A Control Method for Central Air Conditioning Cooling Towers Based on Edge-Cloud Collaborative Computing

Abstract

This invention discloses a central air conditioning cooling tower control method based on edge-cloud collaborative computing, belonging to the field of cooling tower technology. It collects data from sensors and transmits the data to edge nodes for preliminary processing and fusion. Then, an improved particle swarm optimization algorithm is used to optimize the acquired data. Subsequently, a beetle whisker-particle swarm optimization algorithm is employed to optimize the water distribution flow rate. Finally, a combination of deep reinforcement learning and model predictive control is used to achieve intelligent control of the cooling tower cluster. This invention, employing the aforementioned edge-cloud collaborative computing-based central air conditioning cooling tower control method, can improve the intelligence and energy efficiency of cooling towers, reduce energy consumption, and improve cooling performance.

Description

Technical Field

[0001] This invention belongs to the field of cooling tower technology, specifically relating to a central air conditioning cooling tower control method based on edge-cloud collaborative computing. Background Technology

[0002] Cooling towers are among the most crucial components of refrigeration systems, widely used in data centers, thermal power plants, and construction. Currently, the high energy consumption of industrial cooling towers, both domestically and internationally, remains a challenge that has not been systematically studied and effectively resolved. Furthermore, their low automation levels and high economic costs urgently require improvement. Therefore, with the market development of data centers and the energy industry, the demand for cooling towers and their cooling systems is gradually increasing, necessitating the development of a new type of intelligent, high-efficiency, and energy-saving cooling tower in China. Simultaneously, with the development of cutting-edge technologies such as artificial intelligence, the Internet of Things, cloud computing, and artificial intelligence in China, the low level of intelligence in cooling towers is becoming increasingly apparent.

[0003] In edge-cloud collaboration, cooling tower control systems face numerous challenges: edge node devices have low performance and limited functionality, making it difficult to handle large amounts of time-series data; individual systems lack high-availability recovery mechanisms and are susceptible to node failures; the large amounts of data generated by multiple sensors exceed the communication load capacity of a single cloud architecture, leading to network pressure and latency issues; and the real-time requirements of cloud computing cannot meet the high demands of cooling tower cluster control. Furthermore, traditional cooling tower clusters perform poorly in data fusion and transmission, and particle swarm optimization algorithms have shortcomings in practical applications, resulting in excessive energy consumption and uneven water distribution leading to poor cooling performance. Therefore, a new technical solution is urgently needed. Summary of the Invention

[0004] The purpose of this invention is to provide a central air conditioning cooling tower control method based on edge-cloud collaborative computing, which can improve the intelligence and energy efficiency of the cooling tower, reduce energy consumption, and improve the cooling effect.

[0005] To achieve the above objectives, this invention provides a central air conditioning cooling tower control method based on edge-cloud collaborative computing, comprising the following steps:

[0006] S1. Construct a cloud-edge-device system, which includes a device layer, an edge computing layer, and a cloud layer. The device layer includes intelligent sensor modules.

[0007] S2, the data acquisition layer uses the smart sensor module in S1 to collect real-time data. After receiving the real-time data, the edge computing nodes in the edge computing layer use the improved particle swarm algorithm to process the real-time data and save the processed data in the edge computing data pool.

[0008] S3. Intelligent control of cooling tower clusters is achieved by combining deep reinforcement learning with model predictive control.

[0009] S4. The water distribution flow rate is controlled by the beetle whisker-particle swarm optimization algorithm.

[0010] S5. Repeat steps S2 to S4, continuously adjusting the cooling tower's operating mode based on real-time data and historical records.

[0011] Preferably, the improved particle swarm optimization algorithm in S2 is calculated as follows:

[0012]

[0013] Where ω represents the inertia weight coefficient, and ω(j) represents the inertia weight coefficient at the current iteration step j. max ω represents the maximum inertia weighting coefficient. min T represents the minimum inertia weighting coefficient. max This represents the maximum number of iterations, and j represents the current iteration step;

[0014] c1(j)=c 11 -(c 11 -c 12 )×(j / T max );

[0015] c2(j)=c 21 -(c 22 -c 21 )×(j / T max );

[0016] Where c1(j) represents the speedup factor c1 at the current iteration step j, and c2(j) represents the speedup factor c2 at the current iteration step j. 11 and c 21 c represents the initial value. 12 and c 22 Indicates the termination value;

[0017] The velocity and position of particles are updated by combining the inertia weighting coefficient and the acceleration factor. The calculation method for updating particle velocity and position is as follows:

[0018] v id =ω(j)v id +c1(j)r1(P id -X id )+c2(j)r2(C id -X id );

[0019] Among them, v id P represents the velocity of particle i in dimension d. id X represents the historical best position of particle i in dimension d. id C represents the current position of particle i in dimension d.id The value of the global optimal position in dimension d represents the value of the position. r1 and r2 represent two independent and identically distributed random numbers in [0,1]. c1 and c2 represent speedup factors, which are usually set to 2.

[0020] X i (d+1)=X id +V id ;

[0021] Among them, X i (d+1) represents the new position of particle i in dimension d+1, V id This represents the new velocity of particle i in dimension d.

[0022] Preferably, in S3, the method based on combining deep reinforcement learning and model predictive control includes the following steps:

[0023] S301. Set initial parameters, define reward function, prepare training environment, and initialize SAC algorithm agent and MPC controller.

[0024] The S302 and SAC algorithm agents generate an optimal control parameter set Δu based on the current state of the cooling tower cluster. DRL The MPC controller receives the optimal control parameter set Δu output by the SAC algorithm agent. DRL The MPC controller is based on Δu DRL Calculate the specific control signal Δu MPC The MPC controller is based on Δu MPC The actual load frequency control signal is sent to the variable frequency unit in the cooling tower. The load frequency control signal is used to adjust the operating parameters of the variable frequency unit.

[0025] The S303 and SAC algorithm agents gradually improve their decision-making process, making the system tend towards a more energy-efficient and effective operating mode.

[0026] Preferably, in S4, the beetle whisker-particle swarm optimization algorithm includes the following steps:

[0027] S401. Set parameters and initialize particles. Particles represent the water distribution flow rate configuration scheme.

[0028] S402. Based on the water distribution configuration represented by the particles, calculate the fitness function value f(x) and determine the position P of the individual with the best fitness in the particle population. t and the global optimal position P k ;

[0029] S403, according to P t and P k Based on the information, the particle's velocity and position are adjusted, calculated as follows:

[0030]

[0031] in, This represents the position of particle i in dimension d during the k-th iteration. This represents the velocity of particle i in dimension d at the k-th iteration. This represents the historical best solution for particle i in dimension d. This represents the value of the globally optimal position in dimension d;

[0032] S404. Reset the parameters using the updated particle positions, calculate the total energy consumption under the new water distribution flow configuration, and evaluate whether the optimal energy efficiency data solution is met. Update the parameters using the following formula:

[0033]

[0034] in, This indicates the water distribution flow rate or outlet flow rate on the left side. Indicates the water distribution flow rate or outlet flow rate on the right side, x k This indicates the current location or flow rate, d0 represents the step size, and dir represents a binary variable, typically taking a value of +1 or -1.

[0035] The direction vector sign is calculated to determine the direction of movement.

[0036]

[0037] Update the example position based on the direction vector sign and the step size step:

[0038] x k+1 =x k -dir·step·sign;

[0039] S405. If the new configuration meets the preset optimization criteria, save the optimized data; otherwise, return to S402 to continue the optimization process until the convergence condition is met or the predetermined number of iterations is completed.

[0040] S406. When the optimization process ends, output the water distribution flow rate parameters.

[0041] Preferably, the real-time data includes inlet water temperature information, outlet water temperature information, turbine inlet water flow rate information, fan speed information, water distribution flow rate information, cooling tower heat transfer information, and water pump pressure information.

[0042] Preferably, the cloud layer is used to provide computing and storage services; the edge computing layer is used to manage the cooling tower cluster and optimize local data processing and data transmission at the edge network.

[0043] Preferably, the cloud module includes a cloud computing module, a cloud storage module, and a cloud platform module. The cloud computing module provides computing services, the cloud storage module is used to store data uploaded from edge nodes, and the cloud platform module is used to manage user access permissions, task scheduling, and service coordination, and provides standardized API interfaces.

[0044] Preferably, the edge computing layer includes an execution control module, a data perception module, a modeling and analysis module, and an intelligent decision-making module.

[0045] Preferably, the equipment layer also includes a PLC equipment module and a cooling tower body module.

[0046] Therefore, the present invention employs the aforementioned edge-cloud collaborative computing-based central air conditioning cooling tower control method, which, compared with the prior art, has the following significant advantages:

[0047] (1) This invention realizes the control of water distribution flow, avoids the problem of blockage, improves the efficiency of water resource utilization, and increases the heat transfer efficiency of cooling tower.

[0048] (2) This invention optimizes the cooling tower operating parameters by constructing an improved particle swarm algorithm to process data at the edge nodes, thereby effectively reducing the total power consumption of the cooling tower system and achieving the best energy efficiency.

[0049] (3) This invention reduces reliance on manual intervention, lowers manual operation and maintenance costs, and improves operation and maintenance efficiency.

[0050] (4) This invention proposes a four-layer structure consisting of a structural equipment layer, a data acquisition layer, an edge computing layer, and a cloud layer. It utilizes the powerful computing capabilities of edge computing, which is close to the equipment structure, for real-time data fusion of cooling tower clusters.

[0051] (5) The architecture proposed in this invention has the advantages of fast information transmission and strong compatibility. It supports multiple cooling towers to share cloud service resources, adapts to different business needs, and can expand control of more cooling towers by adding PCI.

[0052] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0053] Figure 1 This is a technical architecture diagram of a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention.

[0054] Figure 2 This is a design diagram of the edge node-cloud system framework for a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention.

[0055] Figure 3This is a cloud-edge-end system framework diagram of a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention.

[0056] Figure 4 This is a flowchart illustrating the real-time data processing of a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention.

[0057] Figure 5 This is a flowchart of the improved particle swarm optimization algorithm for a central air conditioning cooling tower control method based on edge-cloud collaborative computing, as described in this invention.

[0058] Figure 6 This is a schematic diagram of a cooling tower cluster control method for a central air conditioning cooling tower based on edge-cloud collaborative computing according to the present invention.

[0059] Figure 7 This is a flowchart of the water distribution flow optimization algorithm for a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention.

[0060] Figure 8 This is a flowchart illustrating the actual operation of the water distribution flow optimization algorithm for a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention.

[0061] Figure 9 This is a data diagram of the improved particle swarm optimization algorithm for a central air conditioning cooling tower control method based on edge-cloud collaborative computing, as described in this invention.

[0062] Figure 10 This is a data graph showing the energy-saving rate of a central air conditioning cooling tower after optimization, based on an edge-cloud collaborative computing control method of the present invention. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Unless otherwise defined, the technical or scientific terms used in the present invention should have the ordinary meaning understood by those skilled in the art.

[0064] Example 1

[0065] like Figures 1-2 As shown, a central air conditioning cooling tower control method based on edge-cloud collaborative computing according to the present invention includes the following steps:

[0066] S1, such as Figure 3As shown, a cloud-edge-device system is constructed, comprising a device layer, an edge computing layer, and a cloud layer. This system, through a reasonable modular component division, addresses the problem-solving and functional implementation requirements encountered in actual cooling tower operation and maintenance.

[0067] The equipment layer includes a PLC module, a cooling tower body module, and a smart sensor module. The PLC module includes a communication card for motion control, I / O communication cards for auxiliary system functions, a data acquisition module card, and other PCI function cards. These are connected to the cooling tower's actuators via terminal blocks and support expanded control of multiple cooling towers by adding PCI cards. The cooling tower body module contains the water pump motor and corresponding driver for water delivery, as well as auxiliary equipment such as water supply and drainage devices. This module can be selectively linked to an industrial computer to complete the required cooling tower command control and intelligent function execution. The smart sensor module includes temperature sensors, pressure sensors, and flow sensors to acquire various parameters during cooling tower operation.

[0068] The structural equipment layer consists of the cooling tower body module and is used to receive control commands from the edge layer. Based on these commands, it adjusts the operating parameters of the internal equipment of the cooling tower (such as water pump speed and fan speed) to execute specific cooling tasks.

[0069] The data acquisition layer uses intelligent sensor modules to collect information on inlet water temperature, outlet water temperature, turbine inlet water flow rate, fan speed, water distribution flow rate, cooling tower heat transfer, and water pump pressure, and sends the above real-time data to the edge computing layer through the transmission layer.

[0070] The transport layer uses TCP-based application layer transmission and MQTT protocol for data push, while the physical / data link layer uses 5G for real-time data transmission.

[0071] The edge computing layer consists of multiple edge computing nodes distributed near various cooling towers, forming a distributed computing network. The edge computing layer includes a data perception module, a modeling and analysis module, an intelligent decision-making module, and a control execution module. The data perception module is responsible for intelligent information scheduling and data preprocessing, including data cleaning, time alignment, feature extraction, correlation fusion, and intelligent tagging. It stores the processed data in an edge computing data pool, ensuring data extraction and analysis for other modules. The modeling and analysis module extracts perceived data from the edge computing data pool and, combined with theoretical mathematical models, analyzes and constructs the cooling tower status (such as temperature, pressure, and flow) under different operating scenarios. The intelligent decision-making module generates information and instructions to support decision-making, enabling real-time monitoring, data analysis, optimized control, and intelligent decision-making for the cooling tower cluster operation. The control execution module outputs control commands to the underlying devices and receives data feedback from them, forming a closed-loop control system.

[0072] The application layer is used to establish the cloud layer, analyzing and applying data uploaded from edge nodes. The cloud layer includes a cloud computing module, a cloud storage module, and a cloud platform module. The cloud computing module provides high-performance computing services, remotely invoking cloud resources to complete analysis or decision-making tasks for the cooling tower system when faced with large-scale data computation or simulation analysis needs. The cloud storage module stores various types of data uploaded from edge nodes, such as historical data collected by sensors and optimized parameter configurations. This module supports long-term trend analysis, historical data review, and fault diagnosis, providing a foundation for subsequent data mining and deep learning. The cloud platform module manages user access permissions, task scheduling, and service coordination, providing standardized API interfaces to support multi-tenant use of the same cloud platform services, ensuring stable service operation.

[0073] The aforementioned structural equipment layer, data acquisition layer, edge computing layer, and cloud layer constitute the edge node-cloud system framework. This framework utilizes the powerful computing capabilities of edge computing, which is located close to the equipment structure, for real-time data fusion of cooling tower clusters.

[0074] S2, such as Figures 4-5As shown, the data acquisition layer uses the intelligent sensor module in S1 to collect real-time data. After receiving the real-time data, the edge computing nodes in the edge computing layer use an improved particle swarm optimization algorithm to perform data optimization processing at the edge nodes. First, the particle velocity and position are initialized. Real-time data is input, including inlet water temperature, outlet water temperature, turbine inlet flow rate, fan speed, water distribution flow rate, cooling tower heat transfer information, and pump water pressure information. After preprocessing the input real-time data, the total power consumption of the cooling tower system under the current state is calculated based on the preprocessed data. The system performance indicators, inertia weight coefficient, and acceleration factor corresponding to the position of each particle are calculated as follows:

[0075]

[0076] Where ω represents the inertia weight coefficient, and ω(j) represents the inertia weight coefficient at the current iteration step j. max ω represents the maximum inertia weighting coefficient. min T represents the minimum inertia weighting coefficient. max This represents the maximum number of iterations, and j represents the current iteration step;

[0077] c1(j)=c 11 -(c 11 -c 12 )×(j / T max );

[0078] c2(j)=c 21 -(c 22 -c 21 )×(j / T max );

[0079] Where c1(j) represents the speedup factor c1 at the current iteration step j, and c2(j) represents the speedup factor c2 at the current iteration step j. 11 and c 21 c represents the initial value. 12 and c 22 Indicates the termination value.

[0080] The velocity and position of particles are updated by combining the inertia weighting coefficient and the acceleration factor. The calculation method for updating particle velocity and position is as follows:

[0081] v id =ω(j)v id +c1(j)r1(P id -X id )+c2(j)r2(C id -X id );

[0082] Among them, v idP represents the velocity of particle i in dimension d. id X represents the historical best position of particle i in dimension d. id C represents the current position of particle i in dimension d. id The value of the global optimal position in dimension d represents the value of the position. r1 and r2 represent two independent and identically distributed random numbers in [0,1]. c1 and c2 represent speedup constants, which are usually set to 2.

[0083] X i (d+1)=X id +V id ;

[0084] Among them, X i (d+1) represents the new position of particle i in dimension d+1, V id This represents the new velocity of particle i in dimension d.

[0085] By continuously adjusting the velocity and position of particles, the improved particle swarm optimization algorithm can effectively explore the solution space and find the optimal solution. Then, using the updated particle positions, the total energy consumption of the cooling tower is recalculated to find new local and global optima to determine if a better solution has been achieved. If the newly calculated total energy consumption meets the preset optimization criteria, the optimized data is uploaded to the cloud and stored in an edge computing data pool. If the criteria are not met, the optimization process continues until a satisfactory optimization result is achieved or the predetermined number of iterations is completed.

[0086] S3, such as Figure 6 As shown, to achieve intelligent control of cooling tower clusters, this invention employs a combination of Deep Reinforcement Learning (DRL) and Model Predictive Control (MPC), with the Deep Reinforcement Learning using the SAC (Soft Actor-Critic) algorithm. This combination allows for adaptive adjustment of the parameters of the model predictive controller established in the cooling tower, improving energy efficiency and reducing energy consumption. The specific workflow of this method is as follows:

[0087] S301. Set initial parameters, define reward function, prepare training environment, and initialize SAC algorithm agent and MPC controller.

[0088] The S302 and SAC algorithm agents generate an optimal control parameter set Δu based on the current state of the cooling tower cluster (including but not limited to variable flow frequency fluctuation sets and control signal information from other cooling tower controllers). DRLThese parameters are based on the strategy obtained by the SAC algorithm agent through continuous learning and optimization; the MPC controller receives the optimal control parameter set Δu output by the SAC algorithm agent. DRL Based on these parameters, the MPC controller calculates the specific control signal Δu. MPC The MPC controller is based on Δu MPC The system sends actual Load Frequency Control (LFC) signals to the variable frequency units in each cooling tower. These LFC signals are used to adjust the actual operating parameters of the variable frequency units and generate changes, thereby achieving coordinated control of the cooling tower cluster. After each cooling tower executes the control command, it obtains new state observations and immediate rewards (or penalties), which reflect the effectiveness of the control. The SAC algorithm agent updates its internal policy based on the new state and rewards in order to make better choices in the future.

[0089] S303. With the accumulation of time and experience, the SAC algorithm agent gradually improves its decision-making process, making the system tend towards a more energy-efficient and efficient operating mode.

[0090] This invention combines deep reinforcement learning with model predictive control. The SAC algorithm agent generates optimal control parameters based on real-time environmental information, and the MPC controller receives these parameters and generates specific LFC signals, thereby achieving coordinated and stable operation of the cooling tower cluster. This method is suitable for central air conditioning cooling systems in complex industrial environments requiring high precision and dynamic adjustment, such as data centers and large building complexes.

[0091] S4. To achieve water distribution flow control, the beetle-beard particle swarm optimization algorithm is used to optimize the water distribution flow. The beetle-beard particle swarm optimization algorithm is used to set system parameters, calculate fitness, and update the P corresponding to the optimal fitness of the parameters. t and P k The value is then used to further adjust the water distribution flow rate and other relevant parameters.

[0092] like Figures 7-8 As shown, the Beetle Antennae Search-Particle Swarm Optimization (BAS-PSO) algorithm is a hybrid algorithm that incorporates bio-inspired optimization to solve the water distribution flow optimization problem in central air conditioning cooling towers, aiming to achieve uniform water distribution. The following are the specific application steps of this algorithm in setting system parameters, calculating fitness and updating the position corresponding to the optimal fitness, and adjusting the water distribution flow and other relevant parameters:

[0093] S401. Set system parameters such as inlet and outlet water flow rates and inlet water flow rate, and initialize a group of particles, each particle representing a possible water distribution flow rate configuration scheme.

[0094] S402. For each particle, calculate the fitness function value f(x) based on its represented water distribution flow configuration. The fitness function is designed as a comprehensive index reflecting objectives such as water distribution uniformity and energy-saving effect. Determine the individual position P corresponding to the best fitness in the current particle swarm. t (i.e., the optimal position of the current particle in the previous n iterations) and the global optimal position P k (i.e., the optimal position of all particles in the first n iterations).

[0095] S403, according to P t and P k The information is used to adjust the velocity and position of particles using a longhorn beetle whisker search mechanism, further optimizing the water distribution flow configuration. The calculation method is as follows:

[0096]

[0097] in, This represents the position of particle i in dimension d during the k-th iteration. This represents the velocity of particle i in dimension d at the k-th iteration. This represents the historical best solution for particle i in dimension d. This represents the value of the globally optimal position in dimension d;

[0098] S404. Using the updated particle positions, reset the water distribution flow rate and other relevant parameters (such as the outlet flow rate), calculate the total energy consumption under the new water distribution flow rate configuration, and evaluate whether it meets the optimal energy efficiency data solution. Use the following formula to update the water distribution flow rate, outlet flow rate, and other parameters:

[0099]

[0100] in, This indicates the water distribution flow rate or outlet flow rate on the left side. Indicates the water distribution flow rate or outlet flow rate on the right side, x k This indicates the current location or flow rate, d0 represents the step size, and dir represents a binary variable, typically taking a value of +1 or -1.

[0101] The direction vector sign is calculated to determine the direction of movement.

[0102]

[0103] Update the example position based on the direction vector sign and the step size step:

[0104] x k+1 =x k -dir·step·sign;

[0105] S405. If the new configuration meets the preset optimization criteria, save the optimized data; otherwise, return to S402 to continue the optimization process until the convergence condition is met or the predetermined number of iterations is completed.

[0106] S406. When the optimization process ends, output the final determined optimal water distribution flow parameters to ensure that the water distribution is more uniform and reasonable during the operation of the cooling tower, reduce the drift rate, and improve the water resource utilization efficiency and heat transfer efficiency.

[0107] S5. Repeat steps S2 to S4, continuously adjusting the cooling tower's operating mode based on real-time data and historical records to achieve the optimal energy efficiency ratio.

[0108] like Figures 9-10 As shown, through optimization measures, the cooling tower exhibits a high energy saving rate for most of the day, proving the effectiveness of the invention.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A central air conditioning cooling tower control method based on edge-cloud collaborative computing, characterized in that, Includes the following steps: S1. Construct a cloud-edge-device system, which includes a device layer, an edge computing layer, and a cloud layer. The device layer includes intelligent sensor modules. S2, the data acquisition layer uses the smart sensor module in S1 to collect real-time data. After receiving the real-time data, the edge computing nodes in the edge computing layer use the improved particle swarm algorithm to process the real-time data and save the processed data in the edge computing data pool. S3. Intelligent control of cooling tower clusters is achieved by combining deep reinforcement learning with model predictive control. S4. The water distribution flow rate is controlled by the beetle whisker-particle swarm optimization algorithm. S5. Repeat steps S2 to S4, continuously adjusting the cooling tower's operating mode based on real-time data and historical records.

2. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, The improved particle swarm optimization algorithm in S2 is calculated as follows: Where ω represents the inertia weight coefficient, and ω(j) represents the inertia weight coefficient at the current iteration step j. max ω represents the maximum inertia weighting coefficient. min T represents the minimum inertia weighting coefficient. max This represents the maximum number of iterations, and j represents the current iteration step; c1(j)=c 11 -(c 11 -c 12 )×(j / T max ); c2(j)=c 21 -(c 22 -c 21 )×(j / T max ); Where c1(j) represents the speedup factor c1 at the current iteration step j, and c2(j) represents the speedup factor c2 at the current iteration step j. 11 and c 21 c represents the initial value. 12 and c 22 Indicates the termination value; The velocity and position of particles are updated by combining the inertia weighting coefficient and the acceleration factor. The calculation method for updating particle velocity and position is as follows: v id =ω(j)v id +c1(j)r1(P id -X id )+c2(j)r2(C id -X id ); Among them, v id P represents the velocity of particle i in dimension d. id X represents the historical best position of particle i in dimension d. id C represents the current position of particle i in dimension d. id The value of the global optimal position in dimension d represents the value of the position. r1 and r2 represent two independent and identically distributed random numbers in [0,1]. c1 and c2 represent speedup factors, which are usually set to 2. X i (d+1)=X id +V id ; Among them, X i (d+1) represents the new position of particle i in dimension d+1, V id This represents the new velocity of particle i in dimension d.

3. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, In S3, the method based on combining deep reinforcement learning and model predictive control includes the following steps: S301. Set initial parameters, define reward function, prepare training environment, and initialize SAC algorithm agent and MPC controller. The S302 and SAC algorithm agents generate an optimal control parameter set Δu based on the current state of the cooling tower cluster. DRL The MPC controller receives the optimal control parameter set Δu output by the SAC algorithm agent. DRL The MPC controller is based on Δu DRL Calculate the specific control signal Δu MPC The MPC controller is based on Δu MPC The actual load frequency control signal is sent to the variable frequency unit in the cooling tower. The load frequency control signal is used to adjust the operating parameters of the variable frequency unit. The S303 and SAC algorithm agents gradually improve their decision-making process, making the system tend towards a more energy-efficient and effective operating mode.

4. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, In S4, the beetle whisker-particle swarm optimization algorithm includes the following steps: S401. Set parameters and initialize particles. Particles represent the water distribution flow rate configuration scheme. S402. Based on the water distribution configuration represented by the particles, calculate the fitness function value f(x) and determine the position P of the individual with the best fitness in the particle population. t and the global optimal position P k ; S403, according to P t and P k Based on the information, the particle's velocity and position are adjusted, calculated as follows: in, This represents the position of particle i in dimension d during the k-th iteration. This represents the velocity of particle i in dimension d at the k-th iteration. This represents the historical best solution for particle i in dimension d. This represents the value of the globally optimal position in dimension d; S404. Reset the parameters using the updated particle positions, calculate the total energy consumption under the new water distribution flow configuration, and evaluate whether the optimal energy efficiency data solution is met. Update the parameters using the following formula: in, This indicates the water distribution flow rate or outlet flow rate on the left side. Indicates the water distribution flow rate or outlet flow rate on the right side, x k d0 represents the current flow, d0 represents the step size, and dir represents a binary variable, which usually takes the value of +1 or -1. The direction vector sign is calculated to determine the direction of movement. Update the particle position based on the direction vector sign and the step size step: x k+1 =x k -dir·step·sign; S405. If the new configuration meets the preset optimization criteria, save the optimized data; otherwise, return to S402 to continue the optimization process until the convergence condition is met or the predetermined number of iterations is completed. S406. When the optimization process ends, output the water distribution flow rate parameters.

5. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, Real-time data includes inlet water temperature information, outlet water temperature information, turbine inlet water flow rate information, fan speed information, water distribution flow rate information, cooling tower heat transfer information, and water pump pressure information.

6. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, The cloud layer provides computing and storage services; the edge computing layer manages cooling tower clusters and optimizes local data processing and data transmission at the edge network.

7. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, The cloud module includes a cloud computing module, a cloud storage module, and a cloud platform module. The cloud computing module provides computing services, the cloud storage module is used to store data uploaded from edge nodes, and the cloud platform module is used to manage user access permissions, task scheduling, and service coordination, and provides standardized API interfaces.

8. The central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, The edge computing layer includes an execution control module, a data perception module, a modeling and analysis module, and an intelligent decision-making module.

9. A central air conditioning cooling tower control method based on edge-cloud collaborative computing according to claim 1, characterized in that, The equipment layer also includes PLC equipment modules and cooling tower body modules.

Images