Energy-saving optimization control method for water-cooling refrigeration station system based on deep reinforcement learning

Abstract

The present invention relates to the field of energy-saving control technology, and in particular to an energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning. The method comprises: collecting environmental data and refrigeration equipment operation data of the water-cooled refrigeration station system; calculating the energy efficiency score of the refrigeration equipment and the load rate of the refrigeration equipment; calculating the load recommendation rate of the refrigeration equipment based on the energy efficiency score and the load rate of the refrigeration equipment; importing the energy efficiency score and the load recommendation rate of the refrigeration equipment into a cluster analysis algorithm, performing cluster analysis on the refrigeration equipment of the water-cooled refrigeration station system, and dividing the refrigeration equipment into a high-efficiency operation mode, a balanced operation mode, and an inefficient operation mode; extracting refrigeration equipment in the inefficient operation mode, and adjusting the corresponding water pump frequency and cooling tower fan speed.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving control technology, and in particular to an energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning. Background Art

[0002] Water-cooled chiller systems are widely used in large buildings, data centers, and industrial cooling. They are energy-intensive, typically accounting for 30%-50% of a building's total energy consumption. Reducing chiller energy consumption is a key component of energy conservation and emission reduction.

[0003] Disadvantages of existing technologies: Traditional control methods are often based on fixed rules or simple feedback mechanisms (such as adjusting equipment start and stop based on set temperatures), making them difficult to cope with dynamic environmental changes and the complex coupling relationships between equipment. Under partial load conditions, refrigeration equipment may operate in an inefficient state for a long time, resulting in energy waste. Traditional methods do not quantitatively evaluate the energy efficiency and load status of refrigeration equipment, and cannot distinguish between high-efficiency and low-efficiency equipment operating modes, resulting in "one-size-fits-all" control, such as synchronously adjusting the frequency or speed of all equipment, ignoring individual performance differences. Existing control strategies are based on fixed design parameters, but in actual operation, ambient temperature and load demand frequently change. Static strategies cannot optimize equipment combinations and operating parameters in real time, causing some equipment to operate in an inefficient range for a long time. Equipment start-up and shutdown scheduling and parameter adjustment rely on the experience of operation and maintenance personnel, lacking an automated energy efficiency optimization mechanism, resulting in delayed response and energy waste. Summary of the Invention

[0004] The main purpose of the present invention is to provide an energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning, which accurately characterizes the actual energy efficiency of the equipment through an energy efficiency scoring formula; introduces load rate and load recommendation rate to quantify the equipment load status and optimization potential, and provide data support for refined control; adopts the K-Means clustering algorithm to divide the equipment into three operating modes based on energy efficiency score and load recommendation rate, formulates differentiated strategies for different modes, makes full use of cost-effective equipment, accurately adjusts the water pump frequency and cooling tower fan speed, and improves energy efficiency in a targeted manner, solving the defect of "indifferent control" of traditional methods and realizing optimal resource allocation; the whole process is controlled in a closed loop without manual intervention, can respond to environmental and load changes in real time, and adapt to complex working conditions.

[0005] The technical solutions of the present invention are as follows:

[0006] First, a deep reinforcement learning-based energy-saving optimization control method for a water-cooled refrigeration station system is proposed. The method includes the following steps:

[0007] S1. Collect environmental data of the water-cooled refrigeration station system and refrigeration equipment operation data;

[0008] S2. Calculate the energy efficiency score of the refrigeration equipment and calculate the load rate of the refrigeration equipment;

[0009] S3. Calculate the recommended load rate of the refrigeration equipment based on the energy efficiency score and load rate of the refrigeration equipment;

[0010] S4. Import the energy efficiency score and load recommendation rate of the refrigeration equipment into the cluster analysis algorithm, perform cluster analysis on the refrigeration equipment of the water-cooled refrigeration station system, and divide the refrigeration equipment into high-efficiency operation mode, balanced operation mode, and low-efficiency operation mode;

[0011] S5. Extract the refrigeration equipment in the inefficient operation mode and adjust the corresponding water pump frequency and cooling tower fan speed.

[0012] Preferably, the environmental data in S1 include cooling water inlet temperature and cooling water outlet temperature; the refrigeration equipment operation data include refrigeration capacity of refrigeration equipment, power consumption of refrigeration equipment, water pump frequency and cooling tower fan speed.

[0013] Preferably, the calculation formula for the energy efficiency score in S2 is:

[0014] ;

[0015] in, is the energy efficiency score of the i-th refrigeration equipment, is the cooling capacity of the i-th refrigeration equipment, is the power consumption of the i-th refrigeration equipment, is the cooling water inlet temperature of the i-th refrigeration equipment, is the cooling water outlet temperature of the i-th refrigeration equipment, To design the optimal temperature difference for refrigeration equipment, 、 are weight factors, and .

[0016] Preferably, the calculation formula for the load rate in S2 is:

[0017] ;

[0018] in, is the load rate of the i-th refrigeration equipment, is the maximum cooling capacity of the i-th refrigeration equipment.

[0019] Preferably, the calculation formula for the load recommendation rate in S3 is:

[0020] ;

[0021] in, is the recommended load rate of the i-th refrigeration equipment, n is the total number of refrigeration equipment, 、 are weight factors, and .

[0022] Preferably, the S4 includes the following specific steps:

[0023] S41. Extract the energy efficiency score of the i-th refrigeration equipment and load recommendation rate And combined into feature vector ; Randomly select three eigenvectors from the set of all eigenvectors as the initial cluster centers of the cluster analysis algorithm, calculate the Euclidean distance of each eigenvector to each initial cluster center, and assign it to the cluster corresponding to the initial cluster center with the smallest distance;

[0024] S42. Calculate the mean vector of all eigenvectors in a single cluster, update the initial cluster center, and redistribute each eigenvector until the preset number of iterations is reached, then stop the operation and complete the cluster analysis. Each cluster represents an operating mode. Three operating modes are defined based on the cluster analysis results, including an efficient operating mode, a balanced operating mode, and an inefficient operating mode. The cluster analysis algorithm is a K-Means clustering algorithm, and K=3.

[0025] Preferably, the specific content of defining the three operating modes according to the cluster analysis results in S42 is: if the average energy efficiency score of different refrigeration equipment in a single cluster is greater than a preset energy efficiency score threshold, and the average load recommendation rate of different refrigeration equipment in a single cluster is greater than the preset load recommendation rate threshold, the refrigeration equipment in the single cluster is defined as a high-efficiency operating mode; if the average energy efficiency score of different refrigeration equipment in a single cluster is not greater than the preset energy efficiency score threshold, and the average load recommendation rate of different refrigeration equipment in a single cluster is not greater than the preset load recommendation rate threshold, the refrigeration equipment in the single cluster is defined as an inefficient operating mode; if a single cluster does not meet the definitions of a high-efficiency operating mode and an inefficient operating mode, the refrigeration equipment in the single cluster is defined as a balanced operating mode.

[0026] Preferably, the S5 includes the following specific steps:

[0027] S51. Extract the refrigeration equipment in the low-efficiency operation mode and adjust the corresponding water pump frequency. The adjustment formula of the water pump frequency is: ;in, is the pump frequency adjustment value of the jth refrigeration equipment in the low-efficiency operation mode, is the reference frequency of the water pump, is the pump frequency adjustment coefficient, , is the difference between the cooling water outlet temperature and the cooling water inlet temperature of the jth refrigeration equipment in the low-efficiency operation mode, To set the temperature difference reference value;

[0028] S52. Adjust the cooling tower fan speed corresponding to the refrigeration equipment in the low-efficiency operation mode. The adjustment formula for the cooling tower fan speed is: ;in, is the cooling tower fan speed adjustment value of the j-th refrigeration equipment in the low-efficiency operation mode, is the reference value of the cooling tower fan speed, is the cooling tower fan speed adjustment coefficient, .

[0029] In a second aspect, a computer-readable storage medium is proposed, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned energy-saving optimization control method of the water-cooling refrigeration station system based on deep reinforcement learning is implemented.

[0030] In a third aspect, an electronic device is proposed, comprising a memory for storing instructions; and a processor for executing the instructions, so that the device implements the above-mentioned energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning.

[0031] The technical effects of the present invention are as follows:

[0032] A deep reinforcement learning-based energy-saving optimization control method for water-cooled refrigeration station systems was constructed, and the actual energy efficiency of the equipment was accurately characterized through the energy efficiency scoring formula; the load rate and load recommendation rate were introduced to quantify the equipment load status and optimization potential, providing data support for refined control; the K-Means clustering algorithm was used to divide the equipment into three operating modes based on the energy efficiency score and load recommendation rate, and differentiated strategies were formulated for different modes. The cost-effective equipment was fully utilized, and the water pump frequency and cooling tower fan speed were accurately adjusted to improve energy efficiency in a targeted manner. This solved the defect of "indifferent control" in traditional methods and achieved optimal resource allocation; the full-process control closed loop did not require human intervention, and could respond to environmental and load changes in real time to adapt to complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0034] Figure 1 This is a flow chart of the energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning according to Example 1 of the present invention. DETAILED DESCRIPTION

[0035] Example 1

[0036] This embodiment proposes an energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning. It accurately describes the actual energy efficiency of the equipment through the energy efficiency scoring formula; introduces the load rate and load recommendation rate to quantify the equipment load status and optimization potential, and provide data support for refined control; adopts the K-Means clustering algorithm to divide the equipment into three operating modes based on the energy efficiency score and load recommendation rate, formulates differentiated strategies for different modes, makes full use of cost-effective equipment, accurately adjusts the water pump frequency and cooling tower fan speed, improves energy efficiency in a targeted manner, solves the defect of "indifferent control" of traditional methods, and realizes optimal resource allocation; the whole process is controlled in a closed loop, without manual intervention, and can respond to environmental and load changes in real time to adapt to complex working conditions. Specifically, Figure 1 As shown, the adaptive propulsion control method for an amphibious aircraft based on an intelligent algorithm proposed in this embodiment includes the following specific steps:

[0037] S1. Collect environmental data of the water-cooled refrigeration station system and refrigeration equipment operation data;

[0038] S2. Calculate the energy efficiency score of the refrigeration equipment and calculate the load rate of the refrigeration equipment;

[0039] S3. Calculate the recommended load rate of the refrigeration equipment based on the energy efficiency score and load rate of the refrigeration equipment;

[0040] S4. Import the energy efficiency score and load recommendation rate of the refrigeration equipment into the cluster analysis algorithm, perform cluster analysis on the refrigeration equipment of the water-cooled refrigeration station system, and divide the refrigeration equipment into high-efficiency operation mode, balanced operation mode, and low-efficiency operation mode;

[0041] S5. Extract the refrigeration equipment in the inefficient operation mode and adjust the corresponding water pump frequency and cooling tower fan speed.

[0042] In this embodiment, the environmental data in S1 include cooling water inlet temperature and cooling water outlet temperature; the refrigeration equipment operation data include refrigeration capacity of refrigeration equipment, refrigeration equipment power consumption, water pump frequency and cooling tower fan speed.

[0043] In this embodiment, the calculation formula for the energy efficiency score in S2 is:

[0044] ;

[0045] in, is the energy efficiency score of the i-th refrigeration equipment, is the cooling capacity of the i-th refrigeration equipment, is the power consumption of the i-th refrigeration equipment, is the cooling water inlet temperature of the i-th refrigeration equipment, is the cooling water outlet temperature of the i-th refrigeration equipment, To design the optimal temperature difference for refrigeration equipment, 、 are weight factors, and .

[0046] In this embodiment, the calculation formula of the load rate in S2 is:

[0047] ;

[0048] in, is the load rate of the i-th refrigeration equipment, is the maximum cooling capacity of the i-th refrigeration equipment.

[0049] In this embodiment, the calculation formula of the load recommendation rate in S3 is:

[0050] ;

[0051] in, is the recommended load rate of the i-th refrigeration equipment, n is the total number of refrigeration equipment, 、 are weight factors, and .

[0052] In this embodiment, S4 includes the following specific steps:

[0053] S41. Extract the energy efficiency score of the i-th refrigeration equipment and load recommendation rate And combined into feature vector ; Randomly select three eigenvectors from the set of all eigenvectors as the initial cluster centers of the cluster analysis algorithm, calculate the Euclidean distance of each eigenvector to each initial cluster center, and assign it to the cluster corresponding to the initial cluster center with the smallest distance;

[0054] S42. Calculate the mean vector of all eigenvectors in a single cluster, update the initial cluster center, and redistribute each eigenvector until the preset number of iterations is reached, then stop the operation and complete the cluster analysis. Each cluster represents an operating mode. Three operating modes are defined based on the cluster analysis results, including an efficient operating mode, a balanced operating mode, and an inefficient operating mode. The cluster analysis algorithm is a K-Means clustering algorithm, and K=3.

[0055] In this embodiment, the specific content of defining the three operating modes according to the cluster analysis results in S42 is: if the average energy efficiency score of different refrigeration equipment in a single cluster is greater than a preset energy efficiency score threshold, and the average load recommendation rate of different refrigeration equipment in a single cluster is greater than the preset load recommendation rate threshold, the refrigeration equipment in the single cluster is defined as a high-efficiency operating mode; if the average energy efficiency score of different refrigeration equipment in a single cluster is not greater than the preset energy efficiency score threshold, and the average load recommendation rate of different refrigeration equipment in a single cluster is not greater than the preset load recommendation rate threshold, the refrigeration equipment in the single cluster is defined as an inefficient operating mode; if a single cluster does not meet the definitions of a high-efficiency operating mode and a low-efficiency operating mode, the refrigeration equipment in the single cluster is defined as a balanced operating mode.

[0056] In this embodiment, S5 includes the following specific steps:

[0057] S51. Extract the refrigeration equipment in the low-efficiency operation mode and adjust the corresponding water pump frequency. The adjustment formula of the water pump frequency is: ;in, is the pump frequency adjustment value of the jth refrigeration equipment in the low-efficiency operation mode, is the reference frequency of the water pump, is the pump frequency adjustment coefficient, , is the difference between the cooling water outlet temperature and the cooling water inlet temperature of the jth refrigeration equipment in the low-efficiency operation mode, To set the temperature difference reference value;

[0058] S52. Adjust the cooling tower fan speed corresponding to the refrigeration equipment in the low-efficiency operation mode. The adjustment formula for the cooling tower fan speed is: ;in, is the cooling tower fan speed adjustment value of the j-th refrigeration equipment in the low-efficiency operation mode, is the reference value of the cooling tower fan speed, is the cooling tower fan speed adjustment coefficient, .

[0059] The threshold and weight can be set by default according to the present invention, or can be set by the operator.

[0060] Example 2

[0061] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning by calling the computer program stored in the memory.

[0062] The electronic device may vary significantly due to different configurations or performance, and may include one or more processors (Central Processing Units, CPUs) and one or more memories, wherein the memories store at least one computer program, which is loaded and executed by the processor to implement the energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning provided in the above-mentioned method embodiment. The electronic device may also include other components for implementing the device's functions. For example, the electronic device may also have components such as wired or wireless network interfaces and input / output interfaces for data input and output. This embodiment is not described in detail here.

[0063] Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention may be implemented as a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0064] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0065] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowcharts and block diagrams, as well as combinations of processes and blocks in the flowcharts or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 A process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and boxes Figure 1 A step that specifies a function in one or more boxes.

[0067] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all protected by the present invention.

Claims

1. A water-cooling refrigeration station system energy-saving optimization control method based on deep reinforcement learning, characterized by: The specific steps include: S1. Collect environmental data of the water-cooled refrigeration station system and refrigeration equipment operation data; S2. Calculate the energy efficiency score of the refrigeration equipment and calculate the load rate of the refrigeration equipment; S3. Calculate the recommended load rate of the refrigeration equipment based on the energy efficiency score and load rate of the refrigeration equipment; S4. Import the energy efficiency score and load recommendation rate of the refrigeration equipment into the cluster analysis algorithm, perform cluster analysis on the refrigeration equipment of the water-cooled refrigeration station system, and divide the refrigeration equipment into high-efficiency operation mode, balanced operation mode, and low-efficiency operation mode; S5. Detect refrigeration equipment in an inefficient operation mode and adjust the corresponding water pump frequency and cooling tower fan speed; The calculation formula for the energy efficiency score in S2 is: ； in, is the energy efficiency score of the i-th refrigeration equipment, is the cooling capacity of the i-th refrigeration equipment, is the power consumption of the i-th refrigeration equipment, is the cooling water inlet temperature of the i-th refrigeration equipment, is the cooling water outlet temperature of the i-th refrigeration equipment, To design the optimal temperature difference for refrigeration equipment, 、 are weight factors, and ; The calculation formula of the load rate in S2 is: ； in, is the load rate of the i-th refrigeration equipment, is the maximum cooling capacity of the i-th refrigeration equipment; The calculation formula for the load recommendation rate in S3 is: ； in, is the recommended load rate of the i-th refrigeration equipment, n is the total number of refrigeration equipment, 、 are weight factors, and ; The S4 includes the following specific steps: S41. Extract the energy efficiency score of the i-th refrigeration equipment and load recommendation rate And combined into feature vector ; Randomly select three eigenvectors from the set of all eigenvectors as the initial cluster centers of the cluster analysis algorithm, calculate the Euclidean distance of each eigenvector to each initial cluster center, and assign it to the cluster corresponding to the initial cluster center with the smallest distance; S42. Calculate the mean vector of all eigenvectors within a single cluster, update the initial cluster center, and redistribute each eigenvector until a preset number of iterations is reached, then stop the operation to complete the cluster analysis. Each cluster represents an operating mode. Three operating modes are defined based on the cluster analysis results, including an efficient operating mode, a balanced operating mode, and an inefficient operating mode. The cluster analysis algorithm is a K-Means clustering algorithm, with K=3. The specific content of defining three operating modes according to the cluster analysis results in S42 is as follows: if the average energy efficiency score of different refrigeration equipment in a single cluster is greater than a preset energy efficiency score threshold, and the average load recommendation rate of different refrigeration equipment in a single cluster is greater than a preset load recommendation rate threshold, the refrigeration equipment in the single cluster is defined as a high-efficiency operating mode; if the average energy efficiency score of different refrigeration equipment in a single cluster is not greater than the preset energy efficiency score threshold, and the average load recommendation rate of different refrigeration equipment in a single cluster is not greater than the preset load recommendation rate threshold, the refrigeration equipment in the single cluster is defined as an inefficient operating mode; if a single cluster does not meet the definitions of the high-efficiency operating mode and the inefficient operating mode, the refrigeration equipment in the single cluster is defined as a balanced operating mode; The S5 includes the following specific steps: S51. Extract the refrigeration equipment in the low-efficiency operation mode and adjust the corresponding water pump frequency. The adjustment formula of the water pump frequency is: ;in, is the pump frequency adjustment value of the jth refrigeration equipment in the low-efficiency operation mode, is the reference frequency of the water pump, is the pump frequency adjustment coefficient, , is the difference between the cooling water outlet temperature and the cooling water inlet temperature of the jth refrigeration equipment in the low-efficiency operation mode, To set the temperature difference reference value; S52. Adjust the cooling tower fan speed corresponding to the refrigeration equipment in the low-efficiency operation mode. The adjustment formula for the cooling tower fan speed is: ;in, is the cooling tower fan speed adjustment value of the j-th refrigeration equipment in the low-efficiency operation mode, is the reference value of the cooling tower fan speed, is the cooling tower fan speed adjustment coefficient, .

2. The energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning according to claim 1 is characterized in that: The environmental data in S1 include the cooling water inlet temperature and the cooling water outlet temperature; the refrigeration equipment operation data include the refrigeration capacity of the refrigeration equipment, the power consumption of the refrigeration equipment, the water pump frequency and the cooling tower fan speed.

3. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning as described in any one of claims 1-2 is implemented.

4. An electronic device, characterized in that: It includes a memory for storing instructions; a processor for executing the instructions, so that the device implements the energy-saving optimization control method for a water-cooled refrigeration station system based on deep reinforcement learning as described in any one of claims 1 to 2.

Images