Air conditioner control method, device, equipment and readable storage medium

By optimizing the air conditioning control strategy through the particle swarm algorithm and combining temperature and power consumption to calculate fitness, the air conditioning operation with optimal global energy efficiency is achieved, which solves the energy waste and equipment stability problems under traditional air conditioning control methods and improves temperature control accuracy and resource utilization.

CN120512875BActive Publication Date: 2025-09-26INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202510976672.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-15
Publication Date
2025-09-26
Estimated Expiration
2045-07-15

AI Technical Summary

Technical Problem

Traditional air conditioning control methods are based on local temperature changes, resulting in over- or under-cooling in some areas, wasting energy and affecting equipment stability, making it impossible to achieve optimal global energy-saving effects.

Method used

The particle swarm algorithm is used to optimize the air conditioning control strategy. The initial control strategy is randomly generated, the air conditioning operating parameters are used as particles, the fitness is calculated by combining temperature and power consumption, and the target control strategy is iteratively updated to achieve the air conditioning operation with optimal global energy efficiency.

Benefits of technology

It improves the adaptability of air-conditioning control strategies to the overall heat distribution and energy efficiency balance of data centers, improves temperature control accuracy and resource utilization, and solves the energy waste and equipment stability problems under traditional air-conditioning control methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120512875B_ABST
    Figure CN120512875B_ABST
Patent Text Reader

Abstract

The present application discloses a control method, device, equipment and readable storage medium for air conditioners, which relates to the field of data processing technology. The method includes first establishing a fitness calculation model of a particle swarm algorithm based on the temperature of the target area and the power consumption of the air conditioner, which takes into account both local temperature control requirements and energy efficiency, thereby improving the adaptability of the air conditioner control strategy to the overall heat distribution and energy efficiency balance of the data center. Secondly, the operating parameters of the air conditioner are used as particles in the particle swarm algorithm, and the initial control strategy is used as the initial particle swarm of the particle swarm algorithm. The initial particle swarm is iteratively updated through the particle swarm algorithm to obtain a target control strategy, and the operation of multiple air conditioners is controlled according to the target control strategy. It can achieve intelligent air conditioner control under the condition of optimal global energy efficiency, and improve temperature control accuracy and resource utilization.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment, and readable storage medium for controlling an air conditioner. Background Art

[0002] Data centers (DCs) generate a large amount of heat during operation, which can easily cause ambient temperatures to rise and affect data center stability. Therefore, air conditioning systems are essential for effective heat dissipation and temperature control. Controlling air conditioning for proper heat dissipation and temperature control is directly related to heat dissipation efficiency and equipment operational safety.

[0003] Current data center air conditioning control methods are typically based on temperature thresholds. This involves using multiple sensors to monitor the data center temperature in real time. When the temperature exceeds a high threshold, the air conditioner increases cooling capacity; when the temperature falls below a low threshold, cooling is reduced or stopped. While this control method is simple and straightforward and can maintain temperature stability to a certain extent, it relies solely on local temperature fluctuations, failing to consider the overall heat distribution and energy balance of the data center. This can result in over-cooling in some areas and under-cooling in others, wasting energy and impacting equipment operational stability, resulting in low overall resource utilization. Summary of the Invention

[0004] The present application provides a method, apparatus, device, and readable storage medium for controlling an air conditioner, so as to at least solve the problem of low resource utilization when performing air conditioner control in related technologies.

[0005] The present application provides a method for controlling an air conditioner, comprising:

[0006] Determine multiple air conditioners in a target area and randomly generate initial control strategies for the multiple air conditioners; the initial control strategies include initial operating parameters of the multiple air conditioners;

[0007] The operating parameters of the air conditioner are used as particles in the particle swarm algorithm, and the initial control strategy is used as the initial particle swarm of the particle swarm algorithm. The initial particle swarm is iteratively updated through the particle swarm algorithm to obtain the target control strategy. The fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of multiple air conditioners.

[0008] Control the operation of multiple air conditioners according to the target control strategy.

[0009] The present application also provides an air conditioner control device, comprising:

[0010] A strategy initialization module is used to determine multiple air conditioners in a target area and randomly generate initial control strategies for the multiple air conditioners; the initial control strategies include initial operating parameters of the multiple air conditioners;

[0011] The strategy generation module is used to iteratively update the initial particle swarm using the operating parameters of the air conditioner as particles in the particle swarm algorithm and the initial control strategy as the initial particle swarm of the particle swarm algorithm to obtain the target control strategy. The fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of multiple air conditioners.

[0012] The strategy operation module is used to control the operation of multiple air conditioners according to the target control strategy.

[0013] The present application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the steps of the above-mentioned air conditioner control method when executing the computer program.

[0014] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned air conditioner control method are implemented.

[0015] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned air conditioner control method when executed by a processor.

[0016] This application first identifies multiple air conditioners in a target area and randomly generates initial control strategies for them. The initial control strategies include the initial operating parameters of the air conditioners. Then, the air conditioner operating parameters are used as particles in a particle swarm algorithm (PSO), and the initial control strategy is used as the initial particle swarm of the PSO. The PSO iteratively updates the initial particle swarm to obtain the target control strategy. The PSO fitness is calculated based on the temperature of the target area and the power consumption of the air conditioners. Finally, the operation of the air conditioners is controlled according to the target control strategy. First, the PSO fitness calculation model is established based on the temperature of the target area and the power consumption of the air conditioners. This considers both local temperature control requirements and energy efficiency, thereby improving the adaptability of the air conditioner control strategy to the overall thermal distribution and energy efficiency balance of the data center. Second, the air conditioner operating parameters are used as particles in the PSO, and the initial control strategy is used as the initial particle swarm of the PSO. The PSO iteratively updates the initial particle swarm to obtain the target control strategy, and then controls the operation of the air conditioners according to the target control strategy. This approach enables intelligent air conditioner control with optimal global energy efficiency, improving temperature control accuracy and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 One of the flow charts of the air conditioner control method provided in an embodiment of the present application;

[0019] Figure 2 This is a second flow chart of the air conditioner control method provided in an embodiment of the present application;

[0020] Figure 3 Flowchart 3 of the air conditioner control method provided in the embodiment of the present application;

[0021] Figure 4 Flowchart 4 of the air conditioner control method provided in an embodiment of the present application;

[0022] Figure 5 Flowchart 5 of the air conditioner control method provided in an embodiment of the present application;

[0023] Figure 6 A schematic structural diagram of a control device for an air conditioner provided in an embodiment of the present application;

[0024] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] It should be noted that, in the description of this application, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. The terms "first," "second," etc., in this application are used to distinguish similar objects, and are not used to describe a particular order or sequence.

[0027] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0028] With the rapid development of information technology, the scale of data centers continues to expand, leading to increasingly prominent energy consumption issues. Modular data centers, as a new data center architecture, have gained widespread adoption due to their advantages such as rapid deployment and efficient management. However, the air conditioning systems within modular data centers still face challenges in terms of cooling efficiency and energy consumption control.

[0029] Currently, most data centers use a temperature threshold-based air conditioning control method. This method involves installing multiple temperature sensors within the data center to monitor the temperature of different areas in real time. When the temperature in a particular area exceeds a preset high threshold, the air conditioner increases cooling capacity; when the temperature falls below a preset low threshold, the air conditioner reduces cooling capacity or even stops cooling. This simple and straightforward control method can maintain stable data center temperatures to a certain extent. However, temperature threshold-based control suffers from a slow response speed. Specifically, when the load of information technology (IT) equipment in the data center suddenly changes, the temperature sensors detect the temperature change and transmit it to the air conditioning system, which then makes adjustments. This process introduces significant latency, potentially causing IT equipment to remain in a high-temperature environment for a short period of time, impacting its performance and lifespan. Furthermore, this air conditioning control method cannot achieve globally optimal energy savings. Because it relies solely on local temperature changes and fails to consider the overall heat distribution and energy balance of the data center, it can result in overcooling in some areas and undercooling in others, resulting in energy waste.

[0030] Therefore, traditional air conditioning control methods struggle to precisely adjust to the ever-changing load and ambient temperature within the data center, resulting in energy waste and poor cooling performance. Furthermore, they suffer from insufficient coordination and weak fault tolerance when dealing with complex scenarios.

[0031] In response to the above problems, the embodiments of the present application provide a method, apparatus, device, and readable storage medium for controlling an air conditioner. The method includes first determining multiple air conditioners in a target area and randomly generating an initial control strategy for the multiple air conditioners. The initial control strategy includes the initial operating parameters of the multiple air conditioners. Afterwards, the operating parameters of the air conditioners are used as particles in a particle swarm algorithm, and the initial control strategy is used as the initial particle swarm of the particle swarm algorithm. The initial particle swarm is iteratively updated by the particle swarm algorithm to obtain a target control strategy. The fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of the multiple air conditioners. Finally, the operation of the multiple air conditioners is controlled according to the target control strategy. In this way, intelligent air conditioner control can be achieved under the condition of optimal global energy efficiency, thereby improving temperature control accuracy and resource utilization.

[0032] The air conditioning control method provided in the embodiment of the present application is mainly applicable to scenarios where temperature control is performed on a place, such as temperature control of a data center, temperature control of a train carriage, temperature control of a large shopping mall, etc.

[0033] The air conditioner control method provided in the embodiment of the present application can be executed by the air conditioner control device, which can be hardware or software. When the air conditioner control device is hardware, it can be various electronic devices with air conditioner control functions, including but not limited to smartphones, tablet computers, smart watches, computers, robots, etc. When the air conditioner control device is software, it can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, for providing air conditioner control services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0034] Figure 1 This is a flow chart of a method for controlling an air conditioner according to an embodiment of the present application. Figure 1 As shown, the air conditioner control method may include the following steps:

[0035] S11. Determine multiple air conditioners in a target area, and randomly generate initial control strategies for the multiple air conditioners.

[0036] The target area is the area where temperature control is required and may include multiple objects to be temperature-controlled. For example, when the target area is the area where the data center is located, the objects to be temperature-controlled may be the equipment in the data center; when the target area is a high-speed train carriage or a large shopping mall, the objects to be temperature-controlled may be passengers or customers in the area. This helps to combine temperature balance and energy efficiency to accurately optimize the data center's air conditioning control strategy when the target area is the area where the data center is located, thereby improving the operational stability of IT equipment in the data center and the energy efficiency of the air conditioning. The initial control strategy includes the initial operating parameters of each of the multiple air conditioners, such as cooling capacity, air supply volume, and air supply temperature.

[0037] First, determining the number of air conditioners in the target area involves determining the number of air conditioners in the target area, the location of each air conditioner, and the adjustable range of each air conditioner's operating parameters. Specifically, this can be done by deriving the air conditioners located in the target area from a database or configuration file of air conditioner systems corresponding to the target area, or by obtaining external input of the number of air conditioners in the target area.

[0038] Next, initial control strategies are randomly generated for multiple air conditioners. Specifically, for each air conditioner in the target area, specific values ​​are randomly selected within the allowable range of the air conditioner's operating parameters to form a sub-control strategy for that air conditioner. Then, all sub-control strategies for all air conditioners are aggregated to generate the initial control strategies for the multiple air conditioners. This approach ensures the diversity and coverage of the initial strategies, providing a reasonable starting point for subsequent algorithm search.

[0039] S12. The operating parameters of the air conditioner are used as particles in the particle swarm algorithm, and the initial control strategy is used as the initial particle swarm of the particle swarm algorithm. The initial particle swarm is iteratively updated through the particle swarm algorithm to obtain the target control strategy.

[0040] The fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of multiple air conditioners. Specifically, the fitness of the particle swarm algorithm can be the temperature difference of the target area and the power consumption of multiple air conditioners; it can also be the standard deviation of the temperature of the target area and the power consumption of multiple air conditioners; it can also be the temperature difference of the target area, the standard deviation of the temperature of the target area, and the power consumption of multiple air conditioners. In some embodiments, the fitness of the particle swarm algorithm can be the value obtained by normalizing the temperature difference of the target area and the power consumption of multiple air conditioners, and then taking the weighted sum of the two; it can also be the value obtained by normalizing the standard deviation of the temperature of the target area and the power consumption of multiple air conditioners, and then taking the weighted sum of the two; it can also be the value obtained by normalizing the temperature difference of the target area, the standard deviation of the temperature of the target area, and the power consumption of multiple air conditioners, and then taking the weighted sum of the three. The weighted weight value can be a value set according to actual conditions.

[0041] Specifically, the operating parameters of multiple air conditioners within the target area are uniformly modeled as particles in a particle swarm optimization algorithm, with each particle representing a specific set of operating parameters (corresponding to a sub-control strategy). Then, a randomly generated initial control strategy (including multiple sub-control strategies) is used to construct the initial particle swarm of the particle swarm algorithm, which serves as the starting point for the search. During the iterative process, a fitness function based on the target area's temperature and the air conditioner's power consumption is used to evaluate the control performance of each particle. By combining the individual optimal solution of each particle in previous iterations with the global optimal solution of the particle swarm as a whole, the particle swarm optimization algorithm continuously updates the particle position (i.e., the operating parameters), guiding the search towards the optimal control strategy. After multiple rounds of iteration, the final output particle swarm represents the target control strategy for multiple air conditioners in the current target area environment. This strategy optimizes overall energy efficiency while ensuring stable and consistent temperature control.

[0042] S13. Control the operation of the multiple air conditioners according to the target control strategy.

[0043] The target control strategy includes operating parameters of each of the multiple air conditioners, and the operation of the corresponding air conditioner is controlled according to the operating parameters to achieve the effect of air conditioning temperature control.

[0044] In the above scheme, multiple air conditioners in the target area are first identified, and initial control strategies are randomly generated for them. The initial control strategies include the initial operating parameters of each of the multiple air conditioners. Next, the PSO iteratively updates the initial particle swarm using the air conditioner operating parameters as particles in a particle swarm algorithm (PSO), and the initial control strategy as the initial particle swarm of the PSO, to obtain the target control strategy. The PSO fitness is calculated based on the temperature of the target area and the power consumption of the multiple air conditioners. Finally, the operation of the multiple air conditioners is controlled according to the target control strategy. First, the PSO fitness calculation model is established based on the temperature of the target area and the power consumption of the air conditioners. This model considers both local temperature control requirements and energy efficiency, thereby improving the adaptability of the air conditioner control strategy to the overall thermal distribution and energy efficiency balance of the data center. Second, the PSO operating parameters are used as particles in the PSO, and the initial control strategy as the initial particle swarm of the PSO. The PSO iteratively updates the initial particle swarm to obtain the target control strategy, which is then used to control the operation of the multiple air conditioners. It can realize intelligent air-conditioning control under the condition of optimal global energy efficiency, and improve temperature control accuracy and resource utilization.

[0045] In some embodiments, as Figure 2 As shown in Figure 2, the iterative update process of the particle swarm includes the following steps:

[0046] S121 , using a control strategy corresponding to the current particle swarm to control the operation of the air conditioner, and obtaining temperature parameters of the temperature in the target area and power consumption of multiple air conditioners.

[0047] The current particle swarm is the particle swarm corresponding to any iteration round during the iterative update process using the particle swarm algorithm. The temperature parameter is a parameter that can characterize the temperature uniformity or temperature stability in the target area and can be calculated from the temperature in the target area.

[0048] Specifically, the temperature parameters of the target area can be obtained by first adding multiple temperature sensors to the target area to obtain the temperature in the target area, and then calculating the temperature parameters based on the temperature. Adding multiple temperature sensors to the target area can include adding temperature sensors to the data center equipment (each device or a portion of the equipment) when the target area is a data center; or adding temperature sensors at different spatial dimensions (at least at different heights) in the target area when the target area is a high-speed train or a large shopping mall. The power consumption of multiple air conditioners can be obtained by monitoring the power consumption of each air conditioner in real time, thereby obtaining the power consumption of multiple air conditioners.

[0049] S122. Calculate the fitness corresponding to the current particle swarm according to the temperature parameter and the power consumption, and determine the individual optimal solution and the global optimal solution corresponding to each particle in the current particle swarm according to the fitness.

[0050] First, the fitness corresponding to the current particle swarm is calculated based on the temperature parameters and power consumption.

[0051] In some embodiments, temperature parameters include the standard deviation of the temperature within a region and the temperature difference within the region. In this case, the fitness of the current particle swarm can be calculated based on the temperature parameters and power consumption. The fitness of the particles within the region can be determined based on the standard deviation and temperature difference of the temperature within the region, as well as the power consumption of the air conditioner within the region. A region is any region within the target area (including the entire target area or a subregion within the target area). In other words, the fitness value in this case includes three values: the standard deviation of the temperature within the region, the temperature difference within the region, and the power consumption of the air conditioner within the region. In some embodiments, the fitness value can also be the weighted sum of the normalized standard deviation, temperature difference, and power consumption of the air conditioner within the region. This combines the temperature parameters (including the standard deviation and temperature difference) with power consumption when calculating the fitness, enabling a comprehensive, multi-dimensional assessment of the air conditioning control effectiveness. The temperature standard deviation reflects the balance of temperature distribution within the region, while the temperature difference reflects the difference between the highest and lowest temperatures. Together, these two measures the comfort and consistency of temperature control. Furthermore, air conditioner power consumption is incorporated as an energy efficiency indicator to ensure that the control strategy balances comfort and energy conservation. Therefore, it can more comprehensively reflect the pros and cons of the control strategy, and help the particle swarm to more effectively tend to the ideal goal of "stable temperature control and low energy consumption" during the optimization process, thereby improving the overall control performance.

[0052] In some embodiments, since the particle swarm algorithm needs to determine the individual optimal solution and the global optimal solution for each particle in the current swarm based on fitness during the update process, the fitness includes both individual fitness and global fitness. When the region is the subregion where the target particle in the particle swarm corresponds to the air conditioner, the fitness is the individual fitness of the target particle; when the region is the target area, the fitness is the global fitness of the particle swarm. Specifically, when the target area is a modular data center, the subregion can be the area corresponding to a module within the modular data center. When the target area is an area corresponding to a non-modular data center or other location, the subregion can be a subregion divided according to actual circumstances. This allows for flexible selection of evaluation criteria based on regional granularity, improving the regional and holistic nature of the control strategy. Using individual fitness for evaluation in the subregion corresponding to the target particle helps accurately reflect the control effect of the air conditioner in the local environment and achieve more fine-grained optimization. Using global fitness for evaluation within the entire target area comprehensively balances the temperature control and energy consumption performance of all air conditioners to ensure global optimization. Therefore, this fitness assessment method that combines local precise control with global coordinated optimization can improve the overall operating efficiency of the system and the local adjustment accuracy, and achieve a more balanced and efficient air-conditioning control effect.

[0053] In some embodiments, the temperature parameters can also include the regional weights of the subregions corresponding to each particle in the target region. When determining individual fitness, the individual fitness of the particles in the subregions is weighted according to the regional weights. This weighted processing of each subregion during fitness calculation prioritizes temperature stability in key areas, further improving the overall operational reliability of the data center.

[0054] Secondly, the individual optimal solution and global optimal solution corresponding to each particle in the current particle swarm are determined based on the fitness. Specifically, for the target particle in the particle swarm, the solution corresponding to the target particle's minimum individual fitness during the particle swarm iterative update is determined as the target particle's individual optimal solution; the solution corresponding to the target particle with the minimum global fitness during the particle swarm iterative update is determined as the target particle's global optimal solution. For example, if the target particle is the jth particle in the i-th iteration, the individual fitness corresponding to the jth particle in the previous i-1 iterations is calculated, and the operating parameters corresponding to the minimum individual fitness are determined as the individual optimal solution of the jth particle in the i-th iteration. Simultaneously, the global fitness in the previous i-1 iterations is calculated, and the operating parameters corresponding to the jth particle with the minimum global fitness are determined as the global optimal solution of the jth particle in the i-th iteration. In this scheme, by selecting the target particle's minimum individual fitness solution as the individual optimal solution and the target particle solution with the minimum global fitness among all particles as the global optimal solution during the particle swarm iterative process, refined guidance of the target particle is achieved. This approach not only preserves the target particle's own search memory (individual optimality) but also incorporates the optimal information of the entire particle swarm (global optimality), helping to improve the target particle's convergence accuracy and global search capabilities, avoiding being trapped in local optimality. This enhances the algorithm's ability to optimize and focus on key targets, indirectly improving the accuracy and robustness of air conditioning control.

[0055] S123. According to the individual optimal solution and the global optimal solution, the current particle swarm is updated according to the preset velocity vector to obtain an updated particle swarm.

[0056] Specifically, each particle in the current particle swarm is updated using the following update model to obtain an updated particle swarm.

[0057] The update model can be:

[0058] ;

[0059] .

[0060] in, Used to indicate the i Particle No. k The operating parameters for the update. Used to indicate the i Particle No. k+1 The operating parameters for the update. To characterize the i Particle No. k The velocity vector at the time of update, To characterize the i Particle No. k+1 The velocity vector at the time of the update; Used to indicate the i Particle No. k The individual optimal solution at the time of update is Used to indicate the i Particle No. k The global optimal solution at the time of update; Used to represent inertia weight, Used to represent the first learning factor, Used to represent the second learning factor, and is a random number in [0, 1].

[0061] In this solution, a particle swarm algorithm is deeply integrated with air conditioning operation control to achieve an adaptive optimization process based on actual operational feedback. Specifically, after regulating the air conditioning operation using the control strategy corresponding to the current particle swarm, temperature and power consumption data are acquired in real time, and the fitness is calculated to measure the strategy's overall effectiveness in energy saving and temperature control. The search direction of the particles is then adjusted based on the individual optimal solution and the global optimal solution, and the particle swarm is updated, allowing the search process to continuously approach a more optimal control strategy. This control method implements a closed-loop optimization mechanism of perception-evaluation-adjustment, improving the accuracy and energy efficiency of the control strategy while also possessing strong environmental adaptability.

[0062] In some embodiments, as Figure 3 As shown, the air conditioner control method may further include the following steps:

[0063] S1231. Obtain control parameters.

[0064] The control parameter is the load or temperature of any area within the target region. For a data center, the load can be understood as the load on the equipment within the data center. For a high-speed train or a large shopping mall, the load can be understood as passenger density or customer density. The temperature can be the average or maximum temperature of the region.

[0065] Specifically, if the target area is a data center, the load of the equipment in the data center can be directly obtained. If the target area is a high-speed train carriage or a large shopping mall, infrared sensors can be added to the target area to monitor the passenger density or customer density.

[0066] S1232. Determine whether the control parameter is less than or equal to the first load threshold; when the control parameter is less than or equal to the first load threshold, execute S1233; when the control parameter is greater than the first load threshold, execute S1234.

[0067] The first load threshold is a preset value, for example, a default value, or a value set by relevant personnel according to actual conditions.

[0068] S1233: Add a first value to the inertia weight.

[0069] The first value is a preset value, for example, a default value, or a value set by relevant personnel according to actual conditions. At this time, the control parameter is relatively small, indicating that the load is relatively low or the temperature is relatively low, and the demand for temperature control is not urgent. Therefore, as shown in step S123, the inertia weight is updated in the model. Increasing the inertia weight means expanding the global search range and optimizing the Power Usage Effectiveness (PUE) value.

[0070] In some embodiments, when the control parameter is less than or equal to the first load threshold, the temperature fluctuation range is allowed to expand by ±0.5° C., that is, the temperature difference is allowed to fluctuate up and down by 0.5 degrees Celsius.

[0071] S1234. Determine whether the control parameter is greater than the second load threshold; when the control parameter is greater than the second load threshold, execute S1235; when the control parameter is greater than the first load threshold and less than or equal to the second load threshold, execute S1236.

[0072] The second load threshold is greater than the first load threshold and is a preset value, such as a default value or a value set by relevant personnel based on actual conditions. For example, when the control parameter is load, the second load threshold is 80% of the rated load; when the control parameter is temperature, the second load threshold is 28 degrees Celsius.

[0073] S1235: Reduce the second value of the inertia weight and increase the third value of the second learning factor.

[0074] Among them, at this time, the control parameter is relatively large, which proves that the load is relatively high or the temperature is relatively high, and the demand for temperature control is already urgent. Therefore, as shown in step S123, the inertia weight is updated in the model. , the second learning factor is the updated model Reducing the inertia weight while increasing the second learning factor accelerates algorithm convergence, locks in cooling capacity in key areas, and sacrifices some energy consumption to ensure equipment safety. The second and third values ​​are both preset values, such as default values ​​or values ​​set by relevant personnel based on actual conditions.

[0075] S1236, no adjustment.

[0076] At this time, the temperature or load is in a medium range, and it is necessary to balance the temperature stability and air conditioning energy consumption. Therefore, the parameters in the update model are not adjusted, so that it searches for the most appropriate target control strategy according to the normal operation process.

[0077] In this approach, adaptive optimization control for varying load or temperature conditions is achieved by dynamically adjusting the inertia weight and learning factor within the particle swarm algorithm. When the control parameters are low, increasing the inertia weight helps expand the search range, maintain the diversity of particle motion, and avoid premature convergence. When the control parameters are high, reducing the inertia weight and increasing the second learning factor enhances the particles' responsiveness to local optima, accelerating convergence to the optimal solution and enabling faster optimization of temperature control or load. This improves the control system's adjustment flexibility and optimization efficiency under varying conditions.

[0078] In some embodiments, as Figure 4 As shown, the air conditioner control method may further include the following steps:

[0079] S21. Obtain historical load information of the region, and predict the current load based on the historical load information to obtain a predicted load.

[0080] The region is any region in the target area. The historical load information may include parameters such as historical load data, work calendar, and business peak patterns.

[0081] First, the method for obtaining the historical load information of a region can be to query the historical load records of the region and obtain the historical load information from the load records; or to obtain the historical load information input externally.

[0082] Secondly, as a typical scenario for high-reliability distributed control, the EMU system's distributed collaborative control, dynamic load prediction, and multi-level fault tolerance mechanisms provide innovative ideas for data center air conditioning control. For example, the EMU can achieve real-time coordination of all equipment on the train through the Train Control and Management System (TCMS). Therefore, the current load can be predicted based on historical load information to obtain the predicted load. This can be achieved by introducing the predictive control method for slopes and speeds in the EMU traction system, establishing a load time series prediction model based on the Long Short-Term Memory (LSTM) neural network, and predicting the current load. For example, the load prediction function can be: L (t+ ) = f (L (t), L (t- ),…,T(t),Schedule) .in, L(t+ ) Used to indicate t+ The load of the moment, T(t) Used to indicate t The ambient temperature at the moment, L(t) Used to indicate t The load at a given moment, and Schedule is the business scheduling plan.

[0083] S22. Determine the load weight of the area and the actual load in the area.

[0084] The actual load is the load actually measured at the current moment, and the load weight is a pre-set weight value, or a weight value dynamically adjusted according to the prediction confidence. The load weight may include the weight value of the actual load and the weight value of the predicted load.

[0085] S23. Perform weighted fusion processing on the predicted load and the actual load according to the load weight to obtain a weighted load.

[0086] Specifically, according to the formula s=w1×s1+ w2×s2 To calculate the weighted load. s is the weighted load, w1 is the weight value of the predicted load, w2 is the weight value of the actual load, s1 To predict the load, s2 is the actual load.

[0087] S24. When the weighted load is greater than a third load threshold, controlling the operation of the plurality of air conditioners according to the ultimate control strategy until a target control strategy is determined, or the weighted load drops to a target value.

[0088] The ultimate control strategy is used to rapidly cool down the area at the fastest speed while ensuring operational safety. The third load threshold is a preset value, such as a default value, or a value set by relevant personnel based on actual conditions.

[0089] In the above scheme, historical load information for a region is first obtained, and the current load is predicted based on this historical load information to obtain a predicted load. Then, the regional load weight and the actual load within the region are determined, and the predicted and actual loads are weighted and fused according to the load weight to obtain a weighted load. Finally, when the weighted load exceeds a third load threshold, the operation of the multiple air conditioners is controlled according to the ultimate control strategy until a target control strategy is determined, or the weighted load drops to a target value. In this way, in addition to dynamically controlling the air conditioners using the target control strategy determined by the particle swarm algorithm provided in this application, a control method for emergency cooling based on load conditions is also added. This allows for rapid cooling response under high-load conditions in the region while ensuring operational safety, improving temperature control efficiency and system stability in emergency situations, effectively reducing the time the temperature-controlled object is exposed to high temperatures, and helping to extend the temperature-controlled object's residence time or service life. Furthermore, when calculating the load, the actual load and the predicted load are weighted and combined to optimize the control lead time to avoid temperature fluctuations caused by sudden load changes.

[0090] In some embodiments, as Figure 5 As shown, the air conditioner control method may further include the following steps:

[0091] S31. Monitor the risk air conditioners in the target area in abnormal conditions.

[0092] Among them, the risk of abnormal status of air conditioners refers to abnormal status of the air conditioners, such as compressor current fluctuations, excessive fan vibration, insufficient cooling capacity, etc.

[0093] Specifically, one or more of a variety of analysis methods such as operating parameter analysis, energy consumption analysis, temperature control response analysis, and comparison analysis with other air conditioners can be used to monitor the status of the air conditioners in the target area to obtain risky air conditioners.

[0094] S32. Modify the target control strategy based on risk conditioning.

[0095] Specifically, when risky air conditioners are detected in the target area, a fault-tolerant mechanism similar to the "faulty carriage isolation" of a train is automatically triggered to ensure the robustness of temperature control.

[0096] Specifically, the method of correcting the target control strategy based on the risk air conditioner can be: in the particle swarm iterative update process, the particles corresponding to the risk air conditioner are marked as non-operable, and when the control strategy is updated, the particles marked as non-operable are discarded. The correction method can also be to use the air conditioners adjacent to the risk air conditioner to compensate for the missing cooling capacity of the risk air conditioner. For example, when the air conditioner in a certain area fails, the air supply volume in the adjacent area is automatically increased, and the cooling capacity is redistributed through the air duct design (similar to the pressure compensation between the carriages of a train). The correction method can also be to add a device health factor to the fitness of the particle swarm iterative update process, and use the device health factor to control the particles corresponding to the non-risk air conditioners to be selected first. For example, the newly added device health factor H i (Value [0, 1], when fault occurs, H i = 0), ensuring that the algorithm prioritizes control solutions for healthy device combinations. This way, when an air conditioner in the air conditioning system experiences an anomaly, this application also provides a compensation strategy for the abnormal air conditioner, preventing temperature control imbalances in the corresponding area when an air conditioner experiences an anomaly, further improving the system's temperature control robustness under abnormal operating conditions.

[0097] In this solution, by monitoring the target area for abnormally performing air conditioners, we can identify units that may affect temperature control. Based on this, we can modify the target control strategy to prevent regional temperature control failures caused by individual air conditioner anomalies. This risk-based strategy modification mechanism improves system robustness and temperature control accuracy.

[0098] In some embodiments, the distributed control logic of the EMU Train Control and Management System (TCMS) can be leveraged to deploy edge controllers in each air conditioning zone in the data center, creating a collaborative "master controller + edge controller" network. The master controller is responsible for iterative optimization of the global particle swarm algorithm, while the edge controller performs local parameter fine-tuning, forming a coordinated control model similar to the "lead car-trailer" model of an EMU train. Furthermore, EMU communication protocols, such as the Multifunction Vehicle Bus (MVB), are used to synchronize data between controllers in real time, reducing communication latency to less than 50ms and ensuring rapid response to control commands. When a sudden load increase occurs in a specific area, the edge controller prioritizes local emergency cooling mode and simultaneously sends a load mutation signal to the master controller, triggering rapid global particle swarm algorithm reconstruction. This achieves a "local response-global optimization" linkage mechanism, similar to the "local power compensation-train-wide energy redistribution" process of an EMU traction system.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0100] The embodiment of the present application also provides a control device for an air conditioner, such as Figure 6 Said device comprises:

[0101] A strategy initialization module 701 is used to determine multiple air conditioners in a target area and randomly generate initial control strategies for the multiple air conditioners; the initial control strategies include initial operating parameters for each of the multiple air conditioners;

[0102] Strategy generation module 702 is configured to use the operating parameters of the air conditioner as particles in a particle swarm algorithm, and the initial control strategy as the initial particle swarm of the particle swarm algorithm. The initial particle swarm is iteratively updated by the particle swarm algorithm to obtain a target control strategy. The fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of the multiple air conditioners.

[0103] The strategy operation module 703 is used to control the operation of multiple air conditioners according to the target control strategy.

[0104] In some embodiments, the strategy generation module 702 includes an acquisition module, a calculation module, and an update module; the acquisition module is used to control the operation of the air conditioner using the control strategy corresponding to the current particle swarm, and obtain the temperature parameters of the temperature in the target area and the power consumption of multiple air conditioners; the calculation module is used to calculate the fitness corresponding to the current particle swarm based on the temperature parameters and power consumption, and determine the individual optimal solution and the global optimal solution corresponding to each particle in the current particle swarm based on the fitness; the update module is used to update the current particle swarm according to the preset velocity vector based on the individual optimal solution and the global optimal solution to obtain an updated particle swarm.

[0105] In some embodiments, the temperature parameter includes the standard deviation of the temperature in the region and the temperature difference of the temperature in the region; the region is any region in the target area; the calculation module is specifically used to determine the fitness corresponding to the particles in the region based on the standard deviation and temperature difference of the temperature in the region, and the power consumption of the air conditioner in the region.

[0106] In some embodiments, fitness includes individual fitness and global fitness; when the region is a sub-region where the target particle in the particle swarm corresponds to the air conditioner, the fitness is the individual fitness corresponding to the target particle; when the region is a target region, the fitness is the global fitness of the particle swarm.

[0107] In some embodiments, the temperature parameter also includes a regional weight of a sub-region corresponding to each particle in the target region; the calculation module is specifically used to perform weighted processing on the individual fitness of particles in the sub-region according to the regional weight when determining the individual fitness.

[0108] In some embodiments, the computing module is specifically used to: for a target particle in a particle swarm, determine the solution corresponding to the minimum individual fitness of the target particle during the iterative update of the particle swarm as the individual optimal solution of the target particle; and determine the solution of the target particle corresponding to the minimum global fitness during the iterative update of the particle swarm as the global optimal solution of the target particle.

[0109] In some embodiments, the updating module is used to update each particle in the current particle swarm using the following update model to obtain an updated particle swarm; the update model is:

[0110] ;

[0111] ;

[0112] in, Used to indicate the i Particle No. k The operating parameters for the update. Used to indicate the i Particle No. k+1 The operating parameters for the update. To characterize the k The velocity vector at the time of update, To characterize the k+1 The velocity vector at the time of the update; Used to indicate the k The individual optimal solution at the time of update is Used to indicate the k The global optimal solution at the time of update; Used to represent inertia weight, Used to represent the first learning factor, Used to represent the second learning factor, and is a random number in [0,1].

[0113] In some embodiments, the acquisition module is also used to acquire a control parameter; the control parameter is the load or temperature of any area in the target area; the update module is also used to: when the control parameter is less than or equal to a first load threshold, increase the inertia weight by a first value; when the control parameter is greater than a second load threshold, reduce the inertia weight by a second value, and increase the second learning factor by a third value.

[0114] In some embodiments, the control device of the air conditioner also includes a load prediction module, a load determination module and a load fusion module; the load prediction module is used to obtain historical load information of the area, and predict the current load based on the historical load information to obtain a predicted load; the area is any area in the target area; the load determination module is used to determine the load weight of the area and the actual load in the area; the load fusion module is used to perform weighted fusion processing on the predicted load and the actual load according to the load weight to obtain a weighted load; the strategy operation module 703 is also used to control the operation of multiple air conditioners according to the ultimate control strategy when the weighted load is greater than the third load threshold until the target control strategy is determined, or the weighted load is reduced to the target value; the ultimate control strategy is used to rapidly cool the area at the fastest speed while ensuring operational safety.

[0115] In some embodiments, the air conditioner control device also includes a risk status monitoring module and a strategy adjustment module; the risk status monitoring module is used to monitor risk air conditioners with abnormal status in the target area; the strategy adjustment module is used to modify the target control strategy according to the risk air conditioners.

[0116] In some embodiments, the strategy adjustment module is specifically used to: mark the particles corresponding to the risk air conditioner as inoperable during the particle swarm iterative update process, and discard the particles marked as inoperable when updating the control strategy; or, use the air conditioner adjacent to the risk air conditioner to compensate for the missing cooling capacity of the risk air conditioner; or, add a device health factor to the fitness of the particle swarm iterative update process, and use the device health factor to control the particles corresponding to non-risk air conditioners to be selected first.

[0117] In some embodiments, the target area is an area where a data center is located.

[0118] For the description of the features in the embodiments corresponding to the air conditioner control device, reference can be made to the relevant description of the embodiments corresponding to the air conditioner control method, which will not be repeated here.

[0119] The embodiment of the present application also provides an electronic device, such as Figure 7 As shown, the electronic device includes a memory 903 and a processor 902. The memory 903 stores a computer program, and the processor 902 is configured to run the computer program to execute the steps in any of the above-mentioned air conditioner control method embodiments.

[0120] The processor 902 may be a central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the disclosed solution.

[0121] The memory 903 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 903 may be independent and connected to the processor 902 via the bus 904. The memory 903 may also be integrated with the processor 902.

[0122] like Figure 7 As shown, the electronic device may further include a communication interface 901, wherein the communication interface 901, the processor 902, and the memory 903 may be coupled to each other, for example, via a bus 904. The communication interface 901 is used to exchange information with other devices, for example, to support information exchange between the electronic device and other devices.

[0123] It should be pointed out that Figure 7 The device structure shown in the figure does not constitute a limitation on the electronic device, except Figure 7 In addition to the components shown, the electronic device may include more or fewer components than shown, or may combine certain components or arrange the components differently. Furthermore, the electronic device provided in this embodiment can execute the air conditioner control method provided in the above method embodiment. Its implementation principles and technical effects are similar to those of the above method and will not be further described here.

[0124] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above-mentioned air conditioner control method embodiments when run.

[0125] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0126] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned air conditioner control method embodiments are implemented.

[0127] An embodiment of the present application also provides another computer program product, including a non-volatile computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps in any of the above-mentioned air conditioner control method embodiments.

[0128] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0129] The above is a detailed introduction to the control method, device, equipment and readable storage medium of an air conditioner provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core ideas of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A method for controlling an air conditioner, characterized in that: include: determining a plurality of air conditioners in a target area, and randomly generating initial control strategies for the plurality of air conditioners; The initial control strategy includes initial operating parameters of the plurality of air conditioners; The operating parameters of the air conditioner are used as particles in a particle swarm algorithm, the initial control strategy is used as the initial particle swarm of the particle swarm algorithm, and the initial particle swarm is iteratively updated by the particle swarm algorithm to obtain a target control strategy; wherein the fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of the multiple air conditioners; controlling the operation of the plurality of air conditioners according to the target control strategy; The method further comprises: Obtaining historical load information of a region, and predicting a current load based on the historical load information to obtain a predicted load; the region is any region in the target region; determining a load weight for the area and an actual load for the area; Performing weighted fusion processing on the predicted load and the actual load according to the load weight to obtain a weighted load; When the weighted load is greater than a third load threshold, controlling the operation of the plurality of air conditioners according to the ultimate control strategy until the target control strategy is determined, or the weighted load drops to a target value; the ultimate control strategy is used to rapidly cool the area at the fastest speed while ensuring operational safety; The current load is predicted based on the historical load information to obtain the predicted load, and the formula used is: L (t+ ) = f (L (t), L (t- ),…,T(t),Schedule) ,in, L(t+ ) Used to indicate t+ The load at the moment, T(t) Used to indicate t The ambient temperature at the moment, L(t) Used to indicate t The load at a given moment, and Schedule is the business scheduling plan.

2. The control method according to claim 1, characterized in that: The iterative update process includes: Using the control strategy corresponding to the current particle swarm to control the operation of the air conditioner, and obtaining the temperature parameters of the temperature in the target area and the power consumption of the multiple air conditioners; Calculating the fitness corresponding to the current particle swarm according to the temperature parameter and the power consumption, and determining the individual optimal solution and the global optimal solution corresponding to each particle in the current particle swarm according to the fitness; According to the individual optimal solution and the global optimal solution, the current particle swarm is updated according to a preset velocity vector to obtain an updated particle swarm.

3. The control method according to claim 2, characterized in that: The temperature parameters include the standard deviation of the temperature within the region and the temperature difference within the region; The area is any area in the target area; the method further includes: The fitness corresponding to the particles in the area is determined according to the standard deviation and temperature difference of the temperature in the area and the power consumption of the air conditioner in the area.

4. The control method according to claim 3, characterized in that: The fitness includes individual fitness and global fitness; When the region is a subregion where the air conditioner corresponding to the target particle in the particle swarm is located, the fitness is the individual fitness corresponding to the target particle; When the region is a target region, the fitness is the global fitness of the particle swarm.

5. The control method according to claim 4, characterized in that: The temperature parameter also includes a region weight of a sub-region corresponding to each particle in the target region; the method further includes: When determining the individual fitness, the individual fitness of the particles in the sub-region is weighted according to the region weight.

6. The control method according to claim 4, characterized in that: The determining, according to the fitness, the individual optimal solution and the global optimal solution corresponding to each particle in the current particle swarm includes: For a target particle in a particle swarm, the solution corresponding to the minimum individual fitness of the target particle during the iterative update of the particle swarm is determined as the individual optimal solution of the target particle; The solution of the target particle corresponding to the minimum global fitness during the iterative update process of the particle swarm is determined as the global optimal solution of the target particle.

7. The control method according to claim 2, characterized in that: The updating of the current particle swarm according to a preset velocity vector based on the individual optimal solution and the global optimal solution includes: Each particle in the current particle swarm is updated using the following update model to obtain an updated particle swarm; The update model is: ; ; in, Used to indicate the i Particle No. k The operating parameters for the update. Used to indicate the i Particle No. k+1 The operating parameters for the update. To characterize the k The velocity vector at the time of update, To characterize the k+1 The velocity vector at the time of the update; Used to indicate the k The individual optimal solution at the time of update is Used to indicate the k The global optimal solution at the time of update; Used to represent inertia weight, Used to represent the first learning factor, Used to represent the second learning factor, and is a random number in [0,1].

8. The control method according to claim 7, characterized in that: The method further comprises: Acquiring a control parameter; the control parameter being a load or temperature of any area in the target area; When the control parameter is less than or equal to a first load threshold, adding a first value to the inertia weight; When the control parameter is greater than a second load threshold, the inertia weight is reduced by a second value, and the second learning factor is increased by a third value.

9. The control method according to claim 1, characterized in that: The method further comprises: Monitoring the risk air conditioners with abnormal conditions in the target area; The target control strategy is modified according to the risk factor.

10. The control method according to claim 9, characterized in that: The modifying the target control strategy according to the risk control comprises: During the particle swarm iterative update process, the particles corresponding to the risk air conditioner are marked as inoperable, and when the control strategy is updated, the particles marked as inoperable are discarded; or, Using air conditioners adjacent to the risk air conditioner to compensate for the missing cooling capacity of the risk air conditioner; or, The device health factor is added to the fitness of the particle swarm iterative update process, and the device health factor is used to control the particles corresponding to non-risk air conditioners to be preferentially selected.

11. The control method according to any one of claims 1 to 10, characterized in that: The target area is the area where the data center is located.

12. A control device for an air conditioner, characterized in that: include: a strategy initialization module, configured to determine a plurality of air conditioners in a target area and randomly generate initial control strategies for the plurality of air conditioners; The initial control strategy includes the plurality of initial air-conditioning operating parameters; a strategy generation module, configured to use the operating parameters of the air conditioner as particles in a particle swarm algorithm, the initial control strategy being the initial particle swarm of the particle swarm algorithm, and iteratively update the initial particle swarm using the particle swarm algorithm to obtain a target control strategy; wherein the fitness of the particle swarm algorithm is calculated based on the temperature of the target area and the power consumption of the multiple air conditioners; a strategy operation module, configured to control the operation of the plurality of air conditioners according to the target control strategy; The device also includes: a load prediction module, a load determination module and a load fusion module; The load prediction module is configured to obtain historical load information of a region and predict the current load based on the historical load information to obtain a predicted load; the region is any region in the target region; The load determination module is configured to determine a load weight of the area and an actual load in the area; The load fusion module is configured to perform weighted fusion processing on the predicted load and the actual load according to the load weight to obtain a weighted load; The strategy operation module is further configured to control the operation of the plurality of air conditioners according to the ultimate control strategy when the weighted load is greater than a third load threshold until the target control strategy is determined, or the weighted load drops to a target value; the ultimate control strategy is configured to rapidly cool the area at the fastest speed while ensuring operational safety; The load prediction module uses the following formula: L(t+ ) = f (L (t), L (t- ),…,T(t),Schedule) ,in, L(t+ ) Used to indicate t+ The load at the moment, T(t) Used to indicate t The ambient temperature at the moment, L(t) Used to indicate t The load at a given moment, and Schedule is the business scheduling plan.

13. An electronic device, characterized in that: include: memory for storing computer programs; A processor is configured to implement the steps of the air conditioner control method according to any one of claims 1 to 11 when executing the computer program.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the air conditioner control method according to any one of claims 1 to 11 are implemented.

Citation Information

Patent Citations

  • Air conditioner energy-saving control method and system based on multi-objective optimization, medium and product

    CN119642337A