An energy-saving control method and system based on communication between indoor and outdoor units of a multi-connected air conditioner

Abstract

The application provides an energy-saving control method and system based on communication between indoor and outdoor units of a multi-connected air conditioner, which comprises the following steps: collecting operation parameters and environmental temperature data of the indoor and outdoor units to obtain multi-dimensional data, and transmitting the multi-dimensional data to an upper computer; dynamically predicting cold and heat load demands of each indoor unit by the upper computer, establishing a load demand model of an indoor unit group according to temperature difference change trends and historical operation data of the indoor and outdoor units, and calculating a cold quantity distribution scheme; sending operation instructions to each indoor unit and adjusting instructions to the outdoor unit by the upper computer according to the cold quantity distribution scheme; adjusting the related indoor units and the outdoor unit when detecting that the temperature difference between the indoor units exceeds a preset threshold; learning operation modes and user usage habits of each indoor unit by the upper computer, establishing a comfort degree model, and adjusting control algorithm parameters according to system operation effect feedback. The application significantly reduces system energy consumption, improves overall comfort experience, realizes intelligent energy-saving control, and improves overall operation stability.

Description

Technical Field

[0001] This invention relates to the field of air conditioning control technology, specifically to an energy-saving control method and system based on communication between indoor and outdoor units of a multi-split air conditioner. Background Technology

[0002] Multi-split air conditioning systems, with their advantages of small footprint, flexible zone control, high energy efficiency, strong installation adaptability, flexible use, simple and convenient maintenance, and high energy efficiency under partial load, have become the preferred solution for air conditioning systems in large buildings. Their core principle is to achieve coordinated control of refrigerant flow and temperature through a communication network between indoor and outdoor units. However, existing multi-split air conditioning energy-saving control schemes suffer from problems such as high system energy consumption, poor overall comfort, and rigid and unintelligent control processes. Summary of the Invention

[0003] Based on the above-mentioned problems, this invention proposes an energy-saving control method and system based on communication between indoor and outdoor units of a multi-split air conditioner. This invention significantly reduces system energy consumption, improves overall comfort, achieves intelligent energy-saving control, effectively avoids local overload and system fluctuations, and improves overall operational stability.

[0004] In view of this, one aspect of the present invention proposes an energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, comprising: By synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioning system, the first multi-dimensional data is obtained. The first multidimensional data is transmitted to the host computer in real time. The host computer dynamically predicts the cooling and heating load demand of each indoor unit based on artificial intelligence algorithms, and establishes a load demand model of the indoor unit group based on the trend of indoor and outdoor temperature difference and historical operating data, and calculates the optimal cooling capacity allocation scheme. According to the optimal cooling capacity allocation scheme, the host computer sends personalized operation instructions to each indoor unit controller, and at the same time sends system-level adjustment instructions to the outdoor unit, so as to realize the differentiated adjustment of indoor unit operating parameters and the precise matching of outdoor unit output power. By monitoring the temperature difference between indoor units in real time, when the temperature difference between indoor units exceeds the preset threshold, the fan speed and cooling / heating intensity of the relevant indoor units are automatically adjusted, and the refrigerant distribution strategy of the outdoor unit is adjusted accordingly to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit. The host computer continuously learns the operating modes and user habits of each indoor unit, establishes a personalized comfort model, and dynamically adjusts the control algorithm parameters based on system operation feedback to achieve self-optimization of the system operation strategy.

[0005] Optionally, the step of transmitting the first multidimensional data to the host computer in real time, and the host computer dynamically predicting the cooling and heating load requirements of each indoor unit based on artificial intelligence algorithms, includes: The first multidimensional data is timestamped and its data format is standardized. A mapping relationship between the data of each indoor unit and the corresponding outdoor unit is established. Abnormal data is identified and filtered to ensure the integrity and consistency of the transmitted data, thus obtaining the second multidimensional data. The second multidimensional data is layered and packaged according to indoor unit grouping and data type, and transmitted to the host computer in real time. After receiving the second multidimensional data, the host computer classifies and stores it according to time series and device number, and establishes a real-time data cache area and a historical data storage area. The host computer extracts the temperature change trend, load fluctuation characteristics and operating cycle mode of each indoor unit from the second multi-dimensional data, identifies the key factors affecting the demand for cooling and heating loads, and constructs a personalized load feature vector for each indoor unit. Based on the extracted personalized load feature vectors and historical load data, a deep learning algorithm is used to train the load prediction model for each indoor unit. The model parameters are updated regularly according to the deviation between the prediction results and the actual load to improve the prediction accuracy. Using the trained load forecasting model, combined with current real-time data and environmental change trends, the system dynamically predicts the future cooling and heating load demand of each indoor unit, and outputs the corresponding load demand forecast values ​​and confidence level assessment results.

[0006] Optionally, the step of establishing a load demand model for the indoor unit group based on the trend of indoor and outdoor temperature difference changes and historical operating data, and calculating the optimal cooling capacity allocation scheme, includes: Based on real-time collected indoor and outdoor temperature data, the changing trends and fluctuation patterns of indoor and outdoor temperature differences in different time periods are analyzed, temperature difference change patterns at different time scales are identified, and peak and trough periods and variation amplitude characteristics of temperature difference changes are extracted. Historical operating data are classified and archived according to temperature difference change patterns. The load response characteristics and energy consumption performance of each indoor unit under different temperature difference conditions are analyzed. A temperature difference-load correlation feature library is constructed, and a load demand benchmark model of indoor unit groups under similar environmental conditions is established. Based on the geographical location, room characteristics, and usage patterns of the indoor units, multiple indoor units are divided into groups with similar load characteristics. A dedicated load demand model is established for each group using a load demand baseline model. Combined with the current temperature difference trend, the future cooling and heating load demand changes of each group are predicted. Analyze system boundary conditions such as outdoor unit cooling and heating capacity limitations, refrigerant flow distribution constraints, and power load constraints; evaluate the maximum allocable cooling capacity and minimum guaranteed cooling capacity of each indoor unit group; and determine the feasible range and optimization space for cooling capacity allocation. Taking into account the load demand forecast of each indoor unit group, system capacity constraints and energy-saving targets, a multi-objective optimization algorithm is used to calculate the optimal cooling capacity allocation scheme that balances comfort and energy efficiency, and to generate specific operating parameter adjustment instructions for each indoor unit.

[0007] Optionally, the step of sending personalized operating instructions from the host computer to each indoor unit controller and simultaneously sending system-level adjustment instructions to the outdoor unit according to the optimal cooling capacity allocation scheme, to achieve differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power, includes: The host computer generates a personalized set of operating instructions based on the allocated cooling capacity values ​​of each indoor unit in the optimal cooling capacity allocation scheme, combined with the current operating status of each indoor unit and room characteristic parameters. This set includes the target temperature set value, fan speed adjustment amount, and operating mode switching instructions. It also establishes a precise mapping relationship between the allocated cooling capacity and specific control parameters. Based on the total cooling capacity distribution demand of all indoor units, calculate the total system cooling capacity and corresponding power output demand required by the outdoor unit, and formulate a system-level adjustment strategy that includes compressor frequency adjustment, refrigerant flow distribution ratio and system operation mode to ensure accurate matching between the outdoor unit output power and the total demand of the indoor unit group. Personalized operation commands and system-level adjustment commands generated based on system-level adjustment strategies are prioritized, with priority given to critical commands that have a significant impact on system stability. A timing coordination scheme for command execution is also formulated to ensure that outdoor unit system-level adjustments are executed before indoor unit personalized adjustments, thus avoiding operational conflicts caused by system power mismatch. Through the communication network of the multi-split air conditioning system, system-level adjustment commands are sent to the outdoor unit microcomputer control board in real time, while personalized operation commands are sent to the corresponding indoor unit controllers. A two-way communication confirmation mechanism is established between the host computer and the indoor and outdoor unit controllers to ensure the accurate transmission and execution confirmation of all commands. The system monitors the execution status of commands by each indoor unit controller and the outdoor unit microcomputer control board in real time. When a deviation between the actual execution effect and the expected target is detected, the system automatically triggers the command correction mechanism to dynamically fine-tune the indoor unit operating parameters and the outdoor unit output power, thereby achieving closed-loop control and precise matching.

[0008] Optionally, the step of automatically adjusting the fan speed and cooling / heating intensity of the relevant indoor units and correspondingly adjusting the refrigerant distribution strategy of the outdoor unit when the temperature difference between the indoor units exceeds a preset threshold, thereby ensuring that the temperature in each room tends to be balanced while avoiding excessive cooling capacity input from the outdoor unit, includes: Real-time collection of current room temperature data of each indoor unit; construction of temperature difference monitoring matrix between indoor units; calculation of temperature difference between any two indoor units; comparison of each temperature difference with the corresponding preset threshold; identification of indoor unit combination with excessive temperature difference and specific excessive temperature difference range. For the identified cases of excessive temperature difference, the key causes of the temperature difference were analyzed from several aspects, including load difference, fan speed setting difference, and cooling and heating intensity difference, and the temperature difference analysis results were obtained. Based on the temperature difference analysis results, the target indoor unit and the reference indoor unit that need to be adjusted are determined, the adjustment priority and direction for eliminating temperature difference are established, and the first adjustment strategy is obtained. Based on the first adjustment strategy, a coordinated adjustment strategy for the fan speed and cooling / heating intensity of the relevant indoor units is formulated. For indoor units with high temperature, the cooling intensity is increased or the heating intensity is reduced, and for indoor units with low temperature, the opposite adjustment is taken. At the same time, the fan speed configuration of each indoor unit is optimized to accelerate the temperature equalization process. Based on the overall demand changes of the indoor unit parameter adjustment strategy, the refrigerant demand of each refrigeration circuit is recalculated, and the refrigerant distribution ratio and flow control parameters of the outdoor unit are adjusted to ensure that the refrigerant supply matches the actual demand of each indoor unit after adjustment, and to avoid a surge in the total cooling capacity demand of the system due to local adjustment. After the adjustment is implemented, monitor the temperature difference between indoor units, evaluate the temperature difference balancing effect and the change in total system energy consumption. When the temperature difference still exceeds the preset threshold, iterate and optimize the adjustment strategy based on the feedback of the previous adjustment effect until the temperature of each room reaches the preset equilibrium state.

[0009] Optionally, the host computer continuously learns the operating modes and user habits of each indoor unit, establishes a personalized comfort model, and dynamically adjusts the control algorithm parameters based on system operation feedback to achieve self-optimization of the system operation strategy, including: The host computer records and analyzes the power-on and power-off times, temperature setting preferences, fan speed selection habits, and operating mode switching patterns of each indoor unit over a long period of time. It identifies personalized usage characteristics of different time periods, seasons, and users, and extracts user behavior feature vectors including usage frequency, temperature preference range, and operation response time. Based on user behavior feature vectors and environmental comfort theory, a comprehensive evaluation system including temperature comfort, humidity comfort, airflow comfort and noise comfort is established for each indoor unit. Combined with users' historical satisfaction feedback and adjustment frequency data, a personalized comfort prediction model and comfort weight allocation scheme are constructed. Real-time monitoring of energy consumption indicators, temperature control accuracy indicators, and user operation intervention frequency during system operation; establishment of a multi-dimensional quantitative evaluation system for system operation performance; collection of operation performance feedback data including energy saving effect, comfort achievement, and system response speed; and formation of a system performance evaluation database. Based on the operational performance feedback data and the prediction results of the personalized comfort prediction model, the key parameters and optimization directions affecting the system performance in the current control algorithm are identified. An adaptive optimization algorithm is used to fine-tune and dynamically update the core algorithm parameters such as load prediction parameters, temperature difference control threshold and power distribution weight. The optimized core algorithm parameters are applied to the actual system operation, the implementation effect of the new strategy is continuously evaluated, successful optimization experience and parameter configuration are saved to the system knowledge base, an evolutionary learning mechanism for the operation strategy is established, and the system control intelligence level is continuously improved and the personalized adaptability is continuously strengthened.

[0010] Optionally, the load demand model for the indoor unit group can be established using the following load forecasting formula:

[0011] in, Let be the predicted load demand at time t; The base load factor reflects the inherent heat load characteristics of the room; , , The weighting coefficients are obtained through training with historical data. This is the m-th order temperature difference weighting factor, reflecting the degree of influence of different temperature difference amplitudes on the load; Let m be the indoor-outdoor temperature difference term at time t; The rate of temperature change reflects the dynamic trend of ambient temperature change. This is a time decay factor, reflecting the decay characteristics of the impact of historical data on current predictions. Optionally, in the step of sending personalized operating instructions from the host computer to each indoor unit controller and simultaneously sending system-level adjustment instructions to the outdoor unit according to the optimal cooling capacity allocation scheme, thereby achieving differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power, the following dynamic power allocation algorithm is adopted:

[0012] in, This represents the optimal power output for the nth control cycle. This refers to the rated power of the outdoor unit. The efficiency correction factor for the u-th indoor unit reflects the impact of its current operating status on the system efficiency. The real-time cooling capacity requirement of the uth indoor unit; Let be the capacity allocation coefficient for the v-th refrigeration loop; Let v be the available capacity of the v-th refrigeration circuit; This is an environmental correction function that considers the impact of outdoor temperature and humidity on system performance.

[0013] Optionally, in the step of real-time monitoring of temperature differences between indoor units, automatically adjusting the fan speed and cooling / heating intensity of the relevant indoor units when the temperature difference between indoor units exceeds a preset threshold, and correspondingly adjusting the refrigerant distribution strategy of the outdoor unit to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit, the following adaptive adjustment formula is used to achieve temperature difference balance control:

[0014] in, The fan speed adjustment value for the r-th indoor unit; , These are the proportional and derivative control coefficients, which are adaptively adjusted according to the system characteristics. The deviation between the r-th indoor unit and the target temperature; The rate of change of temperature deviation reflects the temperature trend; is the amplitude coefficient of the s-th harmonic component, used to compensate for periodic temperature fluctuations; Let ω be the angular frequency of the s-th harmonic, corresponding to the temperature change pattern of different periods; Let be the phase angle of the s-th harmonic, reflecting the time characteristics of temperature fluctuations.

[0015] Another aspect of the present invention provides an energy-saving control system based on communication between indoor and outdoor units of a multi-split air conditioner, for executing an energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, comprising: an indoor unit, an outdoor unit, and a host computer; The host computer is configured as follows: By synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioning system, the first multi-dimensional data is obtained. Based on artificial intelligence algorithms, the cooling and heating load requirements of each indoor unit are dynamically predicted. Based on the trend of indoor and outdoor temperature difference and historical operating data, a load demand model of the indoor unit group is established, and the optimal cooling capacity allocation scheme is calculated. Based on the optimal cooling capacity allocation scheme, personalized operation commands are sent to each indoor unit controller, and system-level adjustment commands are sent to the outdoor unit to achieve differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power. By monitoring the temperature difference between indoor units in real time, when the temperature difference between indoor units exceeds the preset threshold, the fan speed and cooling / heating intensity of the relevant indoor units are automatically adjusted, and the refrigerant distribution strategy of the outdoor unit is adjusted accordingly to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit. We continuously learn the operating modes of each indoor unit and user habits, establish personalized comfort models, and dynamically adjust control algorithm parameters based on system performance feedback to achieve self-optimization of system operation strategies.

[0016] The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, using the technical solution of this invention, includes: synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioner system to obtain first multi-dimensional data; transmitting the first multi-dimensional data to a host computer in real time; the host computer dynamically predicts the cooling and heating load demand of each indoor unit based on an artificial intelligence algorithm, and establishes a load demand model for the indoor unit group based on the trend of indoor and outdoor temperature difference changes and historical operating data, calculating the optimal cooling capacity allocation scheme; according to the optimal cooling capacity allocation scheme, the host computer sends individual data to each indoor unit controller. Personalized operation commands are sent to the indoor unit, along with system-level adjustment commands to the outdoor unit, enabling differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power. By monitoring temperature differences between indoor units in real time, when a temperature difference exceeds a preset threshold, the system automatically adjusts the fan speed and cooling / heating intensity of the relevant indoor units and correspondingly adjusts the refrigerant distribution strategy of the outdoor unit. This ensures a more balanced room temperature while preventing excessive cooling from the outdoor unit. The host computer continuously learns the operating modes of each indoor unit and user habits, establishing a personalized comfort model. Based on system performance feedback, it dynamically adjusts control algorithm parameters to achieve self-optimization of the system's operating strategy. Through precise load matching and refrigerant distribution optimization, excessive outdoor unit operation is effectively avoided, significantly reducing system energy consumption. Temperature difference balancing control and personalized adjustment ensure uniform temperature distribution in each room, enhancing overall comfort. Through an adaptive learning mechanism, the system can automatically optimize its operating strategy based on user habits, achieving intelligent energy-saving control. Real-time monitoring and collaborative control effectively prevent localized overload and system fluctuations, improving overall operational stability. Attached Figure Description

[0017] Figure 1 This is a flowchart of an energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, provided in one embodiment of the present invention. Figure 2 This is a schematic block diagram of an energy-saving control system based on communication between indoor and outdoor units of a multi-split air conditioner, provided in one embodiment of the present invention. Detailed Implementation

[0018] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0019] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0020] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] The following reference Figures 1 to 2 This invention describes an energy-saving control method and system based on communication between indoor and outdoor units of a multi-split air conditioner, according to some embodiments of the present invention.

[0023] like Figure 1 As shown, one embodiment of the present invention provides an energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, comprising: By synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioning system, the first multi-dimensional data is obtained. It is understood that the indoor unit operating parameters include set temperature, actual temperature, fan speed setting and operating mode, and the outdoor unit operating status parameters include compressor frequency, refrigerant flow distribution ratio and system pressure value; The first multidimensional data is transmitted to the host computer in real time. The host computer dynamically predicts the cooling and heating load demand of each indoor unit based on artificial intelligence algorithms, and establishes a load demand model of the indoor unit group based on the trend of indoor and outdoor temperature difference and historical operating data, and calculates the optimal cooling capacity allocation scheme. According to the optimal cooling capacity allocation scheme, the host computer sends personalized operation instructions to each indoor unit controller, and at the same time sends system-level adjustment instructions to the outdoor unit, so as to realize the differentiated adjustment of indoor unit operating parameters and the precise matching of outdoor unit output power. By monitoring the temperature difference between indoor units in real time, when the temperature difference between indoor units exceeds the preset threshold, the fan speed and cooling / heating intensity of the relevant indoor units are automatically adjusted, and the refrigerant distribution strategy of the outdoor unit is adjusted accordingly to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit. The host computer continuously learns the operating modes and user habits of each indoor unit, establishes a personalized comfort model, and dynamically adjusts the control algorithm parameters based on system operation feedback to achieve self-optimization of the system operation strategy.

[0024] The technical solution adopted in this embodiment effectively avoids excessive operation of the outdoor unit and significantly reduces system energy consumption through precise load matching and refrigerant distribution optimization; it ensures uniform temperature distribution in each room and improves the overall comfort experience through temperature difference balance control and personalized adjustment; through an adaptive learning mechanism, the system can automatically optimize its operating strategy according to usage habits to achieve intelligent energy-saving control; and through real-time monitoring and collaborative control, it effectively avoids local overload and system fluctuations, and improves overall operational stability.

[0025] In some possible embodiments of the present invention, the step of transmitting the first multidimensional data to a host computer in real time, and the host computer dynamically predicting the cooling and heating load requirements of each indoor unit based on an artificial intelligence algorithm, includes: The first multidimensional data is timestamped and its data format is standardized. A mapping relationship between the data of each indoor unit and the corresponding outdoor unit is established. Abnormal data is identified and filtered to ensure the integrity and consistency of the transmitted data, thus obtaining the second multidimensional data. The second multidimensional data is layered and packaged according to indoor unit grouping and data type, and transmitted to the host computer in real time. After receiving the second multidimensional data, the host computer classifies and stores it according to time series and device number, and establishes a real-time data cache area and a historical data storage area. The host computer extracts the temperature change trend, load fluctuation characteristics and operating cycle mode of each indoor unit from the second multi-dimensional data, identifies the key factors affecting the demand for cooling and heating loads, and constructs a personalized load feature vector for each indoor unit. Based on the extracted personalized load feature vectors and historical load data, a deep learning algorithm is used to train the load prediction model for each indoor unit. The model parameters are updated regularly according to the deviation between the prediction results and the actual load to improve the prediction accuracy. Using the trained load forecasting model, combined with current real-time data and environmental change trends, the system dynamically predicts the future cooling and heating load demand of each indoor unit, and outputs the corresponding load demand forecast values ​​and confidence level assessment results.

[0026] In this embodiment, data preprocessing and synchronization mechanisms ensure the accuracy and timeliness of transmitted data, providing a reliable data foundation for subsequent forecasting. The use of hierarchical transmission and intelligent caching strategies significantly improves the transmission efficiency and system response speed of large amounts of multidimensional data. Feature extraction and pattern recognition accurately capture the inherent patterns of load changes, greatly enhancing the accuracy of load forecasting. The continuous training and parameter update mechanism of the intelligent model enables the system to adaptively learn from environmental changes. Dynamic forecasting results provide forward-looking guidance for system control decisions, realizing an active energy-saving control strategy.

[0027] In some possible embodiments of the present invention, the step of establishing a load demand model for the indoor unit group based on the trend of indoor-outdoor temperature difference and historical operating data, and calculating the optimal cooling capacity allocation scheme, includes: Based on real-time collected indoor and outdoor temperature data, the changing trends and fluctuation patterns of indoor and outdoor temperature differences in different time periods are analyzed, the temperature difference change patterns at different time scales (such as daily cycle, weekly cycle and seasonal cycle) are identified, and the peak and trough periods and variation amplitude characteristics of temperature difference changes are extracted. Historical operating data are classified and archived according to temperature difference change patterns. The load response characteristics and energy consumption performance of each indoor unit under different temperature difference conditions are analyzed. A temperature difference-load correlation feature library is constructed, and a load demand benchmark model of indoor unit groups under similar environmental conditions is established. Based on the geographical location, room characteristics, and usage patterns of the indoor units, multiple indoor units are divided into groups with similar load characteristics. A dedicated load demand model is established for each group using a load demand baseline model. Combined with the current temperature difference trend, the future cooling and heating load demand changes of each group are predicted. Analyze system boundary conditions such as outdoor unit cooling and heating capacity limitations, refrigerant flow distribution constraints, and power load constraints; evaluate the maximum allocable cooling capacity and minimum guaranteed cooling capacity of each indoor unit group; and determine the feasible range and optimization space for cooling capacity allocation. Taking into account the load demand forecast of each indoor unit group, system capacity constraints and energy-saving targets, a multi-objective optimization algorithm is used to calculate the optimal cooling capacity allocation scheme that balances comfort and energy efficiency, and to generate specific operating parameter adjustment instructions for each indoor unit.

[0028] In this embodiment, by analyzing temperature difference trends across multiple time scales, the impact of environmental changes on load demand is accurately grasped, significantly improving the accuracy and foresight of load forecasting. The adoption of a group-based modeling strategy ensures both the personalized characteristics of the model and a substantial increase in modeling efficiency and computational speed. A comprehensive analysis of system constraints ensures the feasibility of the cooling capacity allocation scheme and the stability of system operation. A multi-objective optimization algorithm achieves the optimal balance between comfort and energy efficiency, avoiding system performance deviations caused by single-objective optimization. The allocation scheme based on the load demand model provides a scientific basis for system control, realizing a shift from passive response to proactive predictive control.

[0029] In some possible embodiments of the present invention, the step of sending personalized operating instructions from the host computer to each indoor unit controller and simultaneously sending system-level adjustment instructions to the outdoor unit according to the optimal cooling capacity allocation scheme, thereby achieving differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power, includes: The host computer generates a personalized set of operating instructions based on the allocated cooling capacity values ​​of each indoor unit in the optimal cooling capacity allocation scheme, combined with the current operating status of each indoor unit and room characteristic parameters. This set includes the target temperature set value, fan speed adjustment amount, and operating mode switching instructions. It also establishes a precise mapping relationship between the allocated cooling capacity and specific control parameters. Based on the total cooling capacity distribution demand of all indoor units, calculate the total system cooling capacity and corresponding power output demand required by the outdoor unit, and formulate a system-level adjustment strategy that includes compressor frequency adjustment, refrigerant flow distribution ratio and system operation mode to ensure accurate matching between the outdoor unit output power and the total demand of the indoor unit group. Personalized operation commands and system-level adjustment commands generated based on system-level adjustment strategies are prioritized, and critical commands that have a significant impact on system stability are processed first (the impact value of all commands is evaluated for system stability, sorted by the magnitude of the impact value, and commands with an impact value exceeding the preset impact value are designated as critical commands). A timing coordination scheme for command execution is also formulated to ensure that the outdoor unit system-level adjustment is executed before the indoor unit personalized adjustment, thereby avoiding operational conflicts caused by system power mismatch. Through the communication network of the multi-split air conditioning system, system-level adjustment commands are sent to the outdoor unit microcomputer control board in real time, while personalized operation commands are sent to the corresponding indoor unit controllers. A two-way communication confirmation mechanism is established between the host computer and the indoor and outdoor unit controllers to ensure the accurate transmission and execution confirmation of all commands. The system monitors the execution status of commands by each indoor unit controller and the outdoor unit microcomputer control board in real time. When a deviation between the actual execution effect and the expected target is detected, the system automatically triggers the command correction mechanism to dynamically fine-tune the indoor unit operating parameters and the outdoor unit output power, thereby achieving closed-loop control and precise matching.

[0030] In this embodiment, precise parameter mapping and power matching calculations achieve accurate correspondence between cooling capacity allocation and actual control parameters, significantly improving system control accuracy. Priority sorting and timing coordination mechanisms effectively avoid control conflicts between indoor and outdoor units, ensuring system coordination and stability. A two-way communication confirmation mechanism and real-time monitoring system significantly enhance the system's response speed and execution reliability to control commands. Dynamic adjustment and closed-loop control mechanisms enable the system to automatically correct execution deviations, improving the robustness of the control system. Precise matching and coordinated control of indoor and outdoor units maximize the energy-saving potential of the optimal cooling capacity allocation scheme, resulting in a significant improvement in overall system energy efficiency.

[0031] In some possible embodiments of the present invention, the step of automatically adjusting the fan speed and cooling / heating intensity of the relevant indoor units when the temperature difference between indoor units exceeds a preset threshold by real-time monitoring of the temperature differences between the indoor units, and correspondingly adjusting the refrigerant distribution strategy of the outdoor unit to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity input by the outdoor unit, includes: Real-time collection of current room temperature data of each indoor unit; construction of temperature difference monitoring matrix between indoor units; calculation of temperature difference between any two indoor units; comparison of each temperature difference with the corresponding preset threshold; identification of indoor unit combination with excessive temperature difference and specific excessive temperature difference range. For the identified cases of excessive temperature difference, the key causes of the temperature difference were analyzed from several aspects, including load difference, fan speed setting difference, and cooling and heating intensity difference, and the temperature difference analysis results were obtained. Based on the temperature difference analysis results, the target indoor unit and the reference indoor unit that need to be adjusted are determined, the adjustment priority and direction for eliminating temperature difference are established, and the first adjustment strategy is obtained. Based on the first adjustment strategy, a coordinated adjustment strategy for the fan speed and cooling / heating intensity of the relevant indoor units is formulated. For indoor units with high temperature, the cooling intensity is increased or the heating intensity is reduced, and for indoor units with low temperature, the opposite adjustment is taken. At the same time, the fan speed configuration of each indoor unit is optimized to accelerate the temperature equalization process. Based on the overall demand changes of the indoor unit parameter adjustment strategy, the refrigerant demand of each refrigeration circuit is recalculated, and the refrigerant distribution ratio and flow control parameters of the outdoor unit are adjusted to ensure that the refrigerant supply matches the actual demand of each indoor unit after adjustment, and to avoid a surge in the total cooling capacity demand of the system due to local adjustment. After the adjustment is implemented, monitor the temperature difference between indoor units, evaluate the temperature difference balancing effect and the change in total system energy consumption. When the temperature difference still exceeds the preset threshold, iterate and optimize the adjustment strategy based on the feedback of the previous adjustment effect until the temperature of each room reaches the preset equilibrium state and the system cooling capacity input becomes reasonable.

[0032] In this embodiment, the uneven temperature between indoor units is accurately identified and eliminated through a temperature difference monitoring matrix and precise cause analysis, significantly improving the temperature control consistency of each room. A collaborative adjustment strategy avoids system imbalances that may result from independent adjustment of a single unit, achieving coordinated operation of the entire indoor unit group. Dynamic adjustment of the refrigerant distribution strategy effectively avoids energy waste caused by excessive local cooling and heating, significantly improving the overall system energy efficiency. An iterative optimization mechanism ensures the stability and reliability of temperature difference control, preventing temperature oscillations and system instability. The balanced distribution and dynamic maintenance of temperature in each room provide users with a more comfortable and consistent indoor environment experience.

[0033] In some possible embodiments of the present invention, the host computer continuously learns the operating modes and user habits of each indoor unit, establishes a personalized comfort model, and dynamically adjusts the control algorithm parameters based on system operation feedback to achieve self-optimization of the system operation strategy, including: The host computer records and analyzes the power-on and power-off times, temperature setting preferences, fan speed selection habits, and operating mode switching patterns of each indoor unit over a long period of time. It identifies personalized usage characteristics of different time periods, seasons, and users, and extracts user behavior feature vectors including usage frequency, temperature preference range, and operation response time. Based on user behavior feature vectors and environmental comfort theory, a comprehensive evaluation system including temperature comfort, humidity comfort, airflow comfort and noise comfort is established for each indoor unit. Combined with users' historical satisfaction feedback and adjustment frequency data, a personalized comfort prediction model and comfort weight allocation scheme are constructed. Real-time monitoring of energy consumption indicators, temperature control accuracy indicators, and user operation intervention frequency during system operation; establishment of a multi-dimensional quantitative evaluation system for system operation performance; collection of operation performance feedback data including energy saving effect, comfort achievement, and system response speed; and formation of a system performance evaluation database. Based on the operational performance feedback data and the prediction results of the personalized comfort prediction model, the key parameters and optimization directions affecting the system performance in the current control algorithm are identified. An adaptive optimization algorithm is used to fine-tune and dynamically update the core algorithm parameters such as load prediction parameters, temperature difference control threshold and power distribution weight. The optimized core algorithm parameters are applied to the actual system operation, the implementation effect of the new strategy is continuously evaluated, successful optimization experience and parameter configuration are saved to the system knowledge base, an evolutionary learning mechanism for the operation strategy is established, and the system control intelligence level is continuously improved and the personalized adaptability is continuously strengthened.

[0034] In this embodiment, by deeply mining user behavior patterns and constructing a personalized comfort model, the system can accurately understand and meet the personalized needs of different users, significantly improving user experience satisfaction. Adaptive learning and intelligent parameter tuning mechanisms enable the system to learn and continuously improve itself, achieving a fundamental shift from fixed strategies to intelligent evolutionary strategies. A dynamic adjustment mechanism based on operational feedback ensures the system always operates in its optimal state, avoiding the efficiency decay problem of traditional fixed parameter control. Knowledge base updates and strategy evolution mechanisms enable the system to proactively adapt to environmental and user needs changes, significantly improving the system's environmental adaptability and operational stability. The organic combination of the personalized comfort model and energy-saving goals maximizes energy savings while ensuring user comfort, achieving the best balance between economy and comfort.

[0035] In some possible embodiments of the present invention, the load demand model for the indoor unit group is established using the following load forecasting formula:

[0036] in, Let be the predicted load demand at time t; The base load factor reflects the inherent heat load characteristics of the room; , , The weighting coefficients are obtained through training with historical data. This is the m-th order temperature difference weighting factor, reflecting the degree of influence of different temperature difference amplitudes on the load; Let m be the indoor-outdoor temperature difference term at time t; The rate of temperature change reflects the dynamic trend of ambient temperature change. This is the time decay factor, which reflects the decay characteristics of the impact of historical data on current predictions.

[0037] This embodiment achieves accurate prediction of complex environmental changes through multi-stage temperature difference terms and dynamic attenuation mechanisms, significantly improving the accuracy of load forecasting and the timeliness of system response.

[0038] In some possible embodiments of the present invention, the step of sending personalized operating instructions from the host computer to each indoor unit controller and simultaneously sending system-level adjustment instructions to the outdoor unit according to the optimal cooling capacity allocation scheme, thereby achieving differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power, employs the following dynamic power allocation algorithm:

[0039] in, This represents the optimal power output for the nth control cycle. This refers to the rated power of the outdoor unit. The efficiency correction factor for the u-th indoor unit reflects the impact of its current operating status on the system efficiency. The real-time cooling capacity requirement of the uth indoor unit; Let be the capacity allocation coefficient for the v-th refrigeration loop; Let v be the available capacity of the v-th refrigeration circuit; This is an environmental correction function that considers the impact of outdoor temperature and humidity on system performance.

[0040] This embodiment achieves precise adjustment of outdoor unit power by dynamically matching demand and capacity, combined with environmental factor correction, effectively avoiding power overload and energy efficiency loss.

[0041] In some possible embodiments of the present invention, the step of automatically adjusting the fan speed and cooling / heating intensity of the relevant indoor units and correspondingly adjusting the refrigerant distribution strategy of the outdoor unit when the temperature difference between the indoor units exceeds a preset threshold, thereby ensuring that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit, is achieved by using the following adaptive adjustment formula to achieve temperature difference balance control:

[0042] in, The fan speed adjustment value for the r-th indoor unit; , These are the proportional and derivative control coefficients, which are adaptively adjusted according to the system characteristics. The deviation between the r-th indoor unit and the target temperature; The rate of change of temperature deviation reflects the temperature trend; is the amplitude coefficient of the s-th harmonic component, used to compensate for periodic temperature fluctuations; Let ω be the angular frequency of the s-th harmonic, corresponding to the temperature change pattern of different periods; Let be the phase angle of the s-th harmonic, reflecting the time characteristics of temperature fluctuations.

[0043] This embodiment combines PID control with harmonic compensation to achieve precise suppression and rapid balancing of temperature fluctuations, significantly improving the system's temperature control stability.

[0044] In some possible embodiments of the present invention, in the step of the host computer continuously learning the operating modes and user habits of each indoor unit, establishing a personalized comfort model, and dynamically adjusting the control algorithm parameters based on system operation feedback to achieve self-optimization of the system operation strategy, the adaptive learning adopts the following weight update algorithm:

[0045] in, , These are the old and new weight values ​​for the z-th control parameter, respectively. The learning rate controls the step size of parameter updates; The gradient of the loss function with respect to the weights guides the direction of parameter optimization. This is a regularization coefficient to prevent the model from overfitting. is the importance weight of the q-th feature, reflecting the contribution of different features to the control effect; As an activation function, it enhances the model's nonlinear expressive power; Let be the mapping parameter matrix for the q-th feature; Let q be the feature vector of the q-th feature under the z-th control parameter.

[0046] This embodiment achieves continuous improvement and personalized adaptation of the control strategy by integrating gradient optimization and feature weighted learning, which significantly enhances the system's intelligence level and long-term performance.

[0047] Please refer to Figure 2 Another embodiment of the present invention provides an energy-saving control system based on communication between indoor and outdoor units of a multi-split air conditioner, for executing an energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, including: an indoor unit, an outdoor unit, and a host computer; The host computer is configured as follows: By synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioning system, the first multi-dimensional data is obtained. Based on artificial intelligence algorithms, the cooling and heating load requirements of each indoor unit are dynamically predicted. Based on the trend of indoor and outdoor temperature difference and historical operating data, a load demand model of the indoor unit group is established, and the optimal cooling capacity allocation scheme is calculated. Based on the optimal cooling capacity allocation scheme, personalized operation commands are sent to each indoor unit controller, and system-level adjustment commands are sent to the outdoor unit to achieve differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power. By monitoring the temperature difference between indoor units in real time, when the temperature difference between indoor units exceeds the preset threshold, the fan speed and cooling / heating intensity of the relevant indoor units are automatically adjusted, and the refrigerant distribution strategy of the outdoor unit is adjusted accordingly to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit. We continuously learn the operating modes of each indoor unit and user habits, establish personalized comfort models, and dynamically adjust control algorithm parameters based on system performance feedback to achieve self-optimization of system operation strategies.

[0048] It should be known that, Figure 2The block diagram of the energy-saving control system based on communication between indoor and outdoor units of a multi-split air conditioner shown is for illustrative purposes only, and the number of modules shown does not limit the scope of protection of this invention. The energy-saving control system based on communication between indoor and outdoor units of a multi-split air conditioner provided in this embodiment can be used to execute various embodiments of the corresponding energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner. For specific implementation details, please refer to the descriptions of the various method embodiments, which will not be repeated here.

[0049] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0050] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0051] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0052] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0053] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0054] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0055] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0056] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0057] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. An energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner, characterized in that, include: By synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioning system, the first multi-dimensional data is obtained. The first multidimensional data is transmitted to the host computer in real time. The host computer dynamically predicts the cooling and heating load demand of each indoor unit based on artificial intelligence algorithms, and establishes a load demand model of the indoor unit group based on the trend of indoor and outdoor temperature difference and historical operating data, and calculates the optimal cooling capacity allocation scheme. According to the optimal cooling capacity allocation scheme, the host computer sends personalized operation instructions to each indoor unit controller, and at the same time sends system-level adjustment instructions to the outdoor unit, so as to realize the differentiated adjustment of indoor unit operating parameters and the precise matching of outdoor unit output power. By monitoring the temperature difference between indoor units in real time, when the temperature difference between indoor units exceeds the preset threshold, the fan speed and cooling / heating intensity of the relevant indoor units are automatically adjusted, and the refrigerant distribution strategy of the outdoor unit is adjusted accordingly to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit. The host computer continuously learns the operating modes and user habits of each indoor unit, establishes a personalized comfort model, and dynamically adjusts the control algorithm parameters based on system operation feedback to achieve self-optimization of the system operation strategy. The load demand model for the indoor unit group is established using the following load forecasting formula: in, Let be the predicted load demand at time t; The base load factor reflects the inherent heat load characteristics of the room; , , The weighting coefficients are obtained through training with historical data. This is the m-th order temperature difference weighting factor, reflecting the degree of influence of different temperature difference amplitudes on the load; Let m be the indoor-outdoor temperature difference term at time t; The rate of temperature change reflects the dynamic trend of ambient temperature change. This is the time decay factor, reflecting the decay characteristics of the impact of historical data on current predictions; In the step of sending personalized operating instructions from the host computer to each indoor unit controller and simultaneously sending system-level adjustment instructions to the outdoor unit according to the optimal cooling capacity allocation scheme, thereby achieving differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power, the following dynamic power allocation algorithm is adopted: in, This represents the optimal power output for the nth control cycle. This refers to the rated power of the outdoor unit. The efficiency correction factor for the u-th indoor unit reflects the impact of its current operating status on the system efficiency. The real-time cooling capacity requirement of the uth indoor unit; Let be the capacity allocation coefficient for the v-th refrigeration loop; Let v be the available capacity of the v-th refrigeration circuit; This is an environmental correction function that considers the impact of outdoor temperature and humidity on system performance.

2. The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner according to claim 1, characterized in that, The step of transmitting the first multidimensional data to the host computer in real time, and the host computer dynamically predicting the cooling and heating load requirements of each indoor unit based on artificial intelligence algorithms, includes: The first multidimensional data is timestamped and its data format is standardized. A mapping relationship between the data of each indoor unit and the corresponding outdoor unit is established. Abnormal data is identified and filtered to ensure the integrity and consistency of the transmitted data, thus obtaining the second multidimensional data. The second multidimensional data is layered and packaged according to indoor unit grouping and data type, and transmitted to the host computer in real time. After receiving the second multidimensional data, the host computer classifies and stores it according to time series and device number, and establishes a real-time data cache area and a historical data storage area. The host computer extracts the temperature change trend, load fluctuation characteristics and operating cycle mode of each indoor unit from the second multi-dimensional data, identifies the key factors affecting the demand for cooling and heating loads, and constructs a personalized load feature vector for each indoor unit. Based on the extracted personalized load feature vectors and historical load data, a deep learning algorithm is used to train the load prediction model for each indoor unit. The model parameters are updated regularly according to the deviation between the prediction results and the actual load to improve the prediction accuracy. Using the trained load forecasting model, combined with current real-time data and environmental change trends, the system dynamically predicts the future cooling and heating load demand of each indoor unit, and outputs the corresponding load demand forecast values ​​and confidence level assessment results.

3. The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner according to claim 2, characterized in that, The steps of establishing a load demand model for the indoor unit group based on the trend of indoor and outdoor temperature difference changes and historical operating data, and calculating the optimal cooling capacity allocation scheme, include: Based on real-time collected indoor and outdoor temperature data, the changing trends and fluctuation patterns of indoor and outdoor temperature differences in different time periods are analyzed, temperature difference change patterns at different time scales are identified, and peak and trough periods and variation amplitude characteristics of temperature difference changes are extracted. Historical operating data are classified and archived according to temperature difference change patterns. The load response characteristics and energy consumption performance of each indoor unit under different temperature difference conditions are analyzed. A temperature difference-load correlation feature library is constructed, and a load demand benchmark model of indoor unit groups under similar environmental conditions is established. Based on the geographical location, room characteristics, and usage patterns of the indoor units, multiple indoor units are divided into groups with similar load characteristics. A dedicated load demand model is established for each group using a load demand baseline model. Combined with the current temperature difference trend, the future cooling and heating load demand changes of each group are predicted. The system boundary conditions, including the outdoor unit's cooling and heating capacity limitations, refrigerant flow distribution constraints, and power load constraints, are analyzed to evaluate the maximum allocatable cooling capacity and minimum guaranteed cooling capacity of each indoor unit group, thereby determining the feasible range and optimization space for cooling capacity allocation. Taking into account the load demand forecast of each indoor unit group, system capacity constraints and energy-saving targets, a multi-objective optimization algorithm is used to calculate the optimal cooling capacity allocation scheme that balances comfort and energy efficiency, and to generate specific operating parameter adjustment instructions for each indoor unit.

4. The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner according to claim 3, characterized in that, The steps of sending personalized operating instructions from the host computer to each indoor unit controller and simultaneously sending system-level adjustment instructions to the outdoor unit according to the optimal cooling capacity allocation scheme, to achieve differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power, include: The host computer generates a personalized set of operating instructions based on the allocated cooling capacity values ​​of each indoor unit in the optimal cooling capacity allocation scheme, combined with the current operating status of each indoor unit and room characteristic parameters. This set includes the target temperature set value, fan speed adjustment amount, and operating mode switching instructions. It also establishes a precise mapping relationship between the allocated cooling capacity and specific control parameters. Based on the total cooling capacity distribution demand of all indoor units, calculate the total system cooling capacity and corresponding power output demand required by the outdoor unit, and formulate a system-level adjustment strategy that includes compressor frequency adjustment, refrigerant flow distribution ratio and system operation mode to ensure accurate matching between the outdoor unit output power and the total demand of the indoor unit group. Personalized operation commands and system-level adjustment commands generated based on system-level adjustment strategies are prioritized, with priority given to critical commands that have a significant impact on system stability. A timing coordination scheme for command execution is also formulated to ensure that outdoor unit system-level adjustments are executed before indoor unit personalized adjustments, thus avoiding operational conflicts caused by system power mismatch. Through the communication network of the multi-split air conditioning system, system-level adjustment commands are sent to the outdoor unit microcomputer control board in real time, while personalized operation commands are sent to the corresponding indoor unit controllers. A two-way communication confirmation mechanism is established between the host computer and the indoor and outdoor unit controllers to ensure the accurate transmission and execution confirmation of all commands. The system monitors the execution status of commands by each indoor unit controller and the outdoor unit microcomputer control board in real time. When a deviation between the actual execution effect and the expected target is detected, the system automatically triggers the command correction mechanism to dynamically fine-tune the indoor unit operating parameters and the outdoor unit output power, thereby achieving closed-loop control and precise matching.

5. The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner according to claim 4, characterized in that, The steps of monitoring the temperature differences between indoor units in real time, automatically adjusting the fan speed and cooling / heating intensity of the relevant indoor units when the temperature difference between indoor units exceeds a preset threshold, and correspondingly adjusting the refrigerant distribution strategy of the outdoor unit to ensure that the temperature in each room tends to be balanced while avoiding excessive cooling capacity input from the outdoor unit, include: Real-time collection of current room temperature data of each indoor unit; construction of temperature difference monitoring matrix between indoor units; calculation of temperature difference between any two indoor units; comparison of each temperature difference with the corresponding preset threshold; identification of indoor unit combination with excessive temperature difference and specific excessive temperature difference range. For the identified cases of excessive temperature difference, the key causes of the temperature difference were analyzed from several aspects, including load difference, fan speed setting difference, and cooling and heating intensity difference, and the temperature difference analysis results were obtained. Based on the temperature difference analysis results, the target indoor unit and the reference indoor unit that need to be adjusted are determined, the adjustment priority and direction for eliminating temperature difference are established, and the first adjustment strategy is obtained. Based on the first adjustment strategy, a coordinated adjustment strategy for the fan speed and cooling / heating intensity of the relevant indoor units is formulated. For indoor units with high temperature, the cooling intensity is increased or the heating intensity is reduced, and for indoor units with low temperature, the opposite adjustment is taken. At the same time, the fan speed configuration of each indoor unit is optimized to accelerate the temperature equalization process. Based on the overall demand changes of the indoor unit parameter adjustment strategy, the refrigerant demand of each refrigeration circuit is recalculated, and the refrigerant distribution ratio and flow control parameters of the outdoor unit are adjusted to ensure that the refrigerant supply matches the actual demand of each indoor unit after adjustment, and to avoid a surge in the total cooling capacity demand of the system due to local adjustment. After the adjustment is implemented, monitor the temperature difference between indoor units, evaluate the temperature difference balancing effect and the change in total system energy consumption. When the temperature difference still exceeds the preset threshold, iterate and optimize the adjustment strategy based on the feedback of the previous adjustment effect until the temperature of each room reaches the preset equilibrium state.

6. The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner according to claim 5, characterized in that, The host computer continuously learns the operating modes and user habits of each indoor unit, establishes a personalized comfort model, and dynamically adjusts the control algorithm parameters based on system performance feedback to achieve self-optimization of the system's operating strategy. This includes the following steps: The host computer records and analyzes the power-on and power-off times, temperature setting preferences, fan speed selection habits, and operating mode switching patterns of each indoor unit over a long period of time. It identifies personalized usage characteristics of different time periods, seasons, and users, and extracts user behavior feature vectors including usage frequency, temperature preference range, and operation response time. Based on user behavior feature vectors and environmental comfort theory, a comprehensive evaluation system including temperature comfort, humidity comfort, airflow comfort and noise comfort is established for each indoor unit. Combined with users' historical satisfaction feedback and adjustment frequency data, a personalized comfort prediction model and comfort weight allocation scheme are constructed. Real-time monitoring of energy consumption indicators, temperature control accuracy indicators, and user operation intervention frequency during system operation; establishment of a multi-dimensional quantitative evaluation system for system operation performance; collection of operation performance feedback data including energy saving effect, comfort achievement, and system response speed; and formation of a system performance evaluation database. Based on the operational performance feedback data and the prediction results of the personalized comfort prediction model, the key parameters and optimization directions affecting the system performance in the current control algorithm are identified. An adaptive optimization algorithm is used to fine-tune and dynamically update the core algorithm parameters such as load prediction parameters, temperature difference control threshold and power distribution weight. The optimized core algorithm parameters are applied to the actual system operation, the implementation effect of the new strategy is continuously evaluated, successful optimization experience and parameter configuration are saved to the system knowledge base, an evolutionary learning mechanism for the operation strategy is established, and the system control intelligence level is continuously improved and the personalized adaptability is continuously strengthened.

7. The energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner according to claim 6, characterized in that, The step of monitoring the temperature difference between indoor units in real time, automatically adjusting the fan speed and cooling / heating intensity of the relevant indoor units when the temperature difference between indoor units exceeds a preset threshold, and correspondingly adjusting the refrigerant distribution strategy of the outdoor unit to ensure that the temperature of each room tends to be uniform while avoiding excessive cooling capacity of the outdoor unit, adopts the following adaptive adjustment formula to achieve temperature difference balance control: in, The fan speed adjustment value for the r-th indoor unit; , These are the proportional and derivative control coefficients, which are adaptively adjusted according to the system characteristics. The deviation between the r-th indoor unit and the target temperature; The rate of change of temperature deviation reflects the temperature trend; is the amplitude coefficient of the s-th harmonic component, used to compensate for periodic temperature fluctuations; Let ω be the angular frequency of the s-th harmonic, corresponding to the temperature change pattern of different periods; Let be the phase angle of the s-th harmonic, reflecting the time characteristics of temperature fluctuations.

8. An energy-saving control system based on communication between indoor and outdoor units of a multi-split air conditioner, used to execute the energy-saving control method based on communication between indoor and outdoor units of a multi-split air conditioner as described in any one of claims 1 to 7, characterized in that, include: Indoor unit, outdoor unit, and host computer; The host computer is configured as follows: By synchronously collecting indoor unit operating parameters, outdoor unit operating status parameters, and indoor and outdoor ambient temperature data through the controllers of each indoor unit and the microcomputer control board of the outdoor unit in the multi-split air conditioning system, the first multi-dimensional data is obtained. Based on artificial intelligence algorithms, the cooling and heating load requirements of each indoor unit are dynamically predicted. Based on the trend of indoor and outdoor temperature difference and historical operating data, a load demand model of the indoor unit group is established, and the optimal cooling capacity allocation scheme is calculated. Based on the optimal cooling capacity allocation scheme, personalized operation commands are sent to each indoor unit controller, and system-level adjustment commands are sent to the outdoor unit to achieve differentiated adjustment of indoor unit operating parameters and precise matching of outdoor unit output power. By monitoring the temperature difference between indoor units in real time, when the temperature difference between indoor units exceeds the preset threshold, the fan speed and cooling / heating intensity of the relevant indoor units are automatically adjusted, and the refrigerant distribution strategy of the outdoor unit is adjusted accordingly to ensure that the temperature of each room tends to be balanced while avoiding excessive cooling capacity of the outdoor unit. We continuously learn the operating modes of each indoor unit and user habits, establish personalized comfort models, and dynamically adjust control algorithm parameters based on system performance feedback to achieve self-optimization of system operation strategies.

Images