Simulation method and system for data center power utilization effectiveness value of indirect evaporative cooling air conditioner

Abstract

The application discloses a data center electric energy utilization efficiency value simulation calculation method and system of indirect evaporative cooling air conditioner, comprising the following steps: based on a quantum computing platform, constructing an IT load of a data center, a quantum simulation model of an indirect evaporative cooling unit and a dynamic environment thereof, and establishing a dynamic correlation between a cooling unit state and a complex environment variable through quantum many-body simulation. The application breaks through the limitations of traditional optimization methods in a multi-dimensional control space through the optimization capability of quantum computing, can quickly calculate the optimal configuration of the cooling system, especially in high load and extreme environment; by using a quantum machine learning method, not only can the load change be accurately predicted, but also the control strategy can be adjusted in real time, energy waste is reduced, and the response speed and accuracy of the system are improved.

Description

Technical Field

[0001] This invention relates to the field of data center energy-saving control and computer simulation technology, specifically to a method and system for simulating and calculating the energy utilization efficiency of data center power using indirect evaporative cooling air conditioning. Background Technology

[0002] Indirect evaporative cooling, a highly efficient cooling technology that utilizes outdoor natural cold sources, has been widely applied in green data centers. This system cools air by absorbing heat through water evaporation via spraying, combined with airflow heat exchange, significantly reducing the operating time of mechanical cooling. Power Usage Effectiveness (PUE) is a core indicator for measuring the energy efficiency of a data center; reducing PUE means maintaining the normal operation of IT equipment with less energy consumption.

[0003] However, in the existing technology, the simulation calculation and optimized control of the PUE value of indirect evaporative cooling systems face the following significant technical challenges:

[0004] Data center energy efficiency is dynamically affected by multiple factors, including external climate (dry-bulb temperature, wet-bulb temperature, wind speed), internal IT load fluctuations, and equipment aging. Traditional static modeling methods or linear models based on empirical formulas are insufficient to accurately describe the complex nonlinear coupling relationships between these variables (e.g., the nonlinear impact of wet-bulb temperature changes on heat transfer efficiency), resulting in insufficient simulation accuracy.

[0005] Indirect evaporative cooling systems involve a large number of control nodes, including fans, pumps, valves, and compressors. To find the globally optimal combination of control parameters (such as the best match between fan speed and spray water volume), traditional linear programming or genetic algorithms are prone to getting stuck in local optima in large parameter spaces, and the computation is time-consuming, which cannot meet the requirements of real-time scheduling.

[0006] Existing control strategies are mostly "feedback" regulation (i.e., temperature rises and then falls), lacking "feedforward" forecasting capabilities for future loads. Furthermore, in the face of extreme weather or sudden equipment failures, traditional simulation systems struggle to provide emergency strategies within seconds, often leading to the system switching to a high-energy-consumption, conservative operating mode, and even triggering downtime risks. Therefore, this paper proposes a simulation calculation method and system for the energy utilization efficiency of indirect evaporative cooling air conditioning systems in data centers. Summary of the Invention

[0007] The purpose of this invention is to provide a method and system for simulating and calculating the power utilization efficiency of data center systems using indirect evaporative cooling air conditioning. This aims to solve one of the problems existing in the prior art.

[0008] Firstly, to solve the aforementioned technical problems, this application adopts a technical solution: a simulation calculation method for the energy utilization efficiency of data center indirect evaporative cooling air conditioning, comprising the following steps:

[0009] Based on a quantum computing platform, a quantum simulation model of the IT load of a data center, an indirect evaporative cooling unit and its dynamic environment is constructed. Through quantum many-body simulation, a dynamic relationship between the state of several cooling units and complex environmental variables is established.

[0010] Based on the quantum simulation model, the optimal combination of control parameters for the cooling unit is dynamically solved using a quantum optimization algorithm to achieve simulation calculation and optimization of the power utilization efficiency value.

[0011] A load prediction model is built using quantum machine learning to analyze historical data of data centers, predict the heat load of IT equipment and weather changes in future periods, and generate the most suitable allocation scheme for cooling resources by combining quantum scheduling algorithms.

[0012] Based on the discrepancy between real-time monitoring data and simulation prediction data, quantum state characterization and pattern recognition techniques are used to locate the source of the discrepancy and correct the simulation model parameters.

[0013] Based on the revised simulation model and prediction results, dynamic scheduling instructions are generated through a quantum real-time scheduling engine to perform closed-loop control and multi-objective energy efficiency optimization of the cooling unit, thereby realizing real-time simulation and management of data center power utilization efficiency.

[0014] In one possible implementation, establishing a dynamic correlation between the states of several cooling units and complex environmental variables through quantum many-body simulation specifically includes:

[0015] The cooling unit status, fan speed, and equipment load of the indirect evaporative cooling air conditioner are mapped to quantum bit states;

[0016] The nonlinear interaction effects between several cooling units and between the cooling units and external environmental variables such as temperature, humidity and wind speed are handled by utilizing the properties of quantum entanglement.

[0017] A dynamic environmental simulation model was established by simulating the cooling unit response under different environmental conditions in parallel on a quantum computing platform.

[0018] In one possible implementation, the dynamic solution of the optimal combination of control parameters for the cooling unit using a quantum optimization algorithm specifically includes:

[0019] The quantum variational optimization algorithm is adopted, with the energy efficiency ratio of the cooling unit as the objective function and the fan speed, coolant flow rate and evaporative cooling mode as optimization variables.

[0020] The optimal solution is searched in parallel in a multi-dimensional control space, and the control strategy is dynamically adjusted in combination with real-time operating data to output the most suitable control parameters that meet the current environment and load requirements.

[0021] In one possible implementation, the use of quantum machine learning to construct the load prediction model specifically includes:

[0022] Construct a quantum feature embedding model to map historical load data, computer room temperature trends, and external meteorological data into a high-dimensional quantum state space;

[0023] A quantum neural network was constructed using parameterized quantum circuits to learn the spatiotemporal distribution characteristics and nonlinear variation patterns of heat load in data centers;

[0024] By incorporating the prediction calibration mechanism of quantum reinforcement learning, the model parameters are automatically adjusted when the prediction error exceeds a preset threshold, and the load prediction value for future periods is output.

[0025] In one possible implementation, the method of combining quantum scheduling algorithms to generate the optimal allocation scheme for cooling resources specifically includes:

[0026] The cooling resource scheduling problem is transformed into a quantum combinatorial optimization problem;

[0027] Using quantum annealing or quantum approximation optimization algorithms, and with the goal of minimizing total energy consumption while meeting the temperature constraints of the computer room, we calculate the start-up and shutdown status and power allocation scheme of each cooling unit.

[0028] Identify pre-cooling windows based on load forecasts and formulate pre-cooling strategies that include advance cooling and cold storage reserves.

[0029] In one possible implementation, the use of quantum state characterization and pattern recognition techniques to locate the source of the deviation specifically includes:

[0030] Collect actual energy consumption data and simulated predicted energy consumption data, and encode the magnitude and trend of the deviation between the actual energy consumption data and the simulated predicted energy consumption data into quantum state vectors;

[0031] Using quantum singular pattern recognition technology, the main cause of energy efficiency deviation is extracted from the deviated quantum state. The cause of energy efficiency deviation includes decreased evaporation efficiency, equipment aging or abnormal external environment.

[0032] Based on the identified causes of the deviation, the evaporation efficiency coefficient or heat transfer coefficient in the simulation model is adaptively updated using quantum gradient estimation.

[0033] In one possible implementation, the generation of dynamic scheduling instructions through a quantum real-time scheduling engine to perform closed-loop control and multi-objective energy efficiency optimization of the cooling unit specifically includes:

[0034] The allocation scheme generated by the quantum scheduling algorithm is transformed into specific equipment control instructions, which include adjusting the chilled water outlet temperature, adjusting the fan speed, or switching the evaporative cooling mode.

[0035] It receives real-time feedback from the device and triggers a quantum fast fine-tuning algorithm to generate correction instructions when the execution result deviates from the expected target.

[0036] During the scheduling process, multiple objectives such as temperature stability, minimizing total energy consumption, and extending equipment life are comprehensively considered, and a Pareto optimal scheduling strategy is generated based on dynamic weights.

[0037] In one possible implementation, the method further includes:

[0038] Constructing a quantum digital twin and emergency response mechanism:

[0039] A quantum digital twin of the cooling unit is constructed based on the revised simulation model, and the future operating trajectory of the equipment is evolved in real time.

[0040] Quantum parallel simulation technology is used to simulate equipment failures, heat load surges, or extreme weather scenarios, and to assess the risk levels of different emergency strategies.

[0041] The quantum optimization algorithm is used to quickly generate emergency response decisions that include load transfer, activation of backup links, or switching of operating modes.

[0042] In one possible implementation, the method further includes a lifecycle energy efficiency management step:

[0043] Quantum computing is used to model the entire life cycle of a cooling system and dynamically assess the impact of equipment wear, aging, and technological upgrades on energy efficiency.

[0044] An adaptive scheduling library is built based on long-term operational data. Quantum reinforcement learning methods are used to iteratively optimize the scheduling strategy and identify and eliminate energy waste points during operation.

[0045] In one possible implementation, the superposition and entanglement properties of quantum computing are leveraged to model data center environmental variables on quantum computing platforms (such as IBM Qiskit and Google Cirq). Different cooling units (such as evaporative cooling systems, fans, and air conditioning equipment) represent their states using qubits, and quantum simulations of many-body systems are performed to accurately simulate the response of each device. The state of each cooling unit changes over time, taking into account factors such as ambient temperature, humidity, and wind speed.

[0046] Quantum computing can be used to handle complex relationships that traditional computing cannot, especially the interactive effects between multiple cooling units, equipment loads, and changes in the external environment. Through quantum entanglement, multiple possible states can be computed in parallel at the same time, quickly solving for the optimal state of each device under different environmental parameters.

[0047] For example, quantum computing models can simultaneously simulate the state changes of multiple cooling units in a data center's cooling system and their relationship with external variables such as temperature and humidity, thereby quickly calculating the energy utilization efficiency under different environments. Traditional calculation methods may require simulating each variable separately, resulting in poor calculation time and accuracy.

[0048] In one possible implementation, a quantum variational algorithm is applied to find the optimal operating point of the cooling system. Control parameters include fan speed, coolant flow rate, and air conditioning power, and quantum optimization can quickly solve for the control strategy best suited to the current load and environmental changes.

[0049] Adaptive Optimization: Quantum computing's adaptive optimization mechanism is based on real-time operational data from the data center and dynamically adjusts control parameters through reinforcement learning algorithms. As environmental conditions and equipment load change, the quantum optimization algorithm adjusts in real time to achieve the lowest power consumption and maximize cooling efficiency.

[0050] For example, in practical applications, when the external temperature rises, the quantum optimization algorithm can dynamically adjust the operating state of the cooling system in a short time (such as increasing the evaporative cooling capacity, adjusting the fan speed, etc.) to ensure maximum energy efficiency under the new environmental conditions.

[0051] In one possible implementation, a quantum computing platform is used for efficient machine learning training to build a model for predicting data center load changes. Quantum computing can process large-scale data more efficiently than traditional computing, rapidly training predictive models. By quantum training on historical load data, cooling requirements for the next few hours or days can be accurately predicted.

[0052] By combining predicted load change information with cooling system control strategies, quantum optimization scheduling algorithms can optimize resource allocation. These algorithms not only handle cooling load optimization but also consider real-time adjustments to cooling resource allocation, achieving optimal scheduling of cooling equipment.

[0053] For example, if the load on a data center is expected to increase in the next few hours, a quantum computing scheduling system can adjust the allocation of cooling resources in advance (e.g., increase the use of evaporative cooling systems and reduce unnecessary air conditioning loads), thereby reducing energy consumption during peak hours.

[0054] In one possible implementation, the cooling system is simulated in real time under abnormal or extreme conditions (such as extreme weather, equipment failure, heat load surges, etc.), and the optimal emergency response strategy for the system is obtained through quantum computing. Quantum computing can simulate complex emergencies and provide optimal solutions in a very short time.

[0055] Based on quantum simulation results, the system can intelligently identify potential problems in the cooling system (such as the failure of a single cooling unit or system imbalance) and take measures to self-recover. For example, in the event of fan failure or pipe blockage, the system will automatically reschedule the remaining cooling units to ensure that the cooling task is not affected.

[0056] For example, if the system detects a failure in a cooling unit, the quantum simulation model can quickly calculate the optimal recovery strategy under the current conditions (such as activating a backup cooling unit or adjusting the coolant flow rate) and adjust the system configuration within seconds to avoid energy efficiency degradation.

[0057] In one possible implementation, quantum computing is used to model the entire lifecycle of a data center cooling system, taking into account the impact of factors such as equipment wear, aging, and technological upgrades on energy efficiency, and dynamically evaluating the operating status and power utilization efficiency of the equipment.

[0058] By employing quantum optimization algorithms and machine learning techniques, the performance of the cooling system is continuously monitored and optimized, potential energy waste points are identified in a timely manner, and adjustments and optimizations are made. This process can self-optimize based on equipment aging and technological advancements (such as the introduction of new cooling equipment).

[0059] For example, as the service life of cooling equipment increases, the system will adjust the equipment operation strategy according to the quantum optimization algorithm to avoid the decline in energy efficiency caused by equipment aging, and at the same time provide an optimized path for the introduction of new equipment.

[0060] By leveraging the optimization capabilities of quantum computing, the limitations of traditional optimization methods in multi-dimensional control space are overcome, enabling the calculation of the optimal configuration of the cooling system in an instant, especially in high-load and extreme environments.

[0061] By combining quantum machine learning methods, it is possible not only to accurately predict load changes, but also to adjust control strategies in real time, reduce energy waste, and improve the system's response speed and accuracy.

[0062] Quantum computing's high-speed simulation capabilities provide strong technical support for emergency response and fault recovery of cooling systems, enabling rapid decision-making in the event of emergencies and avoiding the impact of system failures on energy efficiency.

[0063] Secondly, to solve the aforementioned technical problems, another technical solution adopted in this application is: a data center power utilization efficiency simulation calculation system for indirect evaporative cooling air conditioning, comprising:

[0064] The quantum modeling and simulation module is configured to build a quantum simulation model of the cooling system and environment based on a quantum computing platform, and to perform quantum many-body simulations.

[0065] The quantum optimization and computation module is configured to run quantum variational optimization algorithms and quantum scheduling algorithms to calculate optimal control parameters and resource allocation schemes;

[0066] The quantum prediction and learning module is configured to run quantum neural networks and quantum reinforcement learning models, and to perform load prediction and model calibration.

[0067] The deviation analysis and correction module is used to analyze the deviation between measured and simulated data, and to use quantum pattern recognition technology to locate the cause and correct the model parameters.

[0068] The real-time scheduling and control module is configured to generate dynamic scheduling commands to perform closed-loop control and emergency response for the cooling unit.

[0069] Thirdly, to solve the above-mentioned technical problems, another technical solution adopted in this application is: a simulation calculation method for the power utilization efficiency of data center indirect evaporative cooling air conditioning, the method comprising the following steps:

[0070] Step 1: In response to the security protection instructions of the data center, construct a quantum simulation model of the data center security posture based on the quantum computing platform, and use quantum many-body simulation technology to establish a dynamic correlation between data flow, access behavior and potential threat characteristics;

[0071] Step 2: Based on the quantum simulation model, use the quantum variational optimization algorithm to dynamically solve for the optimal combination of defense strategies, and perform real-time parameter optimization of firewall rules and encryption protocols;

[0072] Step 3: Utilize quantum machine learning to build a threat prediction model to predict future network traffic anomalies and potential attack paths in the data center, and combine it with quantum scheduling algorithms to generate the optimal allocation scheme for defense resources.

[0073] Step 4: Based on the deviation between real-time monitored security data and simulation prediction data, use quantum acceleration simulation technology to conduct dynamic attack and defense drills, and adjust the defense strategy combination in real time according to the drill results to achieve closed-loop active defense for data security in the data center.

[0074] In one possible implementation, the quantum simulation model of data center security posture built on a quantum computing platform utilizes quantum many-body simulation technology to establish a dynamic correlation between data flow, access behavior, and potential threat characteristics, including:

[0075] Build a secure simulation system deployed on a quantum computing platform to map the network node status, data access frequency, and external attack characteristics of the data center to the state of qubits;

[0076] By leveraging the parallel computing and quantum superposition properties of quantum computing, we simulate dynamic network environments and complex attack methods to address multivariate correlation problems in massive log data.

[0077] By using quantum analogy computing algorithms, threat correlation analysis, which cannot be efficiently solved in classical computing models, is transformed into a quantum algorithm, enabling parallel evaluation of the impact of various potential attack scenarios on data security.

[0078] In one possible implementation, the step of dynamically solving for the optimal defense strategy combination based on the quantum simulation model using a quantum variational optimization algorithm (VQA) includes:

[0079] The security defense objective of the data center is to maximize the interception rate and minimize the false alarm rate, and the optimal defense configuration is searched in the multi-dimensional control space using the quantum variational optimization algorithm.

[0080] In response to dynamically changing network environments and internal data access loads, the threshold parameters and access control lists of the intrusion detection system are calculated and adjusted in real time.

[0081] When a sudden change in the characteristics of an external attack is detected, the effectiveness of the current defense strategy is evaluated in real time using the quantum computing model, and a blocking strategy for the new attack is dynamically generated.

[0082] In one possible implementation, the use of quantum machine learning to construct a threat prediction model to predict future network traffic anomalies and potential attack paths in the data center, and the combination of quantum scheduling algorithms to generate an optimal allocation scheme for defense resources, includes:

[0083] Quantum machine learning algorithms are used to process massive real-time traffic data streams, extract the temporal patterns and behavioral characteristics of network attacks, and predict the level of security threats within a preset time period.

[0084] A smart security scheduling system based on quantum computing is developed to automatically adjust the allocation of computing and bandwidth resources according to the predicted threat level, prioritizing the encryption and backup of core data.

[0085] By analyzing historical attack data and real-time traffic flow, quantum algorithms are used to optimize the deployment of security resources, ensuring that the defense system is strengthened before the peak of attacks arrives.

[0086] By combining quantum computing simulation, quantum optimization, and quantum analogy techniques, not only is the efficiency problem of traditional cooling systems in the face of complex dynamic environments solved, but a brand-new cooling system optimization path is also provided for data centers.

[0087] The high efficiency and parallel processing capabilities of quantum computing ensure that cooling solutions can be quickly adjusted in variable environments and provide real-time decision support for operators, enabling data centers to operate with optimal power efficiency under different load and climate conditions.

[0088] Fourthly, to solve the above-mentioned technical problems, another technical solution adopted in this application is: an electronic device, including a processor, a memory and a communication interface, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the above-mentioned simulation calculation method for the power utilization efficiency value of data center indirect evaporative cooling air conditioner.

[0089] Fifth aspect: To solve the above-mentioned technical problems, another technical solution adopted in this application is: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the data center power utilization efficiency value simulation calculation method of the indirect evaporative cooling air conditioner as described above are implemented.

[0090] The present invention has the following beneficial effects:

[0091] 1. This invention, through the optimization capabilities of quantum computing, overcomes the limitations of traditional optimization methods in multi-dimensional control space, enabling the rapid calculation of the optimal configuration of the cooling system, especially its performance under high load and extreme environments;

[0092] 2. This invention employs quantum machine learning methods, which can not only accurately predict load changes but also adjust control strategies in real time, reducing energy waste and improving the system's response speed and accuracy.

[0093] 3. This invention provides strong technical support for emergency response and fault recovery of cooling systems through the high-speed simulation capabilities of quantum computing, enabling rapid decision-making in the event of emergencies and avoiding the impact of system failures on energy efficiency;

[0094] 4. This invention, through quantum computing technology, can significantly improve the energy efficiency calculation accuracy, optimization strategies, emergency response, and long-term management capabilities of data center cooling systems, making the entire cooling process more intelligent, precise, and efficient. Attached Figure Description

[0095] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0096] Figure 1 This is a flowchart illustrating the simulation calculation method for the data center power utilization efficiency value of the indirect evaporative cooling air conditioner of the present invention.

[0097] Figure 2 This is a flowchart illustrating Embodiment 2 of the present invention;

[0098] Figure 3 This is a block diagram of the data center power utilization efficiency simulation calculation system for the indirect evaporative cooling air conditioner according to Embodiment 3 of the present invention;

[0099] Figure 4 This is a schematic diagram of the structure of the electronic device of the present invention. Detailed Implementation

[0100] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0101] Figure 1 This is a flowchart illustrating the simulation calculation method for the data center power utilization efficiency value of an indirect evaporative cooling air conditioner according to an embodiment of the present invention. It should be noted that if substantially the same result is obtained, the method of this application is not necessarily identical. Figure 1 The sequence of processes shown is limited.

[0102] Example 1:

[0103] like Figure 1 The simulation calculation method for the data center power utilization efficiency value of the indirect evaporative cooling air conditioner shown includes the following steps:

[0104] S10. Based on the quantum computing platform, construct a quantum simulation model of the IT load of the data center, the indirect evaporative cooling unit and its dynamic environment, and establish the dynamic relationship between the state of several cooling units and complex environmental variables through quantum many-body simulation.

[0105] In this embodiment, specifically, the establishment of a dynamic correlation between the states of several cooling units and complex environmental variables through quantum many-body simulation includes:

[0106] The cooling unit status, fan speed, and equipment load of the indirect evaporative cooling air conditioner are mapped to quantum bit states;

[0107] The nonlinear interaction effects between several cooling units and between the cooling units and external environmental variables such as temperature, humidity and wind speed are handled by utilizing the properties of quantum entanglement.

[0108] A dynamic environmental simulation model was established by simulating the cooling unit response under different environmental conditions in parallel on a quantum computing platform.

[0109] S20. Based on the quantum simulation model, the optimal combination of control parameters for the cooling unit is dynamically solved using a quantum optimization algorithm to achieve simulation calculation and optimization of the power utilization efficiency value.

[0110] In this embodiment, specifically, the step of dynamically solving for the optimal combination of control parameters for the cooling unit using a quantum optimization algorithm includes:

[0111] The quantum variational optimization algorithm is adopted, with the energy efficiency ratio of the cooling unit as the objective function and the fan speed, coolant flow rate and evaporative cooling mode as optimization variables.

[0112] The optimal solution is searched in parallel in a multi-dimensional control space, and the control strategy is dynamically adjusted in combination with real-time operating data to output the most suitable control parameters that meet the current environment and load requirements.

[0113] S30. Utilize quantum machine learning to build a load prediction model, analyze historical operating data of the data center, predict the heat load of IT equipment and meteorological changes in future periods, and combine it with quantum scheduling algorithms to generate the most suitable allocation scheme for cooling resources.

[0114] In this embodiment, specifically, the construction of the load prediction model using quantum machine learning includes:

[0115] Construct a quantum feature embedding model to map historical load data, computer room temperature trends, and external meteorological data into a high-dimensional quantum state space;

[0116] A quantum neural network was constructed using parameterized quantum circuits to learn the spatiotemporal distribution characteristics and nonlinear variation patterns of heat load in data centers;

[0117] By combining the prediction calibration mechanism of quantum reinforcement learning, the model parameters are automatically adjusted when the prediction error exceeds a preset threshold, and the load prediction value for future periods is output.

[0118] The optimal allocation scheme for cooling resources, generated by combining quantum scheduling algorithms, specifically includes:

[0119] The cooling resource scheduling problem is transformed into a quantum combinatorial optimization problem;

[0120] Using quantum annealing or quantum approximation optimization algorithms, and with the goal of minimizing total energy consumption while meeting the temperature constraints of the computer room, we calculate the start-up and shutdown status and power allocation scheme of each cooling unit.

[0121] Identify pre-cooling windows based on load forecasts and formulate pre-cooling strategies that include advance cooling and cold storage reserves.

[0122] S40. Based on the deviation between real-time monitoring data and simulation prediction data, quantum state characterization and pattern recognition techniques are used to locate the source of the deviation and correct the simulation model parameters.

[0123] In this embodiment, specifically, the method of locating the source of deviation using quantum state characterization and pattern recognition technology includes:

[0124] Collect actual energy consumption data and simulated predicted energy consumption data, and encode the magnitude and trend of the deviation between the actual energy consumption data and the simulated predicted energy consumption data into quantum state vectors;

[0125] Using quantum singular pattern recognition technology, the main cause of energy efficiency deviation is extracted from the deviated quantum state. The cause of energy efficiency deviation includes decreased evaporation efficiency, equipment aging or abnormal external environment.

[0126] Based on the identified causes of the deviation, the evaporation efficiency coefficient or heat transfer coefficient in the simulation model is adaptively updated using quantum gradient estimation.

[0127] Constructing a quantum digital twin and emergency response mechanism:

[0128] A quantum digital twin of the cooling unit is constructed based on the revised simulation model, and the future operating trajectory of the equipment is evolved in real time.

[0129] Quantum parallel simulation technology is used to simulate equipment failures, heat load surges, or extreme weather scenarios, and to assess the risk levels of different emergency strategies.

[0130] The quantum optimization algorithm is used to quickly generate emergency response decisions that include load transfer, activation of backup links, or switching of operating modes.

[0131] S50. Based on the corrected simulation model and prediction results, dynamic scheduling instructions are generated through the quantum real-time scheduling engine to perform closed-loop control and multi-objective energy efficiency optimization of the cooling unit, thereby realizing real-time simulation and management of data center power utilization efficiency.

[0132] In this embodiment, specifically, the step of generating dynamic scheduling instructions through a quantum real-time scheduling engine to perform closed-loop control and multi-objective energy efficiency optimization of the cooling unit includes:

[0133] The allocation scheme generated by the quantum scheduling algorithm is transformed into specific equipment control instructions, which include adjusting the chilled water outlet temperature, adjusting the fan speed, or switching the evaporative cooling mode.

[0134] It receives real-time feedback from the device and triggers a quantum fast fine-tuning algorithm to generate correction instructions when the execution result deviates from the expected target.

[0135] During the scheduling process, multiple objectives such as temperature stability, minimizing total energy consumption, and extending equipment life are comprehensively considered, and a Pareto optimal scheduling strategy is generated based on dynamic weights.

[0136] S60. Steps for full lifecycle energy efficiency management:

[0137] Quantum computing is used to model the entire life cycle of a cooling system and dynamically assess the impact of equipment wear, aging, and technological upgrades on energy efficiency.

[0138] An adaptive scheduling library is built based on long-term operational data. Quantum reinforcement learning methods are used to iteratively optimize the scheduling strategy and identify and eliminate energy waste points during operation.

[0139] In this embodiment, specifically, the intelligent cooling scheduling for dealing with sudden high temperatures is as follows: the system uses a quantum machine learning model, combined with weather forecasts and historical data, to predict in advance that the outdoor wet-bulb temperature will rise rapidly within the next 2 hours.

[0140] On the quantum computing platform, the system simulated tens of thousands of possible control strategies in parallel. It not only considered the current temperature, but also simulated the impact of different combinations of fan speeds and spray volumes on the computer room temperature and total energy consumption after the temperature rises in the future.

[0141] Within seconds, the system found the optimal solution: it suggested that the chilled water temperature be fine-tuned and the backup spray system be started 30 minutes before the temperature rises, so as to store cold in advance with lower energy consumption.

[0142] After the control command was issued, the cooling system transitioned smoothly. When high temperatures occurred, the computer room temperature remained stable, and there were no energy consumption spikes due to sudden high temperatures, effectively reducing the PUE value throughout the day.

[0143] In this embodiment, specifically, the advantages of quantum computing (such as superposition and entanglement) are utilized to accurately simulate the behavior of multiple cooling units, thereby evaluating the system's energy efficiency under different environments. On quantum computing platforms (such as IBM Qiskit or Google Cirq), data center cooling units (such as evaporative cooling systems, fans, air conditioning equipment, etc.) are represented by qubits, and their states (on / off, different power levels, etc.) are represented by different states of the qubits. For example, the three operating modes of a cooling unit (low / medium / high power) can be expressed by the superposition of multiple states of the qubits. Leveraging the superposition property of quantum computing, the performance of multiple cooling units under different operating states can be simulated simultaneously. Parallel computation of multiple unit states is achieved through the superposition and entanglement of qubits, overcoming the serial bottleneck of traditional computing. This allows the system to quickly evaluate the response of all cooling units, making it particularly suitable for scenarios with varying environmental conditions such as external temperature, humidity, and wind speed.

[0144] In addition to the cooling unit states, external environmental variables (such as temperature, humidity, and wind speed) also need to be incorporated into quantum computing. These variables are dynamically input through quantum functions to derive the system's response under different environments. Each cooling unit adjusts its operating state according to changes in the external environment, and quantum simulation can quickly solve for the correlation between each variable and the cooling effect. Assuming the system contains three cooling units, quantum computing, through the superposition of qubits, can simultaneously simulate their performance under low, medium, and high power states in a single simulation. When the ambient temperature rises from 30°C to 35°C, quantum computing can calculate the response of each cooling unit to the temperature change in real time, yielding optimized energy efficiency results within seconds, significantly improving computational speed and accuracy.

[0145] In cooling system simulations, quantum entanglement enables parallel computation of the relationships between multiple cooling units (such as the impact of one unit's operating state on the energy efficiency of another). This approach quickly reflects the interaction effects between multiple variables, thereby finding the optimal configuration for the entire system. Leveraging the high-speed computing power of quantum computing, the effects of changes in environmental conditions such as temperature, humidity, and wind speed on cooling equipment can also be simulated, recreating the behavior of the cooling system under different scenarios. For example, the response of a cooling unit to external temperature may be nonlinear; quantum computing can accurately model this complex relationship and optimize the operation of the cooling equipment by incorporating other environmental factors such as humidity and wind speed.

[0146] Beyond calculating energy efficiency, quantum computing supports multi-objective optimization. For example, a cooling system needs to achieve optimal energy efficiency while also considering factors such as equipment lifespan and maintenance costs. Leveraging the parallel processing capabilities of quantum computing, multiple objectives can be optimized simultaneously during the same computation, quickly yielding the optimal solution that satisfies all conditions. For instance, when external humidity changes, quantum computing can quickly simulate its impact on cooling units, while also incorporating the effect of wind speed on the cooling system. Through quantum entanglement, multiple units of the cooling system can be simulated synchronously, thereby finding the optimal cooling strategy under changing environments. Traditional computing requires simulating the results of each environmental condition separately and then comparing them one by one; quantum computing, however, can simultaneously calculate the impact of multiple variables within a unified framework.

[0147] The multi-body simulation and quantum correlation modeling capabilities of quantum computing platforms provide powerful computing support for the optimization of the entire cooling system. Quantum computing can rapidly simulate the state changes of multiple cooling units in parallel operations, efficiently handling the complex interaction effects between each unit and changes in the external environment. This improves the simulation accuracy and computational efficiency of the cooling system under variable environments, laying the foundation for subsequent cooling strategy optimization, load forecasting, and energy efficiency management. When simulating data centers facing environmental fluctuations, quantum computing can more quickly calculate the optimal operating state of each cooling unit under changes in multiple variables such as temperature and humidity, providing timely and accurate energy efficiency assessments. This capability can provide decision-makers with optimization solutions in a short time, helping data centers achieve more efficient power utilization and cooling operations. Quantum computing not only provides parallel computing capabilities that traditional computing cannot achieve, but also handles complex nonlinear relationships and multi-dimensional variable optimization problems. This allows the cooling system to respond to changing environmental conditions in real time, significantly improving the energy efficiency and operational efficiency of the data center.

[0148] In this embodiment, specifically, a quantum variational optimization algorithm is used to quickly locate the optimal operating point of the cooling system in a multidimensional control space, thereby improving cooling efficiency and reducing energy consumption. The quantum variational optimization algorithm is a quantum algorithm that integrates classical optimization algorithms (such as gradient descent) with quantum computing capabilities, enabling efficient searching for optimal solutions in high-dimensional control spaces. Its core advantage lies in leveraging the superposition and entanglement properties of quantum computing to explore multiple solution spaces in parallel computation. The control parameters of the cooling system (such as fan speed, coolant flow rate, and air conditioning power) are all input into the algorithm as optimization variables. Under given constraints, the quantum algorithm can efficiently search for the optimal configuration of these control variables.

[0149] Cooling system operation is affected by various factors such as external ambient temperature and humidity, internal load, and cooling unit performance. Traditional methods are inefficient in dealing with such multi-dimensional and nonlinear problems, while quantum variational optimization algorithms can leverage the parallelism of quantum computing to simultaneously optimize multiple control variables. For example, when the external temperature rises, the algorithm can simultaneously adjust parameters such as the power and fan speed of multiple cooling units, enabling the cooling system to respond quickly and switch to its optimal operating state. Quantum variational optimization algorithms measure optimization effectiveness through objective functions. For example, the objective function can be defined as the energy efficiency ratio (EER) of the cooling system, which is the ratio of energy consumption per unit of computing load to the energy consumption of the cooling system. By minimizing this objective function, the quantum algorithm can automatically adjust various parameters of the cooling system, improving the overall energy efficiency of the data center.

[0150] Assuming a rapid increase in external temperature and a corresponding rise in cooling system load, this algorithm can quickly adjust its control strategy. By increasing evaporative cooling or adjusting fan speed, it ensures the cooling system adapts to the new environmental conditions and maintains minimal power consumption. During this process, the algorithm uses quantum computing to process different adjustment strategies in parallel, quickly identifying the optimal combination. Combined with the adaptive optimization mechanism of quantum computing, control parameters are dynamically adjusted based on real-time data from the data center and environmental changes, ensuring the cooling system is always in optimal operating condition and maximizing energy efficiency. Quantum computing can fuse reinforcement learning algorithms with real-time data to dynamically adjust the cooling system's operating strategy. After real-time monitoring of data center load, external environmental changes (such as temperature and humidity), and the operating status of cooling units, the quantum optimization algorithm adjusts control parameters such as fan speed and coolant flow rate in real time based on this feedback information.

[0151] Within the quantum optimization framework, reinforcement learning algorithms can more efficiently adjust control strategies driven by real-time data streams, achieving continuous improvements in energy efficiency. For example, when the cooling system load increases, the system will increase cooling capacity; when the load decreases, the system will automatically reduce cooling output to avoid wasting energy. During data center operation, external climate and internal load constantly change. Quantum optimization algorithms respond to these changes in real time through adaptive mechanisms, ensuring timely adjustments to the cooling system's operating strategy. For instance, when the external temperature rises, the system can automatically adjust the water flow rate and fan speed of the evaporative cooling unit; while when the temperature drops, the system can reduce energy consumption. Suppose the data center load suddenly increases, and the cooling equipment needs to increase its cooling capacity to cope. With the help of an adaptive optimization mechanism combining quantum computing and reinforcement learning, after receiving feedback on the real-time load increase, the cooling system will automatically adjust control parameters such as coolant flow rate and fan speed to ensure efficient operation even with increased load, avoiding a decrease in energy efficiency.

[0152] Quantum optimization algorithms are used to automatically adjust various control parameters of the cooling system, ensuring maximum energy efficiency and reducing energy consumption. These parameters can be automatically adjusted, including fan speed, coolant flow rate, evaporative coolant flow rate, and the on / off status of cooling equipment. Based on real-time data and changes in the external environment, the quantum algorithm calculates the optimal configuration of each parameter under current conditions and immediately adjusts the operating status of the cooling equipment. Through quantum optimization, the cooling system not only maintains a low power utilization efficiency (PUE) value but also adjusts cooling capacity and energy consumption according to the actual load of the equipment. When the data center load is high, the system increases cooling output; when the load is low, the system reduces cooling capacity to avoid energy waste. When the heat load suddenly increases, the cooling system requires more cooling resources to cope with the temperature rise. The quantum optimization algorithm can calculate the optimal cooling strategy, providing sufficient cooling capacity by adjusting fan speed and coolant flow rate while avoiding energy waste caused by over-cooling.

[0153] By employing quantum variational optimization algorithms and adaptive optimization mechanisms, the cooling system control strategy is adjusted in real time to maximize energy efficiency and reduce power usage effectiveness (PUE) under varying loads and environmental conditions. Quantum computing not only efficiently solves multi-dimensional optimization problems but also responds to changes in the data center in real time, enabling dynamic adjustments to the cooling system to improve energy efficiency and reduce energy consumption. This adaptive mechanism, combining quantum computing and reinforcement learning, significantly enhances the energy efficiency of the cooling system, ensuring that the data center maintains optimal performance under various operating conditions.

[0154] In this embodiment, specifically, based on quantum machine learning (QML) and quantum scheduling algorithms, accurate prediction of future cooling load is achieved, and the prediction results are transformed into a dynamic scheduling strategy for cooling resources in real time, allowing the entire cooling system to operate in a state of "knowing the future", which greatly reduces energy consumption and response latency.

[0155] A quantum feature embedding model is constructed to map historical load data (such as server CPU utilization, data center temperature trends, and air-cooled heat load curves) to a quantum state space. The quantum state space possesses high-dimensionality and superposition properties, enabling it to express nonlinear relationships that are difficult for traditional models to capture. A quantum neural network is used for training; this network learns through parameterized quantum circuits and is more expressive than traditional RNNs / LSTMs when handling high-dimensional dynamic systems. Leveraging the quantum superposition property, multiple future trends can be learned simultaneously, accelerating model convergence. A hybrid learning framework is employed: a front-end quantum neural network learns complex distribution structures, while a back-end classical neural network handles numerical regression output, enabling prediction of load changes over the next 1 hour, 3 hours, and 24 hours. Historical data from the data center shows that load increases daily from 2:00 PM to 5:00 PM due to data analysis services, with additional backup tasks on Tuesdays and Thursdays, and significant impacts from summer ambient temperatures. The QML model can capture these periodic and nonlinear characteristics through the quantum feature embedding layer, accurately predicting the cooling demand curve for the next 6 hours and informing the system in advance that the load will peak at 3:00 PM.

[0156] Constructing a Quantum Reinforcement Learning (QRL) Agent: This agent takes real-time load, ambient temperature, and equipment efficiency as input. It compares the predicted values ​​of the QML model with the real-time data; if the error exceeds a threshold, it automatically adjusts the prediction model parameters. Quantum Reward Mechanism: The reward function is composed of cooling energy consumption, temperature fluctuations, and prediction bias. Quantum encoding can explore multiple policy spaces in a single training iteration, improving calibration efficiency. Adaptive Prediction Updates: If a sudden change in load pattern is detected (such as a sudden increase in computing cluster traffic), QRL immediately corrects the QML output to ensure prediction accuracy. If a sudden AI training service goes live, causing a 50% surge in load within 10 minutes, QRL will detect the abnormal bias (predicted value 40%, actual value 90%) and immediately trigger a rapid calibration process, allowing QML to learn the new load pattern within minutes and preventing the system from misjudging cooling needs.

[0157] Establish a cooling resource scheduling model: Cooling units include chilled water units, natural cooling units, fans, evaporative cooling towers, etc. Minimize total energy consumption while meeting the computer room temperature requirements. Transform the scheduling problem into a quantum optimization problem (e.g., QUBO model). Employ quantum annealing to obtain the optimal scheduling scheme: Quantum annealing is suitable for solving combinatorial optimization problems such as "which cooling units should be turned on and how to allocate power," and can find a near-global optimal solution from a massive number of combinations in a very short time. Dynamic refresh mechanism for scheduling strategy: Quantum scheduling optimization is run every 1-5 minutes, and the cooling strategy is dynamically updated based on the load prediction of QML and the calibration results of QRL. If the prediction shows that the load will increase by 30% in 3 hours, the quantum scheduling system will calculate and execute the strategy in advance: utilize the low external temperature period to store cooling capacity, adjust the operation combination of evaporative cooling towers and fans, and shut down chilled water units that are about to enter the inefficient range. This can reduce the cooling system energy consumption by 15% while avoiding overload operation during peak periods.

[0158] Pre-cooling window identification: The quantum model identifies temperature curves and cooling demand changes over the next 1-24 hours, pinpointing the optimal time for low-cost pre-cooling. Pre-cooling strategy formulation: During the low-temperature period before load increases, the system automatically activates efficient cooling sources to lower the server room temperature (e.g., from 26°C to 23°C), reducing cooling pressure during peak load. Dynamic pre-cooling control: The pre-cooling amplitude is adjusted based on prediction deviations (calibrated by QRL) to avoid over-cooling and wasted energy. For example, if the load peaks at 16:00 and the outside temperature is expected to be lower from 11:00 to 12:00, the system automatically decides to perform efficient, low-cost pre-cooling from 11:00 to 12:00 and reduce chiller load during the peak load period from 16:00 to 17:00. Simulation results show a 20% reduction in peak power consumption, a 0.5°C reduction in temperature fluctuation, and a 10% extension of fan life.

[0159] The system receives prediction and scheduling optimization results in real time, integrating the outputs of QML (prediction), QRL (calibration), and quantum scheduling (optimization) into executable instructions. It executes cooling equipment-level scheduling actions: adjusting chiller outlet water temperature and fan speed, switching evaporative cooling modes, controlling the start and stop of the cold source, and simultaneously implementing closed-loop temperature control and anomaly handling—if the temperature approaches the upper limit, an emergency cooling action is immediately triggered. If a cooling unit failure is detected, a backup scheduling scheme is immediately invoked. During execution, if an increase in wet-bulb temperature leads to a decrease in evaporative cooling efficiency, the quantum scheduling engine automatically switches to the chilled water link and adjusts its power to maintain optimal energy consumption.

[0160] In this embodiment, specifically, by leveraging the ultra-high-speed parallel computing capabilities of quantum simulation, the behavior of the cooling system under various extreme, abnormal, and sudden conditions can be predicted in real time, forming a dynamic emergency strategy and realizing intelligent self-recovery of the system, ensuring that the data center cooling system can still operate efficiently under scenarios such as temperature changes, equipment failures, and energy constraints.

[0161] Digital Twin Construction: Based on the quantum temperature control model in step 1 and the prediction data in step 3, a "quantum digital twin" of the cooling system running on quantum hardware is constructed. This covers all cooling equipment, including chilled water systems, fans, cooling towers, heat exchangers, and evaporative cooling units. Quantum State Description of System Behavior: Equipment states (such as flow rate, power, cooling efficiency, and failure probability) are mapped to quantum states, and future behavioral trajectories are simulated through state evolution. Nanosecond-Level Evolution Simulation: Compared to classical simulations that take seconds to minutes, quantum simulation can predict multiple future scenarios in nanoseconds to milliseconds. For example, if the current ambient temperature is rising 20% ​​faster than predicted, posing a risk of increased cooling tower fan vibration, the quantum simulation model can quickly extrapolate the rate of chilled water temperature increase and whether the chiller load will enter an unstable range within the next 30 minutes, providing actionable recommendations.

[0162] Emergency Scenario Library Design: Several common and extreme emergency scenarios are predefined, including equipment failure scenarios (fan failure, chiller shutdown, pump failure, power outage), heat load surge scenarios (surge in instantaneous computing tasks in the data center), extreme weather scenarios (surge in wet-bulb temperature, combination of high temperature and high humidity), and resource-constrained scenarios (peak electricity price periods, grid power limits). Quantum Parallel Simulation: Utilizing quantum superposition states, multiple future paths are simulated in parallel at once to quickly determine "which scenario is most likely to occur" and "the best handling strategy under that scenario." Dynamic Risk Level Determination: The quantum algorithm automatically calculates the probability of occurrence for each scenario and provides a risk level (e.g., low risk, medium risk, and high risk). If the system detects a sudden increase in the cooling tower inlet temperature (possibly caused by a change in external wind direction), the quantum simulation will automatically assess: whether it will lead to a decrease in evaporative cooling efficiency in the next 10 minutes, how much the fan speed needs to be increased if it does, and whether it is necessary to switch to a backup cooling link. The system provides the optimal emergency strategy within 50 milliseconds to avoid temperature anomalies.

[0163] An emergency response target set is formed, and the response strategy must simultaneously meet four requirements: temperature safety within limits, lowest energy consumption, balanced equipment load, and minimal impact range of the fault. Quantum optimization algorithms (such as QAOA and quantum annealing) are used to solve the problem: emergency decisions are transformed into combinatorial optimization problems. Quantum annealing can rapidly find a near-global optimal strategy within a vast space of possible solutions. Decisions are translated into specific actions: switching chiller operating modes, adjusting chilled water flow, prioritizing the use of high-efficiency cooling branches, temporarily shutting down high-risk cooling equipment, and adjusting energy consumption curves to adapt to electricity pricing policies. If chiller A experiences abnormal vibration, and quantum simulation detects a potential shutdown risk within 30 minutes, the quantum optimization system will automatically generate emergency actions: reducing the load of chiller A from 70% to 40%, while simultaneously increasing the load of chiller B from 40% to 65% (not exceeding its high-efficiency range), adjusting the fan units to compensate for the overall heat exchange decrease, and activating the backup evaporative cooling module. The entire calculation process takes only about 100 milliseconds.

[0164] Fault Mode Identification: Utilizing quantum simulation results, the system identifies degradation trends and potential failure points in cooling equipment, such as whether a 10% drop in chilled water pump flow is caused by impeller damage. Automatic Recovery Scheduling: For minor faults (such as abnormal fan speed or heat exchanger scaling), the system automatically adjusts other cooling units to share the workload; for severe faults, it automatically isolates the faulty unit. Real-time Health Updates: After the self-recovery strategy is executed, the quantum model updates the cooling system's health matrix to avoid reusing potentially faulty equipment. If one of the main chilled water pumps has insufficient flow, the system automatically switches to a dual-pump collaborative mode, temporarily reducing the cooling supply to some temperature-insensitive areas and notifying maintenance personnel in the background; the entire process takes no more than a few seconds.

[0165] Anticipating potential crises: If a sharp rise in the ambient wet-bulb temperature is predicted within the next 20 minutes, quantum simulations can anticipate the impact of this change on evaporative cooling efficiency. Preemptive intervention in the cooling system: Automatically increasing pre-cooling capacity, adjusting chilled water temperature in advance, and activating high-efficiency chillers to address future risks. For example, if a 5°C rise in wet-bulb temperature after 15 minutes would lead to a 30% decrease in evaporative cooling efficiency, the system intervenes in advance: lowering the chilled water supply temperature by 1.5°C, activating an additional heat exchange module as a backup, and adjusting the fan configuration to increase airflow speed, ultimately preventing temperature control overruns.

[0166] In other embodiments, specifically, the system collects three types of data in real time: actual energy consumption data (such as fan power consumption, evaporative cooling section power consumption, chiller unit power consumption, etc.), simulated predicted energy consumption data (the scheduling prediction value provided in step S30), and energy efficiency evaluation indicators (such as power utilization efficiency, cooling system energy efficiency ratio COP, efficiency of each linked cold source, etc.). The deviation between the predicted value and the actual value is encoded as a quantum state vector, and quantum amplitude encoding is used to embed the magnitude and trend of the deviation into a quantum superposition state. The quantum state can simultaneously express multiple deviation modes, such as seasonal deviation, time period deviation, equipment aging deviation, and instantaneous environmental anomaly deviation. By performing Hadamard gate or rotating door operations on the quantum state, it is made more suitable for subsequent deviation analysis.

[0167] For example, data from a certain day shows that the simulated cooling energy consumption of the computer room is predicted to be 52 kWh, while the actual monitored energy consumption is 57 kWh, a deviation of 5 kWh (the actual energy consumption is higher). After quantum state encoding, this can be presented as a superposition pattern: 70% probability corresponds to "decreased evaporation efficiency," 20% probability corresponds to "decreased fan efficiency," and 10% probability corresponds to "load prediction deviation." Quantum encoding allows the system to analyze multiple sources of deviation simultaneously. By leveraging quantum coherence to "mode amplify" the deviation states, subtle trends are highlighted in quantum measurements and made easier to identify. Using quantum singular pattern recognition, similar to a quantum version of PCA, the main causal patterns are extracted from the deviation states. The correlation between the deviation and the environment and equipment status is determined by the degree of quantum decoherence, and the root cause ranking of the deviation is obtained through quantum measurement. For example: insufficient prediction of wet-bulb temperature in the evaporation section; aging of the packing leading to a decrease in actual heat exchange efficiency; high concentration of external air particles affecting evaporation; and the chilled water pump operating point deviating from optimal conditions.

[0168] If quantum pattern recognition detects that the main source of deviation is "decreased efficiency in the evaporative cooling section" with a probability of 82%, the system will determine that recent climate change has led to an increase in wet-bulb temperature, causing the actual energy efficiency of the evaporation section to be lower than the simulation model's expectations, thus automatically triggering model correction. Based on the source of deviation, the simulation model parameters that need updating are quantized, including the evaporation efficiency coefficient, heat transfer coefficient, chiller energy efficiency curve, fan aerodynamic efficiency parameters, and heat flux response time constant. Quantum gradient estimation is used to update these parameters: multiple parameters are simultaneously perturbated and estimated in the quantum state, allowing for a single calculation to assess the impact of multidimensional parameter changes on the deviation, with an update speed several times faster than traditional optimizers. Quantum reinforcement learning is used to determine the final modification magnitude, minimizing the deviation. For example, the system initially assumed an evaporation efficiency of 0.82, but quantum deviation analysis showed the actual value was closer to 0.76. The correction process is as follows: quantum gradient estimation calculates the deviation reduction for "adjusting from 0.82 to 0.78" and "adjusting from 0.82 to 0.76," respectively, selecting the value with the smallest deviation as the update value and writing it into the simulation model, making the model approximate the actual cooling capacity.

[0169] A feedback loop for energy efficiency after model correction is established: actual energy consumption—quantum bias detection—model parameter correction—new simulation results—re-comparison with reality, forming a quantum-classical hybrid closed-loop system. If the bias continues to converge, it indicates that the model has been accurately corrected; if the bias increases, the quantum optimizer is triggered to retrain. Changes in the energy efficiency curve are pushed to step S50 (quantum real-time execution engine) in real time to execute the corresponding adjustment actions. After model correction, the original bias of 5kWh has decreased to 1.2kWh. If the system detects that the bias continues to decrease to 0.8kWh or 0.6kWh, the correction process is closed, and the system enters a stable period; if the bias suddenly increases, it indicates that there are external weather changes, cooling unit failures, or a surge in heat load due to the launch of new services, and the correction process in step S40 will be restarted.

[0170] Different deviation thresholds are set for different cooling equipment, such as ±3% for evaporative cooling sections, ±2% for chilled water systems, and ±5% for fan energy consumption. If the deviation exceeds the threshold, an alarm is immediately triggered and the "conservative mode" cooling source operation strategy is activated. If the deviation returns to normal, the quantum adaptive correction mode is restored. If the deviation in the evaporative section suddenly rises to 10% (far exceeding the 3% threshold), the system immediately triggers a series of actions: automatically checking the wet-bulb temperature sensor, improving fan efficiency, switching part of the load to the chilled water system, and pushing alarm information to ensure that the data center temperature does not exceed the limit.

[0171] In this embodiment, specifically, the quantum modeling, prediction, and deviation correction results of steps S10 to S40 are transformed into real-time scheduling instructions for the cooling system, enabling the data center cooling system to achieve high energy efficiency, low deviation, rapid response, and autonomous optimization operation. The scheduling input data includes the future load prediction data from step S30, the deviation-corrected energy efficiency model parameters from step S40, and the current actual equipment status (pumps, fans, chillers, current, voltage, etc.). By transforming the scheduling problem into a quantum combinatorial optimization problem, quantum annealing or variable quantum optimization (VQE / QAOA) is used to solve it at the nanosecond to millisecond level, outputting the power setting, load allocation, operating mode, and backup link start / stop strategy for each cooling unit. For example, if the system predicts a 15% increase in room load over the next 10 minutes and the deviation correction indicates a 5% decrease in evaporation efficiency, quantum scheduling will output a solution: increase the chilled water pump flow rate by 10%, increase the speed of fan unit A by 8%, activate one unit in the standby evaporation section, and fine-tune the load of chiller B to the high-efficiency range. After the scheduling result is issued, the equipment provides real-time feedback on the execution status (flow rate, current, temperature). If there is a deviation from the simulation model, the quantum fast fine-tuning algorithm is automatically triggered, generating fine-tuning instructions within 50-200 milliseconds. For example, if the room temperature decrease is less than the expected 0.5℃ after the fan speed is increased, the fan angle, pump flow rate, and chilled water temperature will be further fine-tuned by 0.3℃ to allow the system to quickly converge to the ideal temperature.

[0172] The system simultaneously focuses on four objectives: temperature stability, minimizing total energy consumption, extending equipment lifespan (avoiding prolonged high-load operation), and rapid response (maintaining optimal energy utilization efficiency). It uses quantum algorithms to calculate the trade-offs between these objectives in a superposition state, generating the optimal solution and supporting dynamic weight adjustments. For example, during peak electricity price periods, priority is given to reducing total energy consumption. At this time, total energy consumption accounts for 50%, temperature control stability for 30%, and equipment lifespan for 20%. After optimization, the chiller load decreases by 10%, total energy consumption decreases by 12%, and the computer room temperature only rises slightly by 0.2℃. The system maps the quantum emergency prediction results from step S40 in real time, automatically activating backup cooling links, pre-adjusting fan / pump operating status, and adjusting chilled water temperature and flow rate before abnormal critical points. For example, if the predicted external wet-bulb temperature rises by 6℃ in 15 minutes, the system increases fan speed by 12%, chilled water pump flow by 8%, and activates the backup evaporator section in advance, ensuring that the computer room temperature fluctuation is only 0.3℃ and the energy efficiency decrease is only 1.2%. Simultaneously, the system records the deviation between each scheduling operation and the actual results, iteratively optimizing future scheduling strategies through quantum reinforcement learning to form an adaptive scheduling library. For example, after a week of operation, the system discovered that chilled water pumps often underestimated energy consumption in high humidity environments. After learning from this, the system automatically increased the pump flow rate by 5% in the next scheduling cycle, reducing energy efficiency deviation by 30% and making temperature control more stable. Ultimately, the system fully implements the prediction, optimization, and correction results into actual operation, dynamically generating scheduling plans to truly achieve closed-loop feedback, anomaly prevention, and historical iterative optimization of the cooling system, continuously ensuring the high energy efficiency and high stability of the data center cooling system under various operating conditions.

[0173] Example 2:

[0174] like Figure 2 As shown, to solve the above-mentioned technical problems, based on Embodiment 1, another technical solution adopted in this application is: a simulation calculation method for the power utilization efficiency value of data center indirect evaporative cooling air conditioning, the method comprising the following steps:

[0175] Step 1: In response to the security protection instructions of the data center, construct a quantum simulation model of the data center security posture based on the quantum computing platform, and use quantum many-body simulation technology to establish a dynamic correlation between data flow, access behavior and potential threat characteristics;

[0176] Step 2: Based on the quantum simulation model, use the quantum variational optimization algorithm to dynamically solve for the optimal combination of defense strategies, and perform real-time parameter optimization of firewall rules and encryption protocols;

[0177] Step 3: Utilize quantum machine learning to build a threat prediction model to predict future network traffic anomalies and potential attack paths in the data center, and combine it with quantum scheduling algorithms to generate the optimal allocation scheme for defense resources.

[0178] Step 4: Based on the deviation between real-time monitored security data and simulation prediction data, use quantum acceleration simulation technology to conduct dynamic attack and defense drills, and adjust the defense strategy combination in real time according to the drill results to achieve closed-loop active defense for data security in the data center.

[0179] In this embodiment, specifically, the quantum simulation model of data center security posture built based on a quantum computing platform, which utilizes quantum many-body simulation technology to establish a dynamic correlation between data flow, access behavior, and potential threat characteristics, includes:

[0180] Build a secure simulation system deployed on a quantum computing platform to map the network node status, data access frequency, and external attack characteristics of the data center to the state of qubits;

[0181] By leveraging the parallel computing and quantum superposition properties of quantum computing, we simulate dynamic network environments and complex attack methods to address multivariate correlation problems in massive log data.

[0182] By using quantum analogy computing algorithms, threat correlation analysis, which cannot be efficiently solved in classical computing models, is transformed into a quantum algorithm, enabling parallel evaluation of the impact of various potential attack scenarios on data security.

[0183] In this embodiment, specifically, the step of dynamically solving for the optimal defense strategy combination based on the quantum simulation model using a quantum variational optimization algorithm includes:

[0184] The security defense objective of the data center is to maximize the interception rate and minimize the false alarm rate, and the optimal defense configuration is searched in the multi-dimensional control space using the quantum variational optimization algorithm.

[0185] In response to dynamically changing network environments and internal data access loads, the threshold parameters and access control lists of the intrusion detection system are calculated and adjusted in real time.

[0186] When a sudden change in the characteristics of an external attack is detected, the effectiveness of the current defense strategy is evaluated in real time using the quantum computing model, and a blocking strategy for the new attack is dynamically generated.

[0187] In this embodiment, specifically, the step of using quantum machine learning to construct a threat prediction model to predict future network traffic anomalies and potential attack paths in the data center, and combining this with a quantum scheduling algorithm to generate an optimal allocation scheme for defense resources, includes:

[0188] Quantum machine learning algorithms are used to process massive real-time traffic data streams, extract the temporal patterns and behavioral characteristics of network attacks, and predict the level of security threats within a preset time period.

[0189] A smart security scheduling system based on quantum computing is developed to automatically adjust the allocation of computing and bandwidth resources according to the predicted threat level, prioritizing the encryption and backup of core data.

[0190] By analyzing historical attack data and real-time traffic flow, quantum algorithms are used to optimize the deployment of security resources, ensuring that the defense system is strengthened before the peak of attacks arrives.

[0191] By combining quantum computing simulation, quantum optimization, and quantum analogy techniques, not only is the efficiency problem of traditional cooling systems in the face of complex dynamic environments solved, but a brand-new cooling system optimization path is also provided for data centers.

[0192] The high efficiency and parallel processing capabilities of quantum computing ensure that cooling solutions can be quickly adjusted in variable environments and provide real-time decision support for operators, enabling data centers to operate with optimal power efficiency under different load and climate conditions.

[0193] In this embodiment, a quantum computing model is specifically constructed, focusing on the calculation process of power utilization efficiency (PUE) for data centers, with a key emphasis on the optimization and scheduling of the cooling system. A simulation system based on quantum computing platforms such as IBM Qiskit and Google Cirq is built to simulate complex cooling environments such as climate change and equipment load variations. Quantum computing, with its ability to efficiently handle diverse environmental variables, can calculate the energy efficiency of data centers more quickly and accurately compared to traditional simulation methods.

[0194] In this embodiment, specifically, a quantum analogy computing algorithm is used to transform multivariate correlation and optimization problems that are difficult to solve efficiently in traditional computing models into quantum algorithms, significantly improving computational efficiency. Leveraging the characteristics of parallel computing and quantum superposition, this algorithm can process multiple candidate cooling solutions simultaneously and quickly identify the optimal solution. For example, when simulating a data center cooling system, traditional methods require calculating the correlation between the energy efficiency and environmental changes of each cooling unit individually, while quantum computing, through quantum superposition and parallel computing, can simultaneously consider multiple parameter combinations and rapidly provide an optimization solution.

[0195] In this embodiment, specifically, a quantum optimization algorithm (such as quantum variational optimization) is employed, integrating quantum computing with classical optimization techniques to adjust various parameters of the cooling system, such as wind speed, evaporation rate, and equipment load, to accurately find the optimal cooling configuration. Simultaneously, through real-time calculation and optimization of energy allocation and cooling scheduling using quantum algorithms, the system can flexibly respond to dynamic scenarios such as external climate changes and internal data center load variations, adjusting the operating status of air conditioners and fans in real time to effectively reduce energy waste. For example, when the external temperature changes drastically, the quantum computing model can assess the cooling demand in real time and dynamically adjust the power output of the cooling system based on historical data and the current load, thereby avoiding over-cooling or under-cooling.

[0196] Quantum computing algorithms are used to predict future heat load and power demand in data centers, and machine learning models are combined to further optimize cooling strategies. Quantum computing can efficiently process massive real-time datasets, extract effective patterns, and accurately predict future cooling needs. Based on this, intelligent energy scheduling systems can be developed that automatically adjust the resource allocation of the cooling system according to future load forecasts, ensuring that cooling tasks are completed with minimal energy consumption. For example, through real-time data stream and historical data analysis, quantum computing can predict energy efficiency changes over the next few hours or days, and reduce energy consumption during peak loads by optimizing scheduling, thereby significantly reducing overall power utilization efficiency (PUE) over long-term scales.

[0197] In this embodiment, specifically, relying on quantum accelerated simulation technology and leveraging the parallel processing capabilities of quantum computing, the energy efficiency of the cooling system under different operating conditions is calculated in real time, simulating the impact of equipment load and climate change on cooling demand. Combining the quantum simulation results, AI algorithms provide optimization decision support for the data center. The system can analyze and provide the optimal cooling solution in real time, while also providing data support for operators. For example, when a data center faces a sudden heat wave, traditional simulation methods may require several hours to recalculate cooling requirements, while quantum computing can provide optimization decisions within seconds, helping the data center respond in advance and avoid excessive energy consumption.

[0198] In this embodiment, the application of quantum computing brings multiple core advantages: First, it efficiently handles complex variables, significantly improving the accuracy and timeliness of power utilization efficiency (PUE) calculations; second, the quantum analogy algorithm breaks through the bottleneck of traditional optimization methods in solving multi-dimensional parameters, enabling real-time optimization of the cooling system; third, parallel processing capabilities greatly accelerate simulation calculations, ensuring the timeliness and accuracy of data center energy efficiency assessment and adjustment, especially when dealing with complex cooling strategies and environmental changes; fourth, combining quantum computing and artificial intelligence, the system can predict future load changes based on real-time data, dynamically adjust the allocation of cooling resources, maximize energy efficiency, and reduce energy waste; fifth, in the event of sudden changes in ambient temperature, quantum computing can quickly provide decisions and optimize cooling strategies to avoid over-cooling or under-cooling, further improving overall energy efficiency.

[0199] In this embodiment, specifically, quantum computing simulates the dynamic changes of environmental variables and the cooling system, avoiding the computational delays and accuracy errors that may occur in traditional simulation methods. It can quickly process complex multidimensional data and optimize computational paths, significantly improving simulation efficiency. The quantum optimization algorithm can dynamically adjust the cooling system strategy based on real-time data during runtime, ensuring that the system is always in the best operating state and avoiding excessive energy consumption caused by environmental changes or load fluctuations. The quantum computing-based load prediction system can provide early warnings during high loads and adjust the allocation of cooling resources, optimizing energy use and coping with sudden weather changes or load increases, ensuring efficient system operation. By precisely optimizing the cooling strategy, the system reduces cooling energy waste (especially during high load periods), maximizes the power utilization efficiency (PUE) of the data center, achieves energy conservation and emission reduction, and conforms to the development direction of modern green technologies. At the same time, quantum computing can also provide intelligent decision support for data center operators, enabling them to react quickly in the face of complex environments and operating conditions, ensuring system stability and energy saving.

[0200] In this embodiment, specifically, the combination of quantum computing simulation, quantum optimization, and quantum analogy techniques not only solves the efficiency problem of traditional cooling systems in the face of complex dynamic environments, but also constructs a completely new path for optimizing data center cooling systems. The high efficiency and parallel processing capabilities of quantum computing ensure rapid adjustment of cooling solutions under changing environments, while providing real-time decision support for operators, enabling data centers to operate stably with optimal power utilization efficiency (PUE) under different load and climate conditions.

[0201] Example 3:

[0202] like Figure 3 As shown, to solve the above-mentioned technical problems, based on Embodiment 1, another technical solution adopted in this application is: a data center power utilization efficiency simulation calculation system for indirect evaporative cooling air conditioning, comprising:

[0203] The quantum modeling and simulation module is configured to build a quantum simulation model of the cooling system and environment based on a quantum computing platform, and to perform quantum many-body simulations.

[0204] The quantum optimization and computation module is configured to run quantum variational optimization algorithms and quantum scheduling algorithms to calculate optimal control parameters and resource allocation schemes;

[0205] The quantum prediction and learning module is configured to run quantum neural networks and quantum reinforcement learning models, and to perform load prediction and model calibration.

[0206] The deviation analysis and correction module is used to analyze the deviation between measured and simulated data, and to use quantum pattern recognition technology to locate the cause and correct the model parameters.

[0207] The real-time scheduling and control module is configured to generate dynamic scheduling commands to perform closed-loop control and emergency response for the cooling unit.

[0208] For other details regarding the implementation techniques of each module in the above embodiments, please refer to the description in the simulation calculation method of data center power utilization efficiency value of indirect evaporative cooling air conditioner in Embodiment 1 above, which will not be repeated here.

[0209] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system-type embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0210] Example 4:

[0211] like Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. It illustrates a structural schematic diagram suitable for implementing the electronic device in the embodiment of the present disclosure. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0212] like Figure 4 As shown, the electronic device includes a processor, a memory, and a communication interface. The memory stores a computer program, and when the processor executes the computer program, it implements the data center power utilization efficiency simulation calculation method for the indirect evaporative cooling air conditioner of the various embodiments of this disclosure. The electronic device can exchange data with other devices or systems through the communication interface to achieve real-time updating and sharing of drug information.

[0213] The processor in the aforementioned electronic device serves as its core, responsible for executing the computer program stored in the memory to implement various functions of the paperless conference terminal's intelligent interaction method. The processor can employ a high-performance multi-core CPU or a dedicated chip to meet the demands of complex calculations and real-time processing. The memory stores the operating system, applications, data, and computer programs. In this embodiment, the memory stores the computer program implementing the paperless conference terminal's intelligent interaction method. The memory can be RAM, ROM, Flash memory, or other types of non-volatile memory. The communication interface connects the electronic device to other devices or networks, enabling data transmission and exchange. In this embodiment, the communication interface supports multiple communication protocols and interface standards, such as Wi-Fi, Bluetooth, USB, and Ethernet, to meet communication needs in different scenarios.

[0214] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0215] Example 5:

[0216] According to embodiments of the present disclosure, a computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements the functions of the aforementioned data center power utilization efficiency value simulation calculation method for indirect evaporative cooling air conditioning according to various embodiments of the present disclosure.

[0217] The aforementioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0218] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0219] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for simulating data center power usage effectiveness value of indirect evaporative cooling air conditioning, characterized in that, The method comprises the following steps: Based on the quantum computing platform, the IT load of the data center, the indirect evaporative cooling unit and the quantum simulation model of its dynamic environment are constructed, the dynamic correlation between the states of the cooling units and the complex environmental variables is established through quantum many-body simulation, and the specific steps include: Mapping the cooling unit state, fan speed and equipment load of the indirect evaporative cooling air conditioner to the state of a quantum bit; Using the quantum entanglement characteristics to process the nonlinear interaction effects between the cooling units and between the cooling units and the external temperature, humidity and wind speed environmental variables; Simulating the response of the cooling unit under different environmental conditions in parallel on the quantum computing platform to establish a dynamic environment simulation model; Based on the quantum simulation model, the optimal combination of control parameters of the cooling unit is dynamically solved by using a quantum optimization algorithm, and the specific steps include: Using a quantum variational optimization algorithm, taking the energy efficiency ratio of the cooling unit as the objective function, and taking the fan speed, cooling liquid flow and evaporative cooling mode as the optimization variables; Parallel search for the optimal solution in the multi-dimensional control space, dynamically adjust the control strategy combined with real-time operation data, and output the optimal control parameters that meet the current environmental and load demand to realize the simulation calculation and optimization of the electric energy utilization efficiency value; Using quantum machine learning to construct a load prediction model, analyzing historical operation data of the data center, predicting the IT equipment thermal load and meteorological changes in the future period, and generating the optimal allocation scheme of cooling resources combined with the quantum scheduling algorithm; Based on the deviation between real-time monitoring data and simulation prediction data, the quantum state representation and pattern recognition technology are used to locate the deviation source and correct the simulation model parameters; Based on the corrected simulation model and prediction results, the dynamic scheduling instructions are generated through the quantum real-time scheduling engine to realize the closed-loop control and multi-objective energy efficiency optimization of the cooling unit, and realize the real-time simulation and management of the electric energy utilization efficiency value of the data center.

2. The data center power usage effectiveness value emulation calculation method of an indirect evaporative cooling air conditioner according to claim 1, characterized in that, The quantum machine learning is used to construct a load prediction model, and the specific steps include: Constructing a quantum feature embedding model to map historical load data, computer room temperature trends and external meteorological data to a high-dimensional quantum state space; Using a parameterized quantum circuit to construct a quantum neural network to learn the spatiotemporal distribution characteristics and nonlinear variation law of the data center thermal load; Combined with the prediction calibration mechanism of quantum reinforcement learning, when the prediction error exceeds the preset threshold, the model parameters are automatically adjusted, and the load prediction value in the future period is output.

3. The data center power usage effectiveness value emulation calculation method of an indirect evaporative cooling air conditioner according to claim 1, characterized in that, The quantum scheduling algorithm is combined to generate the optimal allocation scheme of cooling resources, and the specific steps include: Convert the cooling resource scheduling problem into a quantum combinatorial optimization problem; Using quantum annealing algorithm or quantum approximate optimization algorithm, under the premise of meeting the computer room temperature constraint, taking the minimum total energy consumption as the target, calculating the start-stop state and power distribution scheme of each cooling unit; According to the load prediction result, the pre-cooling window is identified, and the pre-cooling strategy including pre-cooling and cold storage is formulated.

4. The data center power usage effectiveness value emulation calculation method of an indirect evaporative cooling air conditioner according to claim 1, characterized in that, The quantum state representation and pattern recognition technology are used to locate the deviation source, and the specific steps include: Collecting actual energy consumption data and simulation prediction energy consumption data, and encoding the deviation size and trend of the actual energy consumption data and the simulation prediction energy consumption data into a quantum state vector; The quantum singular mode recognition technology is used to extract a main cause mode of the energy efficiency deviation from the deviation quantum state, and the cause mode includes evaporation efficiency reduction, device aging or external environment abnormality. According to the identified deviation cause, the quantum gradient estimation is used to adaptively update the evaporation efficiency coefficient or the heat exchange coefficient in the simulation model. 5.The data center power usage effectivity value emulation calculation method of an indirect evaporative cooling air conditioner according to claim 1, wherein, The dynamic scheduling instruction is generated by the quantum real-time scheduling engine, and the cooling unit is closed-loop controlled and multi-target energy efficiency optimized, specifically including: The deployment scheme generated by the quantum scheduling algorithm is converted into specific device control instructions, and the instructions include adjusting the chilled water outlet temperature, adjusting the fan speed or switching the evaporative cooling mode. Real-time device execution feedback is received, and when the execution result deviates from the expected target, a quantum rapid fine-tuning algorithm is triggered to generate a correction instruction. During the scheduling process, the temperature stability, total energy consumption minimization and device life extension are comprehensively considered, and a Pareto most suitable scheduling strategy is generated based on dynamic weights. 6.The data center power usage effectivity value emulation calculation method of an indirect evaporative cooling air conditioner according to claim 1, wherein, The method further includes: A quantum digital twin and emergency response mechanism is constructed: Based on the corrected simulation model, a quantum digital twin of the cooling unit is constructed, and the future operation trajectory of the device is evolved in real time; Device failure, thermal load surge or extreme weather scenarios are preplayed by using quantum parallel simulation technology, and the risk levels of different emergency strategies are evaluated; An emergency response decision including load transfer, standby link activation or operation mode switching is quickly generated by using a quantum optimization algorithm. 7.The data center power usage effectivity value emulation calculation method of an indirect evaporative cooling air conditioner according to claim 1, wherein, The method further includes a full life cycle energy efficiency management step: A quantum computing is used to model the cooling system throughout its life cycle, and the effects of device wear, aging and technology upgrade on the electrical energy utilization efficiency are dynamically evaluated; Based on long-term operation data, an adaptive scheduling library is constructed, and a quantum reinforcement learning method is used to iteratively optimize the scheduling strategy to identify and eliminate energy waste points in operation.

8. The system for simulating and calculating the PUE value of the data center air-conditioned by the indirect evaporative cooling air-conditioner according to any one of claims 1 to 7, wherein It includes: A quantum modeling and simulation module is configured to construct a quantum simulation model of the cooling system and the environment based on a quantum computing platform, and perform quantum many-body simulation; A quantum optimization and calculation module is configured to run a quantum variational optimization algorithm and a quantum scheduling algorithm to calculate optimal control parameters and resource deployment schemes; A quantum prediction and learning module is configured to run a quantum neural network and a quantum reinforcement learning model to perform load prediction and model calibration; A deviation analysis and correction module is configured to analyze the deviation between measured and simulated data, locate the cause by using quantum mode recognition technology, and correct the model parameters; A real-time scheduling and control module is configured to generate dynamic scheduling instructions to closed-loop control and emergency response of the cooling unit.

Images