Refrigeration system upper control method, device, equipment and storage medium

Abstract

The present application relates to a method, device, equipment and storage medium for upper-level control of a refrigeration system. The method comprises: based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, training multiple initial control strategies to obtain target control strategies corresponding to each initial control strategy, using the operating status, weather forecast data, and cold load forecast data of the refrigeration system to determine the optimal target control strategy from multiple target control strategies, and obtaining target control instructions according to the optimal target control strategy; the target control instructions are used to perform upper-level control on the refrigeration equipment in the refrigeration system. The method provided in the embodiment of the present application can solve the problem of low adaptability of a single control strategy under variable weather and building cold load conditions.

Description

Technical Field

[0001] The present application relates to the technical field of building refrigeration system control, and in particular to a refrigeration system upper-level control method, device, equipment and storage medium. Background Art

[0002] At present, the energy consumption of public building operation accounts for a large proportion of the energy consumption of building operation, and more than 40% of the energy consumption of public buildings comes from the refrigeration system. The refrigeration system generally includes equipment such as chillers, water distribution pumps, cooling towers, and air conditioning units, which can discharge the heat in the indoor air to the outdoor air through efficient heat exchange technology. The refrigeration system has complex hydraulic and thermal coupling characteristics, and the operating efficiency of different equipment components has complex mutual influences. Therefore, controlling the refrigeration system is an important method for the efficient operation of the refrigeration system.

[0003] The control of the refrigeration system is divided into upper control and lower control. Upper control refers to the control of the operating mode of the refrigeration system equipment, for example, setting the start and stop status of the chiller, the chiller outlet water temperature, etc. Lower control refers to the control of the components of the refrigeration system equipment, for example, setting the speed of the compressor in the chiller, etc. The energy efficiency improvement of the refrigeration system mainly depends on the upper control.

[0004] However, the current upper-level control method for refrigeration systems has a single strategy, resulting in low adaptability of the method. Summary of the invention

[0005] Based on this, it is necessary to provide a refrigeration system upper control method, device, equipment and storage medium to improve the adaptability of the refrigeration system upper control method in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a refrigeration system upper control method, comprising:

[0007] Based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain target control strategies corresponding to each initial control strategy;

[0008] Determine an optimal target control strategy from a plurality of target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system;

[0009] A target control instruction is obtained according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0010] In one embodiment, based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain target control strategies corresponding to each of the initial control strategies, including:

[0011] For each of the initial control strategies, according to the control target, the operating status, the cooling load measurement data and the historical meteorological data, a simulated control instruction output under the initial control strategy is obtained;

[0012] According to the simulation control instructions corresponding to each of the initial control strategies, the target control strategies corresponding to each of the initial control strategies are determined.

[0013] In one embodiment, determining the target control strategy corresponding to each initial control strategy according to the simulation control instruction corresponding to each initial control strategy includes:

[0014] For each simulation control instruction corresponding to the initial control strategy, the refrigeration equipment in the refrigeration system is controlled by using the simulation control instruction to obtain a control result and a new operating state corresponding to the simulation control instruction;

[0015] According to the control result and the new operation state corresponding to the simulation control instruction under each of the initial control strategies, the target control strategy corresponding to each of the initial control strategies is determined.

[0016] In one embodiment, the target control strategy corresponding to each initial control strategy is determined according to the control result and the new operation state corresponding to the simulation control instruction under each initial control strategy, including:

[0017] For each control result corresponding to the simulation control instruction under the initial control strategy, if the control result meets the preset condition, the initial control strategy is used as the target control strategy;

[0018] If the control result does not meet the preset condition, the initial control strategy is modified using the control result to obtain an intermediate control strategy, and the new analog control instruction output under the intermediate control strategy is executed according to the control target, the new operating state, the cooling load measurement data and the historical meteorological data. The refrigeration equipment in the refrigeration system is controlled using the new analog control instruction to obtain a new control result corresponding to the new analog control instruction and the next new operating state step, until the new control result meets the preset condition, and the control strategy of the analog control instruction output for the last time is used as the target control strategy.

[0019] In one embodiment, the optimal target control strategy is determined from a plurality of target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system, including:

[0020] According to the operating state, the cooling load forecast data and the meteorological forecast data, using each of the target control strategies, outputting simulation control instructions corresponding to each of the target control strategies;

[0021] For each of the simulation control instructions, obtaining a control result corresponding to the simulation control instruction;

[0022] According to each of the control results, an optimal target control strategy is determined from a plurality of the target control strategies.

[0023] In one embodiment, the method further comprises:

[0024] According to the performance simulation equation of each refrigeration device in the refrigeration system, an initial refrigeration system model is obtained;

[0025] The parameters in the initial refrigeration system model are calibrated using the cooling load, heating load and power data of the refrigeration system to obtain the refrigeration system model.

[0026] In a second aspect, the present application also provides a refrigeration system upper control device, comprising:

[0027] The first determination module is used to train multiple initial control strategies based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model to obtain the target control strategy corresponding to each of the initial control strategies.

[0028] The second determination module is used to determine the optimal target control strategy from multiple target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system.

[0029] The third determination module is used to obtain a target control instruction according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0031] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0032] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0033] The above-mentioned upper-level control method, device, equipment and storage medium of the refrigeration system train multiple initial control strategies based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, obtain the target control strategy corresponding to each initial control strategy, and use the operating status, weather forecast data, and cold load forecast data of the refrigeration system to determine the optimal target control strategy from multiple target control strategies, and obtain the target control instruction according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system. Due to the changeable characteristics of weather and building cold load, the adaptability of controlling the refrigeration system using only a single upper-level control strategy is low. Therefore, in the embodiment of the present application, an optimal control strategy is determined from multiple target control strategies for upper-level control, that is, the method provided by the embodiment of the present application can solve the problem of low adaptability of a single control strategy under changeable weather and building cold load conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 An application environment diagram of a refrigeration system upper control method provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of a flow chart of a refrigeration system upper control method provided in an embodiment of the present application;

[0037] Figure 3 One of the flow charts of a method for determining a target control strategy provided in an embodiment of the present application;

[0038] Figure 4 A second flow chart of a method for determining a target control strategy provided in an embodiment of the present application;

[0039] Figure 5 A schematic diagram of a control strategy training method provided in an embodiment of the present application;

[0040] Figure 6 A flowchart of a method for determining an optimal target control strategy provided in an embodiment of the present application;

[0041] Figure 7 A schematic diagram of a process for calibrating a refrigeration system model provided in an embodiment of the present application;

[0042] Figure 8An integrated intelligent control strategy structure diagram provided in an embodiment of the present application;

[0043] Fig. 9 An engineering application effect diagram provided for an embodiment of the present application;

[0044] Fig.10 A structural block diagram of a target control strategy determination device provided in an embodiment of the present application;

[0045] Fig.11 An internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The refrigeration system upper control method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, Figure 1 An application environment diagram of a refrigeration system upper control method provided in an embodiment of the present application. The control device 102 can access meteorological data on the Internet in the form of an application program interface (API). The control device 102 can also be connected to the device 104 that carries the building automation system in the form of TCP / IP protocol to collect cooling load data, and send target control instructions to the device 104 that carries the building automation system. The target control instructions are parsed by the building automation system as lower-level control instructions of the refrigeration system device 106, and transmitted to the refrigeration system device 106 through the Modbus protocol to realize the operation control of the refrigeration equipment. Among them, Modbus is a serial communication protocol. The control device 102 can be a personal computer, a microcomputer, a laptop computer, an Internet of Things device, etc.

[0048] In an exemplary embodiment, Figure 2 A schematic diagram of a flow chart of a refrigeration system upper control method provided in an embodiment of the present application, which provides a refrigeration system upper control method, and the method is applied to Figure 1 Taking the control device 102 in the example as an example, the method includes the following steps:

[0049] S201. Based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain target control strategies corresponding to each initial control strategy.

[0050] The refrigeration equipment may include refrigeration units, water pumps and cooling towers. The control targets include system power consumption, system power costs, etc. The initial control strategy may be a sequential least squares strategy, a dual-simulation regression strategy, a differential evolution strategy, a reinforcement learning strategy, etc.

[0051] In the embodiment of the present application, the hyperparameters of the initial control strategy can be initialized, and the default hyperparameter values ​​of the algorithm can be selected. According to the control target of the refrigeration system, the operating status of each refrigeration device in the refrigeration system model, the cold load measurement data and the historical meteorological data can be input into the initial control strategy to obtain the simulation control instructions, and the refrigeration system model can be controlled by the simulation control instructions to obtain the control results and the new operating status, and determine whether the control results meet the conditions to obtain the target control strategies corresponding to each initial control strategy, so as to optimize the hyperparameter values ​​based on the default hyperparameter values.

[0052] S202: Determine the optimal target control strategy from multiple target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system.

[0053] The meteorological forecast data may be future weather forecast data obtained from the Internet, such as air dry bulb temperature, air relative humidity, solar radiation intensity, wind speed, etc. The cooling load forecast data may be predicted cooling load data of a building refrigeration system.

[0054] In the embodiment of the present application, the operating status, weather forecast data, and cooling load forecast data of the refrigeration system can be input into each target control strategy to obtain the simulation control instructions corresponding to each target control strategy, and then each simulation control instruction is input into the refrigeration system model to obtain the control result corresponding to each simulation control instruction. The target control strategy corresponding to the best control result is taken as the optimal target control strategy.

[0055] S203, obtaining a target control instruction according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0056] In an embodiment of the present application, the cooling load prediction data and the weather prediction data may be input into the optimal target control strategy to obtain a higher-level control strategy for the refrigeration equipment in the refrigeration system.

[0057] In the above-mentioned upper-level control method of the refrigeration system, multiple initial control strategies are trained based on the control target of the refrigeration system and the operating status of each refrigeration equipment in the refrigeration system model, and the target control strategy corresponding to each initial control strategy is obtained. The optimal target control strategy is determined from multiple target control strategies using the operating status, meteorological forecast data, and cold load forecast data of the refrigeration system, and the target control instruction is obtained according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system. At present, the strategy of the upper-level control method of the refrigeration system is single, resulting in low adaptability of the method. Due to the changeable characteristics of meteorology and building cold load, the adaptability of upper-level control of the refrigeration system using only a single strategy is low. In the embodiment of the present application, an optimal control strategy is determined from multiple target control strategies for upper-level control, that is, the method provided by the embodiment of the present application can solve the problem of low adaptability of a single control strategy under changeable meteorological and building cold load conditions.

[0058] In an exemplary embodiment, Figure 3 One of the flow charts of a method for determining a target control strategy provided in an embodiment of the present application is as follows: Figure 3 As shown, this embodiment involves a possible implementation method of how to train multiple initial control strategies based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model to obtain a target control strategy corresponding to each initial control strategy. On the basis of the above embodiment, the above S201 includes:

[0059] S301. For each initial control strategy, according to the control target, the operating status, the cooling load measurement data and the historical meteorological data, a simulation control instruction output under the initial control strategy is obtained.

[0060] Among them, the algorithm of the initial control strategy can adopt a sequential least squares programming algorithm, a double simulated annealing algorithm, a differential evolution control algorithm, a reinforcement learning algorithm, etc. The cooling load measurement data is actual measured data.

[0061] In an embodiment of the present application, for each initial control strategy, the operating status of each device in the current refrigeration system simulated by the refrigeration system model, the cooling load measurement data and the historical meteorological data can be input into the initial control strategy, and each initial control strategy outputs the simulation control instructions corresponding to the initial control strategy.

[0062] S302 . Determine the target control strategy corresponding to each initial control strategy according to the simulation control instruction corresponding to each initial control strategy.

[0063] For example, Figure 4 A second flow chart of a method for determining a target control strategy provided in an embodiment of the present application is as follows: Figure 4As shown, this embodiment involves a possible implementation method of how to determine the target control strategy corresponding to each initial control strategy according to the simulation control instructions corresponding to each initial control strategy. On the basis of the above embodiment, the above S302 includes:

[0064] S401. For each simulation control instruction corresponding to each initial control strategy, the refrigeration equipment in the refrigeration system is controlled by using the simulation control instruction to obtain a control result and a new operation state corresponding to the simulation control instruction.

[0065] In an embodiment of the present application, the simulation control instructions corresponding to each initial control strategy can be respectively input into the refrigeration system model to simulate the control of the refrigeration equipment, and the control result and new operating state corresponding to each simulation control instruction can be obtained.

[0066] S402 , determining a target control strategy corresponding to each initial control strategy according to the control result and the new operation state corresponding to the simulation control instruction under each initial control strategy.

[0067] Exemplarily, this embodiment relates to a possible implementation method of determining a target control strategy corresponding to each initial control strategy according to the control result and the new operating state corresponding to the simulation control instruction under each initial control strategy. On the basis of the above embodiment, the above S402 includes:

[0068] Case 1: For the control results corresponding to the simulated control instructions under each initial control strategy, if the control results meet the preset conditions, the initial control strategy is used as the target control strategy.

[0069] In the embodiment of the present application, it can be determined whether the control result corresponding to the simulation control instruction under each initial control strategy meets the preset conditions. If so, the initial control strategy can be used as the target control strategy.

[0070] Specifically, the preset condition may be whether the control result is stable, for example, whether the change value of the control result from the second training is less than the previous one is less than a preset threshold, and the preset threshold may be 0.001%. If this is the first training, the control result value is retained for the judgment of the change value of the control result of the next training.

[0071] Case 2: If the control result does not meet the preset conditions, the initial control strategy is modified using the control result to obtain an intermediate control strategy, and the new analog control instructions output under the intermediate control strategy are executed according to the control target, the new operating status, the cooling load measurement data and the historical meteorological data. The refrigeration equipment in the refrigeration system is controlled using the new analog control instructions to obtain the new control result corresponding to the new analog control instructions and the next new operating status step until the new control result meets the preset conditions. The control strategy of the analog control instructions output for the last time is used as the target control strategy.

[0072] In the embodiment of the present application, if the control result does not meet the preset conditions, the initial control strategy is corrected using the control result, that is, the hyperparameters in the initial control strategy are adjusted to obtain an intermediate control strategy. Then the control target, the new operating state, the cold load measurement data and the historical meteorological data are continuously input into the intermediate control strategy to obtain a new simulation control instruction output under the intermediate control strategy, the new simulation control instruction is input into the refrigeration system model, the refrigeration equipment in the refrigeration system is simulated and controlled, and the new control result corresponding to the new simulation control instruction and the next new operating state are obtained. Then determine whether the new control result meets the preset conditions, if so, the intermediate control strategy is used as the target control strategy. If not, the intermediate control strategy is corrected using the new control result, and the next new simulation control instruction output under the next intermediate control strategy is continued according to the next new operating state, the cold load measurement data and the historical meteorological data, the next new simulation control instruction is used to control the refrigeration equipment in the refrigeration system, and the new control result corresponding to the next new simulation control instruction and the next new operating state are obtained, until the next new control result meets the preset conditions, and the control strategy of the simulation control instruction output for the last time is used as the target control strategy.

[0073] Figure 5 A schematic diagram of a control strategy training method provided in an embodiment of the present application. Figure 5As shown, the operating state, cooling load measurement data and historical meteorological data can be input into the control strategy (initial control strategy at this time) to obtain a simulation control instruction, and the simulation control instruction is used to control the refrigeration system model to obtain a control result and a new operating state. If the control result meets the preset conditions, the initial control strategy is used as the target control strategy. If the control result does not meet the preset conditions, the initial control strategy is modified by the control result to obtain an intermediate control strategy, and the new simulation control instruction output under the intermediate control strategy is obtained according to the new operating state, cooling load measurement data and historical meteorological data. The refrigeration equipment in the refrigeration system is controlled by the new simulation control instruction to obtain a new control result corresponding to the new simulation control instruction and the next new operating state step, until the new control result meets the preset conditions, and the control strategy of the simulation control instruction output for the last time is used as the target control strategy.

[0074] Usually, each target control strategy is updated and trained once a month. First, the refrigeration system data collected within this month (the operating status of each refrigeration device in the refrigeration system model) is used to recalibrate and update the refrigeration system model. Then, the building measured cooling load data and historical meteorological data collected within this month are used to update the hyperparameters of the control strategy. This ensures that the control strategy can adapt and give corresponding refrigeration system control instructions under changes in seasons, building usage behavior, and refrigeration system performance.

[0075] In this embodiment, the target control strategy is obtained by training the initial control strategy, which can improve the adaptability of the controller to changes in seasons, building usage behavior, and refrigeration system performance, and ensure the reliability of the upper-level control strategy of the refrigeration system in actual projects.

[0076] In an exemplary embodiment, Figure 6 A flow chart of a method for determining an optimal target control strategy provided in an embodiment of the present application is shown as follows: Figure 6 As shown, this embodiment involves how to use the operating status, weather forecast data, and cooling load forecast data of the refrigeration system to determine the optimal target control strategy from multiple target control strategies, including:

[0077] S601. According to the operation status, cooling load forecast data and meteorological forecast data, each target control strategy is used to output simulation control instructions corresponding to each target control strategy.

[0078] In the embodiment of the present application, before each implementation of the upper control, the control results of each target control strategy can be simulated. For each target control strategy, the operating status of each refrigeration device in the refrigeration system model, the cold load forecast data and the meteorological forecast data can be input into the target control strategy, and the simulation control instructions corresponding to each target control strategy can be output.

[0079] For example, in the day-ahead control of the ice storage system, for each target control strategy, the building cooling load forecast data, meteorological forecast data (outdoor temperature forecast, outdoor relative humidity forecast) and operating status for the next 24 hours can be input into the target control strategy to obtain the simulation control instructions corresponding to each target control strategy. The simulation control instruction is an instruction for the system to melt ice and store ice in the next 24 hours. In other words, according to the time step and prediction window of the input data, the target control instruction under the same time step and prediction window can be given through the target control strategy. It helps to automatically adjust the appropriate control method according to the specific boundary conditions, thereby improving the robustness of the control results and improving the control results of the refrigeration system.

[0080] S602: For each analog control instruction, obtain a control result corresponding to the analog control instruction.

[0081] In the embodiment of the present application, for each simulation control instruction, the simulation control instruction can be input into the refrigeration system model to obtain a control result corresponding to the simulation control instruction.

[0082] S603: Determine the optimal target control strategy from multiple target control strategies according to each control result.

[0083] In the embodiment of the present application, a target control strategy with the best control result can be determined from multiple target control strategies, and the target control strategy with the best control result can be used as the optimal target control strategy.

[0084] In this embodiment, before each implementation of the upper control, the control results of each target control strategy can be simulated to find the optimal target control strategy. The optimal target control strategy can be used to output the target control instruction to perform upper control on the refrigeration system. Due to the variability of weather and building cooling load, the adaptability of only a single strategy is low. The method provided in the embodiment of the present application can solve the problem of low adaptability of a single control strategy under variable weather and building cooling load conditions, thereby improving the robustness of the control results and improving the control results of the refrigeration system. In addition, it solves the problem that the effects of existing intelligent upper control technologies for refrigeration systems are mostly evaluated by simulation analysis methods and are rarely used in actual projects.

[0085] Figure 7 A schematic diagram of a process for calibrating a refrigeration system model provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the method includes:

[0086] S701. Obtain an initial refrigeration system model according to the performance simulation equation of each refrigeration device in the refrigeration system.

[0087] Among them, the performance of the refrigeration unit in the refrigeration equipment can be simulated by the internal efficiency DCOP / external efficiency ICOP method to obtain the performance simulation equation of the refrigeration unit. The performance of the water pump in the refrigeration equipment is described by the flow-head-power curve method to obtain the performance simulation equation of the water pump. The performance of the cooling tower in the refrigeration equipment can be simulated by the heat transfer unit number ε-NTU method to obtain the performance simulation equation of the cooling tower. The pipeline characteristics in the refrigeration equipment are described by the resistance equation to obtain the performance simulation equation of the pipeline.

[0088] In the embodiment of the present application, the DCOP / ICOP method can be used to simulate the performance simulation equation of the refrigeration unit, the flow-head-power curve method can be used to simulate the performance simulation equation of the water pump, the ε-NTU method can be used to simulate the performance simulation equation of the cooling tower, and the resistance equation can be used to simulate the performance simulation equation of the pipeline. The above performance simulation equations can be used as an initial refrigeration system model to simulate the refrigeration system.

[0089] S702: calibrate the parameters in the initial refrigeration system model using the cooling load, heating load and power data of the refrigeration system to obtain a refrigeration system model.

[0090] Among them, the cooling load, heating load and electricity data of the refrigeration system are the cooling, heating and electricity data, which can be collected in real time. It should be noted that in the implementation of this application, the cooling load, heating load and electricity data of the refrigeration system that are not collected in real time can also be used to calibrate the parameters in the initial refrigeration system model, that is, the cooling load, heating load and electricity data measured for a period of time are used to calibrate the simulation data in the initial refrigeration system model to obtain the refrigeration system model.

[0091] In this embodiment, each refrigeration device in the refrigeration system is simulated, and the simulated data in the initial refrigeration system model is calibrated using the measured data, which can improve the accuracy of the refrigeration system model. Further, the subsequent refrigeration system upper control results using the refrigeration system model can be improved.

[0092] Figure 8 This is a structural diagram of an integrated intelligent control strategy provided by an embodiment of the present application. Figure 8As shown, the performance simulation equations of each refrigeration device in the refrigeration system can be used to complete the model initialization, that is, to obtain the initial refrigeration system model, and then the cold load, heat load and power data of the refrigeration system can be used to calibrate the parameters in the initial refrigeration system model to obtain the refrigeration system model. According to the refrigeration system model and the control target, multiple initial control strategies are trained to obtain the target control strategies corresponding to each initial control strategy. Control strategies include sequential least squares programming control strategy, double simulated annealing control strategy, differential evolution control strategy, reinforcement learning control strategy, etc. The optimal target control strategy is determined from multiple target control strategies based on the operating status, meteorological forecast data, and cold load forecast data of the refrigeration system; the target control instruction is obtained according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0093] Fig. 9 An engineering application effect diagram provided for the embodiment of the present application. It shows the comparison of electricity costs from May to September between the optimal target control strategy provided by the present application and the control strategy in the traditional technology. It shows the refrigeration system of a large commercial complex, which can save 170,000 yuan in electricity costs for the refrigeration system during the cooling season throughout the year, saving 16% compared with the original strategy.

[0094] It should be noted that the upper control method of the refrigeration system provided in the embodiment of the present application mainly involves access to the Internet and the building automation system during field deployment. The Raspberry Pi equipped with the (target control strategy) controller is powered by an independent power supply, and its connection to the Internet can be achieved through a network communication cable or a WIFI transceiver, and its access to the building automation system is achieved through a network communication cable. After the connection is completed, the network communication address of the Raspberry Pi needs to be configured according to the on-site environment to achieve normal data exchange between the Raspberry Pi and the Internet and the building automation system, thereby realizing the deployment and application of this method. The control strategy hardware deployment device and communication method with a microcomputer as the core, through the Raspberry Pi microcomputer equipped with an integrated control strategy for the refrigeration system, realizes physical connection by means of network cables, WIFI transceivers, etc., realizes data exchange by means of TCP / IP, API, Modbus, etc., and realizes the deployment and application of the integrated intelligent upper control strategy for the building refrigeration system. It solves the problem that the existing intelligent upper control technology of the refrigeration system is mostly in the methodology stage, and there is less research on the hardware deployment device involving the control strategy, and provides a technical implementation scheme for the hardware system communication method.

[0095] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiment of the present application also provides a refrigeration system upper control device for implementing the refrigeration system upper control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more refrigeration system upper control device embodiments provided below can refer to the limitations of the refrigeration system upper control method above, and will not be repeated here.

[0097] In an exemplary embodiment, Fig.10 A structural block diagram of a target control strategy determination device provided in an embodiment of the present application, such as Fig.10 As shown, a refrigeration system upper control device 1000 is provided, comprising: a first determination module 1001, a second determination module 1002 and a third determination module 1003, wherein:

[0098] The first determination module 1001 is used to train multiple initial control strategies based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model to obtain a target control strategy corresponding to each initial control strategy.

[0099] The second determination module 1002 is used to determine the optimal target control strategy from multiple target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system.

[0100] The third determination module 1003 is used to obtain a target control instruction according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0101] In an exemplary embodiment, the first determining module 1001 includes:

[0102] The first determination submodule is used to obtain the simulated control instructions output under the initial control strategy according to the control target, the operating status, the cooling load measurement data and the historical meteorological data for each initial control strategy.

[0103] The second determination submodule is used to determine the target control strategy corresponding to each initial control strategy according to the simulation control instruction corresponding to each initial control strategy.

[0104] In an exemplary embodiment, the second determining submodule includes:

[0105] The first determining unit is used to control the refrigeration equipment in the refrigeration system using the simulated control instructions corresponding to each initial control strategy, and obtain the control result and new operation state corresponding to the simulated control instructions.

[0106] The second determination unit is used to determine the target control strategy corresponding to each initial control strategy according to the control result and the new operation state corresponding to the simulation control instruction under each initial control strategy.

[0107] In an exemplary embodiment, the second determination unit is specifically used to determine the control results corresponding to the simulated control instructions under each initial control strategy. If the control results meet the preset conditions, the initial control strategy is used as the target control strategy; if the control results do not meet the preset conditions, the initial control strategy is modified using the control results to obtain an intermediate control strategy, and the new simulated control instructions output under the intermediate control strategy are executed according to the control objectives, new operating status, cooling load measurement data and historical meteorological data, and the refrigeration equipment in the refrigeration system is controlled using the new simulated control instructions to obtain new control results corresponding to the new simulated control instructions and the next new operating status, until the new control results meet the preset conditions, and the control strategy of the simulated control instructions output for the last time is used as the target control strategy.

[0108] In an exemplary embodiment, the second determination module 1002 is specifically used to output the simulation control instructions corresponding to each target control strategy using each target control strategy according to the operation state, cooling load prediction data and meteorological prediction data. For each simulation control instruction, a control result corresponding to the simulation control instruction is obtained; and according to each control result, an optimal target control strategy is determined from multiple target control strategies.

[0109] In an exemplary embodiment, the refrigeration system upper control device 1000 further includes:

[0110] The third determination submodule is used to obtain an initial refrigeration system model according to the performance simulation equation of each refrigeration device in the refrigeration system.

[0111] The calibration submodule is used to calibrate the parameters in the initial refrigeration system model using the cooling load, heating load and power data of the refrigeration system to obtain the refrigeration system model.

[0112] Each module in the above-mentioned refrigeration system upper control device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0113] In an exemplary embodiment, a computer device is provided. The computer device is a control device that carries the above-mentioned refrigeration system upper control method, which can be a terminal. Its internal structure diagram can be as shown in Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network or other technologies. When the computer program is executed by the processor, a method for controlling a refrigeration system is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0114] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0116] Based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain the target control strategy corresponding to each initial control strategy;

[0117] Determine the optimal target control strategy from multiple target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system;

[0118] The target control instruction is obtained according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0119] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0120] For each initial control strategy, the simulated control instructions output under the initial control strategy are obtained according to the control target, operating status, cooling load measurement data and historical meteorological data;

[0121] According to the simulation control instructions corresponding to each initial control strategy, the target control strategy corresponding to each initial control strategy is determined.

[0122] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0123] For the simulation control instructions corresponding to each initial control strategy, the refrigeration equipment in the refrigeration system is controlled by using the simulation control instructions to obtain the control results and new operating states corresponding to the simulation control instructions;

[0124] According to the control results and new operating states corresponding to the simulated control instructions under each initial control strategy, the target control strategy corresponding to each initial control strategy is determined.

[0125] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0126] For the control results corresponding to the simulated control instructions under each initial control strategy, if the control results meet the preset conditions, the initial control strategy is used as the target control strategy;

[0127] If the control result does not meet the preset conditions, the initial control strategy is modified using the control result to obtain an intermediate control strategy, and the new analog control instructions output under the intermediate control strategy are executed according to the control target, the new operating state, the cooling load measurement data and the historical meteorological data. The refrigeration equipment in the refrigeration system is controlled using the new analog control instructions to obtain the new control result corresponding to the new analog control instructions and the next new operating state step until the new control result meets the preset conditions, and the control strategy of the analog control instructions output for the last time is used as the target control strategy.

[0128] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0129] According to the operation status, cooling load forecast data and meteorological forecast data, each target control strategy is used to output the simulation control instructions corresponding to each target control strategy;

[0130] For each analog control instruction, a control result corresponding to the analog control instruction is obtained;

[0131] According to each control result, the optimal target control strategy is determined from multiple target control strategies.

[0132] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0133] According to the performance simulation equation of each refrigeration equipment in the refrigeration system, an initial refrigeration system model is obtained;

[0134] The cooling load, heating load and power data of the refrigeration system are used to calibrate the parameters in the initial refrigeration system model to obtain the refrigeration system model.

[0135] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0136] Based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain the target control strategy corresponding to each initial control strategy;

[0137] Determine the optimal target control strategy from multiple target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system;

[0138] The target control instruction is obtained according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0139] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0140] For each initial control strategy, the simulated control instructions output under the initial control strategy are obtained according to the control target, operating status, cooling load measurement data and historical meteorological data;

[0141] According to the simulation control instructions corresponding to each initial control strategy, the target control strategy corresponding to each initial control strategy is determined.

[0142] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0143] For the simulation control instructions corresponding to each initial control strategy, the refrigeration equipment in the refrigeration system is controlled by using the simulation control instructions to obtain the control results and new operating states corresponding to the simulation control instructions;

[0144] According to the control results and new operating states corresponding to the simulated control instructions under each initial control strategy, the target control strategy corresponding to each initial control strategy is determined.

[0145] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0146] For the control results corresponding to the simulated control instructions under each initial control strategy, if the control results meet the preset conditions, the initial control strategy is used as the target control strategy;

[0147] If the control result does not meet the preset conditions, the initial control strategy is modified using the control result to obtain an intermediate control strategy, and the new analog control instructions output under the intermediate control strategy are executed according to the control target, the new operating state, the cooling load measurement data and the historical meteorological data. The refrigeration equipment in the refrigeration system is controlled using the new analog control instructions to obtain the new control result corresponding to the new analog control instructions and the next new operating state step until the new control result meets the preset conditions, and the control strategy of the analog control instructions output for the last time is used as the target control strategy.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0149] According to the operation status, cooling load forecast data and meteorological forecast data, each target control strategy is used to output the simulation control instructions corresponding to each target control strategy;

[0150] For each analog control instruction, a control result corresponding to the analog control instruction is obtained;

[0151] According to each control result, the optimal target control strategy is determined from multiple target control strategies.

[0152] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0153] According to the performance simulation equation of each refrigeration equipment in the refrigeration system, an initial refrigeration system model is obtained;

[0154] The cooling load, heating load and power data of the refrigeration system are used to calibrate the parameters in the initial refrigeration system model to obtain the refrigeration system model.

[0155] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0156] Based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain the target control strategy corresponding to each initial control strategy;

[0157] Determine the optimal target control strategy from multiple target control strategies by using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system;

[0158] The target control instruction is obtained according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0160] For each initial control strategy, the simulated control instructions output under the initial control strategy are obtained according to the control target, operating status, cooling load measurement data and historical meteorological data;

[0161] According to the simulation control instructions corresponding to each initial control strategy, the target control strategy corresponding to each initial control strategy is determined.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0163] For the simulation control instructions corresponding to each initial control strategy, the refrigeration equipment in the refrigeration system is controlled by using the simulation control instructions to obtain the control results and new operating states corresponding to the simulation control instructions;

[0164] According to the control results and new operating states corresponding to the simulated control instructions under each initial control strategy, the target control strategy corresponding to each initial control strategy is determined.

[0165] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0166] For the control results corresponding to the simulated control instructions under each initial control strategy, if the control results meet the preset conditions, the initial control strategy is used as the target control strategy;

[0167] If the control result does not meet the preset conditions, the initial control strategy is modified using the control result to obtain an intermediate control strategy, and the new analog control instructions output under the intermediate control strategy are executed according to the control target, the new operating state, the cooling load measurement data and the historical meteorological data. The refrigeration equipment in the refrigeration system is controlled using the new analog control instructions to obtain the new control result corresponding to the new analog control instructions and the next new operating state step until the new control result meets the preset conditions, and the control strategy of the analog control instructions output for the last time is used as the target control strategy.

[0168] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0169] According to the operation status, cooling load forecast data and meteorological forecast data, each target control strategy is used to output the simulation control instructions corresponding to each target control strategy;

[0170] For each analog control instruction, a control result corresponding to the analog control instruction is obtained;

[0171] According to each control result, the optimal target control strategy is determined from multiple target control strategies.

[0172] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0173] According to the performance simulation equation of each refrigeration equipment in the refrigeration system, an initial refrigeration system model is obtained;

[0174] The cooling load, heating load and power data of the refrigeration system are used to calibrate the parameters in the initial refrigeration system model to obtain the refrigeration system model.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0176] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A refrigeration system upper control method, characterized in that: The method comprises: Based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model, multiple initial control strategies are trained to obtain target control strategies corresponding to each of the initial control strategies; the control target includes system power consumption and system electricity cost, and the multiple initial control strategies include sequential least squares strategy, dual analog regression strategy, differential evolution strategy and reinforcement learning strategy; Determining an optimal target control strategy from a plurality of target control strategies using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system; the weather forecast data includes future weather forecast data; Obtaining a target control instruction according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system; The method further comprises: According to the performance simulation equation of each refrigeration device in the refrigeration system, an initial refrigeration system model is obtained; The cooling load, heating load and power data of the refrigeration system are used to calibrate the parameters in the initial refrigeration system model to obtain the refrigeration system model.

2. The method according to claim 1, characterized in that The control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model are used to train multiple initial control strategies to obtain target control strategies corresponding to each of the initial control strategies, including: For each of the initial control strategies, according to the control target, the operating status, the cooling load measurement data and the historical meteorological data, a simulation control instruction output under the initial control strategy is obtained; According to the simulation control instructions corresponding to each of the initial control strategies, the target control strategies corresponding to each of the initial control strategies are determined.

3. The method according to claim 2, characterized in that Determining the target control strategy corresponding to each of the initial control strategies according to the simulation control instructions corresponding to each of the initial control strategies includes: For each simulation control instruction corresponding to the initial control strategy, the refrigeration equipment in the refrigeration system is controlled by using the simulation control instruction to obtain a control result and a new operating state corresponding to the simulation control instruction; According to the control results and new operating states corresponding to the simulation control instructions under each of the initial control strategies, the target control strategies corresponding to each of the initial control strategies are determined.

4. The method according to claim 3, characterized in that Determining the target control strategy corresponding to each of the initial control strategies according to the control result and the new operating state corresponding to the simulation control instruction under each of the initial control strategies includes: For the control results corresponding to the simulation control instructions under each of the initial control strategies, if the control results meet the preset conditions, the initial control strategy is used as the target control strategy; If the control result does not meet the preset condition, the initial control strategy is modified using the control result to obtain an intermediate control strategy, and the new analog control instructions output under the intermediate control strategy are executed according to the control target, the new operating state, the cooling load measurement data and the historical meteorological data. The refrigeration equipment in the refrigeration system is controlled using the new analog control instructions to obtain a new control result corresponding to the new analog control instructions and the next new operating state, until the new control result meets the preset condition, and the control strategy of the analog control instructions output for the last time is used as the target control strategy.

5. The method according to claim 1, characterized in that: The method of using the operating status, weather forecast data, and cooling load forecast data of the refrigeration system to determine the optimal target control strategy from a plurality of target control strategies includes: According to the operating state, the cooling load forecast data and the meteorological forecast data, using each of the target control strategies, outputting simulation control instructions corresponding to each of the target control strategies; For each of the analog control instructions, obtaining a control result corresponding to the analog control instruction; According to each of the control results, an optimal target control strategy is determined from the multiple target control strategies.

6. A refrigeration system upper control device, characterized in that: The device comprises: The first determination module is used to train multiple initial control strategies based on the control target of the refrigeration system and the operating status of each refrigeration device in the refrigeration system model to obtain a target control strategy corresponding to each of the initial control strategies; the control target includes system power consumption and system electricity cost, and the multiple initial control strategies include sequential least squares strategy, dual analog regression strategy, differential evolution strategy and reinforcement learning strategy; A second determination module is used to determine an optimal target control strategy from a plurality of target control strategies by using the operating status, meteorological forecast data, and cooling load forecast data of the refrigeration system; the meteorological forecast data includes future weather forecast data; A third determination module is used to obtain a target control instruction according to the optimal target control strategy; the target control instruction is used to perform upper-level control on the refrigeration equipment in the refrigeration system; The device also includes: According to the performance simulation equation of each refrigeration device in the refrigeration system, an initial refrigeration system model is obtained; The cooling load, heating load and power data of the refrigeration system are used to calibrate the parameters in the initial refrigeration system model to obtain the refrigeration system model.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images