Multi-environment self-adaptive refrigeration control system based on artificial intelligence

Abstract

The invention discloses a multi-environment self-adaptive refrigeration control system based on artificial intelligence, relates to the technical field of intelligent control and refrigeration, and is used for solving the problems that accurate cooling capacity scheduling and system-level energy efficiency coordination cannot be realized under the multi-environment concurrent requirement, and the operation efficiency of a refrigeration system and the use safety of a user are reduced. Dynamic balance and intelligent distribution of cooling capacity among multiple regions are realized by introducing a distributed game model constructed based on cooling capacity demand difference and environmental parameters, cooling capacity demand data are encrypted by adopting a truncated Gaussian mechanism, and cooling capacity scheduling strategies and running state data of different regions are fused on the premise of not influencing the scheduling precision, so that the scheduling precision is improved. And a system-level objective function is constructed, combined optimization is performed, and the mapping relation between the environment characteristics and the cooling capacity characteristics is continuously updated, so that load models and control targets in different scenes can be dynamically adapted, the universality and flexibility of the system are improved, and the engineering practicability of the system is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical fields of intelligent control and refrigeration technology. More specifically, the present invention relates to a multi-environment adaptive refrigeration control system based on artificial intelligence. Background Art

[0002] Multi-zone refrigeration control technology is a technology that coordinates the cooling demand of multiple zones to optimize system energy efficiency and meet the application requirements of different scenarios. This technology has broad application prospects in scenarios such as data centers, large commercial buildings, and smart homes. However, the existing technology has limitations in dealing with conflicts in multi-zone cooling demand, especially in terms of global energy efficiency optimization in complex environments, which may lead to a decrease in system operation efficiency and an increase in energy consumption.

[0003] The existing technology has the following deficiencies: Currently, most multi-zone refrigeration systems rely on fixed-threshold control strategies, lacking a real-time response mechanism for dynamic changes in cooling demand. At the same time, there are no effective privacy protection measures when processing user environment data, resulting in the inability to achieve precise cooling scheduling and system-level energy efficiency coordination under multi-environment concurrent demands, reducing the operation efficiency of the refrigeration system and the security of user use. Therefore, a multi-environment adaptive refrigeration control system based on artificial intelligence is proposed.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the existing technology, the embodiments of the present invention provide a multi-environment adaptive refrigeration control system based on artificial intelligence. By introducing a distributed game model driven by cooling capacity difference and a privacy protection algorithm of truncated Gaussian mechanism, it realizes intelligent cooling distribution and global optimization control of energy efficiency for multi-zone environments, and solves the problems proposed in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solution: A multi-environment adaptive refrigeration control system based on artificial intelligence, including a cooling demand acquisition unit, an intelligent distribution decision unit, a privacy protection encryption unit, and a global energy efficiency optimization unit; The cooling demand acquisition unit is used to collect cooling demand data and environmental parameter data, classify each region according to the cooling demand data and judge whether to start the privacy protection mechanism. If it is necessary to start, the marked signal is transmitted to the privacy protection encryption unit. Otherwise, the cooling demand data and environmental parameter data are transmitted to the intelligent distribution decision unit together; The intelligent allocation decision-making unit is used to analyze the difference in cooling demand, construct a distributed game model by integrating the difference in cooling demand and environmental parameter data, and perform preliminary calculations on the cooling allocation strategy through the distributed game model, and send the calculation results to the privacy protection encryption unit or the global energy efficiency optimization unit; The privacy protection encryption unit is used to encrypt the cooling demand data, generate noise data by using the truncated Gaussian mechanism, and transmit the encrypted data and processing signals to the global energy efficiency optimization unit; The global energy efficiency optimization unit is used to adjust the system operation parameters according to the processing signals input from different units.

[0007] In a preferred embodiment, the cooling demand data includes the target temperature, humidity range, and heat load coefficient, and the environmental parameter data includes the outdoor temperature, humidity, and wind speed, where the target temperature is the desired temperature value set within the region.

[0008] In a preferred embodiment, the cooling demand acquisition unit classifies each region according to the cooling demand data, that is, classifies the high-temperature demand regions as type I regions according to the target temperature, and classifies the low-temperature demand regions as type II regions.

[0009] In a preferred embodiment, the privacy protection mechanism disturbs the true distribution of the cooling demand data by introducing random noise, and the noise intensity is dynamically adjusted by the truncated Gaussian mechanism.

[0010] In a preferred embodiment, the intelligent allocation decision-making unit compares the heat load coefficients of different regions to confirm the difference in cooling demand, and constructs a distributed game model by respectively combining the difference in cooling demand and the change in environmental parameters recorded in multiple time periods into a demand change data set and an environmental change data set.

[0011] In a preferred embodiment, the specific steps for the intelligent allocation decision-making unit to construct a distributed game model are as follows: Data preparation: Combine the demand change data set and the environmental change data set into an input matrix X, set the objective function as y, and set a ratio to divide the input matrix into a training data set and a validation data set; Model construction: Define the objective function of the distributed game model, and use the hybrid quantum-classical optimization algorithm to accelerate the model convergence; Model evaluation: Calculate the objective function by using the training data set and the validation data set respectively, and adjust the weight coefficient of the objective function according to the calculation results; Evaluate the rationality of cooling allocation: Select the optimal solution in the calculated objective function and compare it with the preset allocation threshold to evaluate the rationality of cooling allocation.

[0012] In a preferred embodiment, when the privacy protection encryption unit encrypts the cooling demand data, it sets a noise distribution range, first standardizes the cooling demand data, and when the standardized data conforms to the characteristics of a normal distribution, it uses the truncated Gaussian mechanism to generate noise data.

[0013] In a preferred embodiment, the noise data in the privacy protection encryption unit includes a noise intensity and a noise distribution range. The privacy protection degree of the cooling demand is analyzed based on the noise data, and the privacy protection error is analyzed according to the true distribution of the cooling demand data. The security of the cooling demand data is determined by integrating the privacy protection degree and the privacy protection error.

[0014] In a preferred embodiment, the global energy efficiency optimization unit activates the privacy protection mechanism when it receives the processing signal transmitted by the cooling demand acquisition unit; When it receives the processing signal transmitted by the intelligent allocation decision unit, it adjusts the cooling allocation strategy; When it receives the processing signal transmitted by the privacy protection encryption unit, it corrects the system operation parameters according to the security of the cooling demand data.

[0015] In a preferred embodiment, when the global energy efficiency optimization unit adjusts the system operation parameters, it adjusts the compressor frequency, fan speed, and coolant flow rate of the refrigeration equipment according to the cooling allocation strategy.

[0016] Technical effects and advantages of the present invention: By introducing a distributed game model constructed based on the cooling demand difference and environmental parameters, the present invention realizes the dynamic balance and intelligent allocation of cooling among multiple regions. The truncated Gaussian mechanism is used to encrypt the cooling demand data, which ensures the privacy and security of user environmental data without affecting the scheduling accuracy. By integrating the cooling scheduling strategies and operation status data of different regions, a system-level objective function is constructed and jointly optimized, and the mapping relationship between environmental characteristics and cooling characteristics is continuously updated, which can dynamically adapt to the load models and control objectives in different scenarios, improve the versatility and flexibility of the system, and enhance the engineering practicability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the construction and optimization process of the distributed game model in the multi-environment adaptive refrigeration control system based on artificial intelligence of the present invention.

[0018] Figure 2 It is a structural block diagram of the multi-environment adaptive refrigeration control system based on artificial intelligence of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention. Embodiment

[0020] The present invention provides a multi-environment adaptive refrigeration control system based on artificial intelligence, and its structure mainly includes a cooling demand acquisition unit, an intelligent allocation decision-making unit, a privacy protection encryption unit, and a global energy efficiency optimization unit.

[0021] These units are connected by a high-speed communication bus for signal connection and data transmission, as Figure 1 shown. The cooling demand acquisition unit is located at the front end of the system and is responsible for collecting the cooling demand data and environmental parameter data of each area, and classifying the high-temperature demand areas as Class I areas and the low-temperature demand areas as Class II areas according to the target temperature.

[0022] The intelligent allocation decision-making unit is connected to the cooling demand acquisition unit, receives the classified cooling demand data and environmental parameter data, analyzes the cooling demand difference, and constructs a distributed game model.

[0023] The privacy protection encryption unit is respectively connected to the cooling demand acquisition unit and the intelligent allocation decision-making unit, encrypts the data that needs to be protected, and then transmits it to the global energy efficiency optimization unit.

[0024] The global energy efficiency optimization unit, as the core component at the backend of the system, receives the processing signals from other units and adjusts the system operation parameters.

[0025] The specific implementation method of the cooling demand acquisition unit is as follows: This unit includes multiple sensor nodes, which are used to collect the target temperature, humidity range, heat load coefficient, and cooling demand data in real time, and record the environmental parameter data of outdoor temperature, humidity, and wind speed at the same time.

[0026] The sensor nodes upload the data to the core processor of the cooling demand acquisition unit through the high-speed communication bus.

[0027] The core processor first classifies the cooling demand data to determine whether it is necessary to start the privacy protection mechanism.

[0028] Specifically, the process of determining whether it is necessary to start the privacy protection mechanism is as follows: By collecting the difference between the set target temperature and the current temperature in the current scenario, the volume of the current scenario, and the acquisition frequency in the current scenario, normalizing them, and substituting them into the weighted formula to obtain the privacy sensitivity score of the current scenario; Compare the privacy sensitivity score of the current scenario with a preset sensitivity threshold. If the privacy sensitivity score of the current scenario is greater than or equal to the preset sensitivity threshold, activation is required. Conversely, if the privacy sensitivity score of the current scenario is less than the preset sensitivity threshold, the cooling demand data and environmental parameter data are directly transmitted to the intelligent allocation decision unit.

[0029] Among them, the methods of standardization include, but are not limited to, standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on non-linear mapping function. The application methods of standardization are not elaborated here; It should be noted that the preset sensitivity threshold is obtained by the experimenter through comprehensive analysis of the statistical distribution law of regional cooling demand characteristics in multiple typical application scenarios and the influence degree of user behavior patterns on the privacy leakage risk, which is not elaborated here; Furthermore, if activation is required, a marking signal is generated and sent to the privacy protection encryption unit through a high-speed communication bus; In practical applications, the cooling demand acquisition unit is usually deployed in various areas of the building complex, such as data center computer rooms, office areas, and laboratories, etc., to ensure comprehensive coverage of the cooling demands in different areas.

[0030] After receiving the cooling demand data and environmental parameter data, the intelligent allocation decision unit first compares the heat load coefficients in different areas to confirm the cooling demand differences, and combines the cooling demand differences and environmental parameter changes in multiple time periods into a demand change data set and an environmental change data set respectively.

[0031] Subsequently, the intelligent allocation decision unit constructs a distributed game model, and the specific steps are as Figure 2 shown.

[0032] First, combine the demand change data set and the environmental change data set into an input matrix X, and set the objective function y.

[0033] The input matrix X is divided into a training data set and a validation data set according to a certain proportion for subsequent model evaluation.

[0034] Secondly, in the model construction stage, define the objective function of the distributed game model, and use a hybrid quantum-classical optimization algorithm to accelerate model convergence.

[0035] The hybrid quantum-classical optimization algorithm dynamically adjusts the optimization path through the quantum annealing process combined with the adaptive step size strategy, significantly improving the solution efficiency.

[0036] Finally, in the model evaluation stage, calculate the objective function using the training data set and the validation data set respectively, adjust the weight coefficients, and select the optimal solution to compare with the preset allocation threshold to evaluate the rationality of cooling allocation.

[0037] After completing the above steps, the intelligent allocation decision unit sends the preliminary calculation results to the privacy protection encryption unit or the global energy efficiency optimization unit.

[0038] The core function of the privacy protection encryption unit is to encrypt the cooling demand data to prevent privacy risks caused by data leakage.

[0039] The specific implementation method is as follows: First, the privacy protection encryption unit standardizes the received cooling demand data to make it conform to the characteristics of the normal distribution.

[0040] Subsequently, the truncated Gaussian mechanism is used to generate noise data, and the noise intensity is dynamically adjusted by the truncated Gaussian mechanism to ensure that the noise distribution interval is reasonable and meets the privacy protection requirements.

[0041] The noise data includes the noise intensity and the noise distribution range. By analyzing the noise data, the privacy protection degree of the cooling demand data can be evaluated.

[0042] In addition, the privacy protection encryption unit also calculates the privacy protection error according to the true distribution of the cooling demand data, and determines the security of the cooling demand data by integrating the privacy protection degree and the privacy protection error.

[0043] After completing the encryption process, the privacy protection encryption unit transmits the noise data and the processing signal to the global energy efficiency optimization unit through the high-speed communication bus.

[0044] The global energy efficiency optimization unit is the core control module of the entire system, and is responsible for adjusting the system operation parameters according to the processing signals input from different units.

[0045] When receiving the processing signal input from the cooling demand acquisition unit, the global energy efficiency optimization unit activates the privacy protection mechanism; When receiving the processing signal input from the intelligent allocation decision unit, it adjusts the cooling distribution strategy; When receiving the processing signal input from the privacy protection encryption unit, it corrects the system operation parameters according to the security of the cooling demand data.

[0046] In actual operation, the global energy efficiency optimization unit optimizes the cooling distribution strategy by adjusting the compressor frequency, fan speed and coolant flow rate of the refrigeration equipment.

[0047] For example, for the high-temperature demand area, that is, the first-class area, the compressor frequency and the coolant flow rate are appropriately increased to increase the cooling capacity; For the low-temperature demand area, that is, the second-class area, the fan speed is reduced to reduce the energy consumption.

[0048] Meanwhile, the global energy efficiency optimization unit continuously monitors the deviation between the actual temperature and the target temperature in each area, and dynamically adjusts the optimization strategy according to the deviation value to ensure the minimization of temperature control fluctuations.

[0049] In actual application scenarios, this system can be deployed in large commercial complexes or industrial plants.

[0050] For example, in a comprehensive building complex including a data center, an office area, and a laboratory, the cooling demand acquisition units are distributed in each area to collect cooling demand data and environmental parameter data in real time.

[0051] The intelligent allocation decision-making unit constructs a distributed game model based on the collected data and preliminarily calculates the cooling allocation strategy.

[0052] If sensitive data is involved, the privacy protection encryption unit encrypts it before transmitting it to the global energy efficiency optimization unit.

[0053] The global energy efficiency optimization unit adjusts the parameters of the refrigeration equipment according to the final cooling allocation strategy to ensure that the cooling demand in each area is met while reducing the overall energy consumption.

[0054] Through the above technical solutions, this system realizes the intelligent coordination and efficient allocation of multi-area cooling demands, improves the global energy efficiency and reduces the energy consumption, while effectively preventing the risk of leakage of cooling demand data.

[0055] To enable the relevant personnel in this technical field to fully understand and implement the present invention better, the specific implementation principle of the present invention is further supplemented and explained below in combination with a specific application scenario.

[0056] In a large commercial complex, the building includes multiple functional areas such as a data center, an office area, and a laboratory.

[0057] The cooling demands in each area vary significantly. For example, the data center requires a continuous low-temperature environment to ensure the operation of equipment, while the office area needs to dynamically adjust the cooling capacity according to the personnel density.

[0058] To meet these complex demands, this system uses the cooling demand acquisition unit to continuously monitor the cooling demand data such as the target temperature, humidity range, and heat load coefficient in each area, and records the environmental parameter data such as the outdoor temperature, humidity, and wind speed.

[0059] The sensor nodes upload the collected data to the core processor of the cooling demand acquisition unit, and the core processor classifies the high-temperature demand areas as type-one areas and the low-temperature demand areas as type-two areas according to the target temperature.

[0060] Subsequently, the classified cooling demand data and environmental parameter data are transmitted to the intelligent allocation decision-making unit for analysis and processing.

[0061] The intelligent allocation decision-making unit first compares the heat load coefficients in different regions, confirms the difference in cooling demand, and combines the differences in cooling demand over multiple time periods and the changes in environmental parameters into a demand change data set and an environmental change data set respectively.

[0062] On this basis, the intelligent allocation decision-making unit constructs a distributed game model, and its specific implementation steps are as follows: First, combine the demand change data set and the environmental change data set into an input matrix X, and set the objective function y; Secondly, divide the training data set and the validation data set in a certain proportion for subsequent model evaluation. In the model construction stage, after defining the objective function, a hybrid quantum-classical optimization algorithm is used to accelerate the model convergence.

[0063] The hybrid quantum-classical optimization algorithm dynamically adjusts the optimization path through the quantum annealing process combined with the adaptive step size strategy, thereby significantly improving the solution efficiency.

[0064] In the model evaluation stage, use the training data set and the validation data set to calculate the objective function respectively and adjust the weight coefficients, and select the optimal solution to compare with the preset allocation threshold to evaluate the rationality of the cooling allocation.

[0065] After completing the above steps, the intelligent allocation decision-making unit sends the preliminary calculation results to the privacy protection encryption unit or the global energy efficiency optimization unit.

[0066] If sensitive data is involved, the privacy protection encryption unit will encrypt the cooling demand data.

[0067] Specifically, the privacy protection encryption unit first standardizes the received cooling demand data to make it conform to the normal distribution characteristics.

[0068] Subsequently, the truncated Gaussian mechanism is used to generate noise data, and the noise intensity is dynamically adjusted by the truncated Gaussian mechanism to ensure that the noise distribution interval is reasonable and meets the privacy protection requirements.

[0069] Through the analysis of the noise data, the privacy protection degree of the cooling demand data can be evaluated. In addition, the privacy protection encryption unit also calculates the privacy protection error according to the true distribution of the cooling demand data, and determines the security of the cooling demand data by combining the privacy protection degree and the privacy protection error.

[0070] After completing the encryption process, the privacy protection encryption unit transmits the noise data and the processing signal to the global energy efficiency optimization unit through the high-speed communication bus.

[0071] The global energy efficiency optimization unit, as the core component at the backend of the system, is responsible for adjusting the system operation parameters according to the processing signals transmitted from different units.

[0072] When receiving the processing signal transmitted by the cooling demand acquisition unit, the global energy efficiency optimization unit activates the privacy protection mechanism; When receiving the processing signal transmitted by the intelligent allocation decision unit, adjust the cooling allocation strategy; When receiving the processing signal transmitted by the privacy protection encryption unit, correct the system operation parameters according to the security of the cooling demand data.

[0073] In actual operation, the global energy efficiency optimization unit optimizes the cooling allocation strategy by adjusting the compressor frequency, fan speed and coolant flow rate of the refrigeration equipment.

[0074] For example, for the high-temperature demand area, i.e., the first-class area, appropriately increase the compressor frequency and coolant flow rate to increase the cooling capacity; For the low-temperature demand area, i.e., the second-class area, reduce the fan speed to reduce energy consumption.

[0075] Meanwhile, the global energy efficiency optimization unit monitors the deviation between the actual temperature and the target temperature in each area in real time, and dynamically adjusts the optimization strategy according to the deviation value to ensure the minimum temperature control fluctuation.

[0076] In the above scenario, this system comprehensively covers the cooling demands of different areas through the cooling demand acquisition unit. The intelligent allocation decision unit realizes the intelligent coordination and efficient allocation of cooling demands based on the distributed game model. The privacy protection encryption unit effectively prevents the risk of leakage of cooling demand data. The global energy efficiency optimization unit ensures that the cooling demands of each area are met while reducing the overall energy consumption by dynamically adjusting the parameters of the refrigeration equipment.

[0077] Through the above technical solution, this system realizes the intelligent coordination and efficient allocation of multi-area cooling demands, improves the global energy efficiency and reduces the energy consumption, while meeting the requirements of modern multi-area refrigeration systems for high efficiency, intelligence and security.

[0078] The content not described in detail in the specification belongs to the prior art well-known to those skilled in the art, and the model parameters of each electrical appliance are not specifically limited, and conventional equipment can be used.

[0079] In this technical solution, since the electrical control components not mentioned belong to the prior art, they are not shown in the figure and will not be described here.

[0080] The above formulas are all dimensionless and take their numerical values for calculation. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0081] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0082] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0083] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0084] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0085] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0086] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0088] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0089] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

Claims

1. An artificial intelligence-based multi-environment adaptive refrigeration control system, characterized in that: It includes a cooling demand acquisition unit, an intelligent allocation decision-making unit, a privacy protection encryption unit, and a global energy efficiency optimization unit; The cooling demand acquisition unit is used to collect cooling demand data and environmental parameter data, classify each region according to the cooling demand data, and determine whether to activate the privacy protection mechanism. If activation is required, it will transmit a marking signal to the privacy protection encryption unit. Otherwise, it will transmit the cooling demand data and environmental parameter data to the intelligent allocation decision-making unit together; The intelligent allocation decision-making unit is used to analyze the cooling demand difference, construct a distributed game model by integrating the cooling demand difference and environmental parameter data, and perform preliminary calculations on the cooling allocation strategy through the distributed game model, and send the calculation results to the privacy protection encryption unit or the global energy efficiency optimization unit; The privacy protection encryption unit is used to encrypt the cooling demand data, generate noise data by using the truncated Gaussian mechanism, and transmit the encrypted data and processing signals to the global energy efficiency optimization unit; The global energy efficiency optimization unit is used to adjust the system operation parameters according to the processing signals transmitted by different units.

2. The multi-environment adaptive refrigeration control system based on artificial intelligence according to claim 1, characterized in that: The cooling demand data includes the target temperature, humidity range, and heat load coefficient, and the environmental parameter data includes the outdoor temperature, humidity, and wind speed, where the target temperature is the expected temperature value set within the region.

3. The multi-environment adaptive refrigeration control system based on artificial intelligence according to claim 2, characterized in that: The cooling demand acquisition unit classifies each region according to the cooling demand data, that is, classifies the high-temperature demand regions as type I regions according to the target temperature, and classifies the low-temperature demand regions as type II regions.

4. The multi-environment adaptive refrigeration control system based on artificial intelligence according to claim 3, characterized in that: The privacy protection mechanism interferes with the true distribution of the cooling demand data by introducing random noise, and the noise intensity is dynamically adjusted by the truncated Gaussian mechanism.

5. The multi-environment adaptive refrigeration control system based on artificial intelligence according to claim 2, characterized in that: The intelligent allocation decision-making unit compares the heat load coefficients of different regions to confirm the cooling demand difference, and constructs a distributed game model by recording the cooling demand difference and environmental parameter changes within multiple time periods and merging them into a demand change data set and an environmental change data set respectively.

6. The multi-environment adaptive refrigeration control system based on artificial intelligence according to claim 5, characterized in that: The specific steps for the intelligent allocation decision-making unit to construct a distributed game model are as follows: Data preparation: Merge the demand change data set and the environmental change data set into an input matrix X, set the objective function as y, and set a ratio to divide the input matrix into a training data set and a validation data set; Model construction: Define the objective function of the distributed game model, and use a hybrid quantum-classical optimization algorithm to accelerate model convergence; Model evaluation: Calculate the objective function using the training data set and the validation data set respectively, and adjust the weight coefficients of the objective function according to the calculation results; Evaluate the rationality of cooling allocation: Select the optimal solution in the calculated objective function and compare it with the preset allocation threshold to evaluate the rationality of cooling allocation.

7. The multi - environment adaptive refrigeration control system based on artificial intelligence according to claim 4, wherein: When the privacy - protection encryption unit encrypts the cooling demand data, it sets a noise distribution interval, first standardizes the cooling demand data, and when the standardized data conforms to the characteristics of a normal distribution, it uses the truncated Gaussian mechanism to generate noise - added data.

8. The multi - environment adaptive refrigeration control system based on artificial intelligence according to claim 7, wherein: The noise - added data in the privacy - protection encryption unit includes noise intensity and noise distribution range. The privacy - protection degree of the cooling demand is analyzed according to the noise - added data, and the privacy - protection error is analyzed according to the true distribution of the cooling demand data. The security of the cooling demand data is determined by comprehensively considering the privacy - protection degree and the privacy - protection error.

9. The multi - environment adaptive refrigeration control system based on artificial intelligence according to claim 2, wherein: The global energy - efficiency optimization unit activates the privacy - protection mechanism when receiving the processing signal transmitted by the cooling demand acquisition unit; Adjusts the cooling distribution strategy when receiving the processing signal transmitted by the intelligent allocation decision unit; When receiving the processing signal transmitted by the privacy - protection encryption unit, corrects the system operation parameters according to the security of the cooling demand data.

10. The multi - environment adaptive refrigeration control system based on artificial intelligence according to claim 9, wherein: When the global energy - efficiency optimization unit adjusts the system operation parameters, it adjusts the compressor frequency, fan speed, and coolant flow rate of the refrigeration equipment according to the cooling distribution strategy.

Images