Cluster temperature control and energy consumption balance optimization control system for group air conditioners

Abstract

The invention discloses a cluster temperature control and energy consumption balance optimization control system for group air conditioners, and relates to the technical field of intelligent control, the system comprises a data acquisition module, temperature data of each indoor area and outdoor temperature change information are acquired in real time through a sensor network, and a preset temperature threshold value interval is combined to determine the temperature of each indoor area; analyzing heterogeneity characteristics of indoor temperature distribution to obtain a temperature distribution state of each area; according to the air conditioner cluster temperature control and energy consumption balance optimization control system, the operation efficiency of an air conditioner system and the comfort degree of a user can be effectively improved, and intelligent temperature management is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a cluster temperature control and energy consumption balancing optimization control system for air conditioners. Background Art

[0002] Intelligent management of indoor building heating systems is a key area for efficient energy utilization and comfort assurance in modern buildings. It not only optimizes energy consumption but also directly impacts user experience and environmental sustainability. Currently, most heating systems rely on a single temperature control logic or preset operating modes. While these systems can meet basic needs to a certain extent, they struggle to cope with complex and ever-changing real-world scenarios.

[0003] Existing approaches suffer from a lack of comprehensive coordination capabilities for dynamic environments and personalized user needs, often leading to inefficient systems and wasted resources. For example, some systems rely solely on a single indoor temperature point for control, ignoring the variability in indoor temperature distribution and the varying user needs across different areas, resulting in overheating or overcooling in some areas. A key challenge in this area lies in coordinating the switching between cooling and heating modes for multiple air conditioning units. First, the dynamic changes in indoor and outdoor temperatures and the real-time differences in user needs require the system to accurately determine the timing of mode switching. Improper switching timing can cause multiple units to operate in conflicting modes simultaneously, increasing energy consumption. Furthermore, the order of mode switching further exacerbates the challenge. Different air conditioning units vary in location, power, and regional requirements, and the rationality of the switching sequence directly impacts the stability and efficiency of the overall system. Unresolved issues regarding switching timing and order make it difficult for the system to maintain efficient operation in a dynamic environment while avoiding mode conflicts. Summary of the Invention

[0004] The purpose of the present invention is to provide a cluster temperature control and energy consumption balance optimization control system for air conditioning, and to establish a unified heating mode coordination mechanism based on outdoor temperature, indoor temperature distribution and user needs to optimize the switching timing and sequence of each air conditioning unit.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a cluster air conditioning temperature control and energy consumption balance optimization control system, the system comprising: The data acquisition module collects temperature data of various indoor areas and outdoor temperature change information in real time through the sensor network. Combined with the preset temperature threshold range, it analyzes the heterogeneous characteristics of indoor temperature distribution and obtains the temperature distribution status of each area; The matching analysis module prioritizes the actual demand differences in the area where each air-conditioning unit is located based on the temperature distribution status and regional demand matching data obtained from the user end, and determines the mode switching demand level of each area; The switching decision module determines the final switching opportunity list based on the mode switching demand level. Based on the final switching opportunity list, it obtains real-time monitoring data of system operation efficiency, analyzes the energy consumption performance of each unit after the mode switch, determines whether it meets the preset efficiency standards, and obtains the evaluation results of system stability assurance; The conflict control module, if the system stability assessment results indicate the presence of overheating or overcooling in a local area, fine-tunes the operating mode of the relevant air conditioning units through the mode conflict avoidance mechanism, reallocates power output, and determines the adjusted operating parameters; The command control module updates the control commands of each air-conditioning unit in real time according to the adjusted operating parameters. It combines the feedback data of regional demand matching to analyze whether the user comfort meets the expectations and obtains the final system operation status report.

[0006] Preferably, the method of determining the final switching timing list based on the mode switching demand level includes obtaining the location information and corresponding power parameters of each air-conditioning unit based on the determined mode switching demand level, analyzing the spatial correlation and power matching between the units, and determining a preliminary reasonable switching sequence plan.

[0007] Preferably, the final switching timing list determined based on the mode switching demand level also includes adjusting the switching timing through a dynamic environment adaptation algorithm if there are multiple air-conditioning units running conflicting modes at the same time in the preliminary switching sequence rationality plan, recalculating the mode switching time point of each unit, and obtaining an optimized switching timing arrangement.

[0008] Preferably, determining the final switching timing list for the mode switching demand level also includes analyzing the potential interference of the external environment on the indoor temperature distribution based on the optimized switching timing arrangement in combination with the outdoor temperature change data, judging whether there are air-conditioning units that need to be switched in advance or delayed, and determining the final switching timing list.

[0009] Preferably, the data acquisition module includes an indoor temperature sensing unit and an outdoor environment sensing unit. The indoor temperature sensing unit is distributed in multiple key areas inside the building and is used to collect local temperature data of different areas in real time; the outdoor environment sensing unit includes a temperature and humidity sensor and a meteorological interface, which is used to obtain real-time meteorological information outside the building. The two are used together to construct a comprehensive temperature characteristic model to assist in judging the temperature distribution status.

[0010] Preferably, the switching decision module includes an energy efficiency evaluation submodule and a switching timing optimization submodule. The energy efficiency evaluation submodule is used to simulate and dynamically monitor the energy consumption level of each air-conditioning unit at a preset switching time. The switching timing optimization submodule uses a heuristic algorithm or fuzzy control strategy based on the simulation results and the current regional load demand to determine the optimal mode switching sequence that is conducive to improving the system energy efficiency.

[0011] Preferably, the conflict control module includes a mode conflict judgment unit and a power redistribution unit. The mode conflict judgment unit is used to identify the conflict state when the cooling and heating modes are running concurrently between the air-conditioning units. The power redistribution unit redistributes the air-conditioning output power by adjusting the operating frequency or cooling / heating intensity according to the spatial position, load intensity and user demand level between the conflicting units, so as to achieve fine-tuning and dynamic balance of the operating mode.

[0012] Preferably, the instruction control module includes a central controller and an edge execution unit. The central controller generates control instructions based on the adjusted operating parameters and comfort feedback results. The edge execution unit is deployed on each air-conditioning equipment body, receives control instructions and performs corresponding mode switching and power adjustment operations, and at the same time transmits the execution status and equipment response status back to the central controller to achieve closed-loop control.

[0013] Preferably, a historical data learning module is also included, which is used to perform machine learning modeling on the environmental data, user preference data and air-conditioning response data accumulated during the long-term operation of the system, and to predict the temperature change trend and user demand fluctuations in a specific time period in the future by constructing a prediction model, so as to provide forward-looking optimization suggestions for the mode switching strategy.

[0014] Preferably, it also includes an abnormality identification and early warning module, which is used to detect abnormal conditions such as abnormal temperature fluctuations, slow response of air-conditioning units or communication interruptions generated during system operation, and generate early warning information when an abnormality is detected, and prompt through the user terminal or the background operation and maintenance platform to improve the reliability of system operation and fault recovery capabilities.

[0015] It can be seen from the above technical solution that the present invention has the following beneficial effects: This cluster of air conditioners uses a temperature control and energy consumption balance optimization control system that collects indoor and outdoor temperature data in real time, analyzes indoor temperature distribution characteristics, prioritizes regions based on user needs, and determines the level of mode switching requirements. Based on the location and power parameters of the air conditioning units, it analyzes spatial correlation and power matching to arrive at a preliminary switching plan. A dynamic environmental adaptation algorithm is used to optimize switching timing, and adjustments are made based on external environmental influences. The present invention also monitors energy consumption performance in real time, evaluates system stability, and uses a mode conflict avoidance mechanism for fine-tuning based on local anomalies. Finally, based on user comfort feedback, control instructions are updated in real time to achieve precise temperature regulation. This method can effectively improve the operating efficiency and user comfort of the air conditioning system, and achieve intelligent temperature management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a system connection diagram of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the present invention provides a technical solution: a cluster temperature control and energy consumption balance optimization control system for air conditioners, the system comprising: The data acquisition module collects temperature data of various indoor areas and outdoor temperature change information in real time through the sensor network. Combined with the preset temperature threshold range, it analyzes the heterogeneous characteristics of indoor temperature distribution and obtains the temperature distribution status of each area; The matching analysis module prioritizes the actual demand differences in the area where each air-conditioning unit is located based on the temperature distribution status and regional demand matching data obtained from the user end, and determines the mode switching demand level of each area; The switching decision module determines the final switching opportunity list based on the mode switching demand level. Based on the final switching opportunity list, it obtains real-time monitoring data of system operation efficiency, analyzes the energy consumption performance of each unit after the mode switch, determines whether it meets the preset efficiency standards, and obtains the evaluation results of system stability assurance; The conflict control module, if the system stability assessment results indicate the presence of overheating or overcooling in a local area, fine-tunes the operating mode of the relevant air conditioning units through the mode conflict avoidance mechanism, reallocates power output, and determines the adjusted operating parameters; The command control module updates the control commands of each air-conditioning unit in real time according to the adjusted operating parameters. It combines the feedback data of regional demand matching to analyze whether the user comfort meets the expectations and obtains the final system operation status report.

[0019] The system first relies on a data acquisition module, using sensor nodes deployed in various areas to collect real-time indoor and outdoor temperature data. Sensor types can include thermocouples, thermistors, and infrared thermometers. These sensors aggregate data to a central control unit via wireless transmission protocols such as Zigbee or WiFi. The collected data is used to construct a current indoor temperature distribution model, which delineates different thermal zones based on set temperature thresholds. The system then detects whether the temperature differences between these zones exceed a set threshold for identifying temperature heterogeneity. For example, if the temperature difference between adjacent zones exceeds 2 degrees Celsius, the zone is identified as exhibiting significant heterogeneity. Next, the matching analysis module acquires user-entered zone demand data, including user-defined comfort temperature ranges, usage time periods, and space priority. The system constructs a demand priority score based on multiple factors, including the degree of deviation between each zone's actual temperature and the target temperature range, the user's weighted usage frequency for that zone, and comfort sensitivity. The system then uses a weighted hierarchical analysis method to prioritize the control of each air conditioning unit. Priority scoring is performed using a weighted summation method, with each indicator assigned a fixed weight based on its relative importance. For example, temperature deviation is weighted 0.4, usage frequency is weighted 0.3, and user comfort sensitivity is weighted 0.3. After ranking, the switching decision module combines real-time energy consumption monitoring data with historical energy efficiency curves and current power load to develop the optimal mode switching plan. This process uses a rule-based judgment model to determine the feasibility of the switch and simulates the energy efficiency performance after the switch. If the total system energy consumption is below the set threshold of 90% and the operating efficiency of each unit is above 85%, the switching conditions are considered met. If the evaluation results indicate operational conflicts between zones, such as persistent overheating or overcooling in one zone due to heat exchange interference with an adjacent zone, the conflict control module is activated. This control module uses a fine-tuning algorithm to adjust the operating parameters of the relevant air conditioning units, such as compressor power, fan speed, and heat exchanger opening, to balance temperature output and reassess the thermal impact between zones. Finally, the command control module generates control commands based on these updated parameters and sends them to each air conditioning unit, completing the temperature control loop. During the entire process, the system continuously receives comfort feedback information from the user end, which is used for subsequent optimization of control strategies to improve response accuracy and user experience.

[0020] By introducing regional temperature heterogeneity analysis and matching it with user needs, the system achieves differentiated control of multiple air conditioning units in spatial distribution, significantly improving the precision and personalization of indoor temperature control. Combining the switching decision-making mechanism with energy efficiency evaluation standards, it not only effectively avoids energy consumption peaks and improves overall energy efficiency, but also ensures operational stability and comfort. The addition of a conflict control module further alleviates the common temperature conflict issues in multi-unit operation, enabling the system to maintain good performance in complex usage scenarios. Through feedback-driven control instruction optimization and dynamic adjustment strategies, the system possesses excellent adaptability and scalability.

[0021] Based on the mode switching demand level, the final switching timing list is determined, including obtaining the location information and corresponding power parameters of each air-conditioning unit based on the determined mode switching demand level, analyzing the spatial correlation and power matching between units, and determining a preliminary reasonable switching sequence plan.

[0022] In this implementation, after obtaining the ranking of mode switching needs, the system further incorporates spatial and energy consumption analysis mechanisms to achieve precise switching scheduling and system load balancing. First, the system extracts the location information of each air conditioning unit within the building from the deployment database, including its floor number, room number, and spatial geometric position relative to other units. This location information is converted into a set of spatial coordinates for subsequent spatial correlation calculations. Next, the system obtains the current power parameters of each air conditioning unit, including its maximum power, current output power, and historical average energy consumption. To assess the spatial correlation between air conditioning units, the system employs a distance-weighted model. This model calculates a correlation influence factor based on the Euclidean distance between units. The closer the distance, the higher the influence factor, which can be set, for example, as the inverse of the relative distance. Furthermore, to analyze power matching, the system compares the power difference between each pair of units and sets a power difference tolerance range. For example, if the tolerance range is set to 10%, a high matching is considered if the power difference between the two units falls within this range. The system then weights the spatial correlation factor and the power matching factor to form a combined scoring metric. The combined score for each pair of units indicates the feasibility of coordinated switching. A higher overall score indicates that switching two units simultaneously is more likely to maintain system thermal balance and energy stability. The system constructs a scoring matrix for all units and applies a high-to-low priority strategy to determine a preliminary switching sequence, prioritizing units with strong spatial correlation and high power matching. This entire process optimizes the switching combination through iterative screening, ensuring that switching operations do not cause sudden load increases or abnormal heat distribution in any particular area, thereby improving the dynamic adaptability of the control strategy and the regulatory stability of the entire system.

[0023] This implementation incorporates location information and power parameters for collaborative analysis of air conditioning units. This allows the system to determine the switching opportunity list based not only on the urgency of user needs but also on the spatial impact between units and the coordination of energy output. This effectively avoids regional overheating, overcooling, or energy consumption surges caused by centralized switching or uncoordinated operation. This mechanism further improves the overall system's operational stability and energy efficiency, while ensuring dynamic safety and high responsiveness during mode switching.

[0024] Based on the level of mode switching demand, the final switching timing list is determined. If there are multiple air-conditioning units running conflicting modes at the same time in the preliminary switching sequence rationality plan, the switching timing will be adjusted through the dynamic environmental adaptation algorithm, and the mode switching time point of each unit will be recalculated to obtain the optimized switching timing arrangement.

[0025] In this implementation, after generating a preliminary switching sequence, the system performs a conflict analysis on the operating mode switching arrangements of all air conditioning units. The judgment criteria are: if the switching time difference between two or more air conditioning units is less than 5 minutes, and there is a directional conflict between heating and cooling between their target operating modes, or if this causes thermal disturbances in adjacent areas, an operational conflict is identified. The system then activates a dynamic environmental adaptation algorithm to resolve the incoordination issues caused by synchronized switching. This algorithm first invokes the environmental monitoring module to collect real-time temperature, humidity, wind speed, and direction data for each area, as well as historical control response data for the air conditioning units. It then evaluates the current thermal load intensity of each conflicting unit. The system then ranks the conflicting units by importance, based on user comfort priority, unit output power contribution, historical thermal stability score for the area in which they are located, and the coefficient of their spatial location's impact on neighboring areas. For example, if a unit has a high user priority, its power output exceeds 120% of the average power of all units, and its historical stability score is above 85%, then that unit will be prioritized to retain its original switching time. For secondary units, the system sets a time window that allows adjustment, usually 10 minutes before and after, and then simulates the impact of different delay schemes on the thermal dynamics of the entire system in this window through sliding search. The system introduces a stability scoring model, which takes the weighted sum of the temperature fluctuation amplitude, user comfort reduction value and energy consumption increase per unit time of each simulation scheme as the comprehensive evaluation index of the scheme. In the scoring model, the weight of temperature fluctuation is 0.5, the weight of comfort reduction is 0.3, and the weight of energy consumption increase is 0.2. Finally, the system selects the time combination scheme with the highest comprehensive score, and redefines the mode switching time point of all relevant air-conditioning units accordingly. The entire process is refreshed every 5 minutes on the server side to ensure that the system maintains real-time responsiveness to environmental changes and avoids operational anomalies such as local overheating, energy overload or user complaints.

[0026] This implementation effectively avoids energy waste and localized thermal disturbances caused by conflicting air conditioning unit operations by introducing a dynamic environmental adaptation mechanism. The system can flexibly adjust switching sequences based on actual environmental conditions, enhancing its adaptability to complex building thermal environments while also improving switching security and user satisfaction. In particular, in multi-user, multi-functional zoning scenarios, this mechanism ensures operational continuity in high-priority areas and balances overall operational cadence through intelligent delay strategies, improving both regulation efficiency and intelligent control.

[0027] Based on the level of mode switching demand, determining the final switching timing list also includes analyzing the potential interference of the external environment on the indoor temperature distribution based on the optimized switching timing arrangement and combining it with outdoor temperature change data, judging whether there are air-conditioning units that need to be switched earlier or later, and determining the final switching timing list.

[0028] This implementation, based on the optimized switching schedule, further considers the dynamic impact of external environmental variables and establishes a coupled indoor-outdoor temperature prediction mechanism to enhance the control system's proactive adjustment capabilities. The system first accesses an external meteorological data interface to obtain real-time current and short-term future outdoor temperature trends. This model, combined with data such as sunlight intensity, wind speed and direction, constructs an outdoor heat load trend model. This model, combined with building thermal parameters such as building orientation, window structure, and thermal conductivity of exterior wall materials, estimates the rate at which outdoor temperature fluctuations are transmitted to each indoor zone. The system calculates the external thermal interference factor on an hourly basis. If the interference factor for a particular zone exceeds a set threshold, for example, 1.3 times the average, the zone is identified as experiencing strong interference. The system also compares this interference factor with the control window of each air conditioning unit at the optimized switching time. If an external temperature increase or decrease is predicted to cause the indoor target temperature to deviate by more than 1 degree Celsius within the next 30 minutes, and the unit's original switching timing has not yet occurred, it is identified as a candidate for adjustment. At this point, the system activates the dynamic switching timing correction module, calculating the amount of time to advance or delay based on factors such as interference intensity, temperature change rate, and unit operating inertia. The calculation method is: the interference intensity coefficient multiplied by the expected temperature change rate, then multiplied by the regional response hysteresis factor. The result is the recommended adjustment time value (in minutes), which is also subject to the user-defined comfort tolerance and switching frequency threshold. Finally, the system reorders all units requiring adjustment and updates their switching schedule, completing the generation of the final switching timing list, ensuring the system's ability to proactively respond to climate changes and maintain a stable indoor thermal environment.

[0029] The data acquisition module includes an indoor temperature sensing unit and an outdoor environment sensing unit. The indoor temperature sensing unit is distributed in multiple key areas inside the building and is used to collect local temperature data in different areas in real time; the outdoor environment sensing unit includes a temperature and humidity sensor and a meteorological interface to obtain real-time meteorological information outside the building. The two are used together to build a comprehensive temperature characteristic model to assist in judging the temperature distribution status.

[0030] In this implementation, the data acquisition module's functions are divided into two collaborative sub-units, each providing global temperature sensing for the building's internal and external environments. The indoor temperature sensing unit utilizes a distributed layout strategy, with sensors located throughout key occupied spaces, heat-loaded areas, areas prone to thermal imbalances, and ventilation-sensitive areas. Local temperature information is uploaded in real time via wireless networking. Each sensor node supports a sampling frequency of at least once per minute, with an error of no more than 0.2 degrees Celsius, ensuring high-resolution and high-precision data input. Meanwhile, the outdoor environment sensing unit, deployed in an unobstructed area outside the building, integrates temperature and humidity sensors and a real-time meteorological interface module. In addition to local sensing, it also accesses city-level meteorological data via an API, enabling real-time perception of wind speed, direction, sunshine intensity, and rainfall trends. The system fuses indoor and outdoor temperature data, using weighted averaging, regional correction, and trend analysis algorithms to compensate for blind spots or delayed sensing. The system then constructs a multidimensional temperature signature model using metrics such as multi-region temperature difference distribution, temperature change rate, and thermal diffusion gradient to represent the thermal landscape of the entire building at a specific moment. This model provides data support for subsequent temperature distribution status determination and air conditioning mode switching strategy formulation. During the data fusion process, each data point is dynamically weighted based on its sensor weight, historical bias correction value, and data consistency confidence to improve model robustness and environmental adaptability.

[0031] The switching decision module includes an energy efficiency evaluation submodule and a switching timing optimization submodule. The energy efficiency evaluation submodule is used to simulate and dynamically monitor the energy consumption level of each air-conditioning unit at a preset switching time. The switching timing optimization submodule uses a heuristic algorithm or fuzzy control strategy based on the simulation results and the current regional load demand to determine the optimal mode switching sequence that is conducive to improving the system energy efficiency.

[0032] This implementation decouples performance evaluation and strategic decision-making in mode switching control by subdividing the switching decision module into an energy efficiency evaluation submodule and a switching timing optimization submodule. The energy efficiency evaluation submodule first accesses historical operating data for each air conditioning unit from the system database based on a preset switching schedule. This data includes information such as unit time energy consumption, cooling load response curves, cooling efficiency, and startup instantaneous power consumption under different operating modes. The system then uses an energy consumption simulation model based on thermodynamic balance calculations and power-load response relationships, combining parameters such as the current room temperature, setpoint temperature, and load variation trends, to predict each unit's short-term energy consumption at the set switching point. For example, if a unit is expected to switch to cooling mode within the next 15 minutes, the model estimates its projected energy consumption based on its current ambient temperature difference, cooling load, and power efficiency function, and records this value in a simulated energy consumption matrix. Subsequently, the switching timing optimization submodule uses the simulation matrix output, combined with the current load demand levels and user comfort priorities of each building zone, to construct a multi-objective optimization function. The goal is to maximize the overall system energy efficiency ratio, minimize peak switching power fluctuations, and maintain regional temperature balance. The submodule uses heuristic algorithms, such as greedy algorithms or simulated annealing, to select the scheduling sequence with the highest energy efficiency score from among possible switching sequences. Furthermore, to address dynamic control in highly complex scenarios, the system incorporates fuzzy control logic, inferring rules based on fuzzy variables such as regional load levels, switching delay tolerance, and local overload risk, and outputs a corresponding fine-tuning strategy for switching timing. Ultimately, the optimal switching sequence output by the system can be dynamically modified and applied to the air conditioning units in real time, ensuring optimal system energy efficiency and a smooth switching process while meeting user needs.

[0033] The conflict control module includes a mode conflict judgment unit and a power redistribution unit. The mode conflict judgment unit is used to identify the conflict status when the cooling and heating modes are running concurrently between air-conditioning units. The power redistribution unit redistributes the air-conditioning output power by adjusting the operating frequency or cooling / heating intensity according to the spatial position, load intensity and user demand level between the conflicting units, thereby achieving fine-tuning and dynamic balance of the operating mode.

[0034] This embodiment incorporates a dedicated conflict control module within the cluster air conditioning control system. The core of this module is a mode conflict identification unit and a power redistribution unit, which collaborate to achieve dynamic balance adjustment. First, the mode conflict identification unit continuously analyzes the current operating mode information of all air conditioning units. If it detects that two or more units are in cooling and heating states during overlapping time periods, and the spatial distance between them is less than 10 meters or they belong to the same thermal block, the system determines a "mode conflict." To accurately determine the impact of the conflict, the system further calculates the temperature deviation in the overlapping areas of heat impact between adjacent conflicting units. If the deviation exceeds 1.5 degrees Celsius, a significant conflict is identified. After the identification results are passed to the power redistribution unit, the unit comprehensively evaluates the location of the conflicting units, the current heat load intensity in the area, and the user demand level. The heat load intensity is calculated based on the temperature difference per unit area and the historical rate of change. The user demand level is divided into three levels: high, medium, and low, based on comfort sensitivity, and assigned priority weights. Based on these factors, the system constructs a weighted adjustment priority matrix and redistributes cooling or heating power after sorting. Adjustments include reducing the compressor operating frequency of low-priority units, adjusting the opening of electronic expansion valves, limiting air flow speed, or shortening the compressor's continuous operating period to ensure stable output for high-priority units. During the control process, the system performs a balance check every three minutes. If the temperature difference in the conflicting area steadily decreases and user feedback is normal, the current fine-tuning strategy is maintained. If it fails to meet the target, the next round of redistribution optimization is initiated. Ultimately, this mechanism achieves dynamic coordination of local temperatures, ensuring overall operational balance and maximizing energy efficiency.

[0035] The command control module includes a central controller and an edge execution unit. The central controller generates control commands based on the adjusted operating parameters and comfort feedback results. The edge execution unit is deployed on each air-conditioning equipment body, receives control commands and performs corresponding mode switching and power adjustment operations, and at the same time transmits the execution status and equipment response status back to the central controller to achieve closed-loop control.

[0036] In this implementation, the command control module, as the core component of the system's execution layer, is responsible for three key functions: command issuance, device response, and operation monitoring. The central controller, the system's decision-making center, utilizes the integrated control strategy module to generate personalized control commands for each air conditioning unit based on the adjusted operating parameters output by the front-end acquisition module, analysis module, and switching decision module, as well as user comfort feedback. These commands include control parameters such as the target operating mode (cooling / heating / ventilation), operating power level, compressor frequency, fan speed level, and expected response time window. All commands are transmitted to the corresponding edge execution unit via a wired or wireless communication bus (such as Modbus, BACnet, or MQTT). The edge execution unit is directly integrated into each air conditioning unit and includes a local control chip, communication interface, and device status sensing module. Upon receiving a command from the central controller, this unit immediately interprets the command content and performs operations such as mode switching, frequency conversion, and power output adjustment based on the unit's actual state. Once the unit responds, its internal status sensing module packages the current operating mode, temperature feedback, operating status code, fault information, and response latency, and transmits this information back to the central controller in real time via the protocol stack. The central controller compares expected control results with actual device feedback to assess control accuracy and response timeliness. If anomalies such as response delays, execution deviations, or communication interruptions are detected, the system automatically initiates fault diagnosis and fault-tolerant control, invoking backup commands or reissuing command packets to ensure a stable closed-loop control system. This closed-loop structure cycles every 30 seconds, enabling continuous optimization and real-time correction of system operating status, enhancing system reliability and intelligence.

[0037] It also includes a historical data learning module, which is used to perform machine learning modeling on the environmental data, user preference data and air-conditioning response data accumulated during the long-term operation of the system. By building a predictive model, it predicts the temperature change trend and user demand fluctuations in a specific time period in the future, and provides forward-looking optimization suggestions for the mode switching strategy.

[0038] This implementation adds a historical data learning module to the system architecture as a core component of strategic analysis and predictive control. This module maintains constant access to the system's operational database, continuously collecting and organizing three core data types: environmental data, including indoor temperature, humidity, air velocity, and outdoor weather records; user preference data, encompassing behavioral characteristics such as set temperatures, comfort feedback, and device usage frequency over different time periods; and air conditioner response data, recording response time, cooling and heating efficiency, and stability indicators for each device under different modes and power settings. After data cleaning and standardization, the module uses a combination of supervised learning and time series modeling to construct temperature trend prediction models and user demand trend models. The temperature prediction model analyzes the response relationship between climate conditions and indoor temperature in historical time series, employing models such as long-short-term memory neural networks or temporal convolutional networks to accurately predict temperature changes over the next 6 to 24 hours. The user demand model uses a combination of clustering and regression modeling to identify usage preference patterns for different user groups over different time periods and under different external conditions, and generates personalized demand prediction curves. Before each scheduling cycle begins, the system uses the module's forecast results to cross-compare them with current system status data. The system then generates warnings for potential load peaks, assesses user comfort risks, and provides optimization recommendations. If the forecast indicates a temperature rise in a particular area within the next hour, accompanied by high demand, the system proactively plans mode switching, power allocation strategies, and soft-start control strategies, effectively avoiding energy waste and delayed response times.

[0039] It also includes an abnormality identification and early warning module, which is used to detect abnormal conditions such as abnormal temperature fluctuations, slow response of air-conditioning units or communication interruptions during system operation, and generate early warning information when an abnormality is detected, and prompt through the user terminal or the background operation and maintenance platform to improve the reliability of system operation and fault recovery capabilities.

[0040] This implementation introduces an anomaly identification and early warning module as a key functional module for system operational status monitoring and proactive safety management. This module accesses data streams from each air conditioning unit, sensor node, and control communication link in real time, comparing and analyzing operational parameters including temperature data, device operating status, execution feedback latency, and communication integrity. The system employs multi-dimensional anomaly identification criteria. For example, a temperature fluctuation exceeding 3 degrees Celsius in a particular area within 10 minutes, or a temperature difference exceeding 2 degrees Celsius from an adjacent area, is considered "abnormal temperature fluctuation." An air conditioning unit's failure to transmit data within 5 seconds of a control command is considered "sluggish response." The inability to complete data communication with an air conditioning unit or sensor within two consecutive monitoring cycles is considered "communication interruption." This module utilizes a rule engine combined with anomaly detection algorithms to perform data sliding window statistics, trend analysis, and time series consistency checks. It also incorporates an anomaly classification mechanism (e.g., general, severe, and critical), with dynamically adjustable thresholds to suit different application environments and control requirements. When an anomaly is triggered, the system immediately generates an alert containing the anomaly type, time, device number, scope of impact, and recommended actions. This alert is communicated via pop-up windows on the user terminal interface, alarm logs on the backend operations and maintenance management platform, and, when necessary, SMS, email, or app push notifications. Furthermore, the module features a self-recovery attempt function. When a communication anomaly occurs, it automatically switches to an alternate communication path or retry mechanism to attempt to resend the command. In the event of a slow response, the device's self-test logic is invoked to determine whether the cause is a temporary load fluctuation or hardware anomaly, providing a basis for subsequent manual intervention.

[0041] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The cluster temperature control and energy consumption balance optimization control system of the air conditioning group is characterized by: The system comprises: The data acquisition module collects temperature data of various indoor areas and outdoor temperature change information in real time through the sensor network. Combined with the preset temperature threshold range, it analyzes the heterogeneous characteristics of indoor temperature distribution and obtains the temperature distribution status of each area; The matching analysis module prioritizes the actual demand differences in the area where each air-conditioning unit is located based on the temperature distribution status and regional demand matching data obtained from the user end, and determines the mode switching demand level of each area; The switching decision module determines the final switching opportunity list based on the mode switching demand level. Based on the final switching opportunity list, it obtains real-time monitoring data of system operation efficiency, analyzes the energy consumption performance of each unit after the mode switch, determines whether it meets the preset efficiency standards, and obtains the evaluation results of system stability assurance; The conflict control module, if the system stability assessment results indicate the presence of overheating or overcooling in a local area, fine-tunes the operating mode of the relevant air conditioning units through the mode conflict avoidance mechanism, reallocates power output, and determines the adjusted operating parameters; The command control module updates the control commands of each air-conditioning unit in real time according to the adjusted operating parameters. It combines the feedback data of regional demand matching to analyze whether the user comfort meets the expectations and obtains the final system operation status report.

2. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1 is characterized by: The method of determining the final switching timing list based on the mode switching demand level includes obtaining the location information and corresponding power parameters of each air-conditioning unit based on the determined mode switching demand level, analyzing the spatial correlation and power matching between the units, and determining a preliminary reasonable switching sequence plan.

3. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 2 is characterized by: The final switching timing list determined based on the mode switching demand level also includes adjusting the switching timing through a dynamic environmental adaptation algorithm if there are multiple air-conditioning units running conflicting modes at the same time in the preliminary switching sequence rationality plan, recalculating the mode switching time point of each unit, and obtaining an optimized switching timing arrangement.

4. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 3 is characterized by: Determining the final switching timing list for the mode switching demand level also includes analyzing the potential interference of the external environment on the indoor temperature distribution based on the optimized switching timing arrangement in combination with the outdoor temperature change data, judging whether there are air-conditioning units that need to be switched early or late, and determining the final switching timing list.

5. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1 is characterized by: The data acquisition module includes an indoor temperature sensing unit and an outdoor environment sensing unit. The indoor temperature sensing unit is distributed in multiple key areas inside the building and is used to collect local temperature data of different areas in real time; the outdoor environment sensing unit includes a temperature and humidity sensor and a meteorological interface, which is used to obtain real-time meteorological information outside the building. The two are used together to build a comprehensive temperature characteristic model to assist in judging the temperature distribution status.

6. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1 is characterized by: The switching decision module includes an energy efficiency evaluation submodule and a switching timing optimization submodule. The energy efficiency evaluation submodule is used to simulate and dynamically monitor the energy consumption level of each air-conditioning unit at a preset switching time. The switching timing optimization submodule uses a heuristic algorithm or fuzzy control strategy based on the simulation results and the current regional load demand to determine the optimal mode switching sequence that is conducive to improving system energy efficiency.

7. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1 is characterized by: The conflict control module includes a mode conflict judgment unit and a power redistribution unit. The mode conflict judgment unit is used to identify the conflict state when the cooling and heating modes are running concurrently between air-conditioning units. The power redistribution unit redistributes the air-conditioning output power by adjusting the operating frequency or cooling / heating intensity according to the spatial position, load intensity and user demand level between the conflicting units, thereby achieving fine-tuning and dynamic balance of the operating mode.

8. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1 is characterized by: The command control module includes a central controller and an edge execution unit. The central controller generates control commands based on the adjusted operating parameters and comfort feedback results. The edge execution unit is deployed on each air-conditioning equipment body, receives control commands and performs corresponding mode switching and power adjustment operations, and at the same time transmits the execution status and equipment response status back to the central controller to achieve closed-loop control.

9. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1, characterized in that: It also includes a historical data learning module, which is used to perform machine learning modeling on the environmental data, user preference data and air-conditioning response data accumulated during the long-term operation of the system. By building a predictive model, it predicts the temperature change trend and user demand fluctuations in a specific time period in the future, and provides forward-looking optimization suggestions for the mode switching strategy.

10. The cluster air conditioning temperature control and energy consumption balance optimization control system according to claim 1, characterized in that: It also includes an abnormality identification and early warning module, which is used to detect abnormal conditions such as abnormal temperature fluctuations, slow response of air-conditioning units or communication interruptions during system operation, and generate early warning information when an abnormality is detected, and prompt through the user terminal or the background operation and maintenance platform to improve the reliability of system operation and fault recovery capabilities.

Images