Global optimization method and device for energy efficiency of air conditioning system, electronic equipment and storage medium

Abstract

The invention discloses a data center air conditioning system energy efficiency global optimization method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining data center outdoor meteorological parameters and thermal environment characteristic data of each machine room, generating a plurality of cooperative operation parameter combinations of air conditioning terminal systems and cold source systems, on the basis of a preset air-water heat exchange model and a preset constraint condition, feasibility verification is carried out on the cooperative operation parameter combination to construct a feasible cooperative operation parameter combination set; and taking the condition that the total energy consumption of the air conditioning system meets the preset condition as an optimization target, performing global search on the feasible collaborative operation parameter combination set by adopting a preset optimization algorithm, determining an optimal global operation parameter combination, and dynamically adjusting the hydraulic balance of the air conditioning system based on the optimal global operation parameter combination so as to realize the global optimization of the energy efficiency of the air conditioning system. Operation energy consumption of the data center air conditioning system can be effectively reduced, and therefore the overall energy efficiency of the air conditioning system can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and apparatus for global optimization of energy efficiency in an air conditioning system, as well as electronic equipment and storage media. Background Technology

[0002] With the rapid development of information technologies such as cloud computing and big data, data centers, as the core hubs for information processing and storage, are experiencing a continuous increase in scale and computing power, leading to a sharp rise in overall power consumption. In the total energy consumption of data centers, the air conditioning system, as a key infrastructure ensuring stable equipment operation, plays a crucial role in heat dissipation, ensuring the normal operation of information technology (IT) equipment, and maintaining a suitable indoor temperature and humidity environment. Its energy consumption is particularly prominent, typically accounting for 30%-50% of the total power consumption of a data center, making it one of the core factors restricting the improvement of data center energy efficiency. Existing data center air conditioning systems mainly consist of three core parts: a chilled water system, a chilled water / cooling water network, and air conditioning terminal systems. The chilled water system is responsible for producing cooling capacity; the chilled water / cooling water network is responsible for transporting the low-temperature chilled water produced by the chilled water system to the air conditioning terminal systems within the computer room, and returning the returned water after absorbing heat from the computer room environment to the chilled water system for reprocessing; the air conditioning terminal systems mainly achieve heat dissipation and cooling of IT equipment such as servers through heat exchange with the computer room environment.

[0003] Currently, when optimizing the energy efficiency of data center air conditioning systems, the chilled water system and the air conditioning terminal system are typically optimized separately as independent subsystems. However, there is a strong coupling relationship between the two in the energy transfer process: the heat exchange demand of the air conditioning terminal system directly determines the cooling load and water supply parameters of the chilled water system, while the temperature and flow rate of the chilled water provided by the chilled water system, in turn, restricts the heat dissipation capacity of the air conditioning terminal system. Optimizing them independently can easily lead to conflicting control objectives. For example, the chilled water system tends to provide higher temperatures of chilled water to improve the energy efficiency of the main unit, while the air conditioning terminal system tends to use lower supply air temperatures to ensure the heat dissipation safety of IT equipment, thus requiring lower supply water temperatures. This inconsistency in objectives makes it difficult for the air conditioning system to simultaneously meet the optimization needs of both systems, limiting further reductions in overall energy consumption and resulting in lower overall energy efficiency of the air conditioning system. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for global energy efficiency optimization of air conditioning systems. Its main purpose is to improve the overall energy efficiency of air conditioning systems.

[0005] According to a first aspect of the present invention, a method for global energy efficiency optimization of an air conditioning system is provided, comprising: Acquire outdoor meteorological parameters of the data center and thermal environment characteristics of each computer room; Based on the outdoor meteorological parameters and the thermal environment characteristic data, multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems are generated. Based on the preset air-water heat exchange model and the preset constraints including air-water heat exchange matching constraints, the feasibility of the collaborative operation parameter combination is verified in order to construct a set of feasible collaborative operation parameter combinations. The air-water heat exchange model is used for the air-water heat exchange between the indoor circulating air of the computer room and the chilled water of the cold source system. With the goal of ensuring that the total energy consumption of the air conditioning system meets the preset conditions, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operation parameter combinations to determine the optimal global operation parameter combination. Based on the optimal combination of global operating parameters, the chilled water pipe network of the air conditioning system is dynamically adjusted to achieve global optimization of the energy efficiency of the air conditioning system.

[0006] Optionally, the step of generating multiple combinations of coordinated operation parameters for air conditioning terminal systems and cold source systems based on the outdoor meteorological parameters and the thermal environment characteristic data includes: Based on the outdoor meteorological parameters and the thermal environment characteristic data, the cooling load requirements of each computer room are determined. Based on the cooling load demand and the preset air supply prediction model, multiple candidate combinations of air supply parameters for air conditioning terminals are generated. For any candidate combination of air supply parameters, based on the cooling load demand and the preset energy consumption model of the cooling source system, determine the matching combination of cooling operation parameters of the cooling source system. Any candidate air supply parameter combination is paired with its matching cooling operation parameter combination to form multiple coordinated operation parameter combinations.

[0007] Optionally, the step of generating multiple candidate combinations of air conditioning terminal air supply parameters based on the cooling load demand and a preset air supply prediction model includes: Obtain the airflow organization characteristics of each computer room; The cooling load demand and the airflow organization characteristics are input into a preset air supply prediction model, and multiple candidate combinations of air supply parameters for air conditioning terminals are generated under the condition of satisfying preset air supply parameter constraints. The process of determining the matching combination of cooling operation parameters for the cooling source system based on the cooling load demand and the preset energy consumption model of the cooling source system includes: The total cooling load of the data center is obtained by summarizing the cooling load requirements of each computer room. For any candidate combination of air supply parameters, based on the total cooling load and the preset energy consumption model of the cooling source system, a matching combination of cooling operation parameters for the cooling source system is determined.

[0008] Optionally, the method further includes: Based on the historical air supply operation parameters of each air conditioning terminal, a preset air conditioning terminal energy consumption model is constructed; Based on the historical air supply operation parameter combination, parameter identification is performed on the neural network model to be trained in order to construct the preset air supply prediction model.

[0009] Optionally, the preset cold source system energy consumption model includes: energy consumption models for multiple cold source equipment such as refrigeration units, chilled water pumps, cooling water pumps, and cooling towers. Before determining the combination of cooling operation parameters of the cold source system based on the cooling load demand and the preset cold source system energy consumption model, the method further includes: Based on the historical cooling operation parameters of the cold source system, parameter identification is performed on the energy consumption models of multiple cold source devices to construct a preset cold source system energy consumption model that reflects the energy consumption characteristics of each cold source device. The step of determining the combination of cooling operation parameters for the cold source system based on the cooling load demand and the preset energy consumption model of the cold source system includes: The total cooling load of the data center is obtained by summarizing the cooling load requirements of each computer room. Using the total cooling load demand and outdoor meteorological parameters as input, and under the premise of meeting the operating constraints of the cold source equipment and ensuring that the cooling capacity of the cold source system is not lower than the total cooling load demand, the preset cold source system energy consumption model is invoked to generate the cooling operation parameter combination of the cold source system.

[0010] Optionally, the preset constraints include: system-level coupling constraints, which include air-water heat exchange matching constraints, cooling capacity supply and demand balance constraints, and chilled water flow conservation constraints. The feasibility verification of the coordinated operation parameter combinations based on the preset air-water heat exchange model and the preset constraints including the air-water heat exchange matching constraints, to construct a set of feasible coordinated operation parameter combinations, includes: For any set of coordinated operation parameters, based on the preset air-water heat exchange model, calculate the total air-side heat exchange of the air conditioning terminal system and the sum of the heat exchange of each air conditioning terminal. Calculate the sum of chilled water flow rates allocated to each air conditioning terminal, the total water-side heat exchange of the cold source system, the total cooling capacity, and the total chilled water supply flow rate; Verify whether the wind-side heat exchange and the total water-side heat exchange satisfy the wind-water heat exchange constraint; Verify whether the sum of the total cooling capacity and the heat exchange capacity of each air conditioning terminal meets the cooling supply and demand balance constraint; Verify whether the sum of the total chilled water supply flow rate and the flow rate allocated to each air conditioning terminal satisfies the chilled water flow rate conservation constraint; If each verification result is passed, then any of the collaborative operation parameter combinations will be included in the set of feasible collaborative operation parameter combinations.

[0011] Optionally, the preset energy consumption condition is to minimize the total energy consumption of the air conditioning system. The optimization objective is to use a preset optimization algorithm to perform a global search on the combination of coordinated operating parameters to determine the global operating parameter combination, including: The adjustable parameters in the combination of collaborative operation parameters are used as optimization decision variables; Construct the objective function for the total energy consumption of the air conditioning system; Multiple candidate solutions are generated in the decision variable space using a preset optimization algorithm, and the total energy consumption of the air conditioning system corresponding to each candidate solution is calculated based on the objective function. At the same time, it is verified whether they meet the preset constraints. The global optimal solution is updated based on the total energy consumption of the air conditioning system corresponding to each candidate solution. When the convergence condition is met, the candidate solution with the minimum total energy consumption of the air conditioning system and the preset constraint condition is output as the optimal global operating parameter combination.

[0012] Optionally, the total energy consumption of the air conditioning system includes the energy consumption of the air conditioning terminal and the energy consumption of the cold source system; the step of generating multiple candidate solutions in the decision variable space using a preset optimization algorithm, calculating the total energy consumption of the air conditioning system corresponding to each candidate solution based on the objective function, and verifying whether it satisfies the preset constraints includes: Multiple candidate solutions are generated in the decision variable space using a pre-defined optimization algorithm; For each candidate solution, a preset cold source system energy consumption model is invoked, and the corresponding cold source system energy consumption is calculated based on the cooling operation parameters therein; and a preset air conditioning terminal energy consumption model is invoked, and the corresponding air conditioning terminal energy consumption is calculated based on the air supply parameters therein; Add the energy consumption of the air conditioning terminal to the energy consumption of the cold source system to obtain the total energy consumption of the air conditioning system corresponding to the candidate solution; Verify whether the candidate solution satisfies the preset constraints, which include device operation constraints and system-level coupling constraints.

[0013] Optionally, the step of dynamically adjusting the hydraulic balance of the air conditioning system based on the optimal global operating parameter combination to achieve global optimization of the energy efficiency of the air conditioning system includes: Based on the chilled water demand parameters of each air conditioning terminal and the topology of the chilled water network in the optimal global operating parameter combination, the predicted chilled water parameter values ​​of each pipeline node in the network are deduced. The predicted chilled water parameter values ​​are compared with the actual monitoring values, and the opening degree of each level of hydraulic balancing device in the pipeline network and the operating parameters of the chilled water pumps are dynamically adjusted based on the comparison results.

[0014] According to a second aspect of the present invention, an air conditioning system energy efficiency global optimization device is provided, comprising: The acquisition module is configured to acquire thermal environment characteristic data of each computer room in the data center. The generation module is configured to generate multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems based on the thermal environment characteristic data. The construction module is configured to perform feasibility verification on the combination of collaborative operation parameters based on a preset air-water heat exchange model and preset constraint conditions including air-water heat exchange matching constraints, so as to construct a set of feasible collaborative operation parameter combinations. The preset air-water heat exchange model is used for air-water heat exchange between the indoor circulating air of the computer room and the chilled water of the cold source system. The determination module is configured to use a preset optimization algorithm to perform a global search on the set of feasible collaborative operation parameter combinations, with the optimization objective being that the total energy consumption of the air conditioning system meets preset conditions, and to determine the optimal global operation parameter combination. The optimization module is configured to dynamically adjust the hydraulic balance of the air conditioning system based on the optimal combination of global operating parameters, so as to achieve global optimization of the energy efficiency of the air conditioning system.

[0015] Optionally, the generation module includes: The determination submodule is configured to determine the cooling load requirements of each computer room based on the outdoor meteorological parameters and the thermal environment characteristic data. The generation submodule is configured to generate multiple candidate combinations of air conditioning terminal air supply parameters based on the cooling load demand and the preset air supply prediction model. The determining submodule is configured to determine the matching cooling operation parameter combination of the cooling source system based on the cooling load demand and the preset cooling source system energy consumption model for any candidate air supply parameter combination. The pairing submodule is configured to pair any candidate air supply parameter combination with its matching cooling operation parameter combination to form multiple coordinated operation parameter combinations.

[0016] Optionally, the generation submodule is specifically configured to acquire the airflow organization characteristics of each computer room; input the cooling load demand and the airflow organization characteristics into a preset air supply prediction model, and generate multiple candidate air supply parameter combinations for air conditioning terminals under the condition of satisfying preset air supply parameter constraints. The determining submodule is configured to aggregate the cooling load requirements of each computer room to obtain the total cooling load of the data center; For any candidate combination of air supply parameters, based on the total cooling load and the preset energy consumption model of the cooling source system, a matching combination of cooling operation parameters for the cooling source system is determined.

[0017] Optionally, the construction module is further configured to construct a preset air conditioning terminal energy consumption model based on the historical air supply operation parameters of each air conditioning terminal; and to perform parameter identification on the neural network model to be trained based on the combination of the historical air supply operation parameters in order to construct the preset air supply prediction model.

[0018] Optionally, the preset cold source system energy consumption model includes: multiple cold source equipment energy consumption models corresponding to refrigeration units, chilled water pumps, cooling water pumps and cooling towers. The constructed module is also configured to identify parameters of multiple cold source equipment energy consumption models based on the historical cooling operation parameters of the cold source system, and construct a preset cold source system energy consumption model that reflects the energy consumption characteristics of each cold source equipment. The determination submodule is configured to summarize the cooling load requirements of each computer room to obtain the total cooling load of the data center; taking the cooling load requirements and outdoor meteorological parameters as input, and under the premise of meeting the operating constraints of the cold source equipment and ensuring that the cooling capacity of the cold source system is not lower than the total cooling load requirements, the module calls the preset cold source system energy consumption model to generate the cooling operation parameter combination of the cold source system.

[0019] Optionally, the preset constraints include: system-level coupling constraints, which include air-water heat exchange matching constraints, cooling supply and demand balance constraints, and chilled water flow conservation constraints. The construction module is also specifically configured to calculate the total air-side heat exchange of the air conditioning terminal system and the sum of the heat exchange of each air conditioning terminal for any group of coordinated operation parameters based on the preset air-water heat exchange model. Calculate the sum of chilled water flow rates allocated to each air conditioning terminal, the total water-side heat exchange of the cold source system, the total cooling capacity, and the total chilled water supply flow rate; verify whether the air-side heat exchange and the total water-side heat exchange satisfy the air-water heat exchange constraint; verify whether the total cooling capacity and the sum of the heat exchange of each air conditioning terminal satisfy the cooling capacity supply-demand balance constraint; verify whether the total chilled water supply flow rate and the sum of the flow rates allocated to each air conditioning terminal satisfy the chilled water flow rate conservation constraint; if all verification results are passed, then any combination of collaborative operation parameters is included in the feasible collaborative operation parameter combination set.

[0020] Optionally, the preset energy consumption condition is to minimize the total energy consumption of the air conditioning system, and the determining module includes: The adjustment submodule is configured to use adjustable parameters from feasible combinations of collaborative operation parameters as optimization decision variables. The submodule is configured to construct the objective function for the total energy consumption of the air conditioning system. The optimization submodule is configured to generate multiple candidate solutions in the decision variable space using a preset optimization algorithm, calculate the total energy consumption of the air conditioning system corresponding to each candidate solution based on the objective function, and verify whether it meets the preset constraints. The output submodule is configured to update the global optimal solution based on the total energy consumption of the air conditioning system corresponding to each candidate solution, and when the convergence condition is met, output the candidate solution with the minimum total energy consumption of the air conditioning system and that satisfies the preset constraint condition as the optimal global operating parameter combination.

[0021] Optionally, the total energy consumption of the air conditioning system includes the energy consumption of the air conditioning terminal and the energy consumption of the cold source system; the optimization submodule is specifically configured to generate multiple candidate solutions in the decision variable space using a preset optimization algorithm; for each candidate solution, call a preset cold source system energy consumption model and calculate the corresponding cold source system energy consumption based on the cooling operation parameters therein; and call a preset air conditioning terminal energy consumption model and calculate the corresponding air conditioning terminal energy consumption based on the air supply parameters therein; add the air conditioning terminal energy consumption and the cold source system energy consumption to obtain the total energy consumption of the air conditioning system corresponding to the candidate solution; verify whether the candidate solution meets preset constraints, the preset constraints including equipment operation constraints and system-level coupling constraints.

[0022] Optionally, the optimization module is specifically configured to deduce the predicted chilled water parameter values ​​of each pipeline node in the network based on the chilled water demand parameters of each air conditioning terminal and the topology of the chilled water network in the global operating parameter combination; compare the predicted chilled water parameter values ​​with the actual monitoring values; and dynamically adjust the opening degree of each level of hydraulic balancing device and the operating parameters of the chilled water pump in the network based on the comparison results.

[0023] According to a third aspect of the present invention, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0024] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0025] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0026] The present invention provides a method, apparatus, electronic device, and storage medium for global energy efficiency optimization of data center air conditioning systems. By acquiring thermal environment characteristic data of each computer room in the data center, multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems are generated. Based on a preset air-water heat exchange model and preset constraints including air-water heat exchange matching constraints, the feasibility of the collaborative operation parameter combinations is verified to construct a set of feasible collaborative operation parameter combinations. This ensures that the air side of the air conditioning terminal system and the water side of the cold source system are coordinated and consistent in terms of cooling capacity, flow rate, and heat exchange capacity, avoiding capacity redundancy or insufficient cooling caused by decoupling of the air conditioning system. Meanwhile, with the goal of meeting the preset conditions for total energy consumption of the air conditioning system, a preset optimization algorithm is used to perform a global search on the set of feasible collaborative operation parameter combinations to determine the optimal global operation parameter combination. This overcomes the limitations of existing technologies that rely on local optimization or parameter adjustment of the cold source system or air conditioning terminal system. In other words, under the premise of meeting preset constraints, including air-water heat exchange matching constraints, the hydraulic balance of the air conditioning system can be dynamically adjusted, thereby coordinating the linkage and collaborative operation between the air supply of the air conditioning terminal and the cooling supply of the cold source system. Therefore, controlling the operation of the air conditioning system based on the optimal global operation parameter combination can ensure the stability of the heat exchange system of the entire air conditioning system, achieve global energy efficiency optimization of the air conditioning system, and achieve the goal of global energy efficiency optimization of the air conditioning system. This can effectively reduce the operating energy consumption of the data center air conditioning system and improve the overall energy efficiency of the air conditioning system.

[0027] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0028] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of the invention. Wherein: Figure 1 A framework diagram of a data center air conditioning system; Figure 2 This is a flowchart illustrating a global energy efficiency optimization method for an air conditioning system provided in an embodiment of the present invention. Figure 3 A schematic diagram illustrating another process for global energy efficiency optimization of an air conditioning system provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an air conditioning system energy efficiency global optimization device provided in an embodiment of the present invention; Figure 5 A schematic block diagram of an example electronic device 400 provided for an embodiment of the present invention. Detailed Implementation

[0029] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0030] With the rapid development of information technologies such as cloud computing and big data, data centers, as the core hubs for information processing and storage, are experiencing a continuous increase in scale and computing power, leading to a sharp rise in overall power consumption. In the total energy consumption of data centers, the air conditioning system, as a key infrastructure ensuring stable equipment operation, plays a crucial role in heat dissipation, ensuring the normal operation of IT equipment, and maintaining a suitable temperature and humidity environment. Its energy consumption is particularly prominent, typically accounting for 30%-50% of the total power consumption of a data center, making it one of the core factors restricting the improvement of data center energy efficiency. Existing data center air conditioning systems mainly consist of three core parts: a chilled water system, a chilled water / cooling water network, and air conditioning terminal systems. The chilled water system is responsible for producing cooling capacity; the chilled water / cooling water network transports the low-temperature chilled water produced by the chilled water system to the air conditioning terminal systems within the computer room, and returns the returned water, after absorbing heat from the computer room environment, to the chilled water system for reprocessing; the air conditioning terminal systems primarily achieve heat dissipation and cooling of IT equipment such as servers through heat exchange with the computer room environment. Figure 1 The diagram shows the framework of a data center air conditioning system. Specifically, the cold source system includes chiller units, chilled water pumps, cooling water pumps, and cooling towers. The chilled water network consists of supply pipes, manifolds / distributors, return pipes, valves, pumps, and corresponding pipe fittings. The cooling water network connects the condensers of the chiller units to the cooling towers. Through heat exchange between the cooling water and chilled water, the heat absorbed from the computer room environment and the heat generated during the operation of the chiller units are transferred to the cooling towers for dissipation. The cooled water is then returned to the condensers, forming a complete heat dissipation cycle. The air conditioning terminal system mainly includes precision air conditioners, cold aisle air conditioners, and other equipment in the computer room. Through heat exchange with the computer room environment, it achieves heat dissipation and cooling of IT equipment such as servers.

[0031] Currently, when optimizing the energy efficiency of data center air conditioning systems, the chilled water system and the air conditioning terminal system are typically optimized separately as independent subsystems. Specifically, based on collected data such as the computer room environment and air conditioning equipment operating parameters, the system proactively predicts subsequent operating conditions and system energy consumption, automatically seeks and distributes the optimal combination of operating parameters, dynamically optimizes the operating status of the chilled water system or the air conditioning terminal system, improves the energy efficiency of the chilled water system or the air conditioning terminal system, and thus reduces the energy consumption of the air conditioning system. However, there is a strong coupling relationship between the two in the energy transfer process: the heat exchange demand of the air conditioning terminal system directly determines the cooling load and water supply parameters of the chilled water system, while the temperature and flow rate of the chilled water provided by the chilled water system, in turn, restricts the heat dissipation capacity of the air conditioning terminal system. Optimizing them independently can easily lead to conflicting control objectives. For example, the chilled water system tends to provide higher temperatures of chilled water to improve the energy efficiency of the main unit, while the air conditioning terminal system tends to use lower supply air temperatures to ensure the heat dissipation safety of IT equipment, thus requiring lower supply water temperatures. This inconsistency in objectives makes it difficult for the air conditioning system to simultaneously meet the optimization needs of both systems, limiting further reductions in overall energy consumption and resulting in lower overall energy efficiency of the air conditioning system.

[0032] In other words, existing energy consumption optimization methods for data center air conditioning systems suffer from the following significant technical bottlenecks: Firstly, there is insufficient deep coordination between the cooling source system and the air conditioning terminal system in their optimization control. The cooling capacity adjustment of the cooling source system largely relies on preset local parameters such as outlet and return water temperatures, while the operation control of the air conditioning terminal system focuses on changes in temperature and humidity within the computer room. The two systems operate independently, lacking effective information exchange and linkage mechanisms, resulting in a "lone wolf" control mode. If this simple linkage control ignores the matching of air and water heat exchange, it may lead to a mismatch between the chilled water supply cooling capacity and the actual heat exchange demand on the indoor circulating air side. For example, excessive cooling capacity may result in energy waste, or insufficient cooling capacity may fail to meet heat dissipation requirements. This type of control mode cannot coordinate the entire process of cooling capacity production, transmission, and consumption from the perspective of the overall air conditioning system, making it difficult to achieve optimal global energy efficiency configuration and severely restricting the energy-saving optimization effect of the entire air conditioning system.

[0033] On the other hand, in the traditional optimization of air conditioning terminal systems, most optimization is achieved by controlling the air supply parameters of the terminal system (such as setting the air volume and supply air temperature), adjusting the start / stop status of the terminal equipment, and regulating the chilled water flow rate of the air conditioning terminals. However, the method of controlling the air supply air temperature by adjusting the chilled water flow rate at the terminals does not consider the impact of chilled water flow rate adjustment on the hydraulic balance of the entire chilled water network. When terminal equipment changes the flow rate by adjusting chilled water valves, it disrupts the original hydraulic balance within the network, potentially causing hydraulic imbalances such as the actual flow rate of some terminal equipment deviating from the design value (or expected adjustment value). This can lead to failure to meet the load demand, thereby affecting the heat exchange performance stability of the entire air conditioning system and even causing risks such as overheating in localized computer rooms.

[0034] Therefore, how to solve the overall low energy efficiency of existing data center air conditioning systems is an urgent technical problem to be solved in the field of data center air conditioning systems. How to solve the poor stability of existing data center air conditioning systems is also an urgent technical problem to be solved in the field of data center air conditioning systems. In particular, how to solve the low energy efficiency and poor stability of existing data center air conditioning systems is an urgent technical problem to be solved in the field of data center air conditioning systems.

[0035] Here, embodiments of the present invention provide a method, apparatus, electronic device and storage medium for global energy efficiency optimization of data center air conditioning systems, aiming to improve the energy efficiency and stability of data center air conditioning systems, and in particular, to improve the stability of data center air conditioning systems while improving their energy efficiency.

[0036] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for global energy efficiency optimization of a data center air conditioning system according to embodiments of the present invention.

[0037] Figure 2 This is a flowchart illustrating a global energy efficiency optimization method for an air conditioning system provided in an embodiment of the present invention.

[0038] like Figure 2 As shown, the method includes the following steps: Step 101: Obtain outdoor meteorological parameters of the data center and thermal environment characteristics of each computer room.

[0039] Outdoor meteorological parameters for data centers refer to a set of physical quantities describing the real-time or predicted atmospheric environmental conditions of the geographical location of the data center. In air conditioning system energy efficiency optimization, these parameters may include: dry-bulb temperature, wet-bulb temperature, relative humidity, atmospheric pressure, wind speed, wind direction, and solar radiation intensity. The thermal environment of a data center's server room is determined by factors such as the server room's spatial environment (e.g., size, dimensions, hot and cold aisle enclosure), the spatial relationship of IT equipment, the operating power of IT equipment, air conditioning type (room-level air conditioning, in-row air conditioning), and air conditioning supply and return air parameters (supply and return air temperature, air volume). Thermal environment characteristic data refers to a set of key parameters used to describe the internal thermal state and airflow characteristics of the data center server room. It accurately reflects the heat dissipation conditions and heat load distribution of IT equipment, providing input for subsequent air conditioning control, energy efficiency optimization, and thermal management. Specifically, the thermal environment characteristic data includes: the inlet air temperature and return air temperature of each server rack, the real-time power consumption of IT equipment, the relative humidity of the server room, and the spatial relationship between the air conditioning terminals and the server racks.

[0040] Step 102: Based on the outdoor meteorological parameters of the data center and the thermal environment characteristics of each computer room, generate multiple combinations of collaborative operation parameters for air conditioning terminal systems and cold source systems.

[0041] In this embodiment of the invention, step 102 calculates the amount of heat each computer room needs to dissipate based on outdoor meteorological parameters of the data center and thermal environment characteristics of each computer room, thus determining the cooling load requirement of each computer room. Preferably, the effectiveness of cooling capacity distribution can be evaluated by combining the spatial layout of air conditioning terminals and IT cabinets within the computer room, the closure of hot and cold aisles, and other airflow organization characteristics. Then, based on the cooling load requirements of each computer room, multiple air supply parameter combinations for air conditioning terminal systems are generated, and the cooling load requirements of all computer rooms are summarized to obtain the total cooling load of the data center. For each candidate air supply parameter combination, the cooling source system cooling operation parameter combination that can meet the total cooling load is calculated. Finally, each air conditioning terminal air supply parameter combination is paired with its matching cooling source system cooling operation parameter combination to form a complete "air conditioning terminal-cooling source" collaborative operation parameter combination. All pairing schemes that pass the preliminary feasibility verification constitute a set of feasible collaborative operation parameter combinations, providing a candidate solution space for subsequent energy efficiency assessment and global optimization.

[0042] It should be noted that each air supply parameter combination includes: on / off status, supply air temperature, return air temperature, and supply air volume. Each air supply parameter combination represents a feasible terminal operation strategy, which can achieve different airflow organization effects while ensuring that the cabinet inlet air temperature does not exceed the safety threshold. Cooling operation parameter combinations include the refrigeration unit start / stop status, chilled water pump frequency, cooling tower fan speed, etc.

[0043] Step 103: Based on the preset feng shui heat exchange model and preset constraints including feng shui heat exchange matching constraints, perform feasibility verification on the combination of collaborative operation parameters to construct a set of feasible collaborative operation parameter combinations.

[0044] It should be noted that for each combination of collaborative operation parameters generated in step 102, firstly, based on the air-water heat exchange model, the air-water heat exchange between the indoor circulating air of the computer room and the chilled water of the cold source system is calculated. Then, based on the air-water heat exchange and preset constraints including air-water heat exchange matching constraints, a constraint verification is performed to determine whether the air-water heat exchange matching constraints and various preset operation constraints are met. The preset constraints include, but are not limited to: thermal safety constraints such as the cabinet inlet air temperature not exceeding 27°C, operating limits of air conditioning and cold source equipment (such as fan frequency range, host start / stop status), and system-level coupling constraints (such as cooling supply and demand balance, chilled water flow conservation, air-water heat exchange matching, etc.).

[0045] Combinations that fail constraint verification are considered infeasible and are eliminated, not participating in subsequent energy consumption calculations. For feasible combinations that pass verification, the preset air conditioning terminal energy consumption model and the preset cooling source system energy consumption model are invoked respectively. Based on their air supply parameters (such as air supply temperature and air volume) and cooling parameters (such as host load, water pump frequency, and cooling tower operating status), the energy consumption of the air conditioning terminal system and the cooling source system are calculated separately, and the two are added together to obtain the total energy consumption of the air conditioning system corresponding to the combination. This total energy consumption value will serve as the core evaluation index for subsequent global optimization search, used to compare the energy efficiency of different collaborative operation strategies.

[0046] Step 104: With the goal of ensuring that the total energy consumption of the air conditioning system meets the preset conditions, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operation parameter combinations to determine the optimal global operation parameter combination.

[0047] In this embodiment of the invention, step 104 involves taking the feasible combinations of collaborative operating parameters calculated in step 103 and their corresponding total energy consumption of the air conditioning system as input, and setting the optimization objective as: the total energy consumption of the air conditioning system meets preset conditions. Subsequently, a preset optimization algorithm is invoked to perform a global traversal or intelligent search on all feasible solutions in the set of feasible collaborative operating parameter combinations. During the search process, total energy consumption is used as the evaluation index to comprehensively compare the energy efficiency performance of each combination, and finally, the collaborative operating parameter combination with the lowest total energy consumption and that satisfies all constraints is selected as the optimal global operating parameter combination.

[0048] The preset optimization algorithm can be an exhaustive comparison method, genetic algorithm, particle swarm optimization, or other search strategies suitable for the discrete solution space; this embodiment of the invention is not limited thereto. The optimal combination of global operating parameters can completely define the coordinated operating state of the air conditioning terminal system and the cooling source system, including key control variables such as air supply parameters, main unit start / stop, and water pump frequency, providing precise instructions for subsequent system control execution.

[0049] Step 105: Based on the optimal combination of global operating parameters, dynamically adjust the hydraulic balance of the air conditioning system to achieve global optimization of the air conditioning system's energy efficiency.

[0050] Energy efficiency optimization can refer to reducing the total energy consumption of the air conditioning system and improving the overall power utilization efficiency. Global energy efficiency optimization means optimizing the entire air conditioning system, rather than just adjusting a single fan or main unit.

[0051] In this embodiment of the invention, based on the optimal global operating parameter combination, the data center automatic control system can issue corresponding operating parameter instructions to the air conditioning terminal equipment and the cold source system, including supply air temperature, fan frequency, host start / stop status and water pump operating frequency, to drive the air conditioning system to operate according to the optimal energy efficiency collaborative strategy, thereby achieving global optimization of the air conditioning system's energy efficiency.

[0052] The data center air conditioning system energy efficiency global optimization method provided in this invention obtains thermal environment characteristic data of each computer room in the data center; generates multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems; and performs feasibility verification on the combinations of collaborative operation parameters based on a preset air-water heat exchange model and preset constraints including air-water heat exchange matching constraints, so as to construct a set of feasible collaborative operation parameter combinations. This can ensure that the air side of the air conditioning terminal system and the water side of the cold source system are coordinated and consistent in terms of cooling capacity, flow rate and heat exchange capacity, and avoid capacity redundancy or insufficient cooling caused by system decoupling. Simultaneously, under the condition of meeting preset constraints, the total energy consumption of the air conditioning system corresponding to each combination of coordinated operating parameters can be calculated. Taking the total energy consumption of the air conditioning system meeting the preset conditions as the optimization objective, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operating parameter combinations to determine the optimal global operating parameter combination. This can overcome the limitations of existing technologies that optimize or adjust parameters locally in the cold source system or air conditioning terminal system. That is, under the premise of meeting the preset constraints, the hydraulic balance of the air conditioning system can be dynamically adjusted, thereby coordinating the linkage and coordinated operation between the air supply of the air conditioning terminal and the cooling supply of the cold source system. Therefore, controlling the operation of the air conditioning system based on the optimal global operating parameter combination can ensure the stability of the heat exchange system of the entire air conditioning system, realize the global optimization of the energy efficiency of the air conditioning system, achieve the goal of global energy efficiency optimization of the air conditioning system, thereby effectively reducing the operating energy consumption of the data center air conditioning system and improving the overall energy efficiency of the air conditioning system.

[0053] Figure 3 This is a flowchart illustrating a global energy efficiency optimization method for an air conditioning system provided in an embodiment of the present invention.

[0054] like Figure 3 As shown, the method includes the following steps: Step 201: Obtain outdoor meteorological parameters of the data center and thermal environment characteristics of each computer room.

[0055] The thermal environment characteristic data has been described in detail in step 101 and will not be repeated here.

[0056] Step 202: Based on the outdoor meteorological parameters of the data center and the thermal environment characteristics of each computer room, determine the cooling load requirements of each computer room.

[0057] For this embodiment of the invention, the thermal environment characteristic data obtained in step 201 can be analyzed first to extract the real-time operating power of IT equipment in each computer room. Combined with the equipment heating efficiency model, the heat that each computer room currently needs to dissipate, i.e., the cooling load demand, can be calculated. Simultaneously, the physical layout information of each computer room can be obtained from the data center infrastructure information database or space configuration database, including the relative positions of air conditioning terminals and IT cabinets, whether cold / hot aisles are closed, floor air supply opening ratio, blind flange installation status, etc., forming airflow organization characteristics describing the efficiency of cooling load distribution. The cooling load demand reflects how much cooling is needed. The cooling load can be the heat that the air conditioning system must remove to maintain the thermal environment safety of the computer room (e.g., cabinet inlet air temperature ≤ 27℃), which is mainly converted from the electrical energy of IT equipment. The airflow organization characteristics reflect "how the cooling is effectively delivered," describing the path efficiency of how cold air flows and covers the heat source after being delivered from the air conditioner. The cooling load demand of each computer room can be used as the basic input for subsequent air supply strategy generation and system co-optimization. Alternatively, both can constitute the basic input for subsequent air supply strategy generation and system co-optimization.

[0058] Step 203: Based on the cooling load demand of each computer room and the preset air supply prediction model, generate multiple candidate combinations of air supply parameters for air conditioning terminals.

[0059] In an optional embodiment of the present invention, the method further includes: performing parameter identification on the neural network model to be trained based on the historical air supply operation parameter combination, so as to construct the preset air supply prediction model.

[0060] In an optional embodiment of the present invention, generating multiple candidate combinations of air conditioning terminal air supply parameters based on the cooling load demand and a preset air supply prediction model includes: The cooling load demand is input into a preset air supply prediction model, and multiple candidate combinations of air supply parameters for air conditioning terminals are generated under the condition of satisfying preset air supply parameter constraints.

[0061] The specific constraints of the preset air supply parameters are as follows: (1) (2) (3) In the formula, The airflow temperature at the rack inlet is ℃; Let m³ / h be the air supply volume of the j-th air conditioning terminal in the i-th computer room. and Let be the upper and lower limits of the air supply volume of the j-th air conditioning terminal in the i-th computer room, in m³ / h; Let be the load (kW) borne by the j-th air conditioning terminal in the i-th computer room; and Let represent the lower limit of cooling capacity and the rated cooling load of the j-th air conditioning terminal in the i-th computer room, in kW.

[0062] The preset air supply prediction model is as follows: (4) In the formula, air density, kg / m³; is the specific heat capacity of air, kJ / (kg·℃); , These are the return air temperature and supply air temperature of the j-th air conditioning terminal in the i-th computer room, respectively.

[0063] In other words, it can generate multiple candidate combinations of air supply parameters for the air conditioning terminal. , , Based on any candidate combination of air supply parameters , , With a preset energy consumption model for the air conditioning terminal system, the total energy consumption of the air conditioning terminal system can be calculated.

[0064] The specific energy consumption model for the pre-set air conditioning terminal system is as follows: (5) In the formula, The total energy consumption of the air conditioning terminal system is expressed in kWh. Let be the energy consumption of the j-th air conditioning terminal in the i-th computer room, in kW; Let be the rated power consumption of the j-th air conditioning terminal in the i-th computer room; Let be the rated air volume of the j-th air conditioning terminal in the i-th computer room.

[0065] It should be noted that the cooling load demand and the airflow organization characteristics are also input into the preset air supply prediction model, and multiple candidate combinations of air supply parameters for the air conditioning terminal are generated under the condition of satisfying the preset air supply parameter constraints.

[0066] Step 204: For any candidate air supply parameter combination, determine the matching cooling operation parameter combination of the cooling source system based on the cooling load demand and the preset energy consumption model of the cooling source system.

[0067] In an optional embodiment of the present invention, based on the cooling load demand and a preset energy consumption model of the cooling source system, a matching combination of cooling operation parameters for the cooling source system is determined, including: The total cooling load of the data center is obtained by summarizing the cooling load requirements of each computer room. For any candidate combination of air supply parameters, based on the total cooling load and the preset energy consumption model of the cooling source system, a matching combination of cooling operation parameters for the cooling source system is determined.

[0068] It should be noted that the total cooling load of the data center can be obtained by aggregating the cooling load requirements of each server room, specifically including: (6) (7) in, The total cooling load of the entire data center The cooling load borne by the chiller unit is m, the total number of machine rooms is m, and the total number of air conditioning terminals in all machine rooms is n. The values ​​of m and n can be determined according to the actual project and are not limited.

[0069] In an optional embodiment of the present invention, the preset cold source system energy consumption model includes: energy consumption models for multiple cold source equipment such as refrigeration units, chilled water pumps, cooling water pumps, and cooling towers. Before determining the cooling operation parameter combination of the cold source system based on the total cooling load demand and the preset cold source system energy consumption model, the method further includes: Based on the historical cooling operation parameters of the cold source system, parameter identification is performed on the energy consumption models of multiple cold source devices to construct a preset cold source system energy consumption model that reflects the energy consumption characteristics of each cold source device. Correspondingly, determining the combination of cooling operation parameters for the cooling source system based on the total cooling load demand and the preset energy consumption model of the cooling source system includes: Using the total cooling load demand and outdoor meteorological parameters as input, and under the premise of meeting the operating constraints of the cold source equipment and ensuring that the cooling capacity of the cold source system is not lower than the total cooling load demand, the preset cold source system energy consumption model is invoked to generate the cooling operation parameter combination of the cold source system.

[0070] It should be noted that the preset energy consumption model for the cold source system is used to accurately calculate the actual energy consumption of the chiller units, chilled water pumps, cooling water pumps, and cooling towers under different operating conditions, providing fundamental support for the overall energy efficiency optimization of the data center air conditioning system. This model consists of four sub-models: the chiller unit energy consumption model, the chilled water pump energy consumption model, the cooling water pump energy consumption model, and the cooling tower heat exchange and energy consumption model. All undetermined coefficients in the models can be calibrated by collecting historical operating data from the equipment and using parameter identification methods such as the least squares method.

[0071] For any candidate air supply parameter combination, the corresponding total cooling load requirement is first obtained; then, based on the preset cold source system energy consumption model, feasible chiller unit start-stop combinations are traversed, and the required chilled water flow rate, cooling water flow rate, and cooling tower air volume are calculated for each combination; further, the chiller unit energy consumption model, chilled water pump model, cooling water pump model, and cooling tower energy consumption model are called to calculate the total energy consumption of the cold source system; under the conditions that the cooling capacity is not lower than the cooling load and the operating constraints of the cold source equipment are met, the cold source operating parameter combination with the lowest total energy consumption is selected as the matching scheme.

[0072] 1. Energy consumption model of refrigeration unit The actual performance of a chiller unit is affected by the chilled water outlet temperature, the cooling water inlet temperature, and the load rate. Its structure is as follows: (1) Cooling capacity correction factor The correction factor for the cooling capacity of the αth refrigeration unit , represented as: (8) In the formula: The chilled water outlet temperature of the chiller unit, in °C; The temperature of the cooling water entering the refrigeration unit, in °C; , , , , , These are coefficients to be determined.

[0073] Maximum available cooling capacity of the αth refrigeration unit for: (9) In the formula: Let α be the rated cooling capacity of the αth refrigeration unit, in kJ.

[0074] (2) Full-load energy efficiency ratio correction factor The ratio of input energy to cooling capacity (EIR) varies with water temperature, and its correction factor EIRFT is: (10) In the formula: , , , , , These are coefficients to be determined.

[0075] (3) Partial load correction factor Considering the characteristics of partial load operation, a partial load correction factor is introduced. : (11) Among them, load rate Defined as: (12) In the formula: Let α be the cooling load borne by the α-th refrigeration unit, in kW; and let x be the number of refrigeration units. , , These are undetermined coefficients; the specific data can be determined based on the actual project and are not limited.

[0076] (4) Partial load correction factor

[0077] The actual electrical power of the αth refrigeration unit is: (13) In the formula, The rated COP for the αth refrigeration unit.

[0078] Chilled water flow rate: (14) Chilled water inlet temperature: (15) Cooling water flow rate: (16) Cooling water outlet temperature: (17) In the formula: is the specific heat capacity of water, kJ / kg℃; The mass density of water is kg / m³. 3 ; The temperature difference between the inlet and outlet water of the chilled water in the chiller unit, in °C. 2. Chilled Water Pump Energy Consumption Model The electrical power of the βth chilled water pump Ratio to chilled water pump speed The relation is a fourth-degree polynomial: (18) The chilled water pump speed ratio is defined as: (19) In the formula, This indicates the rated speed of the chilled water pump, in r / s; This indicates the actual rotational speed of the chilled water pump, in r / s; , The actual and rated frequencies of the chilled water pumps are in Hz; the chilled water flow rate is... m 3 / h; Rated flow rate of chilled water pump m 3 / h; These are coefficients to be determined.

[0079] 3. Cooling water pump energy consumption model The power of the θth cooling water pump The model is similar in form to a refrigeration pump: (20) The cooling water pump speed ratio is defined as: (twenty one) 4. Cooling tower heat transfer model and energy consumption model (1) Heat exchange of cooling tower No. The heat exchange capacity of the cooling tower

[0080] (twenty two) The total heat exchange of the system satisfies the law of conservation of energy. (twenty three) The air outlet enthalpy is given by the heat transfer efficiency model: (twenty four) In the formula, The enthalpy (kJ / kg) of saturated humid air at the temperature at which the cooling water enters the cooling tower. Heat transfer efficiency between saturated humid air on the cooling water surface and inlet air : (25) Number of heat transfer units in a cooling tower : (26) The heat capacity ratio of the two fluids entering and exiting : (27) In the formula, c and b are relevant parameters of the cooling tower, which can be identified by using the least squares method and other methods based on the historical operating data of the cooling tower.

[0081] (2) Cooling tower fan energy No. Actual power of cooling tower fan : (28) Cooling tower fan speed ratio: (29) In the formula, e0, e1...e3 are undetermined parameters of the model. These undetermined parameters can be identified using methods such as the least squares method based on the historical operating data of the cooling tower.

[0082] 5. Pre-set energy consumption model for the cold source system In summary, the total energy consumption of the cooling system is the sum of the energy consumption of each subsystem: (30) In the formula, x represents the number of chiller units, y represents the number of chilled pumps, w represents the number of cooling pumps, and z represents the number of cooling towers. The values ​​of x, y, w, and z are determined based on the actual project and are not limited. In actual projects, the number of chiller units x, the number of chilled pumps y, and the number of cooling pumps w can be set to be the same.

[0083] 6. Operating constraints of cold source equipment (1) Physical constraints of each piece of equipment (31) chilled water: (32) (33) (34) (35) (36) (37) Cooling water: (38) (39) (40) (41) (42) (43) (2) Mutual constraints between equipment Constraints between the refrigeration unit and the cooling water pump: (44) Constraints between refrigeration unit and chilled water pump (45) Constraints between cooling water pump and cooling tower (46) (47) (48) In the formula, The lower limit of the load rate borne by the αth refrigeration unit; The lower limit of the chilled water outlet temperature of the refrigeration unit, in °C; This represents the upper limit of the chilled water outlet temperature for the refrigeration unit, in °C. The lower limit of the chilled water inlet temperature for the refrigeration unit, in °C; This represents the upper limit of the chilled water inlet temperature for the refrigeration unit, in °C. The lower limit of the temperature difference between the inlet and outlet chilled water of the chiller unit, in °C; This represents the upper limit of the temperature difference between the inlet and outlet chilled water of the chiller unit, in °C. Let m be the lower limit of the flow rate of the βth chilled water pump. 3 / h; The upper limit of the flow rate of the βth chilled water pump, m 3 / h; The wet-bulb temperature of the weather, in °C; The approximation setting for the cooling tower, in °C; The temperature difference between the inlet and outlet cooling water of the refrigeration unit, in °C; The lower limit of the temperature difference between the inlet and outlet cooling water of the refrigeration unit, in °C; This is the upper limit of the temperature difference between the inlet and outlet cooling water of the refrigeration unit, in °C; For the first The lower limit of the fan frequency in the cooling tower, in Hz; For the first The upper limit of the fan frequency in a cooling tower, in Hz; For the first The lower limit of the flow rate of the cooling water pump, in m³. 3 / h; Let m be the upper limit of the flow rate of the θ-th cooling water pump. 3 / h; is the specific heat capacity of water, kJ / kg·℃; The mass density of water is kg / m³. 3 ; For the first Airflow rate in the cooling tower, m 3 / h; - These are the parameters to be identified.

[0084] Step 205: Pair any candidate air supply parameter with its matched cooling operation parameter combination to form multiple coordinated operation parameter combinations.

[0085] Step 206: Based on the preset feng shui heat exchange model and preset constraints including feng shui heat exchange matching constraints, perform feasibility verification on the combination of collaborative operation parameters to construct a set of feasible collaborative operation parameter combinations.

[0086] Optionally, the preset constraints include: system-level coupling constraints, which include air-water heat exchange matching constraints, cooling capacity supply and demand balance constraints, and chilled water flow conservation constraints. The construction of a feasible set of collaborative operation parameter combinations includes: for any collaborative operation parameter group, based on a preset air-water heat exchange model, calculating the total air-side heat exchange of the air conditioning terminal system and the sum of the heat exchange of each air conditioning terminal; calculating the sum of chilled water flow allocated to each air conditioning terminal, the total water-side heat exchange of the cold source system, the total cooling capacity, and the total chilled water supply flow; verifying whether the air-side heat exchange and the total water-side heat exchange satisfy the air-water heat exchange constraints; verifying whether the total cooling capacity and the sum of the heat exchange of each air conditioning terminal satisfy the cooling capacity supply and demand balance constraints; verifying whether the total chilled water supply flow and the sum of the flow allocated to each air conditioning terminal satisfy the chilled water flow conservation constraints; if all verification results are passed, then any collaborative operation parameter combination is included in the feasible set of collaborative operation parameter combinations.

[0087] It should be noted that in the air conditioning terminal system, the chilled water from the cooling source equipment and the return air from the computer room exchange heat within the air conditioning terminal, i.e., air-water heat exchange, thereby cooling the IT equipment. To accurately describe the energy transfer capacity of this process, this invention uses the minimum heat capacity ratio method, modeling from two dimensions: heat transfer constraints and energy conservation, to calculate the actual heat exchange at the air conditioning terminal. The air-water heat exchange matching constraints, cooling capacity supply and demand balance constraints, and chilled water flow conservation constraints can be found in the following sections: 1. Feng Shui heat exchange constraints For the j-th air conditioning terminal in the i-th computer room, the heat capacity ratios on the air side and water side are defined as follows: (1) Wind-side heat capacity (49) (2) Water-side heat capacity (50) In the formula: , It is the first The heat capacity of air and water at the j-th air conditioning terminal in a computer room is expressed in W / ℃. It is the density of air (kg / m³). is the specific heat capacity of air, kJ / kg℃; It is the first The airflow rate in the j-th air conditioning terminal in a computer room, m³ / h. It is the density of water (kg / m³). It is the specific heat capacity of water, kJ / kg℃; It is the first The water flow rate in the j-th air conditioning terminal in the computer room, m³ / h.

[0088] (3) Wind and water heat exchange constraints (51) (52) Typically, in data center air conditioning terminals, the air-side heat capacity is less than the water-side heat capacity, i.e.: (53) (54) And it satisfies: (55) (4) Pre-set Feng Shui heat exchange model (56) In the formula: It is the heat exchange capacity of the air-water system at the j-th air conditioning terminal in the i-th computer room, in kW; The actual heat exchange efficiency of the feng shui system; It is the return air temperature (°C) of the j-th air conditioning terminal in the i-th computer room; It is the temperature of the chilled water entering the air conditioning terminal, which is equal to the temperature of the chilled water exiting the refrigeration unit, in °C.

[0089] in: (57) (58) (59) (60) In the formula: This represents the number of heat transfer units; It is the heat capacity ratio; The heat transfer coefficient of the air conditioning terminal is expressed in W / m²·K. The heat exchange area of ​​the air conditioning terminal is measured in m². , , , The coefficients and exponents for the experimental fitting reflect the influence of wind speed and water flow on heat exchange. They can be identified by using methods such as least squares based on historical data from the air conditioning terminal.

[0090] 2. Constraints on the balance between cooling supply and demand The actual heat removed by all air conditioning terminals through air-water heat exchange is equal to the total cooling capacity currently provided by the cold source system: (61) 3. Constraint on chilled water flow rate The sum of the chilled water flow consumed by all air conditioning terminals is equal to the total flow provided by the chilled water pump on the cold source side: (62) Where m is the total number of computer rooms, n is the total number of air conditioning terminals in all computer rooms, and y is the number of chilled water pumps. Let β be the chilled water flow rate of the chilled water pump. For the first i Computer Room j Chilled water flow rate at each end.

[0091] Step 207: With the goal of ensuring that the total energy consumption of the air conditioning system meets the preset conditions, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operation parameter combinations to determine the optimal global operation parameter combination.

[0092] In this embodiment of the invention, the preset energy consumption condition is to minimize the total energy consumption of the air conditioning system. The step of using the total energy consumption of the air conditioning system meeting the preset energy consumption condition as the optimization objective, and employing a preset optimization algorithm to perform a global search on the coordinated operating parameter combination to determine the global operating parameter combination, includes: using adjustable parameters in the coordinated operating parameter combination as optimization decision variables; constructing an objective function for the total energy consumption of the air conditioning system; generating multiple candidate solutions in the decision variable space using the preset optimization algorithm, and calculating the total energy consumption of the air conditioning system corresponding to each candidate solution based on the objective function, while verifying whether it meets the preset constraint condition; updating the global optimal solution according to the total energy consumption of the air conditioning system corresponding to each candidate solution, and when the convergence condition is met, outputting the candidate solution with the minimum total energy consumption of the air conditioning system and meeting the preset constraint condition as the optimal global operating parameter combination.

[0093] In this embodiment of the invention, the total energy consumption of the air conditioning system includes the energy consumption of the air conditioning terminal and the energy consumption of the cold source system. The step of generating multiple candidate solutions in the decision variable space using a preset optimization algorithm, and calculating the total energy consumption of the air conditioning system corresponding to each candidate solution based on the objective function, while verifying whether it satisfies the preset constraints, includes: generating multiple candidate solutions in the decision variable space using a preset optimization algorithm; for each candidate solution, calling a preset cold source system energy consumption model and calculating the corresponding cold source system energy consumption based on the cooling operation parameters therein; and calling a preset air conditioning terminal energy consumption model and calculating the corresponding air conditioning terminal energy consumption based on the air supply parameters therein; adding the air conditioning terminal energy consumption to the cold source system energy consumption to obtain the total energy consumption of the air conditioning system corresponding to the candidate solution; and verifying whether the candidate solution satisfies the preset constraints, which include equipment operation constraints and system-level coupling constraints.

[0094] It should be noted that the device operation constraints and system-level coupling constraints can refer to steps 203 and 205, and are not limited here. The preset optimization algorithm can be a genetic algorithm or a particle swarm optimization algorithm. To better understand the determination of the optimal combination of global operating parameters, an example using the particle swarm optimization algorithm is provided as follows: 1. Construct a complete decision variable space. The decision variable space covers all controllable operating parameters in the combination of coordinated operating parameters, including the air supply parameter combination of the air conditioning terminal system and the cooling parameter combination of the cold source system. These parameters together constitute a multi-dimensional vector, and each specific combination of values ​​represents a candidate system operating strategy.

[0095] 2. Initialize the Particle Swarm Optimization Algorithm. Within the physically permissible range of the aforementioned decision variables, the system randomly generates several initial "particles," each corresponding to a candidate running scheme. In subsequent iterations, each particle dynamically adjusts its flight speed and direction based on its own historical best position and the global best position discovered by the entire swarm to date, gradually converging towards low-energy regions, thereby continuously generating a new set of candidate solutions in each iteration.

[0096] 3. For each generated candidate solution, the system sequentially executes the following energy efficiency assessment and feasibility verification process: Step 1: Call the preset energy consumption model of the cold source system to calculate the energy consumption of the cold source system.

[0097] That is, input the cold source operating parameters contained in the candidate solutions into the preset cold source system energy consumption model (refer to formula 8-30), calculate the energy consumption of each cold source device item by item, and sum them to obtain the total energy consumption of the cold source system; Step 2: Call the preset air conditioning terminal energy consumption model to calculate the energy consumption of the air conditioning terminal system.

[0098] The air supply parameters in the candidate solutions are then input into the air conditioning terminal energy consumption model (refer to Formula 5), ​​and the total energy consumption of all air conditioning terminals is summed to obtain the total energy consumption of the air conditioning terminals. Step 3: Calculate the total energy consumption of the air conditioning system.

[0099] That is, by adding the two energy consumption components mentioned above, we obtain the total system energy consumption corresponding to the candidate solution: Step 4: Verify whether the preset constraints are met.

[0100] That is, verify whether the equipment operation constraints are met (refer to formulas 31-48) and whether the system-level coupling constraints are met (refer to formulas 49-62). If a candidate solution violates any of the above constraints, it is determined to be an infeasible solution, and the system will impose a very large penalty value on its total energy consumption, causing it to be automatically eliminated during the optimization process.

[0101] Through the aforementioned closed-loop mechanism of generation, computation, and verification, the particle swarm optimization algorithm continuously selects high-quality candidate solutions that are both energy-efficient and compliant in each iteration, and finally converges to the optimal combination of global operating parameters that minimizes total energy consumption under all constraints.

[0102] Step 208: Based on the optimal combination of global operating parameters, dynamically adjust the hydraulic balance of the air conditioning system to achieve global optimization of the air conditioning system's energy efficiency.

[0103] In this embodiment of the invention, the method further includes: parsing the optimal global operating parameter combination to generate equipment control commands for the cold source system and air conditioning terminals; and sending the equipment control commands to the corresponding equipment controllers. Step 207, which involves dynamically adjusting the hydraulic balance of the air conditioning system based on the optimal global operating parameter combination to achieve global optimization of the air conditioning system's energy efficiency, includes: deduce the predicted chilled water parameter values ​​for each pipeline node in the pipeline network based on the chilled water demand parameters of each air conditioning terminal and the topology of the chilled water pipeline network in the optimal global operating parameter combination; compare the predicted chilled water parameter values ​​with the actual monitored values, and dynamically adjust the opening degree of each level of hydraulic balancing device and the operating parameters of the chilled water pumps in the pipeline network based on the comparison results. Specifically, the flow rate and resistance loss of each branch pipe are calculated step by step until the main pipe, and the chilled water flow rate, pressure, and temperature difference of the corresponding nodes in the supply and return water pipeline network are finally determined. After comparing the calculated parameter values ​​with the actual monitored values, the opening degree of the dynamic balancing valves at each level of the pipeline network and the frequency of the chilled water pumps are dynamically adjusted through the hydraulic balance adjustment and control system.

[0104] It should be noted that after determining the optimal combination of global operating parameters, to ensure that the terminal equipment of the air conditioning system can accurately obtain the required chilled water flow rate and temperature, thereby achieving efficient and stable thermal management, a dynamic adjustment mechanism based on the hydraulic characteristics of the pipe network can be further introduced. This mechanism includes two core components: chilled water pipe network parameter prediction and dynamic adjustment based on measured feedback, as detailed below: First, the system obtains the chilled water demand parameters specified for each air conditioning terminal from the optimal global operating parameter combination. These parameters include, for example, the required chilled water flow rate, allowable supply and return water temperature difference, and target supply water temperature for each terminal. Simultaneously, the system invokes a pre-constructed chilled water network topology. This topology provides a complete description of the physical connections of the chilled water system, including the layout of main pipes, branch pipes, and branch nodes; the length, diameter, material, and friction coefficient of each pipe segment; and the hydraulic balancing devices at each level. These devices may include static balancing valves, dynamic differential pressure balancing valves, electric regulating valves, and the installation location and performance characteristics of chilled water pumps.

[0105] Then, based on the aforementioned chilled water demand parameters and pipeline topology, the system runs a hydraulic calculation model to perform a forward simulation of the entire chilled water pipeline network. This simulation process uses the demand flow rate at each end as boundary conditions, and, combined with pipeline resistance characteristics, calculates the pressure value of each key node in the network, the flow distribution of each pipeline segment, and the actual available water supply temperature at each end. Finally, it outputs a set of predicted chilled water parameters covering the entire network, including but not limited to: predicted flow rate of each branch, predicted pressure of each node, predicted pump outlet head, and predicted inlet water temperature at each end.

[0106] Subsequently, the predicted parameter values ​​can be compared with real-time monitoring data collected by sensors actually deployed in the chilled water network. This monitoring data typically comes from pressure transmitters, electromagnetic flow meters, and temperature sensors installed at pump outlets, main pipe bifurcation points, branch inlets, and end-point equipment inlets / outlets. The comparison includes: the deviation between actual and predicted flow rates in each branch, the difference between actual and predicted pressure at key nodes, and the deviation between actual and target water temperatures at the end points. The system sets reasonable tolerance thresholds, such as flow rate deviation not exceeding ±10% and pressure deviation not exceeding ±0.05 MPa. When the deviation at any monitoring point exceeds this threshold, it is determined that the current hydraulic state of the network has not reached the expected optimization target, and a dynamic adjustment program needs to be initiated.

[0107] Specifically, the dynamic adjustment procedure may include: adjusting the opening degree of hydraulic balancing devices at each level and adjusting the operating parameters of chilled water pumps. Regarding adjusting the opening degree of hydraulic balancing devices at each level, the opening degree of the electric regulating valves or dynamic balancing valves in the corresponding branches or areas can be automatically adjusted according to the direction and magnitude of the deviation. Regarding adjusting the operating parameters of chilled water pumps, the total flow demand of the entire network, the current operating frequency of the pumps, the outlet pressure, and the efficiency curve can be comprehensively evaluated to dynamically adjust the speed of the chilled water pumps. If overall monitoring shows insufficient flow at multiple terminals and low network pressure, the pump frequency can be appropriately increased to improve the system head and total flow rate; if the pump outlet pressure is found to be too high and many valves are in a throttling state, the pump frequency can be reduced to reduce energy consumption while meeting the minimum demand at the terminals.

[0108] It can also be explained that the hydraulic balance calculation method for the pipeline network is as follows: (1) Node flow conservation: that is, at any pipeline node, the total flow into the node is equal to the total flow out of the node.

[0109] (63) In the formula, For the node The flow rate of a branch pipe is taken as positive when flowing into the node and negative when flowing out. S is the total number of branch pipes connected to the node.

[0110] (2) Loop pressure balance: that is, in any closed pipe loop, the algebraic sum of the resistance losses of each branch pipe is zero.

[0111] (64) In the formula, This represents the resistance loss along the layer in the Kth branch pipe of the pipeline network. Let H be the local resistance loss of the k-th local resistance component, H be the number of straight pipe sections in the pipeline network, and P be the number of local resistance components.

[0112] (3) Layer drag loss: (65) In the formula, λ is the friction coefficient, which is related to the pipe roughness and Reynolds number; L is the pipe length, m; D is the pipe inner diameter, m; v is the water flow velocity in the pipe, m / s; and g is the gravitational acceleration, m / s².

[0113] (4) Local resistance loss: (66) In the formula, This is a local resistance coefficient, which is related to the type of components such as valves, elbows, and tees.

[0114] Through the aforementioned control mechanism, this invention can continuously maintain the hydraulic balance and thermal matching of the chilled water network under conditions such as load changes, equipment aging, or environmental disturbances. This ensures that each air conditioning terminal accurately receives the required cooling capacity while minimizing the energy consumption of water pumps, thereby supporting the entire data center air conditioning system to achieve true global energy efficiency optimization and stable and reliable operation.

[0115] The data center air conditioning system energy efficiency global optimization method provided in this invention obtains thermal environment characteristic data of each computer room in the data center; generates multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems; and performs feasibility verification on the combinations of collaborative operation parameters based on a preset air-water heat exchange model and preset constraints including air-water heat exchange matching constraints, so as to construct a set of feasible collaborative operation parameter combinations. This can ensure that the air side of the air conditioning terminal system and the water side of the cold source system are coordinated and consistent in terms of cooling capacity, flow rate and heat exchange capacity, and avoid capacity redundancy or insufficient cooling caused by system decoupling. Simultaneously, under the condition of meeting preset constraints, the total energy consumption of the air conditioning system corresponding to each combination of coordinated operating parameters can be calculated. Taking the total energy consumption of the air conditioning system meeting the preset conditions as the optimization objective, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operating parameter combinations to determine the optimal global operating parameter combination. This can overcome the limitations of existing technologies that optimize or adjust parameters locally in the cold source system or air conditioning terminal system. That is, under the premise of meeting the preset constraints, the hydraulic balance of the air conditioning system can be dynamically adjusted, thereby coordinating the linkage and coordinated operation between the air supply of the air conditioning terminal and the cooling supply of the cold source system. Therefore, controlling the operation of the air conditioning system based on the optimal global operating parameter combination can ensure the stability of the heat exchange system of the entire air conditioning system, realize the global optimization of the energy efficiency of the air conditioning system, achieve the goal of global energy efficiency optimization of the air conditioning system, thereby effectively reducing the operating energy consumption of the data center air conditioning system and improving the overall energy efficiency of the air conditioning system.

[0116] Figure 4 This is a schematic diagram of the structure of a global energy efficiency optimization device for a data center air conditioning system provided in an embodiment of the present invention, as shown below. Figure 4 As shown, it includes: The acquisition module 31 is configured to acquire thermal environment characteristic data of each computer room in the data center; The generation module 32 is configured to generate multiple combinations of collaborative operation parameters between the air conditioning terminal system and the cold source system based on the thermal environment characteristic data. The construction module 33 is configured to perform feasibility verification on the combination of collaborative operation parameters based on a preset air-water heat exchange model and preset constraint conditions including air-water heat exchange matching constraints, so as to construct a set of feasible collaborative operation parameter combinations. The preset air-water heat exchange model is used for the air-water heat exchange between the indoor circulating air of the computer room and the chilled water of the cold source system. The determination module 34 is configured to use a preset optimization algorithm to perform a global search on the set of feasible collaborative operation parameter combinations, with the optimization objective being that the total energy consumption of the air conditioning system meets preset conditions, and to determine the optimal global operation parameter combination. The optimization module 35 is configured to dynamically adjust the hydraulic balance of the air conditioning system based on the optimal global operating parameter combination, so as to achieve global optimization of the energy efficiency of the air conditioning system.

[0117] Optionally, the generation module 32 includes: The determination submodule is configured to determine the cooling load requirements of each computer room based on the thermal environment characteristic data. The acquisition submodule is configured to acquire the airflow organization characteristics of each computer room; The generation submodule is configured to generate multiple candidate combinations of air conditioning terminal air supply parameters based on the cooling load demand and the preset air supply prediction model. The determining submodule is configured to determine the matching cooling operation parameter combination of the cooling source system based on the cooling load demand and the preset cooling source system energy consumption model for any candidate air supply parameter combination. The pairing submodule is configured to pair any candidate air supply parameter combination with its matching cooling operation parameter combination to form multiple coordinated operation parameter combinations.

[0118] Optionally, the generation submodule is specifically configured to input the cooling load demand and the airflow organization characteristics into a preset air supply prediction model, and generate multiple candidate combinations of air supply parameters for air conditioning terminals under the condition of satisfying preset air supply parameter constraints. The determination submodule is configured to aggregate the cooling load requirements of each computer room to obtain the total cooling load of the data center; and for any candidate combination of air supply parameters, determine the matching combination of cooling operation parameters of the cooling source system based on the total cooling load and the preset energy consumption model of the cooling source system.

[0119] Optionally, the construction module 33 is further configured to construct a preset air conditioning terminal energy consumption model based on the historical air supply operation parameters of each air conditioning terminal; and to perform parameter identification on the neural network model to be trained based on the combination of historical air supply operation parameters in order to construct the preset air supply prediction model.

[0120] Optionally, the preset cold source system energy consumption model includes: multiple cold source equipment energy consumption models corresponding to refrigeration units, chilled water pumps, cooling water pumps and cooling towers. The constructed module 33 is also configured to identify parameters of multiple cold source equipment energy consumption models based on the historical cooling operation parameters of the cold source system, and construct a preset cold source system energy consumption model that reflects the energy consumption characteristics of each cold source equipment. The determining submodule is configured to take the total cooling load demand and outdoor meteorological parameters as input, and under the premise of meeting the operating constraints of the cold source equipment and ensuring that the cooling capacity of the cold source system is not lower than the total cooling load demand, call the preset cold source system energy consumption model to generate the cooling operation parameter combination of the cold source system.

[0121] Optionally, the preset constraints include: system-level coupling constraints, which include air-water heat exchange matching constraints, cooling capacity supply and demand balance constraints, and chilled water flow conservation constraints. The construction module 33 is further configured to, for any group of collaborative operation parameters, calculate the total air-side heat exchange of the air conditioning terminal system, the sum of the heat exchange of each air conditioning terminal, and the sum of the chilled water flow allocated to each air conditioning terminal; calculate the total water-side heat exchange, total cooling capacity, and total chilled water supply flow of the cold source system; verify whether the air-side heat exchange and the total water-side heat exchange satisfy the air-water heat exchange constraints; verify whether the total cooling capacity and the sum of the heat exchange of each air conditioning terminal satisfy the cooling capacity supply and demand balance constraints; verify whether the total chilled water supply flow and the sum of the flow allocated to each air conditioning terminal satisfy the chilled water flow conservation constraints; if all verification results are passed, then any group of collaborative operation parameters is included in the set of feasible collaborative operation parameter combinations.

[0122] Optionally, the preset energy consumption condition is to minimize the total energy consumption of the air conditioning system. The determining module 34 includes: The adjustment submodule is configured to use the adjustable parameters in the combination of collaborative operation parameters as optimization decision variables; The submodule is configured to construct the objective function for the total energy consumption of the air conditioning system. The optimization submodule is configured to generate multiple candidate solutions in the decision variable space using a preset optimization algorithm, calculate the total energy consumption of the air conditioning system corresponding to each candidate solution based on the objective function, and verify whether it meets the preset constraints. The output submodule is configured to update the global optimal solution based on the total energy consumption of the air conditioning system corresponding to each candidate solution, and when the convergence condition is met, output the candidate solution with the minimum total energy consumption of the air conditioning system and that satisfies the preset constraint condition as the optimal global operating parameter combination.

[0123] Optionally, the total energy consumption of the air conditioning system includes the energy consumption of the air conditioning terminal and the energy consumption of the cold source system; the optimization submodule is specifically configured to generate multiple candidate solutions in the decision variable space using a preset optimization algorithm; for each candidate solution, call a preset cold source system energy consumption model and calculate the corresponding cold source system energy consumption based on the cooling operation parameters therein; and call a preset air conditioning terminal energy consumption model and calculate the corresponding air conditioning terminal energy consumption based on the air supply parameters therein; add the air conditioning terminal energy consumption and the cold source system energy consumption to obtain the total energy consumption of the air conditioning system corresponding to the candidate solution; verify whether the candidate solution meets preset constraints, the preset constraints including equipment operation constraints and system-level coupling constraints.

[0124] Optionally, the optimization module 35 is specifically configured to deduce the predicted chilled water parameter values ​​of each pipeline node in the network based on the chilled water demand parameters of each air conditioning terminal and the topology of the chilled water network in the optimal global operating parameter combination; compare the predicted chilled water parameter values ​​with the actual monitoring values; and dynamically adjust the opening degree of each level of hydraulic balancing device and the operating parameters of the chilled water pump in the network based on the comparison results.

[0125] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of the present invention, and the principle is the same. Therefore, the present invention will not limit the scope of the apparatus.

[0126] The data center air conditioning system energy efficiency global optimization device provided in this embodiment of the invention acquires thermal environment characteristic data of each computer room in the data center; generates multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems; and performs feasibility verification on the combinations of collaborative operation parameters based on a preset air-water heat exchange model and preset constraint conditions including air-water heat exchange matching constraints, so as to construct a set of feasible collaborative operation parameter combinations. This can ensure that the air side of the air conditioning terminal system and the water side of the cold source system are coordinated and consistent in terms of cooling capacity, flow rate and heat exchange capacity, and avoid capacity redundancy or insufficient cooling caused by system decoupling. Simultaneously, under the condition of meeting preset constraints, the total energy consumption of the air conditioning system corresponding to each combination of coordinated operating parameters can be calculated. Taking the total energy consumption of the air conditioning system meeting the preset conditions as the optimization objective, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operating parameter combinations to determine the optimal global operating parameter combination. This can overcome the limitations of existing technologies that optimize or adjust parameters locally in the cold source system or air conditioning terminal system. That is, under the premise of meeting the preset constraints, the hydraulic balance of the air conditioning system can be dynamically adjusted, thereby coordinating the linkage and coordinated operation between the air supply of the air conditioning terminal and the cooling supply of the cold source system. Therefore, controlling the operation of the air conditioning system based on the optimal global operating parameter combination can ensure the stability of the heat exchange system of the entire air conditioning system, realize the global optimization of the energy efficiency of the air conditioning system, achieve the goal of global energy efficiency optimization of the air conditioning system, thereby effectively reducing the operating energy consumption of the data center air conditioning system and improving the overall energy efficiency of the air conditioning system.

[0127] According to an embodiment of the present invention, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the aforementioned... Figure 2-3 The method described.

[0128] According to an embodiment of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the aforementioned... Figure 2-3 The method described.

[0129] According to an embodiment of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the aforementioned... Figure 2-3 The method described.

[0130] Figure 5 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0131] like Figure 5 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. The RAM 403 can also store various programs and data required for the operation of the electronic device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0132] Multiple components in electronic device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0133] The computing unit 401 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the global energy efficiency optimization method for a data center air conditioning system. For example, in some embodiments, the global energy efficiency optimization method for a data center air conditioning system can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, computing unit 401 may be configured to perform the aforementioned global energy efficiency optimization method for data center air conditioning systems by any other suitable means (e.g., by means of firmware).

[0134] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fibers, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0139] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0140] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0141] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0142] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for global energy efficiency optimization of a data center air conditioning system, characterized in that, include: Acquire outdoor meteorological parameters of the data center and thermal environment characteristics of each computer room; Based on the outdoor meteorological parameters and the thermal environment characteristic data, multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems are generated. Based on the preset air-water heat exchange model and preset constraints including air-water heat exchange matching constraints, the feasibility of the coordinated operation parameter combination is verified in order to construct a set of feasible coordinated operation parameter combinations. The preset air-water heat exchange model is used for the air-water heat exchange between the indoor circulating air of the computer room and the chilled water of the cold source system. With the goal of ensuring that the total energy consumption of the air conditioning system meets the preset conditions, a preset optimization algorithm is used to perform a global search on the set of feasible coordinated operation parameter combinations to determine the optimal global operation parameter combination. Based on the optimal combination of global operating parameters, the hydraulic balance of the air conditioning system is dynamically adjusted to achieve global optimization of the energy efficiency of the air conditioning system.

2. The method according to claim 1, characterized in that, Based on the outdoor meteorological parameters and the thermal environment characteristic data, multiple combinations of coordinated operation parameters for air conditioning terminal systems and cold source systems are generated, including: Based on the outdoor meteorological parameters and the thermal environment characteristic data, the cooling load requirements of each computer room are determined. Based on the cooling load demand and the preset air supply prediction model, multiple candidate combinations of air supply parameters for air conditioning terminals are generated. For any candidate combination of air supply parameters, based on the cooling load demand and the preset energy consumption model of the cooling source system, determine the matching combination of cooling operation parameters of the cooling source system. Any candidate air supply parameter combination is paired with its matching cooling operation parameter combination to form multiple coordinated operation parameter combinations.

3. The method according to claim 2, characterized in that, The preset cold source system energy consumption model includes: energy consumption models for multiple cold source equipment such as refrigeration units, chilled water pumps, cooling water pumps, and cooling towers. Before determining the matching combination of cooling operation parameters for the cold source system based on the cooling load demand and the preset cold source system energy consumption model, the method further includes: Based on the historical cooling operation parameters of the cold source system, parameter identification is performed on the energy consumption models of multiple cold source devices to construct a preset cold source system energy consumption model that reflects the energy consumption characteristics of each cold source device. The step of determining the matching combination of cooling operation parameters for the cooling source system based on the cooling load demand and the preset energy consumption model of the cooling source system includes: The total cooling load of the data center is obtained by summarizing the cooling load requirements of each computer room. Using the total cooling load and outdoor meteorological parameters as input, the preset energy consumption model of the cold source system is invoked to generate a matching combination of cooling operation parameters for the cold source system, provided that the operating constraints of the cold source equipment are met and the cooling capacity of the cold source system is not lower than the total cooling load requirement.

4. The method according to claim 1, characterized in that, The preset constraints include: system-level coupling constraints, which include air-water heat exchange matching constraints, cooling supply and demand balance constraints, and chilled water flow conservation constraints. Based on the preset air-water heat exchange model and the preset constraints, the feasibility of the coordinated operation parameter combinations is verified to construct a set of feasible coordinated operation parameter combinations, including: For any set of coordinated operation parameters, based on the preset air-water heat exchange model, calculate the total air-side heat exchange of the air conditioning terminal system and the sum of the heat exchange of each air conditioning terminal. Calculate the sum of chilled water flow rates allocated to each air conditioning terminal, the total water-side heat exchange of the cold source system, the total cooling capacity, and the total chilled water supply flow rate; Verify whether the wind-side heat exchange and the total water-side heat exchange satisfy the wind-water heat exchange constraint; Verify whether the sum of the total cooling capacity and the heat exchange capacity of each air conditioning terminal meets the cooling supply and demand balance constraint; Verify whether the sum of the total chilled water supply flow rate and the flow rate allocated to each air conditioning terminal satisfies the chilled water flow rate conservation constraint; If each verification result is passed, then any of the collaborative operation parameter combinations will be included in the set of feasible collaborative operation parameter combinations.

5. The method according to claim 1, characterized in that, The preset energy consumption condition is to minimize the total energy consumption of the air conditioning system. The optimization objective is to ensure that the total energy consumption of the air conditioning system meets the preset energy consumption condition. A preset optimization algorithm is used to perform a global search on the set of feasible coordinated operation parameter combinations to determine the global operation parameter combinations, including: Use the adjustable parameters in the feasible combination of collaborative operation parameters as optimization decision variables; Construct the objective function for the total energy consumption of the air conditioning system; Multiple candidate solutions are generated in the decision variable space using a preset optimization algorithm, and the total energy consumption of the air conditioning system corresponding to each candidate solution is calculated based on the objective function. At the same time, it is verified whether they meet the preset constraints. The global optimal solution is updated based on the total energy consumption of the air conditioning system corresponding to each candidate solution. When the convergence condition is met, the candidate solution with the minimum total energy consumption of the air conditioning system and the preset constraint condition is output as the optimal global operating parameter combination.

6. The method according to claim 1, characterized in that, The step of dynamically adjusting the hydraulic balance of the air conditioning system based on the optimal global operating parameter combination to achieve global optimization of the air conditioning system's energy efficiency includes: Based on the chilled water demand parameters of each air conditioning terminal and the topology of the chilled water network in the optimal global operating parameter combination, the predicted chilled water parameter values ​​of each pipeline node in the network are deduced. The predicted chilled water parameter values ​​are compared with the actual monitoring values, and the opening degree of each level of hydraulic balancing device in the pipeline network and the operating parameters of the chilled water pumps are dynamically adjusted based on the comparison results.

7. A global energy efficiency optimization device for an air conditioning system, characterized in that, include: The acquisition module is configured to acquire thermal environment characteristic data of each computer room in the data center. The generation module is configured to generate multiple combinations of collaborative operation parameters between air conditioning terminal systems and cold source systems based on the thermal environment characteristic data. The construction module is configured to perform feasibility verification on the combination of collaborative operation parameters based on a preset air-water heat exchange model and preset constraint conditions including air-water heat exchange matching constraints, so as to construct a set of feasible collaborative operation parameter combinations. The preset air-water heat exchange model is used for air-water heat exchange between the indoor circulating air of the computer room and the chilled water of the cold source system. The determination module is configured to use a preset optimization algorithm to perform a global search on the set of feasible collaborative operation parameter combinations, with the optimization objective being that the total energy consumption of the air conditioning system meets preset conditions, and to determine the optimal global operation parameter combination. The optimization module is configured to dynamically adjust the hydraulic balance of the air conditioning system based on the optimal combination of global operating parameters, so as to achieve global optimization of the energy efficiency of the air conditioning system.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images