Energy consumption optimization method, device and equipment for heating, ventilation and air conditioning system and storage medium

Abstract

The invention belongs to the technical field of air conditioning system control, and discloses a heating ventilation air conditioning system energy consumption optimization method, device and equipment and a storage medium. Exporting the physical model of the heating ventilation air-conditioning system as an FMU file; an FMU file is loaded through an interface of Python, and an optimization solution algorithm is constructed; obtaining operation parameters of the target equipment based on the current cooling load by utilizing an optimization solution algorithm; the method comprises the steps that target equipment operation parameters are issued to register addresses of corresponding point positions of a heating ventilation air conditioning system to achieve energy consumption optimization control, a regional cooling system model is established by adopting a Buildings library in Modelica, the lowest power consumption serves as an optimization target, the genetic algorithm is used for solving the optimal operation working condition parameters of all subsystems under the condition that the cooling capacity supply requirement is met, and the optimal operation working condition parameters of all the subsystems are calculated according to the optimal operation working condition parameters of all the subsystems under the condition that the cooling capacity supply requirement is met. The problem of multi-device linkage can be solved, and automatic optimization control can be carried out on a complex system through a computer technology without depending on experience.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning system control, and in particular to a method, device, equipment and storage medium for optimizing energy consumption of a heating, ventilation and air conditioning system. Background Art

[0002] Currently, there are two main approaches to optimizing energy consumption in air conditioning systems, both domestically and internationally. One approach involves using more energy-efficient equipment, such as high-efficiency chillers and variable-frequency water pumps. This approach fails to achieve optimal operating conditions for a multi-device system operating in a coordinated manner. The other approach involves using PID control logic, which automatically adjusts the system by setting temperature and pressure differentials. This requires industry experience to fine-tune the PID control targets based on different scenarios, making it difficult to achieve global optimization through empirical analysis for large and complex systems.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, system, equipment and storage medium for optimizing the energy consumption of HVAC systems, aiming to solve the technical problems that the energy consumption optimization of air-conditioning systems at home and abroad cannot solve the optimal working conditions of multi-device linkage operation systems, and it is difficult to achieve global optimization through experience for large and complex systems.

[0005] To achieve the above objectives, the present invention provides a method for optimizing energy consumption of a heating, ventilation and air conditioning system, the method comprising the following steps:

[0006] Using the Modelica multi-domain modeling language, OpenModelica, Dymola, or MWORKS.Sysplorer platforms, and integrating the Modelica Buildings Library and the Modelica Standard Library, to build physical models of HVAC systems;

[0007] Exporting the HVAC system physical model as an FMU file;

[0008] Load the FMU file through the Python interface and build an optimization solution algorithm;

[0009] Obtaining a current cooling load of the HVAC system, and performing an iterative solution based on the current cooling load using the optimization solution algorithm to obtain target equipment operating parameters;

[0010] The SCADA host computer is connected via the OPC UA protocol, and the target device operating parameters are sent to the register address of the corresponding point of the HVAC system to optimize the energy consumption of the HVAC system through the target device operating parameters.

[0011] In some embodiments, the components corresponding to the physical model of the HVAC system include a chiller, a water pump, a cooling tower and a building cooling load. The water pump includes a chilled water pump and a cooling water pump. The chiller module is based on the first component and integrates the DOE-2.1 standard algorithm to achieve dynamic coupling of the compressor efficiency curve and the partial load ratio; the water pump module adopts the second component to achieve real-time coupling calculation between mass flow, head and power parameters; the cooling tower module adopts the third component to establish a heat transfer differential equation based on Merkel theory to realize the wet-bulb temperature parameter for heat exchange calculation; the building cooling load is used to construct an equivalent thermal resistance network model under a fixed cooling load condition through a preset library.

[0012] In some embodiments, the optimization solution algorithm includes: a main algorithm, gene coding, a fitness function and output parameters. The main algorithm is determined based on python according to the preset algorithm logic. The gene coding uses the chiller start and stop parameters, water pump frequency setting value, and cooling tower fan speed as individual gene fragments. The fitness function is the inverse of the sum of the absolute deviation of the total energy consumption of the system and the actual cooling capacity from the cooling load. The output parameter is the individual gene fragment of the optimal energy consumption of the optimization solution algorithm.

[0013] In some embodiments, the preset algorithm logic is to initialize the population, calculate the fitness of individuals in the initial population, and determine whether the stopping condition is met based on the fitness. If the stopping condition is not met, the population is updated through selection, crossover, and mutation operations, and the individual fitness is determined through the new population until the stopping condition is met.

[0014] In some embodiments, the initialization population is used to initialize the device parameters input to the Modelica simulation model, and a random generation of the initialization population is used to ensure a uniform distribution of the solution space; the fitness calculation is to dynamically simulate the parameter settings of the FMU using the individually encoded device parameters to calculate the difference between the total energy consumption and the actual cooling capacity and the required cooling load. The stopping condition is determined based on whether the optimal solution is continuously iterated and stable or reaches a preset number of iterations, and the target device operating parameters are output.

[0015] In some embodiments, the iterative solution adopts a random generation strategy when initializing the population to ensure a uniform distribution of the solution space, triggers a stopping condition when the optimal solution is continuously iterated and stabilized or reaches a preset number of iterations, and dynamically increases the mutation probability when the algorithm converges slowly.

[0016] In addition, to achieve the above-mentioned purpose, the present invention further proposes a heating, ventilation and air conditioning system energy consumption optimization device, the heating, ventilation and air conditioning system energy consumption optimization device comprising:

[0017] Modeling and simulation module, which is used to build HVAC system physical models based on the Modelica multi-domain modeling language using OpenModelica, Dymola, or MWORKS.Sysplorer platforms, integrating the Modelica Buildings Library and the Modelica Standard Library;

[0018] The modeling and simulation module is used to export the HVAC system physical model as an FMU file;

[0019] An optimization solution module, used to load the FMU file through a Python interface and build an optimization solution algorithm;

[0020] The optimization solution module is used to obtain the current cooling load of the HVAC system and perform iterative solution based on the current cooling load using the optimization solution algorithm to obtain target equipment operating parameters;

[0021] The optimization control module is used to connect to the SCADA host computer through the OPC UA protocol and send the target device operating parameters to the register address of the corresponding point of the HVAC system to optimize the energy consumption of the HVAC system through the target device operating parameters.

[0022] In some embodiments, the components corresponding to the physical model of the HVAC system include a chiller, a water pump, a cooling tower and a building cooling load. The water pump includes a chilled water pump and a cooling water pump. The chiller module is based on the first component and integrates the DOE-2.1 standard algorithm to achieve dynamic coupling of the compressor efficiency curve and the partial load ratio; the water pump module adopts the second component to achieve real-time coupling calculation between mass flow, head and power parameters; the cooling tower module adopts the third component to establish a heat transfer differential equation based on Merkel theory to realize the wet-bulb temperature parameter for heat exchange calculation; the building cooling load is used to construct an equivalent thermal resistance network model under a fixed cooling load condition through a preset library.

[0023] In addition, to achieve the above-mentioned purpose, the present invention also proposes a HVAC system energy consumption optimization device, which includes: a memory, a processor, and a HVAC system energy consumption optimization program stored on the memory and runnable on the processor, and the HVAC system energy consumption optimization program is configured to implement the steps of the HVAC system energy consumption optimization method described above.

[0024] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a HVAC system energy consumption optimization program is stored. When the HVAC system energy consumption optimization program is executed by a processor, the steps of the HVAC system energy consumption optimization method as described above are implemented.

[0025] The present invention constructs a physical model of the HVAC system; exports the physical model of the HVAC system as an FMU file; loads the FMU file through a Python interface and constructs an optimization solution algorithm; uses the optimization solution algorithm to obtain the target device operating parameters based on the current cooling load; and sends the target device operating parameters to the register address of the corresponding point in the HVAC system to achieve energy consumption optimization control. By adopting the Buildings library in Modelica to establish a regional cooling system model, with the minimum power consumption as the optimization goal, a genetic algorithm is used to solve the optimal operating parameters of each subsystem while meeting the demand for cooling supply. This can not only solve the problem of multi-device linkage, but also automatically optimize and control complex systems through computer technology without relying on experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of a first embodiment of a method for optimizing energy consumption of a heating, ventilation and air conditioning system according to the present invention;

[0027] Figure 2 Schematic diagram of the system architecture of the HVAC system energy consumption optimization method of the present invention;

[0028] Figure 3 This is a logic diagram for optimizing and solving the energy consumption optimization method for a heating, ventilation and air conditioning system according to the present invention;

[0029] Figure 4 This is a structural block diagram of the first embodiment of the energy consumption optimization device for a HVAC system of the present invention.

[0030] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0031] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0032] The embodiment of the present invention provides a method for optimizing energy consumption of a heating, ventilation and air conditioning system. Figure 1 , Figure 1 This is a flow chart of a first embodiment of a method for optimizing energy consumption of a heating, ventilation and air conditioning system according to the present invention.

[0033] In this embodiment, the HVAC system energy consumption optimization method includes the following steps:

[0034] Step S10: Based on the Modelica multi-domain modeling language, OpenModelica, Dymola or MWORKS.Sysplorer platform is adopted to integrate the Modelica Buildings Library and the Modelica Standard Library to build a physical model of the HVAC system.

[0035] In this embodiment, the executor of this embodiment is a HVAC system energy consumption optimization device, wherein the HVAC system energy consumption optimization device has functions such as data processing, data communication and program running. The HVAC system energy consumption optimization device can be a computer terminal device or other network device, and of course it can also be other devices with similar functions. This embodiment does not limit this.

[0036] It should be noted that currently, there are two main approaches to optimizing energy consumption for air conditioning systems, both domestically and internationally. One approach involves using more energy-efficient equipment, such as high-efficiency chillers and variable-frequency water pumps, but this approach fails to address the optimal operating conditions for a multi-device system operating in a coordinated manner. The other approach involves using PID control logic, which automatically adjusts the system by setting temperature and pressure differentials. This requires industry experience to fine-tune the PID control targets based on different scenarios, making it difficult to achieve global optimization through empirical analysis for large and complex systems.

[0037] In order to solve the above technical problems, in this embodiment, a physical model of the HVAC system is constructed; the physical model of the HVAC system is exported as an FMU file; the FMU file is loaded through the Python interface, and an optimization solution algorithm is constructed; the optimization solution algorithm is used to obtain the target device operating parameters based on the current cooling load; the target device operating parameters are sent to the register address of the corresponding point of the HVAC system to realize energy consumption optimization control. By adopting the Buildings library in Modelica to establish a regional cooling system model, with the minimum power consumption as the optimization goal, a genetic algorithm is used to solve the optimal operating parameters of each subsystem while meeting the demand for cooling supply. This can not only solve the problem of multi-device linkage, but also automatically optimize and control complex systems through computer technology without relying on experience. Specifically, it can be achieved as follows.

[0038] In the specific implementation, the overall structure is first described in this embodiment, and the specific Figure 2 shown. Figure 2The system includes a modeling and simulation module, an optimization and solution module, and a data acquisition and instruction issuance module. The modeling and simulation module uses a modular modeling approach, building a modeling environment based on the open-source software OpenModelica 3.0.0 and Dymola 2023x or the domestically developed platform MWORKS.Sysplorer 2022. It integrates the open-source Modelica Buildings Library 9.1.0 and the basic Modelica Standard Library 4.0.0 to create an air conditioning and cooling system model that includes core components such as chillers, chilled water pumps, cooling water pumps, cooling towers, and building cooling loads. Specifically, the chiller module, based on the Buildings.Fluid.Chillers.ElectricEIR component, integrates the U.S. Department of Energy (DOE)-2.1 standard algorithm to implement dynamic energy consumption analysis coupled with the compressor efficiency curve (EIR-fPLR) and the part load ratio (PLR). The pump module uses the Buildings.Fluid.Movers.FlowControlled_m_flow component to implement real-time coupled calculations of mass flow, head, and power parameters. The cooling tower module uses the Buildings.Fluid.HeatExchangers.CoolingTowers.YorkCalc component, which establishes heat transfer differential equations based on Merkel theory and calculates heat exchange based on wet-bulb temperature parameters. The building load side uses the Modelica.Thermal.HeatTransfer library to construct an equivalent thermal resistance network model for fixed cooling load conditions. Each component, connected by the Modelica.Fluid library, establishes a hydraulic network, forming a complete topology for the chilled water and cooling water circulation systems. The parameter control module dynamically adjusts the water pump operating frequency and the start and stop logic of the chiller and cooling tower by setting fixed control signals.

[0039] After the Modelica simulation model of the cooling and air-conditioning system is constructed, it is exported as an FMU format file, providing a standardized simulation interface for subsequent algorithm optimization and solution. As a model encapsulation solution compliant with the international FMI (Functional Mock-up Interface) specification, the FMU (Functional Mock-up Unit) aims to enable efficient collaboration and system integration of simulation models across multiple disciplines. Its core features are reflected in three aspects: interface standardization—strictly adhering to the FMI 2.0 specification developed by the International Modelica Association, it clearly defines the model's input / output variable sets, simulation step control mechanisms, and data exchange protocols; model blackboxing—through the compilation process, the source code is irreversibly converted to a binary executable file, effectively protecting the model's intellectual property and trade secrets while fully preserving its dynamic characteristics; and cross-platform compatibility—relying on the platform independence established by the FMI standard, a single FMU file can run across Windows, Linux, and macOS operating systems and supports seamless integration in heterogeneous tool chains such as Python, MATLAB, and Simulink.

[0040] The optimization solution module first loads the FMU file exported by the Modelica modeling and simulation module through Python, and then implements the genetic algorithm optimization solution logic. The main steps are to build a cyclic iterative process through core steps such as initializing the population individual encoding, fitness evaluation, and genetic operations (selection-crossover-mutation). The population evolution iteration is continuously executed until the convergence threshold is met, and the optimal control parameter set that meets the multi-objective constraints is finally output. Initializing the population mainly initializes the device parameters input into the Modelica simulation model, and a random initialization population method is used to ensure a uniform distribution of the solution space. Fitness calculation mainly uses the individual encoded device parameters to dynamically simulate the FMU parameter settings and calculate the difference between the total energy consumption and the actual cooling capacity and the required cooling load. The fitness function is defined as the comprehensive inverse of energy consumption and load deviation, and the weight coefficient is set according to the optimization goal; the termination condition is mainly based on the stability of continuous iterations of the optimal solution or the termination of the algorithm when the preset number of iterations is reached, and the optimal control parameters are output; the core of the genetic operation mainly includes three steps: selection, crossover, and mutation. The selection operation uses a tournament mechanism to screen individuals with high fitness, retain elite individuals and directly enter the next generation, and the rest are selected through competition. The crossover operation performs gene segment exchange on the selected individuals (such as simulating binary crossover) to generate a new solution with both parental advantages. The mutation operation uses a Gaussian perturbation mutation strategy to generate new gene segments. When the algorithm converges slowly, the mutation probability is increased to break through the local optimal limit. Through the synergistic effect of selection, crossover, and mutation, the global search and local optimization capabilities are balanced to improve convergence efficiency. The final optimization solution logic diagram is as follows Figure 3 shown.

[0041] The data acquisition and instruction issuance module is connected to the SCADA system through the OPC UA protocol to realize data acquisition and instruction issuance. The SCADA system is a computer control system widely used in the field of industrial automation, which is used to monitor, collect and analyze remote device data in real time and realize centralized control and management. It mainly realizes centralized monitoring and remote control of decentralized devices through a three-level architecture consisting of the field layer (sensors, PLCs, RTUs and other devices collect temperature, pressure and other data in real time and execute control instructions), the communication layer (based on Modbus, Industrial Ethernet and other protocols to achieve efficient data transmission between remote sites and control centers) and the monitoring layer (HMI interface, server and database to complete data visualization, alarm management and historical analysis). Data acquisition refers to the Python program connecting to the SCADA server based on the OPC UA driver, reading the field device access point data such as the chiller supply and return water temperature, water pump flow, pipeline water pressure, etc. through the OPC UA protocol, and storing it in real time in the historical database. Instruction issuance refers to the Python program connecting to the SCADA server based on the OPC UA driver, and issuing the optimal operating parameters of the equipment calculated by the optimization solution module to the specific equipment through the OPC UA protocol.

[0042] In the specific implementation, the OpenModelica, Dymola or MWORKS.Sysplorer platform is adopted based on the Modelica multi-domain modeling language, and the Modelica Buildings Library and Modelica Standard Library are integrated to build the physical model of the HVAC system.

[0043] Among them, the components corresponding to the physical model of the HVAC system include chillers, water pumps, cooling towers and building cooling loads. The water pumps include chilled water pumps and cooling water pumps. The chiller module is based on the first component and integrates the DOE-2.1 standard algorithm to achieve dynamic coupling between the compressor efficiency curve and the partial load ratio; the water pump module adopts the second component to achieve real-time coupling calculation between mass flow, head and power parameters; the cooling tower module adopts the third component to establish a heat transfer differential equation based on Merkel theory to realize the wet-bulb temperature parameter for heat exchange calculation; the building cooling load is used to construct an equivalent thermal resistance network model under a fixed cooling load condition through a preset library.

[0044] It should be noted that the first component is, for example, the Buildings.Fluid.Chillers.ElectricEIR component, the second component is, for example, the Buildings.Fluid.Movers.FlowControlled_m_flow component, the third component is, for example, the Buildings.Fluid.HeatExchangers.CoolingTowers.YorkCalc component, and the preset library is, for example, the Modelica.Thermal.HeatTransfer library.

[0045] Step S20: exporting the HVAC system physical model as an FMU file.

[0046] It should be noted that the FMU (Functional Mock-up Unit), as a model encapsulation solution that complies with the international FMI (Functional Mock-up Interface) specification, aims to achieve efficient collaboration and system integration of simulation models in multiple disciplines. Its core features are reflected in three aspects: interface standardization - strictly adhering to the FMI 2.0 specification developed by the International Modelica Association, clearly defining the model's input / output variable sets, simulation step control mechanism, and data interaction protocol; model black boxing - achieving irreversible conversion of source code through the compilation process to generate binary executable files, effectively protecting the model's intellectual property and trade secrets while fully preserving the model's dynamic characteristics; cross-platform compatibility - relying on the platform independence established by the FMI standard, a single FMU file can run across Windows / Linux / macOS operating systems and support seamless integration in heterogeneous tool chains such as Python, MATLAB, and Simulink.

[0047] After completing the construction of the HVAC system physical model, the model is exported as an FMU format file to provide a standardized simulation interface for subsequent algorithm optimization and solution.

[0048] Step S30: Load the FMU file through the Python interface and build an optimization solution algorithm.

[0049] In the specific implementation, the optimization solution algorithm includes: a main algorithm, gene coding, fitness function and output parameters. The main algorithm is determined based on Python according to the preset algorithm logic. The gene coding uses the chiller start and stop parameters, water pump frequency setting value, and cooling tower fan speed as individual gene fragments. The fitness function is the inverse of the sum of the absolute deviation of the total energy consumption of the system and the actual cooling capacity from the cooling load. The output parameter is the individual gene fragment of the optimal energy consumption of the optimization solution algorithm.

[0050] Further, the algorithm logic can refer to Figure 3 As shown, the preset algorithm logic is to initialize the population, calculate the fitness of individuals in the initial population, and determine whether the stopping condition is met based on the fitness. If the stopping condition is not met, the population is updated through selection, crossover and mutation operations, and the individual fitness is determined through the new population until the stopping condition is met.

[0051] It should be noted that the population initialization is to initialize the device parameters input to the Modelica simulation model, and the random generation of the initialization population is used to ensure the uniform distribution of the solution space; the fitness calculation is to dynamically simulate the FMU parameter settings using the individual encoded device parameters to calculate the difference between the total energy consumption and the actual cooling capacity and the required cooling load. The stopping condition is determined based on whether the optimal solution is continuously iterated and stable or reaches the preset number of iterations, and the target device operating parameters are output.

[0052] For example, a cyclic iterative process is constructed through core steps such as initializing individual population codes, fitness evaluation, and genetic operations (selection-crossover-mutation). The population evolution is iterated continuously until a convergence threshold is met, ultimately outputting an optimal set of control parameters that meets multiple objective constraints. Initializing the population primarily initializes the device parameters input to the Modelica simulation model, using a randomly generated initial population to ensure a uniform distribution across the solution space. Fitness calculation involves dynamically simulating the FMU parameters using the individual encoded device parameters, calculating the difference between total energy consumption and actual cooling capacity and the required cooling load. The fitness function is defined as the combined inverse of the energy consumption and load deviations, with weighting coefficients set according to the optimization objective. Termination criteria are determined primarily when the optimal solution stabilizes after continuous iterations or when a preset number of iterations has been reached, terminating the algorithm and outputting the optimal control parameters. The core genetic operations consist of three steps: selection, crossover, and mutation. The selection process uses a tournament mechanism to select individuals with high fitness, retaining elite individuals and advancing them directly to the next generation. The remaining individuals are then selected through competition. The crossover process involves exchanging gene segments within the selected individuals (e.g., simulating binary crossover) to generate a new solution that combines the advantages of both parents. The mutation operation uses a Gaussian perturbation mutation strategy to generate new gene fragments. When the algorithm converges slowly, the mutation probability is increased to break through the local optimal limit. Through the synergistic effect of selection, crossover, and mutation, the global search and local optimization capabilities are balanced to improve convergence efficiency.

[0053] Step S40: obtaining the current cooling load of the HVAC system, and performing iterative solution based on the current cooling load using the optimization solution algorithm to obtain target equipment operating parameters.

[0054] In practice, the iterative solution process using the optimization algorithm uses a random generation strategy when initializing the population to ensure a uniform distribution of the solution space. A stopping condition is triggered when the optimal solution stabilizes after consecutive iterations or reaches a preset number of iterations. The mutation probability is dynamically increased when the algorithm converges slowly. The optimization algorithm is essentially a genetic algorithm, and the optimal solution obtained through iterations is the target device operating parameters.

[0055] Step S50: connecting to the SCADA host computer via the OPC UA protocol, sending the target device operating parameters to the register address of the corresponding point of the HVAC system, so as to optimize the energy consumption of the HVAC system through the target device operating parameters.

[0056] In this embodiment, the target device operating parameters are distributed. Specifically, the instruction distribution module connects to the SCADA host computer via the OPC UA protocol and sends the optimal operating parameters of each device to the register address of the corresponding point through the protocol, thereby implementing the distribution of operating parameter instructions. After completing this distribution operation, the operating parameters of the HVAC system devices can be adjusted, thereby optimizing the HVAC system's energy consumption.

[0057] In this embodiment, a physical model of the HVAC system is constructed; the physical model of the HVAC system is exported as an FMU file; the FMU file is loaded through a Python interface, and an optimization solution algorithm is constructed; the optimization solution algorithm is used to obtain the target device operating parameters based on the current cooling load; the target device operating parameters are sent to the register addresses of the corresponding points in the HVAC system to achieve energy consumption optimization control. By using the Buildings library in Modelica to establish a district cooling system model, with the minimum power consumption as the optimization goal, a genetic algorithm is used to solve the optimal operating parameters of each subsystem while meeting the cooling supply demand. This can not only solve the problem of multi-device linkage, but also automatically optimize and control complex systems through computer technology without relying on experience.

[0058] In addition, an embodiment of the present invention further proposes a storage medium storing a HVAC system energy consumption optimization program. When the HVAC system energy consumption optimization program is executed by a processor, the steps of the HVAC system energy consumption optimization method described above are implemented.

[0059] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the energy consumption optimization device for a HVAC system of the present invention.

[0060] like Figure 4 As shown, the HVAC system energy consumption optimization device proposed in the embodiment of the present invention includes:

[0061] Modeling and simulation module 10, for building a physical model of a HVAC system based on the Modelica multi-domain modeling language using OpenModelica, Dymola or MWORKS.Sysplorer platform and integrating the Modelica Buildings Library and the Modelica Standard Library;

[0062] The modeling and simulation module 10 is used to export the HVAC system physical model as an FMU file;

[0063] The optimization solution module 20 is used to load the FMU file through the Python interface and build an optimization solution algorithm;

[0064] The optimization solution module 20 is used to obtain the current cooling load of the HVAC system and perform iterative solution based on the current cooling load using the optimization solution algorithm to obtain target equipment operating parameters;

[0065] The optimization control module 30 is used to connect to the SCADA host computer through the OPC UA protocol and send the target device operating parameters to the register address of the corresponding point of the HVAC system to optimize the energy consumption of the HVAC system through the target device operating parameters.

[0066] In this embodiment, a physical model of the HVAC system is constructed; the physical model of the HVAC system is exported as an FMU file; the FMU file is loaded through a Python interface, and an optimization solution algorithm is constructed; the optimization solution algorithm is used to obtain the target device operating parameters based on the current cooling load; the target device operating parameters are sent to the register addresses of the corresponding points in the HVAC system to achieve energy consumption optimization control. By using the Buildings library in Modelica to establish a district cooling system model, with the minimum power consumption as the optimization goal, a genetic algorithm is used to solve the optimal operating parameters of each subsystem while meeting the cooling supply demand. This can not only solve the problem of multi-device linkage, but also automatically optimize and control complex systems through computer technology without relying on experience.

[0067] In some embodiments, the components corresponding to the physical model of the HVAC system include a chiller, a water pump, a cooling tower and a building cooling load. The water pump includes a chilled water pump and a cooling water pump. The chiller module is based on the first component and integrates the DOE-2.1 standard algorithm to achieve dynamic coupling of the compressor efficiency curve and the partial load ratio; the water pump module adopts the second component to achieve real-time coupling calculation between mass flow, head and power parameters; the cooling tower module adopts the third component to establish a heat transfer differential equation based on Merkel theory to realize the wet-bulb temperature parameter for heat exchange calculation; the building cooling load is used to construct an equivalent thermal resistance network model under a fixed cooling load condition through a preset library.

[0068] In some embodiments, the optimization solution algorithm includes: a main algorithm, gene coding, a fitness function and output parameters. The main algorithm is determined based on python according to the preset algorithm logic. The gene coding uses the chiller start and stop parameters, water pump frequency setting value, and cooling tower fan speed as individual gene fragments. The fitness function is the inverse of the sum of the absolute deviation of the total energy consumption of the system and the actual cooling capacity from the cooling load. The output parameter is the individual gene fragment of the optimal energy consumption of the optimization solution algorithm.

[0069] In some embodiments, the preset algorithm logic is to initialize the population, calculate the fitness of individuals in the initial population, and determine whether the stopping condition is met based on the fitness. If the stopping condition is not met, the population is updated through selection, crossover, and mutation operations, and the individual fitness is determined through the new population until the stopping condition is met.

[0070] In some embodiments, the initialization population is used to initialize the device parameters input to the Modelica simulation model, and a random generation of the initialization population is used to ensure a uniform distribution of the solution space; the fitness calculation is to dynamically simulate the parameter settings of the FMU using the individually encoded device parameters to calculate the difference between the total energy consumption and the actual cooling capacity and the required cooling load. The stopping condition is determined based on whether the optimal solution is continuously iterated and stable or reaches a preset number of iterations, and the target device operating parameters are output.

[0071] In some embodiments, the iterative solution adopts a random generation strategy when initializing the population to ensure a uniform distribution of the solution space, triggers a stopping condition when the optimal solution is continuously iterated and stabilized or reaches a preset number of iterations, and dynamically increases the mutation probability when the algorithm converges slowly.

[0072] An embodiment of the present application also provides a HVAC system energy consumption optimization device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store a HVAC system energy consumption optimization program; the processor is used to implement the above-mentioned HVAC system energy consumption optimization method when executing the program stored in the memory.

[0073] The communication bus mentioned in the HVAC system energy optimization device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, and a control bus.

[0074] The communication interface is used for communication between the above-mentioned HVAC system energy consumption optimization device and other devices.

[0075] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located remote from the processor.

[0076] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0077] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0078] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0079] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0080] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

[0081] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0082] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0083] In addition, for technical details not fully described in this embodiment, please refer to the HVAC system energy consumption optimization method provided in any embodiment of the present invention, and will not be repeated here.

[0084] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0085] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0086] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0087] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0088] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts of the above method.

Claims

1. A method for optimizing energy consumption of a heating, ventilation and air conditioning system, characterized in that: The HVAC system energy consumption optimization method comprises: Using the Modelica multi-domain modeling language, OpenModelica, Dymola, or MWORKS.Sysplorer platforms, and integrating the Modelica Buildings Library and the Modelica Standard Library, to build physical models of HVAC systems; Exporting the HVAC system physical model as an FMU file; Load the FMU file through the Python interface and build an optimization solution algorithm; Obtaining a current cooling load of the HVAC system, and performing an iterative solution based on the current cooling load using the optimization solution algorithm to obtain target equipment operating parameters; The SCADA host computer is connected via the OPC UA protocol, and the target device operating parameters are sent to the register address of the corresponding point of the HVAC system to optimize the energy consumption of the HVAC system through the target device operating parameters.

2. The HVAC system energy consumption optimization method according to claim 1, characterized in that: The components corresponding to the HVAC system physical model include a chiller, a water pump, a cooling tower, and a building cooling load. The water pump includes a refrigerated water pump and a cooling water pump. The chiller module is based on the first component and integrates DOE- 2.1 standard algorithm is used to achieve dynamic coupling between the compressor efficiency curve and the partial load ratio; the water pump module uses the second component to achieve real-time coupling calculation between mass flow, head and power parameters; the cooling tower module uses the third component to establish a heat transfer differential equation based on Merkel theory to realize heat exchange calculation using wet-bulb temperature parameters; the building cooling load is used to construct an equivalent thermal resistance network model under fixed cooling load conditions through a preset library.

3. The HVAC system energy consumption optimization method according to claim 1, wherein: The optimization solution algorithm includes: a main algorithm, gene coding, a fitness function and output parameters. The main algorithm is determined based on Python according to the preset algorithm logic. The gene coding uses the chiller start and stop parameters, water pump frequency setting value, and cooling tower fan speed as individual gene fragments. The fitness function is the reciprocal of the sum of the absolute deviation of the total energy consumption of the system and the actual cooling capacity from the cooling load. The output parameter is the individual gene fragment of the optimal energy consumption of the optimization solution algorithm.

4. The method for optimizing energy consumption of a heating, ventilation and air conditioning system according to claim 3, wherein: The preset algorithm logic is to initialize the population, calculate the fitness of individuals in the initial population, determine whether the stopping condition is met based on the fitness, and if the stopping condition is not met, update the population through selection, crossover and mutation operations, and determine the individual fitness through the new population until the stopping condition is met.

5. The method for optimizing energy consumption of a heating, ventilation and air conditioning system according to claim 4, wherein: The initialization population is used to initialize the device parameters input to the Modelica simulation model, and a random generation of the initialization population is used to ensure a uniform distribution in the solution space. The fitness calculation is to dynamically simulate the parameter settings of the FMU using the individually encoded device parameters to calculate the difference between the total energy consumption and the actual cooling capacity and the required cooling load. The stopping condition is determined based on whether the optimal solution is continuously iterated and stable or reaches a preset number of iterations, and the target device operating parameters are output.

6. The method for optimizing energy consumption of a heating, ventilation and air conditioning system according to claim 1, wherein: The iterative solution adopts a random generation strategy when initializing the population to ensure a uniform distribution of the solution space. When the optimal solution is continuously iterated and stable or reaches a preset number of iterations, the stopping condition is triggered, and the mutation probability is dynamically increased when the algorithm converges slowly.

7. A heating, ventilation and air conditioning system energy consumption optimization device, characterized in that: The HVAC system energy consumption optimization device comprises: Modeling and simulation module, which is used to build HVAC system physical models based on the Modelica multi-domain modeling language using OpenModelica, Dymola, or MWORKS.Sysplorer platforms, integrating the Modelica Buildings Library and the Modelica Standard Library; The modeling and simulation module is used to export the HVAC system physical model as an FMU file; An optimization solution module, used to load the FMU file through a Python interface and build an optimization solution algorithm; The optimization solution module is used to obtain the current cooling load of the HVAC system and perform iterative solution based on the current cooling load using the optimization solution algorithm to obtain target equipment operating parameters; The optimization control module is used to connect to the SCADA host computer through the OPC UA protocol and send the target device operating parameters to the register address of the corresponding point of the HVAC system to optimize the energy consumption of the HVAC system through the target device operating parameters.

8. The HVAC system energy consumption optimization device according to claim 7, characterized in that: The components corresponding to the HVAC system physical model include a chiller, a water pump, a cooling tower, and a building cooling load. The water pump includes a refrigerated water pump and a cooling water pump. The chiller module is based on the first component and integrates DOE- 2.1 standard algorithm is used to achieve dynamic coupling between the compressor efficiency curve and the partial load ratio; the water pump module uses the second component to achieve real-time coupling calculation between mass flow, head and power parameters; the cooling tower module uses the third component to establish a heat transfer differential equation based on Merkel theory to realize heat exchange calculation using wet-bulb temperature parameters; the building cooling load is used to construct an equivalent thermal resistance network model under fixed cooling load conditions through a preset library.

9. A heating, ventilation and air conditioning system energy consumption optimization device, characterized in that: The HVAC system energy consumption optimization device includes: a memory, a processor, and a HVAC system energy consumption optimization program stored in the memory and executable on the processor. The HVAC system energy consumption optimization program is configured to implement the steps of the HVAC system energy consumption optimization method according to any one of claims 1 to 6.

10. A storage medium, characterized in that: The storage medium stores a HVAC system energy consumption optimization program, which, when executed by a processor, implements the steps of the HVAC system energy consumption optimization method according to any one of claims 1 to 6.

Images