A control optimization method and system based on regional central air conditioning system

Abstract

The present application provides a control optimization method and system based on a regional central air-conditioning system, which relates to the field of electrical digital data processing. The method includes: obtaining the temperature control requirements of merchants in each region and the location information of the air supply duct, and then determining the wind speed of each air supply duct; determining the basic operating parameters of the central air-conditioning system in different time periods of the day according to the temperature fluctuation curve of each region; inputting the personnel density data and actual temperature data of each region into the prediction model, outputting the operating adjustment parameters of the current time period, and then determining the real-time operating parameters of the central air-conditioning system in each region in combination with the basic operating parameters; the real-time operating parameters are combined with the wind speed to obtain the optimization control strategy of the central air-conditioning system in each region. By implementing this method, the operating state of the air-conditioning system can be dynamically optimized according to real-time data, thereby improving energy efficiency, reducing energy waste, and adjusting the temperature according to actual needs to improve user comfort.

Description

Technical Field

[0001] The present application relates to the field of electronic digital data processing, and in particular to a control optimization method and system based on a regional central air-conditioning system. Background Art

[0002] In modern commercial buildings, central air conditioning systems are key equipment for maintaining indoor temperature comfort. These systems need to efficiently regulate the temperature of multiple areas to meet the needs of different merchants. With the development of building technology and the increase in energy efficiency requirements, higher requirements are placed on the control strategies of central air conditioning systems.

[0003] In the related art, central air conditioning control technology usually relies on a simple temperature feedback control mechanism to achieve a preset temperature setting value by adjusting the fan speed and the output of the cold and hot sources. In addition, many systems use a timing control strategy to adjust the air conditioning output according to a fixed schedule to adapt to the daily usage pattern of the building.

[0004] However, these traditional control methods are difficult to meet the needs of temperature differences and real-time changes between various areas within a building. For example, different stores in a shopping mall may have different temperature requirements due to different opening hours and customer flow. Existing systems often cannot be adjusted flexibly, resulting in energy waste and reduced user comfort. Summary of the invention

[0005] The present application provides a control optimization method and system based on a regional central air-conditioning system, which is used to solve the problem of how to accurately adjust the central air-conditioning system according to the temperature requirements and actual temperature conditions of each region.

[0006] In a first aspect, the present application provides a control optimization method based on a regional central air conditioning system, which is applied to a cloud control system. The method includes:

[0007] Obtain the temperature control requirements of merchants in each area and the location information of air supply ducts in each area;

[0008] Determine the wind speed of each air supply duct according to the temperature control requirement and the location information;

[0009] Determine the basic operating parameters of the central air-conditioning system in each area at different time periods of the day according to the temperature fluctuation curve of each area compared with the outdoor temperature during the day, the temperature fluctuation curve is measured when the central air-conditioning system is not in operation, and the basic operating parameters include temperature set point, output wind speed and operation mode;

[0010] Input the population density data and actual temperature data of each area into the trained prediction model, and output the operation adjustment parameters of the central air-conditioning system in each area in the current time period;

[0011] Determine the real-time operating parameters of the central air-conditioning system in each area according to the operating adjustment parameters and the basic operating parameters;

[0012] The central air-conditioning system in each area is optimized and controlled according to the real-time operating parameters and the wind speed.

[0013] Through the above embodiments, the cloud control system obtains the temperature control requirements and air supply duct location information of merchants in each area, combines the temperature fluctuation curve and personnel density data, and intelligently adjusts the operating parameters of the central air conditioner. This method can dynamically optimize the operating status of the air conditioning system based on real-time data, thereby improving energy efficiency, reducing energy waste, and adjusting the temperature according to actual needs to improve user comfort.

[0014] In some embodiments, the step of determining the wind speed of each air supply duct according to the temperature control requirement and the location information specifically includes:

[0015] Calculate the ratio of the ideal temperature value corresponding to the target merchant area to the standard value, where the ideal temperature value is determined based on the temperature control requirement;

[0016] Determine whether there is a target air supply duct in the target merchant area according to the location information;

[0017] If yes, the wind speed corresponding to each target air supply duct is determined based on a preset ratio-wind speed relationship table;

[0018] If not, the target merchant area is taken as the center, and the air supply ducts within the preset range are determined as the target air supply ducts for wind speed adjustment.

[0019] Through the above embodiment, the cloud control system calculates the ratio of the ideal temperature value to the standard value and checks the existence of the target air supply duct to accurately control the wind speed of each air supply duct, thereby ensuring that the target area can achieve the best temperature control effect, thereby improving the response speed and accuracy of the air-conditioning system.

[0020] In some embodiments, the step of determining the air supply ducts within a preset range as target air supply ducts for wind speed adjustment with the target merchant area as the center specifically includes:

[0021] Calculate the distance between each air supply duct within a preset range and the target business area;

[0022] Determine the effective air supply ducts within the preset range according to the maximum wind speed corresponding to each air supply duct and the distance value;

[0023] The effective air supply duct is determined as the target air supply duct, and the maximum wind speed is turned on to supply air.

[0024] Through the above embodiments, the cloud control system can allocate air conditioning resources more effectively by calculating the distance between the air supply duct and the target area within a preset range and adjusting the wind speed according to the distance, so that areas far away from the central air supply system can also obtain appropriate temperature regulation.

[0025] In some embodiments, before the step of inputting the population density data and the actual temperature data of each area into the trained prediction model and outputting the operation adjustment parameters of the central air-conditioning system of each area in the current time period, the method further includes:

[0026] Obtaining population density data of each area in each sub-time period, as well as corresponding actual temperature data and multiple historical adjustment parameters of the central air-conditioning system in a preset sample time period, wherein the preset sample time period includes a central air-conditioning system operation time period under multiple different weather conditions, and each of the historical adjustment parameters corresponds to energy consumption data of a central air-conditioning system;

[0027] Determine the historical adjustment parameters corresponding to the central air-conditioning system when the energy consumption data is minimum as the target adjustment parameters;

[0028] Constructing a data set based on the personnel density data, the actual temperature data, and the target adjustment data;

[0029] The data set is used to train the machine learning model to obtain a trained prediction model.

[0030] Through the above embodiments, the cloud control system builds a prediction model to analyze data under different weather conditions, learns and predicts the most energy-efficient air conditioning system operating parameters. This not only improves the intelligence level of the system, but also automatically adjusts the operating strategy according to the actual environment to maximize energy utilization and minimize operating costs.

[0031] In some embodiments, the step of obtaining the population density data of each area in each sub-time period, the corresponding actual temperature data and a plurality of historical adjustment parameters of the central air-conditioning system in a preset sample time period, wherein the preset sample time period includes a central air-conditioning system operation time period under a plurality of different weather conditions, and each of the historical adjustment parameters corresponds to an energy consumption data of the central air-conditioning system, specifically includes:

[0032] The operation time period of the central air-conditioning system is intercepted under various weather conditions as a preset sample time period, and the weather condition is a weather condition that affects the energy consumption of the central air-conditioning system;

[0033] Control and adjust the central air-conditioning system according to the basic operating parameters in each preset sample time period;

[0034] Monitor and obtain the population density data and the corresponding actual temperature data in each sub-time period;

[0035] The basic operating parameter is adjusted according to a preset amplitude in each sub-time period to obtain a plurality of historical adjustment parameters;

[0036] The energy consumption data of the current sub-time period is estimated under each of the historical adjustment parameters.

[0037] Through the above embodiments, the cloud control system can more accurately adjust the air-conditioning system to adapt to the external environment by systematically collecting and analyzing data under various conditions, thereby improving energy efficiency and user comfort.

[0038] In some embodiments, the step of optimizing and controlling the central air conditioning system of each area according to the real-time operating parameters and the wind speed specifically includes:

[0039] Adjusting the operating state of the central air conditioning system in each area according to the real-time operating parameters;

[0040] The wind speed of the target air supply duct is individually controlled according to the wind speed.

[0041] Through the above embodiments, the cloud control system comprehensively regulates real-time operating parameters and wind speed, can quickly respond to environmental changes and internal demand changes, and achieve refined temperature management.

[0042] In some embodiments, after the step of optimizing and controlling the central air conditioning system of each area according to the real-time operating parameters and the wind speed, the method further includes:

[0043] Determine whether the newly acquired actual temperature data meets the temperature control requirements of merchants in each region;

[0044] If yes, proceed with subsequent adjustments;

[0045] If not, the prediction model is incrementally trained.

[0046] Through the above embodiment, after executing the optimization control, the cloud control system continues to monitor the temperature data to confirm whether the demand is met. If the actual temperature does not meet the expectation, the system will adjust the prediction model and perform incremental training to improve its performance, so that the prediction model can continuously adapt to new operating conditions and user needs, and improve the accuracy and reliability of the model prediction results.

[0047] In a second aspect, the present application provides a cloud control system, the cloud control system comprising: one or more processors and a memory;

[0048] The memory is coupled to the one or more processors, and the memory is used to store computer program code, which includes computer instructions. The one or more processors call the computer instructions so that the cloud control system can implement a control optimization method based on a regional central air-conditioning system provided in the above embodiment, which will not be repeated here.

[0049] In a third aspect, the present application provides a computer-readable storage medium, including instructions. When the instructions are executed on a cloud control system, the cloud control system can implement a control optimization method based on a regional central air-conditioning system provided in the above embodiment, which will not be repeated here.

[0050] In a fourth aspect, the present application provides a computer program product. When the computer program product runs on a cloud control system, the cloud control system can implement a control optimization method based on a regional central air-conditioning system provided in the above embodiment, which will not be repeated here.

[0051] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0052] 1. The cloud control system obtains the temperature control requirements and air supply duct location information of merchants in each area, combines the temperature fluctuation curve and personnel density data, and intelligently adjusts the operating parameters of the central air conditioner. This method can dynamically optimize the operating status of the air conditioning system based on real-time data, thereby improving energy efficiency, reducing energy waste, and adjusting the temperature according to actual needs to improve user comfort.

[0053] 2. By precisely controlling the wind speed of the air supply duct and adjusting the temperature according to the specific needs of the target merchant area. This refined control strategy not only makes personalized adjustments based on specific location information and temperature requirements, but also implements differentiated management based on the distance and location differences between areas, thereby ensuring that each area can achieve the most ideal temperature state. In this way, the air conditioning system can allocate resources more effectively and improve overall energy utilization and environmental comfort.

[0054] 3. Use historical adjustment parameters and real-time data to train the prediction model, and continuously optimize the accuracy of the prediction model through a feedback mechanism, so that the air-conditioning system can not only automatically adjust its operation strategy to adapt to real-time environmental changes, but also optimize its performance through continuous learning to achieve higher energy efficiency and better user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a control optimization method based on a regional central air conditioning system in an embodiment of the present application;

[0056] Figure 2This is a flow chart of the cloud control system adjusting the wind speed of the air supply ducts in each area in the embodiment of the present application;

[0057] Figure 3 is another flow chart of a control optimization method based on a regional central air conditioning system in an embodiment of the present application;

[0058] Figure 4 It is a schematic diagram of the structure of a physical device of a cloud control system in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0060] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0061] For ease of understanding, the following is a flow chart of the method provided in this implementation. Figure 1 As shown, it is a flow chart of a control optimization method based on a regional central air-conditioning system in an embodiment of the present application.

[0062] S101. Obtain temperature control requirements of merchants in each area and location information of air supply ducts in each area.

[0063] The temperature requirements of merchants can be uploaded to the cloud control system by merchants through personal terminals (such as mobile phones). The cloud system can also automatically infer their temperature preferences by analyzing the merchant's historical temperature setting data and feedback records using machine learning algorithms, and give reasonable default settings when merchants do not submit clear requirements.

[0064] In addition, the location information of the air supply duct can be obtained from the design drawings or completion data of the building stored in the database.

[0065] S102: Determine the wind speed of each air supply duct according to the temperature control requirement and the location information.

[0066] After clarifying the target temperature range and air duct distribution of each area, the cloud control system further decides how to accurately distribute the cold air to each area.

[0067] Specifically, the cloud control system analyzes the specific coordinates of each air outlet to determine which target merchant area it belongs to, and then establishes a mapping relationship between the air supply duct and the target merchant area. By comparing the temperature control requirements between different target merchant areas, the wind speed ratio of each air supply duct is determined, and then the wind speed of each air supply duct is determined.

[0068] S103, determining basic operating parameters of the central air-conditioning system in each area at different time periods in a day according to the temperature fluctuation curve of each area compared with the outdoor temperature in a day.

[0069] When the central air-conditioning system is completely stopped, the cloud control system conducts continuous temperature monitoring of the actual temperature of each indoor area of ​​the building and the meteorological parameters of the outdoor environment for several days. Among them, for the actual indoor temperature, several temperature sensors can be arranged in each area to collect the average temperature changes of the area at all times and high frequency; for the outdoor meteorological parameters, the hourly dry bulb temperature, relative humidity, solar radiation intensity, wind speed and direction, etc. can be recorded. By comparing and analyzing these two types of data, the fluctuation curve of the temperature in different areas relative to the outdoor temperature can be obtained. The shape characteristics of the curve can qualitatively reflect the thermal performance of the enclosure structure in the area.

[0070] Relevant staff can pre-set the mapping relationship between the corresponding values ​​of different temperature fluctuation curves and the basic operating parameters based on actual needs. After generating the temperature fluctuation curve, the cloud system determines the basic operating parameters of the central air-conditioning system in each area at different time periods of the day based on the mapping relationship.

[0071] It should be noted that during the monitoring process, all HVAC equipment, including the fresh air system, needs to be temporarily shut down to eliminate its impact on the room temperature. At the same time, monitoring should be carried out in different seasons and weather conditions to obtain comprehensive sample data.

[0072] S104: Input the population density data and actual temperature data of each area into the trained prediction model, and output the operation adjustment parameters of the central air-conditioning system of each area in the current time period.

[0073] Specifically, the cloud system continuously collects traffic data in each area through various sensors deployed in the building, such as infrared counters and cameras, and calculates the density of people in each area. At the same time, the temperature sensors arranged in each area are also monitoring and reporting the actual temperature data in real time. The cloud system cleans and normalizes these two types of data in a predetermined format, and then inputs them into the trained prediction model. Based on these environmental characteristic data, the prediction model comprehensively analyzes the current gathering of people and the actual temperature distribution, evaluates the actual demand for cooling / heating in each area, and then gives the optimal air-conditioning operation strategy, including a series of parameters such as the temperature setting value, air volume, and fresh air introduction in each area.

[0074] S105. Determine the real-time operating parameters of the central air-conditioning system in each area according to the operating adjustment parameters and the basic operating parameters.

[0075] Specifically, the cloud system reads the basic operating parameters of each area from the database, including temperature setting value, air supply volume, fresh air ratio, etc. At the same time, the real-time population density and temperature data of each area are collected in real time and input into the prediction model to generate corresponding adjustment parameters. The cloud system superimposes the adjustment parameters on the basic parameters, dynamically calibrates the latter, and obtains the corrected real-time operating parameters. This process can be expressed by the following formula: real-time operating parameters = basic operating parameters + adjustment parameters.

[0076] For example, suppose that in the basic operating parameters of a conference room, the temperature setting is 24°C and the air supply is 1000m³ / h. At 10 a.m., due to the large number of people entering the room, the density of people in the conference room suddenly increases, and the actual temperature begins to rise. The prediction model generates adjustment parameters based on these real-time data, and recommends lowering the temperature setting by 2°C and increasing the air supply by 20%. Based on this, the cloud control system calculates the real-time operating parameters as follows:

[0077] Temperature setting: 24°C - 2°C = 22°C;

[0078] Air supply volume: 1000m³ / h × (1+20%) = 1200m³ / h.

[0079] Then, the cloud control system sends these real-time operating parameters to the air-conditioning control unit, instructing the compressor, fan and other equipment to change their operating status, so that the cooling output and air supply capacity of the air-conditioning system match the current load demand, and promptly suppress the further rise of room temperature.

[0080] S106. Optimize and control the central air conditioning system in each area based on real-time operating parameters and wind speed.

[0081] Specifically, the cloud control system sends real-time operating parameters to the control unit of the central air-conditioning system host through the communication interface with the building automation system. The control unit adjusts the working conditions of the compressor, condenser, evaporator and other components accordingly, changes the flow rate and state parameters of the refrigerant, and dynamically matches the cooling / heat delivered to the terminal with the load demand of each area.

[0082] On this basis, the cloud control system controls the control mechanism of the air supply duct openings in each area, and adjusts the air supply duct openings to the wind speed, thereby achieving optimized control of the central air-conditioning system in each area.

[0083] In the above embodiment, the cloud control system intelligently adjusts the operating parameters of the central air conditioner by obtaining the temperature control requirements and air supply duct location information of merchants in each area, combining the temperature fluctuation curve and personnel density data. This method can dynamically optimize the operating status of the air conditioning system based on real-time data, thereby improving energy efficiency, reducing energy waste, and adjusting the temperature according to actual needs to improve user comfort.

[0084] The following is a more detailed description of the process of the method provided by this embodiment. Figure 2 As shown, it is a schematic diagram of a process of adjusting the wind speed of the air supply ducts in each area by the cloud control system in an embodiment of the present application.

[0085] S201. Calculate the ratio of the ideal temperature value corresponding to the target merchant area to the standard value.

[0086] The cloud control system first obtains the ideal temperature value of the target merchant area. The ideal temperature value can be reported directly by the merchant, or it can be automatically inferred by analyzing the merchant's historical temperature setting data and feedback records using a machine learning algorithm. Then, the system reads the preset standard temperature value from the database, which is usually a reference room temperature determined based on factors such as human comfort. Next, the system divides the ideal temperature value by the standard temperature value to obtain the ratio of the two.

[0087] S202: Determine whether there is a target air supply duct in the target merchant area.

[0088] After calculating the ratio of the ideal temperature to the standard temperature, the cloud control system further determines whether there are air supply ducts in the target merchant area. Specifically, the system first retrieves the air supply duct distribution map of the entire building from the database, which indicates the specific location coordinates of each air supply duct. Then, the range coordinate information of the target merchant area is read, and the spatial geometry algorithm is used to determine whether the coordinates of the air supply duct fall within the area. If so, it is marked as the target air supply duct and prepared for wind speed adjustment; if not, it is necessary to expand the search range and find air supply ducts in neighboring areas as alternatives.

[0089] S203: Calculate the distance between each air supply duct and the target business area within a preset range.

[0090] If it is found in step S202 that there is no air supply duct in the target merchant area, the cloud control system will expand the search range to the surrounding area. Specifically, the system first sets a reasonable search radius based on the characteristics of the building layout, and draws a circular preset range with the geometric center of the target merchant area as the center. Then, the system traverses each air supply duct within the range, calculates its Euclidean distance from the center of the target merchant area, and obtains a set of distance values.

[0091] S204: Determine effective air supply ducts within a preset range according to the maximum wind speed and distance value corresponding to each air supply duct.

[0092] After obtaining the distance data between each air supply duct and the target area, the cloud control system also needs to consider the air supply capacity of each duct to further screen out effective ducts. Specifically, the system first retrieves the maximum wind speed parameters of each air supply duct from the database, and then multiplies it by a distance attenuation coefficient to estimate the actual wind speed at the end of the duct. The attenuation coefficient can be fitted through engineering experience or fluid mechanics models, such as 0.9^(distance / 10). Then, the system compares the corrected wind speed with the minimum wind speed threshold required for the target area. If the former is greater than the latter, the air supply duct is judged to be valid, otherwise it is invalid.

[0093] S205: Determine the effective air supply duct as the target air supply duct, and start the air supply at the maximum wind speed.

[0094] According to the judgment result of step S204, the cloud control system classifies all valid air supply ducts as target air supply ducts to form a centrally controlled duct group. Since these ducts have undergone dual screening of position and wind speed, they can efficiently deliver cold air to the target area. Specifically, the system issues an instruction to increase the fan speed of all air supply ducts in the group to the maximum allowed value, so that it can continue to operate at the rated maximum wind speed. In this way, a large range of temperature reduction and improvement in environmental comfort can be achieved in the shortest time. At the same time, in order to prevent overcooling, the system will monitor the temperature changes in the target area in real time and dynamically adjust the fan status according to the feedback data. Once it is detected that the actual temperature is close to the set value, the system will issue a speed reduction or shutdown command to restore the air supply duct to normal operation mode.

[0095] In the above embodiment, the cloud control system can allocate air conditioning resources more effectively by calculating the distance between the air supply duct and the target area within a preset range and adjusting the wind speed according to the distance, so that areas far away from the central air supply system can also obtain appropriate temperature regulation.

[0096] S206. Determine the wind speed corresponding to each target air supply duct based on a preset ratio wind speed relationship table.

[0097] If it is found in step S202 that there are air supply ducts in the target merchant area, the cloud control system can also perform more precise wind speed control on each duct according to the temperature demand differences in different areas. Specifically, the system pre-establishes a ratio-wind speed comparison table to describe the quantitative relationship between the temperature ratio and the duct wind speed. The table is obtained by fitting a large amount of actual engineering data, and can more accurately reflect the impact of wind speed changes on regional temperature, which is not limited here.

[0098] In actual control, the system obtains the target area temperature ratio calculated in step S201, then determines the ideal duct wind speed value corresponding to the ratio by looking up the table, and adjusts the wind speed according to the ideal duct wind speed value.

[0099] In the above embodiment, the cloud control system calculates the ratio of the ideal temperature value to the standard value and checks the existence of the target air supply duct to accurately control the wind speed of each air supply duct, thereby ensuring that the target area can achieve the best temperature control effect, thereby improving the response speed and accuracy of the air-conditioning system.

[0100] Based on the above wind speed adjustment process, another flow chart of a control optimization method based on a regional central air conditioning system provided by this embodiment is introduced below. Figure 3 shown.

[0101] S301. Select a central air-conditioning system operation time period under various weather conditions as a preset sample time period.

[0102] The cloud control system selects sample time periods that can represent the operating characteristics of air conditioners under different weather conditions. Specifically, the system first collects meteorological data over a long period of time (such as a year), including parameters such as temperature, humidity, solar radiation intensity, and wind speed. Then, through data mining algorithms such as cluster analysis, these data are divided into several typical weather modes, such as hot and dry, warm and humid, cold and windy, etc. Next, the system finds the operating time period under each weather mode based on the operating records of the air conditioning system, and intercepts a representative section as a sample.

[0103] For example, in hot and dry summer, the air conditioning system often needs to run at full capacity to cope with the cooling demand caused by high temperatures. The cloud system can select 14:00 to 18:00 in a week in August as a sample time period for such extreme conditions. In mild spring and autumn, the air conditioning operation frequency and load level are relatively low. At this time, 09:00 to 12:00 in a week in April can be selected as a sample.

[0104] S302: Control and adjust the central air-conditioning system according to basic operating parameters in each preset sample time period.

[0105] The cloud control system controls the actual operation of the central air-conditioning system according to the preset basic operating parameters during the selected sample time period. The basic parameters here usually include temperature setting value, fan speed, compressor frequency, etc., which together determine the cooling / heat output and air supply effect of the air conditioner. The system first retrieves the corresponding basic operating parameters from the parameter library, and then sends them to the air conditioner host and terminal device to guide them to operate according to the specified mode.

[0106] It should be noted that the basic operating parameters retrieved from the parameter library correspond to the temperature fluctuation curve of the sample time period.

[0107] S303: Monitor and obtain personnel density data and corresponding actual temperature data in each sub-time period.

[0108] After running for a period of time with specific parameters, the cloud control system collects environmental data in the air-conditioned area in real time to evaluate the current operating effect. The collection process of personnel density data and actual temperature data is not described here.

[0109] S304. In each sub-time period, the basic operating parameters are adjusted according to a preset range to obtain a plurality of historical adjustment parameters.

[0110] According to the population density and actual temperature data collected in step S303, the cloud control system needs to make appropriate adjustments to the basic operating parameters after detecting that the air conditioning operation effect deviates from the expected one, so as to reduce energy consumption as much as possible while ensuring comfort. Specifically, the system pre-sets an adjustment range, such as temperature ±1°C, wind speed ±10%, compressor frequency ±5Hz, etc. In each sub-time period (such as 15 minutes), the system will fine-tune the basic parameters within the above range to obtain a new set of operating parameters, and record them to form the historical adjustment parameters of the period.

[0111] S305: Estimate the energy consumption data of the current sub-time period under each historical adjustment parameter.

[0112] After obtaining a series of historical adjustment parameters, the cloud control system evaluates the energy efficiency performance of each set of parameters in order to screen out the optimal parameters.

[0113] Specifically, the system can pre-establish an air conditioning energy consumption model, which takes outdoor temperature and humidity, set temperature, wind speed, frequency and other parameters as input, and finally outputs the estimated energy consumption per unit time after calculating a series of thermal engineering and fluid mechanics equations. This model is trained based on a large amount of historical operation data and energy consumption measurement data, and can more accurately reflect the actual energy consumption level. In the period corresponding to each historical adjustment parameter, the system substitutes the environmental parameters (outdoor temperature and humidity) and adjustment parameters of the period into the model, and can estimate the energy consumption value of the air conditioning system in the period and store it.

[0114] S306: Determine the historical adjustment parameters corresponding to the central air-conditioning system when the energy consumption data is minimum as the target adjustment parameters.

[0115] Through step S305, the cloud control system obtains the energy consumption estimate corresponding to each historical adjustment parameter. These energy consumption data correspond to the adjustment parameters one by one, and together constitute a parameter-energy consumption mapping relationship table. The system sorts the table from small to large according to the energy consumption value, and can intuitively find the adjustment parameter corresponding to the lowest energy consumption, and determine it as the target adjustment parameter in the sample time period.

[0116] S307. Construct a data set to train a machine learning model based on the personnel density data, the actual temperature data, and the target adjustment data to obtain a trained prediction model.

[0117] The cloud control system uses the various types of data collected and processed in the previous steps (S301 to S306) to build a structured data set for training the machine learning model. Specifically, the system aligns the personnel density data, actual temperature data, and target adjustment parameters according to timestamps to form multiple sets of "feature-label" data pairs. Among them, personnel density and actual temperature are used as feature data reflecting the current environmental status, while target adjustment parameters are used as label data for the expected adjustment effect. Then, the system can use methods such as cross-validation to divide the data set into two parts: a training set and a test set.

[0118] After the data preparation is completed, the system starts to train the machine learning model. Specifically, the system can select appropriate models from commonly used machine learning algorithm libraries (such as Scikit-learn), such as support vector machines (SVM), random forests (RandomForest), neural networks (Neural Network), etc. Then, the system inputs the training set data into the selected model, and optimizes the model parameters through multiple rounds of iterations so that it can predict the target adjustment parameters from the feature data as accurately as possible. After each round of iteration, the system uses the test set data to evaluate the prediction performance of the model, and dynamically adjusts the optimization strategy based on the evaluation results, such as changing hyperparameters such as the learning rate and regularization coefficient.

[0119] After multiple rounds of iterative training, when the prediction accuracy on the test set reaches the preset threshold, the model training is considered complete. At this point, the system permanently saves the trained model parameters to form a deployable prediction model. The model can directly use the population density and actual temperature data as input and output the optimal adjustment parameters for the current environmental state.

[0120] In the above embodiment, the cloud control system builds a prediction model to analyze data under different weather conditions, learns and predicts the most energy-efficient air conditioning system operating parameters. This not only improves the intelligence level of the system, but also automatically adjusts the operating strategy according to the actual environment to maximize energy utilization and minimize operating costs.

[0121] S308. Input the population density data and actual temperature data of each area into the trained prediction model, output the operation adjustment parameters of the central air-conditioning system of each area in the current time period, and then obtain the real-time operation parameters.

[0122] This step has been introduced in step S104 and step S106 and will not be repeated here.

[0123] S309: Determine whether the newly acquired actual temperature data meets the temperature control requirements of merchants in each area.

[0124] After using the prediction model to adjust the air conditioning operating parameters in real time, the cloud control system continuously monitors and evaluates the adjustment effect to determine whether the merchant's temperature requirements are met. Specifically, the system regularly (such as every 5 minutes) obtains the latest actual temperature data from the environmental sensor and compares it with the temperature control requirements submitted by the merchant to determine whether it falls within the target range. If the requirements are met, it is determined that the current adjustment effect meets the merchant's needs, and the system continues to keep the adjustment parameters unchanged, or fine-tunes them according to the output results of the prediction model to maintain good temperature control performance. On the contrary, if the actual temperature exceeds the target range, especially if it falls into the warning interval, an abnormal warning will be issued.

[0125] S310, continue with subsequent adjustments.

[0126] If the cloud control system determines that the current actual temperature meets the merchant's temperature control requirements, it means that the previous adjustment measures are effective, and the system will return to step S308, re-enter the latest collected personnel density and actual temperature data into the prediction model to obtain the optimal adjustment parameters for the next period of time. This process is usually repeated at fixed time intervals (such as 15 minutes), forming a closed-loop control process of "monitoring-prediction-adjustment".

[0127] S311. Perform incremental training on the prediction model.

[0128] When the cloud control system determines that the newly acquired actual temperature data cannot meet the merchant's temperature control needs, it is necessary to re-acquire sample data to perform incremental training on the prediction model to improve its prediction accuracy.

[0129] In the above embodiment, after executing the optimization control, the cloud control system continues to monitor the temperature data to confirm whether the demand is met. If the actual temperature does not meet the expectation, the system will adjust the prediction model and perform incremental training to improve its performance, so that the prediction model can continuously adapt to new operating conditions and user needs, and improve the accuracy and reliability of the model prediction results.

[0130] The cloud control system of the embodiment of the present invention is an electronic device. Figure 4 A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0131] It should be noted that Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0132] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructions (computer programs), or by controlling related hardware through instructions (computer programs), and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein a plurality of instructions are stored in the storage medium, and the instructions can be loaded by the processor to execute any step of the method provided in the embodiment of the present invention.

[0133] Specifically, the storage medium and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more signal lines. The storage medium stores computer execution instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software program and module stored in the storage medium. The storage medium can be, but is not limited to, random access storage medium (Random Access Memory, referred to as: RAM), read-only storage medium (Read Only Memory, referred to as: ROM), programmable read-only storage medium (Programmable Read-Only Memory, referred to as: PROM), erasable read-only storage medium (Erasable Programmable Read-Only Memory, referred to as: EPROM), electrically erasable read-only storage medium (Electric Erasable Programmable Read-Only Memory, referred to as: EEPROM), etc. Among them, the storage medium is used to store programs, and the processor executes the program after receiving the execution instruction.

[0134] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip having signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0135] Since the instructions stored in the storage medium can execute the steps in any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0136] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A control optimization method based on a regional central air conditioning system, applied to a cloud control system, characterized in that: The method comprises: Obtain the temperature control requirements of merchants in each area and the location information of air supply ducts in each area; Determine whether there is a target air supply duct in the target merchant area according to the location information; if not, calculate the distance value between each air supply duct and the target merchant area within a preset range; determine the effective air supply duct within the preset range according to the maximum wind speed corresponding to each air supply duct and the distance value; determine the effective air supply duct as the target air supply duct, and start the maximum wind speed to supply air; Determining the wind speed of each air supply duct according to the temperature control requirement and the location information; Determine the basic operating parameters of the central air-conditioning system in each area at different time periods of the day according to the temperature fluctuation curve of each area compared with the outdoor temperature during the day, wherein the temperature fluctuation curve is measured when the central air-conditioning system is not in operation, and the basic operating parameters include a temperature set point, an output wind speed, and an operating mode; Acquire the population density data of each area in each sub-time period, as well as the corresponding actual temperature data and multiple historical adjustment parameters of the central air-conditioning system in a preset sample time period, wherein the preset sample time period includes the central air-conditioning system operation time period under multiple different weather conditions, and each of the historical adjustment parameters corresponds to energy consumption data of a central air-conditioning system; Determine the historical adjustment parameters corresponding to the central air-conditioning system when the energy consumption data is minimum as the target adjustment parameters; constructing a data set based on the personnel density data, the actual temperature data, and the target adjustment data; Using the data set to train the machine learning model to obtain a trained prediction model; Input the population density data and actual temperature data of each area into the trained prediction model, and output the operation adjustment parameters of the central air-conditioning system in each area in the current time period; Determine the real-time operating parameters of the central air-conditioning system in each area according to the operating adjustment parameters and the basic operating parameters; The central air conditioning system in each area is optimized and controlled according to the real-time operating parameters and the wind speed.

2. The method according to claim 1, characterized in that The step of determining the wind speed of each air supply duct according to the temperature control requirement and the position information specifically includes: Calculating a ratio of an ideal temperature value corresponding to a target merchant area to a standard value, wherein the ideal temperature value is determined according to the temperature control requirement; Determining whether there is a target air supply duct in the target merchant area according to the location information; If so, the wind speed corresponding to each of the target air supply ducts is determined based on a preset ratio wind speed relationship table.

3. The method according to claim 1, characterized in that The step of obtaining the population density data of each area in each sub-time period, the corresponding actual temperature data and a plurality of historical adjustment parameters of the central air-conditioning system in a preset sample time period, wherein the preset sample time period includes a central air-conditioning system operation time period under a plurality of different weather conditions, and each of the historical adjustment parameters corresponds to energy consumption data of a central air-conditioning system, specifically includes: Intercepting a central air-conditioning system operation time period under a variety of different weather conditions as a preset sample time period, wherein the weather conditions are weather conditions that affect the energy consumption of the central air-conditioning system; Controlling and adjusting the central air conditioning system according to the basic operating parameters in each preset sample time period; Monitor and obtain personnel density data and corresponding actual temperature data in each sub-time period; In each sub-time period, the basic operating parameters are adjusted according to a preset amplitude to obtain a plurality of historical adjustment parameters; The energy consumption data of the current sub-time period is estimated under each of the historical adjustment parameters.

4. The method according to claim 1, characterized in that: The step of optimizing and controlling the central air conditioning system in each area according to the real-time operating parameters and the wind speed specifically includes: Adjusting the operating state of the central air-conditioning system in each area according to the real-time operating parameters; The wind speed of the target air supply duct is individually controlled according to the wind speed.

5. The method according to claim 1, characterized in that After the step of optimizing and controlling the central air conditioning system of each area according to the real-time operating parameters and the wind speed, the method further includes: Determine whether the newly acquired actual temperature data meets the temperature control requirements of merchants in each region; If yes, proceed with subsequent adjustments; If not, incremental training is performed on the prediction model.

6. A cloud control system, characterized in that: The cloud control system includes: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the cloud control system to execute the method as described in any one of claims 1-5.

7. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the cloud control system, the cloud control system executes the method as claimed in any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product runs on a cloud control system, the cloud control system executes the method according to any one of claims 1 to 5.

Images