor for operation control, and lack comprehensive perception of complex environmental factors (such as humidity, air quality, CO2 concentration, light intensity, etc.). Multidimensional data of the environment is crucial for the precise control of air-conditioning systems. Since traditional air-conditioning systems fail to effectively integrate multiple environmental sensors, they can only adjust the air-conditioning operation mode based on a single factor of temperature, and cannot respond to changes in other environmental factors in real time. For example, when the air quality is poor, even if the temperature is appropriate, the air conditioner should adjust its operation mode to purify the air; when the light is strong, the air conditioner should also increase its cooling capacity to avoid the temperature rising too quickly. Existing technologies make it difficult to integrate these environmental data, resulting in a low level of intelligence in the air-conditioning system.

[0004] In addition, environmental data is often interfered with by noise, sensor errors, external environmental changes, etc. during the collection process. Traditional systems often do not have effective algorithms to clean and remove abnormal data, which makes the system vulnerable to inaccurate information when making decisions, resulting in unstable air conditioning operation and even energy waste.

[0005] Existing air conditioning systems often rely on fixed temperature settings and operating modes, and users must manually adjust the air conditioning settings to suit their personal needs during use. However, each user has different comfort preferences, and these preferences may change with time, season, activity type, and other factors. Traditional air conditioning systems are unable to make adaptive adjustments based on users' real-time needs and environmental changes, resulting in a large amount of energy waste. For example, when a user leaves the room, the air conditioner may continue to work and cannot automatically enter energy-saving mode; when the user adjusts the temperature, the air conditioner may not respond immediately, causing discomfort or over-operation.

[0006] Although some high-end air conditioning products have begun to introduce intelligent control functions, such as remote adjustment through mobile phone apps, these systems still lack sufficient intelligence and personalization. They usually rely on simple rules or fixed patterns based on time periods and cannot truly make dynamic decisions based on environmental changes and users' immediate needs. In addition, lacking the support of efficient machine learning algorithms, these systems cannot optimize the energy efficiency and comfort of air conditioning based on long-term usage data.

[0007] The high energy consumption of air conditioning equipment is particularly prominent during periods of high grid load, especially during high temperatures in summer, when the air conditioning load reaches its peak, placing enormous pressure on the grid. Existing air conditioning equipment generally cannot proactively consider grid load and energy supply conditions, especially during periods of tight electricity demand, when the air conditioning system may still operate at maximum power, causing grid overload, increased energy costs, and even unstable power supply.

[0008] Although some smart air conditioners have begun to introduce load regulation functions, most existing technologies have a lag in responding to grid load changes, and often rely only on simple time scheduling or preset energy-saving modes for adjustment, lacking a dynamic, real-time regulation mechanism. These systems often fail to comprehensively consider the complex relationship between grid demand, user demand, indoor environmental changes, and energy consumption, resulting in low energy efficiency.

[0009] Modern air conditioning equipment increasingly relies on cloud computing and remote control to achieve intelligent management. However, due to the reliance on cloud computing, there is a certain delay in data transmission and processing, which will affect the system's response speed to sudden environmental changes. In some time-sensitive situations (such as users entering or leaving the room, sudden temperature fluctuations, etc.), the traditional cloud processing mode cannot respond in time, and the adjustment of the air conditioning system may be delayed, affecting the user's comfort.

[0010] In addition, reliance on cloud computing also brings some privacy and security risks, especially when it comes to the collection and transmission of user habits and environmental data. Most existing technologies rely on centralized cloud computing platforms for data analysis and decision-making, but lack localized intelligent decision-making and processing capabilities, which limits the response speed and autonomous decision-making capabilities of air-conditioning equipment.

[0011] Existing air conditioning control systems lack a complete feedback mechanism, which results in their inability to perform real-time self-optimization according to actual conditions during operation. For example, if the air conditioning system only relies on simple temperature settings, it cannot effectively identify changes in user comfort or subtle fluctuations in environmental factors, which may lead to over-cooling or heating and waste of energy. In addition, traditional air conditioning systems lack the ability to learn long-term operating data and cannot gradually optimize control strategies through feedback data during operation.

[0012] Although some high-end air-conditioning products have automatic adjustment modes, most of them are based on fixed rules or rules of thumb and cannot truly achieve intelligent optimization and adaptive adjustment. Summary of the invention

[0013] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an AI-based intelligent energy management method and system for air-conditioning equipment, which can not only provide a comfortable environment, but also achieve efficient energy management, reduce overall energy consumption, and reduce the pressure on the power grid.

[0014] The technical solution adopted by the present invention to solve its technical problem is: The AI-based intelligent energy management method for air conditioning equipment includes the following steps: Collect indoor environmental data in real time through sensors on air-conditioning equipment, including temperature, humidity, air quality, CO2 concentration, and light intensity; Clean, denoise and normalize the collected environmental data to remove outliers and standardize the data; Collect users’ air conditioning setting preference data, including target temperature, usage mode, and operating time period; Based on the collected data, the AI ​​model in the edge computing device is used to infer the operation of the air conditioner and output the results; Based on the output results, generate air conditioning control strategies that adapt to the current environment and user needs, and adjust the temperature, wind speed, and operating mode of the air conditioner; Based on real-time load and grid conditions, dynamically adjust air conditioning operation mode, optimize energy consumption, and adopt energy-saving strategies when load is high or grid is tight; Adjust the air conditioning control strategy based on the feedback data during air conditioning operation.

[0015] As a preferred method, the method of collecting indoor environment data in real time through sensors on air conditioning equipment is: Use temperature sensor to measure indoor temperature; Use humidity sensors to measure the humidity level of indoor air; Use air quality sensors to detect harmful gases in indoor air; Use light sensors to detect indoor light intensity; The above collected data is transmitted to the air conditioning control system through digital output.

[0016] Preferably, the method for cleaning, denoising and normalizing the collected environmental data is: For missing environmental data, we filled the missing data through mean interpolation, checked whether there were duplicate records in the data set, and deleted the redundant duplicates; Smooth the data using a median filter, replacing each point in the data with the median value of its neighborhood; The data is linearly converted to between 0 and 1. The formula is as follows: X′=(X−Xmin) / (Xmax−Xmin) Among them, X is the original data, Xmin and Xmax are the minimum and maximum values ​​of the data respectively, and X′ is the normalized data.

[0017] Preferably, the method for collecting the user's air conditioning setting preference data is: By analyzing the user's historical air conditioning setting records, the user's air conditioning setting preferences during the day, night, weekdays, weekends, and under different environmental conditions are extracted to form a personalized air conditioning preference model for the user; The collected air conditioning setting data, environmental data and user behavior data are stored in the local server.

[0018] Preferably, the method for inferring the operation of the air conditioner through the AI ​​model in the edge computing device is: The edge computing device receives environmental data on indoor and outdoor temperature, humidity, and air quality, as well as the user’s air conditioning setting preference data, by connecting to the real-time data stream of the sensor; Edge devices use pre-deployed AI models to quickly reason about collected data, including: Based on historical data and current environmental conditions, infer the required temperature of the air conditioner in the next period of time; Reasoning whether the air conditioner should switch modes based on current and predicted indoor and outdoor temperature differences and humidity conditions; Based on the temperature difference, humidity, and air quality parameters, infer whether the air conditioner's wind speed needs to be adjusted; Reason whether the air conditioner needs to be turned on or off based on the temperature fluctuations in the room.

[0019] As a preferred method, the method of outputting the inference result of the air conditioner operation through the AI ​​model in the edge computing device is: According to the inference of the required temperature of the air conditioner in the next period of time, a temperature adjustment request signal is output; According to the inference of whether the air conditioner should switch the mode, output a signal for switching the working mode of the air conditioner, including switching from cooling to heating, or entering energy-saving mode; Based on the inference, whether the wind speed of the air conditioner needs to be adjusted, a wind speed adjustment signal is output; Based on the inference of whether the air conditioner needs to be turned on or off, a signal to automatically turn on or off the air conditioner is output.

[0020] As a preferred method, the method of generating an air conditioning control strategy adapted to the current environment and user needs is: If an output temperature adjustment request signal is received, a temperature control strategy is generated; If a signal for switching the working mode of the air conditioner is received, a cooling mode or heating mode strategy is generated; If a wind speed adjustment signal is received, a ventilation mode or dehumidification mode strategy is generated; If an automatic air-conditioning on or off signal is received, a timed on / off strategy is generated.

[0021] Another technical problem to be solved by the present invention is to provide an AI-based intelligent energy management system for air-conditioning equipment, comprising: Data collection module: used to collect environmental data of air-conditioning equipment and user preference data; Data processing module: used to pre-process and clean the collected data and eliminate data noise; AI decision-making module: The AI ​​model running on the edge computing device makes intelligent control decisions for the air-conditioning equipment; Control module: Generates control signals based on AI decision results to adjust operating parameters such as temperature and wind speed of air-conditioning equipment; Feedback module: Provides real-time feedback on the operation status of air-conditioning equipment and adjusts control strategies based on feedback data.

[0022] Another technical problem to be solved by the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, an AI-based intelligent energy management method for air-conditioning equipment as described above is implemented.

[0023] Another technical problem to be solved by the present invention is to provide a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements, for example, an AI-based intelligent energy management method for air-conditioning equipment.

[0024] The beneficial effects of the present invention are: Through data cleaning, denoising and normalization, we ensure that the collected environmental data is accurate, stable and in line with the actual situation. This process solves the impact of sensor errors and environmental noise on data quality, allowing the system to make reasonable decisions based on reliable data; by collecting users' air conditioning setting preference data (such as target temperature, usage mode, operating time period, etc.), combined with AI models for reasoning and intelligent decision-making, the air conditioner can dynamically adjust the operating mode, temperature and wind speed to meet users' comfort needs and optimize energy use.

[0025] By monitoring the grid load and energy consumption in real time, and combining the air conditioner operation status with environmental requirements, the air conditioner operation mode can be adjusted dynamically. For example, during periods when the grid load is high or electricity prices are high, the system will automatically adopt energy-saving strategies (such as increasing temperature settings, reducing wind speeds, entering standby mode, etc.) to optimize the energy consumption of the air conditioner and reduce pressure on the grid; by integrating feedback data (such as instant feedback from users, temperature changes during air conditioner operation, user activity patterns, etc.), the system can optimize control strategies in real time to ensure that the air conditioner always maintains optimal comfort and energy efficiency during operation. For example, if the system detects that the user has left the room, it will automatically turn off the air conditioner; or when the air conditioner load is too large, it will automatically adjust the settings to reduce energy consumption.

[0026] By deploying AI models on edge computing devices, the air conditioning system can perform data processing and decision analysis locally in real time. This edge computing method can significantly reduce the delay of data transmission, allowing the system to respond more sensitively and efficiently to changes in the environment and user needs, and adjust the air conditioning settings in real time; through the reasoning ability of the AI ​​model, the system can predict and analyze load demand and optimize energy consumption. For example, the system can predict temperature fluctuations in the future and adjust the air conditioning operation strategy in advance (such as adjusting the wind speed and setting the temperature) to avoid excessive operation of the air conditioning and reduce energy waste.

[0027] Through the integration of smart home platforms, the air conditioning system can be linked with other devices. For example, when a user enters a room, the air conditioning can be automatically turned on, the lighting system is turned on, and the curtains are automatically adjusted. At the same time, the system is uniformly dispatched according to the operating status and energy consumption of each device, thereby achieving overall energy optimization. DETAILED DESCRIPTION

[0028] The principles and features of the present invention are described below, and the examples are only used to explain the present invention and are not used to limit the scope of the present invention. The present invention is described more specifically by way of example in the following paragraphs. According to the following description and claims, the advantages and features of the present invention will become clearer.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0030] Example The AI-based intelligent energy management method for air conditioning equipment includes the following steps: Collect indoor environmental data in real time through sensors on air-conditioning equipment, including temperature, humidity, air quality, CO2 concentration, and light intensity; Clean, denoise and normalize the collected environmental data to remove outliers and standardize the data; Collect users’ air conditioning setting preference data, including target temperature, usage mode, and operating time period; Based on the collected data, the AI ​​model in the edge computing device is used to infer the operation of the air conditioner and output the results; Based on the output results, generate air conditioning control strategies that adapt to the current environment and user needs, and adjust the temperature, wind speed, and operating mode of the air conditioner; Based on real-time load and grid conditions, dynamically adjust air conditioning operation mode, optimize energy consumption, and adopt energy-saving strategies when load is high or grid is tight; Adjust the air conditioning control strategy based on the feedback data during air conditioning operation.

[0031] The solution can dynamically adjust the air conditioner's operating strategy based on real-time collected environmental data (such as temperature, humidity, air quality, etc.) and the user's personalized needs (such as target temperature, usage mode, etc.). Through intelligent control, the air conditioner can minimize energy waste while ensuring comfort. For example, when the temperature in the room is appropriate and no one is in the room, the air conditioner can automatically reduce power or enter standby mode; when the user enters the room or the environment changes, the air conditioner can respond quickly and adjust the settings, effectively avoiding unnecessary energy consumption.

[0032] By continuously collecting and analyzing users' air conditioning preference data (such as target temperature, usage mode, and operating time period), the AI ​​model can achieve personalized intelligent control to ensure that users can enjoy the best comfort experience in different time periods and scenarios. User needs can be adapted in real time. For example, in sleep mode, the temperature and wind speed of the air conditioner will automatically adjust to an appropriate range; in working mode, the air conditioner will remain in a certain comfortable range to avoid excessive cooling or heating.

[0033] The AI ​​model can generate the most suitable air conditioning control strategy based on a comprehensive analysis of environmental data and user needs. For example, when the CO2 concentration in the environment is high, the air conditioner can automatically switch to ventilation mode to help improve air quality; when the light intensity is strong, the air conditioner can automatically increase the cooling capacity to maintain a stable indoor temperature. In addition, the AI ​​algorithm can learn and adapt to the user's behavior patterns in real time, thereby continuously optimizing the air conditioner's operating strategy and achieving more precise control.

[0034] By introducing real-time load and grid monitoring, the solution can dynamically adjust the air conditioner's operating mode to avoid unnecessary energy consumption during peak grid load periods. For example, when the grid is tight, the air conditioner can automatically enter energy-saving mode to reduce energy consumption and effectively reduce the burden on the grid. This energy-saving strategy not only helps reduce users' electricity bills, but also promotes sustainable energy management.

[0035] The air conditioning system can continuously adjust and optimize the control strategy based on real-time feedback data (such as temperature changes, user behavior, etc.). The AI ​​model can flexibly adjust the control strategy based on this feedback information to further improve the accuracy and efficiency of air conditioning operation. By continuously learning and accumulating operating data, the intelligence level of air conditioning is gradually improved, further improving the user's comfort experience and improving the energy efficiency of the system.

[0036] The method of collecting indoor environment data in real time through sensors on air conditioning equipment is: Use temperature sensor to measure indoor temperature; Use humidity sensors to measure the humidity level of indoor air; Use air quality sensors to detect harmful gases in indoor air; Use light sensors to detect indoor light intensity; The above collected data is transmitted to the air conditioning control system through digital output.

[0037] The method for cleaning, denoising and normalizing the collected environmental data is as follows: For missing environmental data, we filled the missing data through mean interpolation, checked whether there were duplicate records in the data set, and deleted the redundant duplicates; Smooth the data using a median filter, replacing each point in the data with the median value of its neighborhood; The data is linearly converted to between 0 and 1. The formula is as follows: X′=(X−Xmin) / (Xmax−Xmin) Among them, X is the original data, Xmin and Xmax are the minimum and maximum values ​​of the data respectively, and X′ is the normalized data.

[0038] Filling missing data with mean interpolation can avoid air conditioning control decision errors caused by missing data. For example, if the temperature sensor fails to collect data successfully at a certain moment, mean interpolation can use other temperature values ​​in the data set to fill in, thereby avoiding abnormal behavior of the air conditioning control system due to missing data. This method ensures the continuity of data and improves data integrity; it deletes redundant duplicate records to ensure that each collected data is unique and accurate. Duplicate data may cause the air conditioning control system to make inappropriate adjustments based on incorrect information, affecting the system's operating efficiency and energy consumption. Deduplication can eliminate this risk and ensure the accuracy of the control strategy.

[0039] The median filter is used to smooth the data and effectively remove noise caused by sensor fluctuations, environmental changes, or data transmission errors. This ensures that the data is more stable and reduces the impact of outliers on system decisions. By replacing each data point with the median of its neighborhood, the median filter can effectively remove spikes or sudden changes in outliers, ensuring that the air conditioning control system is based on more accurate and stable data.

[0040] Normalizing the data (by linearly converting it to between 0 and 1) allows sensor data of different dimensions and magnitudes (such as temperature, humidity, air quality, and light intensity) to be compared and processed on the same scale. This is very important for subsequent machine learning model training, reasoning, and control decisions. Because many machine learning algorithms (such as neural networks, support vector machines, etc.) are very sensitive to the scale of input data, normalization can speed up the convergence of the algorithm and improve the accuracy and generalization ability of the model; by cleaning, denoising, and normalizing environmental data, the air conditioning control system can respond promptly based on more accurate and stable data. Air conditioning adjustment parameters (such as temperature, humidity, wind speed, etc.) can be dynamically adjusted based on the cleaned high-quality data, thereby improving energy efficiency and user comfort.

[0041] Cleaned and standardized data can help the air conditioning system more accurately perceive and understand changes in the indoor environment, and make more precise control decisions. For example, light intensity and temperature data can accurately reflect changes in indoor heat load, and air quality data can guide whether the air conditioner needs to turn on the air purification function. More accurate data means that the air conditioner can adjust its operation according to real-time needs to achieve the goal of energy saving and consumption reduction.

[0042] The method for collecting the user's air conditioning setting preference data is: By analyzing the user's historical air conditioning setting records, the user's air conditioning setting preferences during the day, night, weekdays, weekends, and under different environmental conditions are extracted to form a personalized air conditioning preference model for the user; The collected air conditioning setting data, environmental data and user behavior data are stored in the local server.

[0043] By analyzing the user's air conditioning setting preferences in different time periods (daytime, nighttime, weekdays, weekends) and under different environmental conditions, a highly personalized air conditioning preference model can be created. This model can accurately predict the user's needs and automatically adjust the air conditioning settings to improve the user's comfort. For example, if the user usually sets the temperature to 24°C during the day on weekdays and prefers a slightly lower temperature on weekends, the air conditioning system can automatically adjust according to these preferences without the user's manual intervention, providing a more customized user experience.

[0044] By deeply understanding the user's air conditioning usage patterns, the air conditioning operation can be optimized according to different environmental conditions and time periods. For example, the system can automatically adjust the air conditioning temperature, wind speed and other parameters to avoid wasting energy when the user does not need the air conditioning (such as when the user is away from home on weekdays). By predicting the user's preferences in advance and adjusting the working status of the air conditioner appropriately, the system can maximize energy savings and reduce unnecessary electricity consumption, thereby achieving energy-saving effects and reducing household energy expenses.

[0045] Storing the user's air conditioning setting data, environmental data, and behavioral data in a local server can effectively enhance the privacy protection of user data. Compared with uploading data to the cloud, local storage can avoid the risk of data leakage and ensure that user personal information is not accessed or abused without authorization. At the same time, local storage can also reduce dependence on the network and improve the speed and responsiveness of data access. In addition, this method is also conducive to ensuring data security and reducing service interruptions caused by cloud platform failures or network problems.

[0046] The method of reasoning about air conditioning operation through the AI ​​model in the edge computing device is: The edge computing device receives environmental data on indoor and outdoor temperature, humidity, and air quality, as well as the user’s air conditioning setting preference data, by connecting to the real-time data stream of the sensor; Edge devices use pre-deployed AI models to quickly reason about collected data, including: Based on historical data and current environmental conditions, infer the required temperature of the air conditioner in the next period of time; Reasoning whether the air conditioner should switch modes based on current and predicted indoor and outdoor temperature differences and humidity conditions; Based on the temperature difference, humidity, and air quality parameters, infer whether the air conditioner's wind speed needs to be adjusted; Reason whether the air conditioner needs to be turned on or off based on the temperature fluctuations in the room.

[0047] The method of outputting the inference results of air conditioner operation through the AI ​​model in the edge computing device is as follows: According to the inference of the required temperature of the air conditioner in the next period of time, a temperature adjustment request signal is output; According to the inference of whether the air conditioner should switch the mode, output a signal for switching the working mode of the air conditioner, including switching from cooling to heating, or entering energy-saving mode; Based on the inference, whether the wind speed of the air conditioner needs to be adjusted, a wind speed adjustment signal is output; Based on the inference of whether the air conditioner needs to be turned on or off, a signal to automatically turn on or off the air conditioner is output.

[0048] Edge computing devices can process and analyze data locally without relying on remote servers or cloud computing. This local processing method greatly reduces the delay of data transmission and processing, enabling the air conditioning control system to respond to environmental changes in real time. For example, when the indoor temperature changes, the edge device can immediately reason and make decisions to adjust the air conditioning temperature, wind speed or mode, thereby improving the immediacy and response speed of air conditioning operation and ensuring that the indoor environment is always in an ideal state.

[0049] Through the AI ​​model's precise reasoning of environmental data, the system can automatically adjust the air conditioner's operating mode and working status according to parameters such as indoor and outdoor temperature difference, humidity, and air quality to optimize energy use. For example, when the ambient temperature is suitable, the air conditioning system can intelligently switch to energy-saving mode, or automatically turn off the air conditioner in a room that is not in use, thereby avoiding energy waste. The AI ​​model can also predict environmental changes in the future and adjust the air conditioning settings in advance to further improve the energy-saving effect of the air conditioner and reduce electricity bills.

[0050] By combining the user's air conditioning setting preferences with environmental sensor data, edge devices can provide each user with a personalized air conditioning control experience. The AI ​​model can infer the most appropriate air conditioning settings based on historical behavior data and real-time environmental conditions to maintain user comfort. For example, the system can automatically adjust the temperature, humidity, wind speed according to user habits, or automatically adjust the ventilation mode according to changes in air quality to improve air quality and user living comfort. In addition, intelligent reasoning can also automatically optimize air conditioning settings according to different scenarios (such as work, rest, etc.) without manual user intervention.

[0051] Placing AI reasoning and control decisions on edge devices not only improves response speed, but also reduces the system's dependence on network connections. Even if the network fails briefly, the air conditioning system can still rely on edge computing devices to operate independently and maintain normal control functions, improving the reliability and stability of the system. In addition, because data is processed locally, user privacy and data security are enhanced, avoiding the risk of privacy leakage that may arise from uploading sensitive data to the cloud.

[0052] AI reasoning can determine in real time when to switch air conditioning modes (such as cooling, heating or energy-saving mode) to adapt to different environments and user needs. The system can automatically select the appropriate working mode based on various factors such as temperature, humidity, and air quality, avoiding the tedious operation of traditional air conditioners that require users to manually adjust. At the same time, the system can intelligently determine whether the air conditioner needs to be turned on or off, further improving the level of automated control, reducing manual operations, and improving user convenience.

[0053] This solution gives the air conditioning system a higher level of intelligence through real-time data collection and intelligent reasoning. Users no longer need to frequently adjust the air conditioning settings, but can rely on the system to automatically make the best adjustments based on environmental conditions and user preferences, so as to enjoy a more seamless and comfortable experience. At the same time, through continuous learning and optimization, the system can become more accurate and efficient as the usage time increases, further improving the user experience.

[0054] The method to generate an air conditioning control strategy that adapts to the current environment and user needs is: If an output temperature adjustment request signal is received, a temperature control strategy is generated; If a signal for switching the working mode of the air conditioner is received, a cooling mode or heating mode strategy is generated; If a wind speed adjustment signal is received, a ventilation mode or dehumidification mode strategy is generated; If an automatic air-conditioning on or off signal is received, a timed on / off strategy is generated.

[0055] This solution automatically generates corresponding control strategies based on signal input, avoiding the tedious operation of users manually adjusting the air conditioner and improving the intelligence level of the air conditioning system. Whether it is temperature adjustment, working mode switching, wind speed adjustment, or air conditioner switch control, it can be automatically adjusted according to real-time environmental data and user needs, greatly improving the system's automation level and user experience.

[0056] Whenever the system receives different types of control signals, it can generate corresponding optimized control strategies based on specific needs. For example, after receiving a temperature adjustment request signal, the system will accurately adjust to the set temperature to ensure that the user's comfort needs are met; and when receiving a wind speed adjustment signal, the system will automatically switch to the appropriate ventilation or dehumidification mode. This signal-driven control strategy ensures that the system can respond in real time according to the actual environment and user needs, providing more personalized services.

[0057] The operating mode and strategy of the air conditioner are not only affected by the user's preferences, but also closely related to the external environment. For example, when the external temperature is high, the air conditioner will automatically enter the cooling mode; in a colder or humid environment, the air conditioner will automatically switch to the heating or dehumidification mode. This flexible strategy generation method enables the air conditioning system to automatically adjust the working mode to adapt to different climatic conditions according to the changes in the current environment, thereby ensuring the best air quality and temperature and humidity control.

[0058] By intelligently generating corresponding control strategies according to environmental requirements, the air conditioner can efficiently adjust its operating mode. For example, when the temperature is close to the set value, the system can adjust the air conditioner's working intensity and enter energy-saving mode or low wind speed operation to reduce energy consumption. In addition, when there are no conditions requiring air conditioning adjustment, the system can automatically turn off the air conditioner or adjust it to standby mode to avoid unnecessary energy waste and further reduce electricity costs.

[0059] Users often have specific air conditioning needs, such as wanting to maintain a comfortable temperature or adjust the air humidity during a certain period of time. By automatically generating appropriate control strategies, the system can seamlessly adapt to these needs. For example, if the user prefers a higher wind speed to cool down quickly, the system will automatically switch to strong wind mode; if the user likes warm and humid air, the air conditioner will automatically enter heating and adjust the humidity. Such personalized adjustments provide users with a more comfortable experience.

[0060] An AI-based intelligent energy management system for air conditioning equipment, comprising: Data collection module: used to collect environmental data of air-conditioning equipment and user preference data; Data processing module: used to pre-process and clean the collected data and eliminate data noise; AI decision-making module: The AI ​​model running on the edge computing device makes intelligent control decisions for the air-conditioning equipment; Control module: Generates control signals based on AI decision results to adjust operating parameters such as temperature and wind speed of air-conditioning equipment; Feedback module: Provides real-time feedback on the operation status of air-conditioning equipment and adjusts control strategies based on feedback data.

[0061] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an AI-based intelligent energy management method for air-conditioning equipment as described above is implemented.

[0062] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the AI-based intelligent energy management method for air-conditioning equipment as described above is implemented.

[0063] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0064] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0065] The above embodiments of the present invention are not intended to limit the protection scope of the present invention, and the implementation modes of the present invention are not limited thereto. All other modifications, replacements or changes made to the above structures of the present invention based on the above contents of the present invention, in accordance with common technical knowledge and customary means in the art, without departing from the above basic technical ideas of the present invention, should fall within the protection scope of the present invention.

Claims

1. An AI-based intelligent energy management method for air conditioning equipment, characterized in that: The following steps are involved: Collect indoor environmental data in real time through sensors on air-conditioning equipment, including temperature, humidity, air quality, CO2 concentration, and light intensity; Clean, denoise and normalize the collected environmental data to remove outliers and standardize the data; Collect users’ air conditioning setting preference data, including target temperature, usage mode, and operating time period; Based on the collected data, the AI ​​model in the edge computing device is used to infer the operation of the air conditioner and output the results; Based on the output results, generate air conditioning control strategies that adapt to the current environment and user needs, and adjust the temperature, wind speed, and operating mode of the air conditioner; Based on real-time load and grid conditions, dynamically adjust air conditioning operation mode, optimize energy consumption, and adopt energy-saving strategies when load is high or grid is tight; Adjust the air conditioning control strategy based on the feedback data during air conditioning operation.

2. The AI-based intelligent energy management method for air conditioning equipment according to claim 1 is characterized in that: The method of collecting indoor environment data in real time through sensors on air conditioning equipment is: Use temperature sensor to measure indoor temperature; Use humidity sensors to measure the humidity level of indoor air; Use air quality sensors to detect harmful gases in indoor air; Use light sensors to detect indoor light intensity; The above collected data is transmitted to the air conditioning control system through digital output.

3. The AI-based intelligent energy management method for air conditioning equipment according to claim 1 is characterized in that: The method for cleaning, denoising and normalizing the collected environmental data is as follows: For missing environmental data, we filled the missing data through mean interpolation, checked whether there were duplicate records in the data set, and deleted the redundant duplicates; Smooth the data using a median filter, replacing each point in the data with the median of its neighborhood; The data is linearly converted to between 0 and 1. The formula is as follows: X′=(X−Xmin) / (Xmax−Xmin) Among them, X is the original data, Xmin and Xmax are the minimum and maximum values ​​of the data respectively, and X′ is the normalized data.

4. The AI-based intelligent energy management method for air conditioning equipment according to claim 1 is characterized in that: The method for collecting the user's air conditioning setting preference data is: By analyzing the user's historical air conditioning setting records, the user's air conditioning setting preferences during the day, night, weekdays, weekends, and under different environmental conditions are extracted to form a personalized air conditioning preference model for the user; The collected air conditioning setting data, environmental data and user behavior data are stored in the local server.

5. The AI-based intelligent energy management method for air conditioning equipment according to claim 1 is characterized in that: The method of reasoning about air conditioning operation through the AI ​​model in the edge computing device is: The edge computing device receives environmental data such as indoor and outdoor temperature, humidity, and air quality, as well as the user’s air conditioning setting preference data, by connecting to the real-time data stream of the sensor; Edge devices use pre-deployed AI models to quickly reason about collected data, including: Based on historical data and current environmental conditions, infer the required temperature of the air conditioner in the next period of time; Reasoning whether the air conditioner should switch modes based on current and predicted indoor and outdoor temperature differences and humidity conditions; Based on the temperature difference, humidity, and air quality parameters, infer whether the air conditioner's wind speed needs to be adjusted; Reason whether the air conditioner needs to be turned on or off based on the temperature fluctuations in the room.

6. The AI-based intelligent energy management method for air conditioning equipment according to claim 5 is characterized in that: The method of outputting the inference results of air conditioner operation through the AI ​​model in the edge computing device is as follows: According to the inference of the required temperature of the air conditioner in the next period of time, a temperature adjustment request signal is output; According to the inference of whether the air conditioner should switch the mode, output a signal for switching the working mode of the air conditioner, including switching from cooling to heating, or entering energy-saving mode; Based on the inference, whether the wind speed of the air conditioner needs to be adjusted, a wind speed adjustment signal is output; Based on the inference of whether the air conditioner needs to be turned on or off, a signal to automatically turn on or off the air conditioner is output.

7. The AI-based intelligent energy management method for air conditioning equipment according to claim 6 is characterized in that: The method to generate an air conditioning control strategy that adapts to the current environment and user needs is: If an output temperature adjustment request signal is received, a temperature control strategy is generated; If a signal for switching the working mode of the air conditioner is received, a cooling mode or heating mode strategy is generated; If a wind speed adjustment signal is received, a ventilation mode or dehumidification mode strategy is generated; If an automatic air-conditioning on or off signal is received, a timed on / off strategy is generated.

8. An AI-based intelligent energy management system for air conditioning equipment, characterized in that: include: Data collection module: used to collect environmental data of air-conditioning equipment and user preference data; Data processing module: used to pre-process and clean the collected data and eliminate data noise; AI decision-making module: The AI ​​model running on the edge computing device makes intelligent control decisions for the air-conditioning equipment; Control module: Generates control signals based on AI decision results to adjust operating parameters such as temperature and wind speed of air-conditioning equipment; Feedback module: Provides real-time feedback on the operation status of air-conditioning equipment and adjusts control strategies based on feedback data.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the AI-based intelligent energy method for air-conditioning equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the AI-based intelligent energy method for air-conditioning equipment as described in any one of claims 1-7 is implemented.