Method and device for controlling heating ventilation system, electronic equipment and storage medium

Abstract

The present disclosure provides a control method and device of a heating and ventilation system, an electronic device and a storage medium, relates to the field of artificial intelligence, in particular to the fields of cloud computing, Internet of Things and the like. The specific implementation scheme is: processing a plurality of candidate control strategies and environment information by using a simulation environment model to obtain a plurality of energy consumption indexes corresponding to the plurality of candidate control strategies respectively; wherein the heating and ventilation system comprises a plurality of devices, the candidate control strategy represents a candidate control mode for the plurality of devices, and the energy consumption index represents the energy consumption generated by running the heating and ventilation system based on the candidate control strategy; a candidate control strategy corresponding to the minimum energy consumption index in the plurality of candidate control strategies is determined as a target control strategy; and the running state of the heating and ventilation system is controlled according to the target control strategy; wherein the simulation environment model represents the relationship between the device information, the environment information and the device energy consumption of the plurality of devices.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the fields of cloud computing, Internet of Things, and the like, and more specifically, the present disclosure provides a control method and device of a heating and ventilation system, an electronic device, a storage medium, a computer program product, and a heating and ventilation device. BACKGROUND

[0002] Data centers, office buildings, commercial buildings, factories, hotels, campuses, and the like are equipped with heating and ventilation systems, which can adjust the temperature, humidity, and the like of the internal space of the buildings, so that the environmental conditions inside the buildings meet the production and living needs.

[0003] For newly built data centers or buildings, it can be considered to start with new hardware materials and use plate liquid cooling, immersion liquid cooling, and the like heat dissipation devices to save the energy consumption of the heating and ventilation system. However, for the heating and ventilation systems that have been put into use, the energy consumption of these heating and ventilation systems is high. SUMMARY

[0004] The present disclosure provides a control method and device of a heating and ventilation system, an electronic device, a storage medium, a computer program product, and a heating and ventilation device.

[0005] According to an aspect of the present disclosure, a control method of a heating and ventilation system is provided, including: processing a plurality of candidate control strategies and environmental information by using a simulation environment model to obtain a plurality of energy consumption indicators corresponding to the plurality of candidate control strategies respectively; wherein the heating and ventilation system includes a plurality of devices, the candidate control strategy represents a candidate control mode for the plurality of devices, and the energy consumption indicator represents the energy consumption generated by running the heating and ventilation system based on the candidate control strategy; determining a candidate control strategy corresponding to the minimum energy consumption indicator in the plurality of candidate control strategies as a target control strategy; and controlling the operating state of the heating and ventilation system according to the target control strategy; wherein the simulation environment model represents the relationship between the device information of the plurality of devices, the environmental information, and the device energy consumption.

[0006] According to another aspect of the present disclosure, a control device of a heating and ventilation system can include a processing module, a strategy determination module, and a control module. The processing module is configured to process a plurality of candidate control strategies and environmental information by using a simulation environment model to obtain a plurality of energy consumption indicators corresponding to the plurality of candidate control strategies respectively; wherein the heating and ventilation system includes a plurality of devices, the candidate control strategy represents a candidate control mode for the plurality of devices, and the energy consumption indicator represents the energy consumption generated by running the heating and ventilation system based on the candidate control strategy; wherein the simulation environment model represents the relationship between the device information of the plurality of devices, the environmental information, and the device energy consumption. The strategy determination module is configured to determine a candidate control strategy corresponding to the minimum energy consumption indicator in the plurality of candidate control strategies as a target control strategy. The control module is configured to control the operating state of the heating and ventilation system according to the target control strategy.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to perform the method provided by the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method provided by the present disclosure.

[0010] According to another aspect of the present disclosure, a heating and ventilation device is provided, comprising: a heating and ventilation system and the electronic device described above.

[0011] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0013] Figure 1 is an application scenario diagram of the control method and device of the heating and ventilation system according to the embodiments of the present disclosure;

[0014] Figure 2 is a schematic flow chart of the control method of the heating and ventilation system according to the embodiments of the present disclosure;

[0015] Figure 3 is a schematic principle diagram of the control method of the heating and ventilation system according to the embodiments of the present disclosure;

[0016] Figure 4A is a schematic structural diagram of a heating and ventilation system according to the embodiments of the present disclosure;

[0017] Figure 4B is a schematic diagram of the first simulation environment model implementation according to the embodiments of the present disclosure;

[0018] Figure 5 is a schematic diagram of the second simulation environment model implementation according to the embodiments of the present disclosure;

[0019] Figure 6is a schematic diagram of a third simulation environment model implementation according to an embodiment of the present disclosure;

[0020] Figure 7 is a schematic diagram of a fourth simulation environment model implementation according to an embodiment of the present disclosure;

[0021] Figure 8 is a schematic diagram of a control method of a heating and ventilation system according to another embodiment of the present disclosure;

[0022] Figure 9 is a schematic structural block diagram of a control device of a heating and ventilation system according to an embodiment of the present disclosure; and

[0023] Figure 10 is a structural block diagram of an electronic device for implementing a control method of a heating and ventilation system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are included to provide a thorough understanding of embodiments of the present disclosure by a person of ordinary skill in the art, and should not be construed as limiting the present disclosure to particular embodiments. Thus, it will be apparent to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0025] Figure 1 is a schematic diagram of an application scenario of a control method and device of a heating and ventilation system 110 according to an embodiment of the present disclosure.

[0026] It should be noted that, Figure 1 The system architecture shown is only an example of a system architecture to which embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0027] As Figure 1 shown, the system architecture 100 according to this embodiment can include a heating and ventilation system 110 and a control device 120.

[0028] The heating and ventilation system 110 can include a plurality of devices, such as a cooling tower, a chilled water pump, a cooling water pump, a chiller, etc., and a pipeline connecting the plurality of devices. The pipeline connects the heat exchange medium inlet and outlet of the devices, thereby forming a circulating flow of the heat exchange medium between the devices. The heating and ventilation system 110 can further include sensors, such as temperature sensors, humidity sensors, pressure sensors, flow sensors, etc., to collect information of the devices and / or the environment.

[0029] The control device 120 can be pre-configured with a simulation environment model. The simulation environment model can be a function fitted based on historical data. For example, the simulation environment model can characterize the relationship between the equipment information, environmental information, and energy consumption of multiple devices.

[0030] The control device 120 can acquire environmental information from the HVAC system 110 or other sensors outside the HVAC system 110, such as temperature and humidity. The control device 120 is used to determine a target control strategy, which may include, for example, the operating frequency of the cooling tower, the operating frequency of the chilled water pump, the operating frequency of the cooling water pump, and the chiller outlet water temperature. The control device 120 also controls the operating state of the HVAC system 110 based on the target control strategy, for example, by sending the target control strategy to the control system so that the HVAC system 110 can adjust the operating state of each device according to the target control strategy.

[0031] In practical applications, the control device 120 can be integrated with the HVAC system 110, or it can be a server located in the cloud, a terminal device located in the control room, etc. This embodiment does not limit this.

[0032] It should be understood that Figure 1 The number of devices and control equipment in the HVAC system shown is merely illustrative. Any number of devices and control equipment can be included in the HVAC system depending on the implementation requirements.

[0033] Figure 2 This is a schematic flowchart of a control method for a heating, ventilation, and air conditioning system according to an embodiment of the present disclosure.

[0034] like Figure 2 As shown, the control method 200 for the HVAC system is used to control the HVAC system, which includes multiple devices such as cooling towers, water pumps, and heat exchangers. The control method 200 may include operations S210 to S230.

[0035] In operation S210, multiple candidate control strategies and environmental information are processed using a simulation environment model to obtain multiple energy consumption indicators corresponding to the multiple candidate control strategies.

[0036] For example, a simulation environment model represents the relationships between device information, environmental information, and device energy consumption of multiple devices. For instance, it represents the relationship between certain device information, certain environmental information, and the energy consumption of certain devices. The simulation environment model can be, for example, a tree model (e.g., XGBoost) or a multilayer perceptron (MLP) model.

[0037] For example, the control strategy represents a control manner for multiple devices, which can include adjustable device parameters in the HVAC system, such as refrigeration pump frequency, cooling pump frequency, cooling tower outlet water temperature, cooling machine outlet water temperature, and the like. For example, a certain control strategy is to control the refrigeration pump frequency at 30 Hz and the cooling tower outlet water temperature at 20 degrees Celsius. The candidate control strategy can be some optional control strategies pre-configured, for example, the range of adjustable device parameters in the HVAC system can be pre-configured, and the candidate control strategy can be a control strategy in the range.

[0038] For example, the energy consumption index represents the energy consumption generated by the HVAC system running based on the candidate control strategy. The energy consumption index includes power, refrigeration capacity, power consumption, and the like, the power can include the power of each device and the total power of the HVAC, the refrigeration capacity can include the refrigeration capacity of each device and the total refrigeration capacity of the HVAC system, and the power consumption can include the power consumption of each device and the total power consumption of the HVAC system.

[0039] In operation S220, the candidate control strategy corresponding to the minimum energy consumption index in the plurality of candidate control strategies is determined as the target control strategy.

[0040] For example, there are three candidate control strategies p1, p2, and p3, and the HVAC system running based on a single candidate control strategy will generate energy consumption, so that three energy consumption indexes m1, m2, and m3 corresponding to the candidate control strategies p1, p2, and p3 can be obtained.

[0041] For example, the second energy consumption index m2 in the above three energy consumption indexes indicates the lowest power, and the candidate control strategy p2 corresponding to the second energy consumption index m2 can be determined as the target control strategy.

[0042] In operation S230, the running state of the HVAC system is controlled according to the target control strategy.

[0043] For example, the running state of each device in the HVAC system can be adjusted so that the adjusted running state is consistent with the target control strategy.

[0044] According to the technical scheme provided by the embodiments of the present disclosure, the energy consumption indexes of each candidate control strategy can be determined based on the simulation environment model first, and then the candidate control strategy corresponding to the minimum energy consumption index is used to control the HVAC system, so that although the devices of the HVAC system are not replaced, the target control strategy with lower energy consumption is selected by the algorithm to run the HVAC system, thereby achieving the effect of saving energy consumption.

[0045] In addition, it needs to be explained that if the energy efficiency indicators of the operation control strategy of the heating and ventilation system in the real business scenario are not pre-evaluated, the candidate control strategy is directly used to control the heating and ventilation system, which has the following problems: when the safety and business constraint conditions are incomplete, there is an uncertain risk in directly controlling the operation control strategy of the heating and ventilation system in the real business scenario. And occupying the means of production, it may affect the normal production and life rhythm, and bring additional experimental cost. The embodiment first verifies the candidate control strategy in the simulation environment of the fusion mechanism model, for example, verifies the energy efficiency indicators, reliability, etc., and then issues the target control strategy to the heating and ventilation system, so that the heating and ventilation system executes the target control strategy, thereby improving the operation safety of the heating and ventilation system.

[0046] Figure 3 is a schematic principle diagram of a control method of a heating and ventilation system according to an embodiment of the present disclosure.

[0047] As Figure 3 shown, the embodiment can include the following main processes: collecting some related historical data 302 in the operation process of the heating and ventilation system 301 in the real business scenario, then determining the simulation environment model 303 based on the historical data 302, and verifying the accuracy of the simulation environment model 303, if the verification fails, continue to determine the simulation environment model 303 based on the historical data 302, in order to update the parameters of the simulation environment model 303. If the verification is passed, the target control strategy 304 is determined based on the simulation environment model 303 by using the optimization algorithm. Next, it can be verified whether the target control strategy 304 meets the predetermined execution condition, if it meets, the heating and ventilation system 301 is run by using the target control strategy 304, if it does not meet, a predetermined control strategy is obtained by degradation processing, and the heating and ventilation system 301 is run by using the predetermined control strategy.

[0048] The simulation environment model involved in the above main process will be described below. Figure 4A to Figure 7

[0049] Figure 4A is a schematic structure diagram of a heating and ventilation system according to an embodiment of the present disclosure, Figure 4B is a schematic diagram of a first simulation environment model implementation according to an embodiment of the present disclosure.

[0050] In the first implementation, multiple devices in the heating and ventilation system can be decoupled, each device is modeled separately to obtain a first sub-model corresponding to the device, and the input and output of multiple first sub-models in the simulation environment model are transmitted to each other, and the input and output relationship between multiple first sub-models is determined based on the connection relationship and heat conduction direction between multiple devices.

[0051] As Figure 4A ​As shown, the plurality of devices can include a chilled water pump 411, a chiller, a cooling water pump 413, and a cooling tower 414. The chiller can include an evaporator 4121 and a condenser 4122. The HVAC system can form a chilled water circulation, a refrigerant circulation, a cooling water circulation, and an outdoor air circulation, which are described as follows.

[0052] The chilled water outlet of the chilled water pump 411 is connected to the chilled water inlet of the evaporator 4121 in the chiller, and the chilled water outlet of the evaporator 4121 is connected to the chilled water inlet of a building terminal. The evaporator 4121, the building terminal, and the chilled water pump 411 can form a chilled water circulation.

[0053] The evaporator 4121 and the condenser 4122 form a refrigerant circulation.

[0054] The cooling water outlet of the cooling tower 414 is connected to the cooling water inlet of the cooling water pump 413, and the cooling water outlet of the cooling water pump 413 is connected to the cooling water inlet of the condenser 4122. The cooling water outlet of the condenser 4122 is connected to the cooling water inlet of the cooling tower 414. The cooling tower 414, the cooling water pump 413, and the condenser 4122 form a cooling water circulation.

[0055] The cooling tower 414 exchanges heat with the outdoor environment by air cooling, thereby forming an outdoor air circulation.

[0056] As shown, the plurality of devices can include a chilled water pump 411, a chiller, a cooling water pump 413, and a cooling tower 414. The chiller can include an evaporator 4121 and a condenser 4122. The HVAC system can form a chilled water circulation, a refrigerant circulation, a cooling water circulation, and an outdoor air circulation, which are described as follows. Figure 4B As shown, the plurality of first sub-models in the simulation environment model can include a chilled water pump sub-model 421, a chiller sub-model 422, a cooling water pump sub-model 423, and a cooling tower sub-model 424.

[0057] For example, each first sub-model can be configured with constraints. For example, the constraint of the chilled water pump sub-model 421 is a numerical range of the operating frequency.

[0058] For example, the environment information 401 can be input into the chilled water pump sub-model 421, and the chilled water pump sub-model 421 outputs the operating frequency of the chilled water pump 411 and a chilled water pump energy consumption sub-index.

[0059] For example, the environment information 401, the operating frequency of the chilled water pump 411, and the operating frequency of the cooling water pump 413 can be input into the chiller sub-model 422, and the chiller sub-model 422 outputs the outlet water temperature of the chiller and a chiller energy consumption sub-index. It can be seen that, since the chilled water pump 411 and the cooling water pump 413 are respectively connected to the evaporator 4121 and the condenser 4122 in the chiller, the chilled water pump 411 and the cooling water pump 413 will affect the chiller, and therefore the outputs of the chilled water pump sub-model 421 and the cooling water pump sub-model 423 can be used as inputs of the chiller sub-model 422.

[0060] For example, environmental information 401 can be input into the cooling tower sub-model 424, and the cooling tower sub-model 424 can output the operating frequency and energy consumption sub-indicators of the cooling tower 414.

[0061] For example, environmental information 401 and the operating frequency of cooling tower 414 can be input into the cooling water pump sub-model 423, and the cooling water pump sub-model 423 outputs the operating frequency and energy consumption sub-indicators of cooling water pump 413. It can be seen that since cooling tower 414 is connected to cooling water pump 413, cooling tower 414 will affect cooling water pump 413; therefore, the output of cooling tower sub-model 424 can be used as the input of cooling water pump sub-model 423.

[0062] For example, the combination of the above-mentioned energy consumption sub-indicators of chilled water pumps, chiller energy consumption sub-indicators, cooling tower energy consumption sub-indicators, and cooling water pump energy consumption sub-indicators can be determined as an energy consumption index 403.

[0063] For example, the operating frequency of the chilled water pump 411, the outlet water temperature of the chiller, the operating frequency of the cooling tower 414, and the operating frequency of the cooling water pump 413 belong to control strategy 403.

[0064] It should be noted that the above example uses multiple devices in a heating and ventilation system, including chilled water pump 411, evaporator 4121, condenser 4122, cooling water pump 413 and cooling tower 414. In other embodiments, some of the heat exchange devices can be considered as devices in the heating and ventilation system, while other heat exchange devices can be ignored. Accordingly, the simulation environment model can ignore the first sub-model corresponding to the other heat exchange device.

[0065] Figure 5 This is a schematic diagram of a second simulation environment model implementation according to an embodiment of the present disclosure.

[0066] like Figure 5 As shown, in the second implementation, multiple devices in the HVAC system do not need to be decoupled, and the process of determining the energy consumption index 503 can be divided into two stages. Accordingly, the simulation environment model includes a second sub-model 531 and a third sub-model 532.

[0067] The second sub-model 531 and the third sub-model 532 need to be determined in advance based on historical data, and then the second sub-model 531 and the third sub-model 532 are applied to output the energy consumption index 503. The following first explains the determination process of the second sub-model 531 and the third sub-model 532, and then explains the application process of the second sub-model 531 and the third sub-model 532.

[0068] The fitting process of the second sub-model 531 and the third sub-model 532 is as follows.

[0069] At time point t, all adjustable parameters in the heating system (such as the frequency of the refrigeration pump, the frequency of the cooling pump, the cooling tower outlet water temperature, the cooling machine outlet water temperature, etc.) are x t , the environmental indicators at the current time point (such as indoor and outdoor temperature and humidity, end precision air conditioning demand, etc.) are v t , other changing working conditions (such as cooling machine inlet water temperature, water pipe flow, water pump pressure, valve opening, etc.) are y t , the target to be optimized (i.e. energy consumption indicator 503, such as unit power, refrigeration capacity) is z t , and the sample space of the four variables is defined as The sub-models f and g can be fitted through steps 1-1 to 1-4.

[0070] Step 1-1: The conditions corresponding to the historical data may be relatively wide and do not meet the actual requirements, so the historical working condition trajectory can be extracted from the historical data under certain expert experience, business rules and safety policies, t ∈ T = {1, 2,..., n} represents each discrete time point, and the working condition and environmental data are saved in the format {(x t , v t , y t , z t )|t ∈ T} as described above.

[0071] Step 1-2: Define the simulation environment fitting functions f(·) and g(·), f(·) is the second sub-model 531 described above, and g(·) is the third sub-model 532 described above, where f: g: After defining the loss function and hyperparameters, f and g can be trained based on the historical data {(x t , v t , y t , z t )|t ∈ T}. As can be seen, f corresponds to the first stage in the second implementation of the simulation environment model described above, and g corresponds to the second stage.

[0072] It should be noted that the present embodiment can train f and g based only on the data at time t. In other embodiments, considering factors such as data lag, inertia, thermal inertia, etc., f and g can also be trained based on the historical data at time t and other historical data before time t, which will be described below.

[0073] Step 1-3: For the fitting functions f and g, define the loss function as mean square error or average error, define the model type as tree model (such as XGBoost) or multilayer perception model (MLP), and optimize the hyperparameter combination by TPE sampling method (Three-Phase Equal Proportions Sampling), and train the simulation models f and g with accuracy and generalization under the optimal hyperparameter combination.

[0074] Step 1-4: After obtaining f and g, new actual working condition data can be continuously collected, and when the number of new records reaches the predetermined number, step 1-1 can be entered to retrain f and g. When the number of new records does not reach the predetermined number, f and g obtained in the last round of training can be used to determine the target control strategy.

[0075] It should be noted that the basic idea of the TPE sampling method in the above is to divide the population into several layers, and then sample in each layer according to a certain proportion, and finally combine the samples of each layer into the total sample. For example, the population can be divided into several layers, each layer has the same characteristics or attributes. Then determine the sampling proportion of each layer, usually according to the size, variance and other factors of each layer. Then randomly sample in each layer, and extract a certain number of samples. Then combine the samples of each layer into the total sample to get the final sampling result. The TPE sampling method has high sampling efficiency and good sample quality, and can reflect the characteristics of the population. However, in actual application, reasonable design and adjustment need to be made according to the specific situation to ensure the accuracy and reliability of the sampling result.

[0076] The above introduces the fitting process of the second sub-model 531 and the third sub-model 532, and the application process of the second sub-model 531 and the third sub-model 532 is as follows.

[0077] The second sub-model 531 is used to process the first stage process, and the second sub-model 531 represents the relationship between the device information of multiple devices, the environment information 501 and the intermediate state variable 504. The input of the second sub-model 531 can include decision information at time t+1, and can also include at least one of the following: decision information at at least one previous time before time t+1, at least one intermediate state variable at at least one previous time. The output of the second sub-model 531 can include the intermediate state variable 504, which can correspond to time t+1.

[0078] The third sub-model 532 is used to process the second stage process. The third sub-model 532 characterizes the relationship between the intermediate variable 504 and the equipment energy consumption. The input to the third sub-model 532 may include the intermediate variable at time t+1, and may also include at least one of the following: decision information at time t+1, at least one decision information from a previous time step, at least one intermediate variable from a previous time step, and at least one energy consumption index 503 from a previous time step. The output of the third sub-model 532 may include the energy consumption index 503 at time t+1.

[0079] For example, candidate control strategy 502 can be input into the second sub-model 531, and the second sub-model 531 outputs intermediate state variable 504. Intermediate state variable 504 can be input into the third sub-model 532, and the third sub-model 532 outputs energy consumption index 503.

[0080] The aforementioned decision-making information may include candidate control strategies 502 and environmental information 501, and may also include equipment status (e.g., start-up and shutdown), secondary cooling demand estimates, and time information reflecting periodic patterns (e.g., week-based dates, day-based times, holidays, etc.). Candidate control strategies 502 may include the operating frequency of chilled water pumps, the operating frequency of cooling water pumps, the operating frequency of cooling towers, the outlet temperature of the cooling main pipe, and the outlet temperature of the chilled water main pipe.

[0081] The aforementioned intermediate variable 504 represents equipment information that varies across multiple devices depending on the control strategy, such as chiller inlet water temperature, valve opening, cooling main inlet water temperature, chilled water inlet water temperature, chilled water flow rate, cooling main flow rate, chilled water supply and return pressure, and cooling water supply and return pressure. The intermediate variable is neither the control strategy requiring decision-making nor the energy consumption requiring evaluation. The intermediate variable 504 can be used to evaluate the "fidelity" of the simulation intermediate state, that is, to assess whether the simulation environment model's handling of the intermediate process is reasonable.

[0082] The aforementioned energy consumption index 503 may include refrigeration power, electricity consumption, etc., such as total chiller power, chilled water pump power, cooling water pump power, and cooling tower power.

[0083] Figure 6 This is a schematic diagram of a third simulation environment model implementation according to an embodiment of the present disclosure.

[0084] like Figure 6 As shown, in the third implementation, multiple devices in the HVAC system do not need to be decoupled, and the determination process of energy consumption index 603 is not the two stages mentioned above, but a single stage. Accordingly, the simulation environment model includes a fourth sub-model 641, which can characterize the relationship between the device information, intermediate variable 604, environmental information 601, and device energy consumption of multiple devices.

[0085] It is understandable that the fourth sub-model 641 needs to be determined in advance based on historical data, and then the fourth sub-model 641 is applied to output the energy consumption index 603. The process of determining the fourth sub-model 641 based on historical data can be referred to g(·) above, and will not be repeated here in this embodiment.

[0086] The process of applying the fourth sub-model 641 is as follows: The input of the fourth sub-model 641 may include decision information (including control strategy 602 and environmental information 601) and intermediate variables 604, and the output of the second sub-model may include energy consumption index 603.

[0087] The third implementation method combines the two stages of the second implementation method into one stage. This avoids the cumulative error between the second and third sub-models when the accuracy of the second sub-model used in the first stage is low, thus reducing the accuracy of the third sub-model in the second stage. This improves the output accuracy of the simulation environment model.

[0088] Figure 7 This is a schematic diagram of a fourth simulation environment model implementation method according to an embodiment of the present disclosure.

[0089] like Figure 7 As shown, the fourth implementation differs from the third in that the HVAC system can include multiple heat exchange units, each of which can include various devices, such as the aforementioned chilled water pump, cooling water pump, and chiller. The gas-liquid circulation channels of the multiple heat exchange units are arranged independently, ensuring that heat exchange occurs only within the devices of the same heat exchange unit, and not between the multiple heat exchange units. For example, the medium in one heat exchange unit will not exchange heat with the medium in another heat exchange unit; this medium includes chilled water, cooling water, refrigerant, etc.

[0090] Accordingly, the simulation environment model includes multiple fourth sub-models corresponding to multiple heat exchange units.

[0091] This embodiment requires determining multiple fourth sub-models based on historical data. The fitting process for a single fourth sub-model can refer to the determination process for the fourth sub-model in the third implementation described above, and will not be repeated here.

[0092] The application process of multiple fourth sub-models is as follows: For the fourth sub-model corresponding to the target heat exchange unit among multiple heat exchange units, the candidate control strategy 702, intermediate variable 703 and environmental information 701 for the target heat exchange unit can be input into the fourth sub-model, and the fourth sub-model outputs the energy consumption index for the target heat exchange unit.

[0093] For example, Figure 7Taking three heat exchange units as an example, the first fourth sub-model 751 outputs the energy consumption index 7031 for the first heat exchange unit, the second fourth sub-model 752 outputs the energy consumption index 7032 for the second heat exchange unit, and the third fourth sub-model 753 outputs the energy consumption index 7033 for the third heat exchange unit.

[0094] The four implementation manners of the simulation environment model are described above. It should be noted that in the four implementation manners described above, any one of the first sub-model, the second sub-model, the third sub-model, and the fourth sub-model can be a physical mechanism model or a model fitted based on historical data, wherein the model fitted based on historical data can be a function or a model based on a neural network, and the present embodiment is not limited thereto.

[0095] After obtaining the simulation environment model, the simulation environment model can be verified to determine whether the accuracy of the simulation environment model meets the requirements. The verification process is described below.

[0096] In the present embodiment, a candidate model can be obtained, and the candidate model can be a simulation environment model that has not been tested. The control strategy includes a test frequency for a water pump in the heating and ventilation system, and the water pump can be a chilled water pump or a chilled water pump. The test frequency and the environmental information can be input into the candidate model, and the candidate model outputs a test power value for the water pump. Or when the candidate model is the second sub-model in the second implementation manner described above, the test flow value can also be output.

[0097] Next, whether the candidate model meets the predetermined verification condition can be determined according to the test frequency and the test information. If it meets, the candidate model is determined as the simulation environment model. If it does not meet, the parameters of the candidate model are continuously adjusted.

[0098] For example, the same water pump frequency and flow value should have a linear relationship, and therefore the predetermined verification condition can include that the test flow value and the test frequency have a linear relationship.

[0099] For another example, based on the linear relationship described above, a first straight line is fitted based on the test flow value and the test frequency, and a second straight line is fitted based on the historical flow value and the historical operating frequency of the water pump. Under the same device model and pipe diameter conditions, the parameters of the first straight line and the parameters of the second straight line are consistent, and the parameters can include the slope and the intercept. Consistency can mean that the difference between the slopes is less than a threshold value, and the difference between the intercepts is less than a threshold value.

[0100] For another example, for the same water pump, the frequency and the power value should have a cubic relationship, and therefore the predetermined verification condition can include that the test power value and the test frequency have a cubic relationship.

[0101] For example, based on the above cubic relationship, a first curve can be fitted based on the test power values and test frequencies, and a second curve can be fitted based on the historical power values and historical operating frequencies of the water pump. Under the same device model and pipe diameter conditions, the parameters of the first curve are consistent with the parameters of the second curve, and the parameters can include the curvature and the intercept.

[0102] For example, the chilled main pipe flow value can be calculated based on the physical mechanism through the chilled water pump frequency and the valve opening value. The calculated chilled main pipe flow value can be compared with the chilled main pipe flow value output by the simulation environment model to verify the simulation environment model. In addition, the flow value can also be effectively obtained through this method for some pipelines without flow meters.

[0103] For example, the refrigeration capacity value can be calculated based on the physical mechanism through the chilled main pipe flow and the chilled main pipe temperature difference, and the calculated refrigeration capacity value can be compared with the refrigeration capacity value output by the simulation environment model to verify the simulation environment model.

[0104] The simulation environment model is verified in this embodiment, and can be used after verification, otherwise the model parameters are continuously adjusted to ensure that the simulation environment model conforms to the physical mechanism, and further ensure the accuracy of the simulation environment model.

[0105] After obtaining the simulation environment model, an optimization algorithm can be used to obtain the target control strategy. The process of solving the optimization algorithm is described below. Taking the second implementation manner of the simulation environment model in the above as an example, the simulation environment model includes the pre-fitted f and g, and the solving process is as follows.

[0106] For example, for any time point t, the environmental conditions v t Below, As a decision variable, the meta-heuristic intelligent optimization algorithm can be used to solve the following optimization problem, where h: may be a function of fitting and calculating a certain constraint index, and b defines the constraint condition, for example, b can include the lower limit of the required refrigeration capacity at the building terminal, in addition, some safety conditions, business constraints and the like can also be added to the constraint condition b.

[0107] For example, the following formula is used for solving.

[0108] min∑ i g i (x, v t , f(x, v t ))

[0109] h(x, v t , f(x, v t ))≤b

[0110] For example, the meanings of the various symbols in the above formula have been described above and will not be repeated here. Through the above formula, the control strategy x t corresponding to the minimum value of the function g is solved for the environmental condition v t , and the control strategy x t is taken as the target control strategy.

[0111] In this embodiment, some formulas that are not explicitly expressed cannot be solved by the traditional structured optimization problem solving framework, so a black box optimization method such as a meta-heuristic optimization algorithm or a heuristic search method is used. The following takes the particle swarm algorithm as an example to describe an implementation of the optimization process, which can include steps 2-1 to 2-5.

[0112] Step 2-1: For a population-based heuristic optimization algorithm, a maximum number of iterations G and a population size p in each iteration can be defined. Given the population size p, at iteration round = 1, the algorithm is started and the initial value x and velocity e of all particles are initialized.

[0113] Step 2-2: According to the principle that a better solution has a higher evaluation value, the trained f and g are used to calculate the evaluation value F, which is calculated as follows, where the is an indicator function that takes a value of 1 when at least one of the subscripts is satisfied and a value of 0 otherwise.

[0114]

[0115] The meanings of the various symbols in the above formula have been described above and will not be repeated here.

[0116] Step 2-3: Record the position and evaluation value of each particle, and record the population optimal position gBest of the current iteration round and the historical optimal position pBest i

[0117] Step 2-4: Update the particle velocity using the velocity update function and update the particle position using the position update function. Where ω is the inertia factor, c1 and c2 are learning factors, which are model hyperparameters and can be empirically valued, and r1 and r2 are random numbers.

[0118] e i = w e i + c1 r1 (pBest i - x i ) + c2 r2 (gBest - x i )

[0119] x i = x i + e i

[0120] The meanings of the various symbols in the above formula have been described above and will not be repeated here.

[0121] Step 2-5: Repeat steps 2-2 to 2-4 above until the number of iterations reaches the maximum number of iterations, and output the global optimal value and the optimal position, i.e., the optimal solution.

[0122] It should be noted that violating the constraint condition b will significantly reduce the evaluation value F of the solution, so in practical applications, attention should be paid to the configured constraint condition b not being too tight to avoid the situation of no solution caused by the constraint condition b. Other solutions also include setting soft constraints, modifying penalty functions, etc.

[0123] The above describes the process of obtaining the target control strategy by using the optimization algorithm.

[0124] After obtaining the target control strategy by using the optimization algorithm, the target control strategy can also be checked to determine whether it needs to be downgraded.

[0125] In this embodiment, the method for controlling the operating state of the HVAC system according to the target control strategy can include the following operations: determining whether the target control strategy meets a predetermined execution condition. If yes, adjusting the operating state of each device in the HVAC system to the operating state indicated by the target control strategy. If no, adjusting the operating state of the HVAC system to a predetermined operating state.

[0126] For example, the predetermined execution condition includes a safety condition, which can represent the boundary value of the adjustment parameter of the device in the normal operating state of the device, such as a frequency of 30-45 Hz and a water temperature of 12-16°C. The target control strategy includes target values for N adjustment parameters of the HVAC system, and each adjustment parameter corresponds to a predetermined value range. If the target value of a certain device exceeds the predetermined value range, it means that the device does not meet the safety condition.

[0127] For another example, the predetermined execution condition includes a business constraint condition, which can represent the boundary value of the adjustment parameter of the device set according to the actual business demand. The business constraint condition is similar to the safety condition, with the difference being that the safety condition is determined based on the device itself, and the business constraint condition is set based on the business demand. For example, the water temperature is 12-16°C in the normal operating state of the device, but the business demand is for the water temperature to be 12-15°C. For another example, the factory requires a temperature of 24-25°C, a frequency of 30-50 Hz, a flow rate of 100-400 liters / second, and a pressure difference of 3-5 Pa in the pipeline.

[0128] For example, the predetermined execution condition includes an action change rate, and a change rate between the target control strategy and a previous control strategy executed by the HVAC system is greater than or equal to a change rate threshold. That is, the target control strategy at time t is determined based on the data at time t, and the change rate between the target control strategy and the control strategy x at time t-1 issued to the HVAC system at time t-1 is t-1 The change rate is greater than or equal to the change rate threshold, and the target control strategy is issued. Otherwise, the control strategy x is issued. t-1 .

[0129] For example, the predetermined execution condition includes a strategy compliance rate. For example, there are N devices, and M devices can satisfy the business constraint condition and the safety condition, and the remaining N-M devices can not satisfy the business constraint condition and the safety condition, 1≤M≤N, and M and N are integers. The ratio of M to N is the strategy compliance rate, which needs to be greater than or equal to a predetermined ratio, which can be 1 or 0.8 or other numerical values.

[0130] It should be noted that the predetermined execution condition can include at least one of the safety condition, the business constraint condition, the action change rate, and the strategy compliance rate. If the target control strategy satisfies the predetermined execution condition, the HVAC system is run according to the target control strategy, otherwise, the degradation processing of the control strategy is performed.

[0131] In some embodiments, the degradation processing process can be an expert experience method, that is, a more reliable HVAC expert or a preconfigured operation strategy of the HVAC system is used as a predetermined control strategy, and the predetermined control strategy is directly executed.

[0132] In some embodiments, the degradation processing process can be a historical optimization method, that is, in the historical execution working condition trajectory, a set of working condition parameters with the lowest refrigeration power is found as the predetermined control strategy under the condition that the environmental conditions are similar, and the predetermined control strategy is directly executed. The environmental conditions include secondary side cooling demand and outdoor environment temperature and humidity, etc.

[0133] In actual applications, only one target control strategy can be checked to see whether it satisfies the predetermined execution condition, and degradation processing is performed if the predetermined execution condition is not satisfied. Alternatively, multiple target control strategies can be checked at a time, and degradation processing is performed if none of them satisfies the predetermined execution condition.

[0134] According to another embodiment of the present disclosure, in steps 1-2 of the above embodiment, the target control strategy can be determined based only on the data at time t.

[0135] In other embodiments, considering the factors such as data lag, inertia, thermal inertia, etc., f and g can also be trained based on the historical data at time t and other historical data before time t. ​​

[0136] Correspondingly, in the process of solving the optimization problem by using the meta-heuristic intelligent optimization algorithm, the sub-model f and the sub-model g are not only simulated and fitted by using the information at time t. In a specific business scenario, if the data collection frequency is high and there is a certain correlation between adjacent two data collections, the time series variable can be added. Thus, more information is used to improve the accuracy of the model, and the working condition trajectory can be predicted in advance, and the optimal strategy is calculated in advance to improve the control efficiency.

[0137] For example, after the target control strategy is issued to the heating and ventilation system, the intermediate state variable in the heating and ventilation system needs a certain time to respond, and the future value needs to be used to determine the intermediate state variable at this time. For example, after the target control strategy is issued to the heating and ventilation system, the intermediate state variable in the heating and ventilation system changes and needs 3 minutes to reach a stable state. If data is collected every 5 minutes, the time series variable can be ignored. If data is collected every 1 minute, the time series variable can be considered.

[0138] For example, for each candidate control strategy in the current time, the simulation environment model can be used to process the candidate control strategy at the current time, the environment information at the current time, at least one control strategy at a previous time, at least one environment information at a previous time, and at least one energy consumption index at a previous time, to obtain an energy consumption index corresponding to the candidate control strategy at the current time.

[0139] For example, the formula in the above can be adjusted, and the adjustment manner is to modify the input and output structure of f to f: The input and output structure of g is modified to g: That is, the prediction of each step uses the known information and historical information of the current state. Correspondingly, the loss function in steps 1-3 can also be designed to be more in line with the characteristics of the time series prediction model, such as mean absolute error (MAE), etc. At the same time, a new hyperparameter τ can be added in the hyperparameter optimization in steps 1-3 above. The hyperparameter τ is the number of historical data used in single-step time series prediction. In addition, the formula above can also be modified as follows:

[0140] min∑ i g i (x,v t ,y,x t-1 ,v t-1 ,y t-1 ,z t-1 ,...,x t-τ ,v t-τ ,y t-τ ,z t-τ )

[0141] h(x,v t ,y,xt-1 , v t-1 , y t-1 ,..., x t-τ , v t-τ , y t-τ , )≤b

[0142]

[0143] Figure 8 is a schematic diagram of a control method of a heating and ventilation system according to another embodiment of the present disclosure.

[0144] According to another embodiment of the present disclosure, the optimization algorithm module of the control strategy adopts a hierarchical optimization regulation algorithm. The regulation granularity is from coarse to fine, which not only ensures the sensitivity and real-time performance of the system, but also gradually refines the optimization space to improve the safety, stability and robustness of the system. Figure 8 The implementation process of the hierarchical optimization algorithm of the system operating parameters is shown. The first process 801 is a device-level joint regulation. The number and sequence of the cold machines to be started, the corresponding number of water pumps and cooling towers to be started, that is, the upper limit of the low-frequency adjustment of the refrigerating capacity, are determined. The second process 802 is a fine adjustment driven by the terminal cooling capacity demand. According to the panel settings, passenger flow and environmental conditions, and regional attributes of the secondary side, the outlet water temperature of the cold machine is adjusted upward and the frequency of the water pump is adjusted downward, that is, the lower limit of the high-frequency adjustment of the refrigeration. The panel settings are, for example, the temperature set on the indoor operation panel is 24℃, and the regional attributes include, for example, game companies, amusement parks, factories, hotels, lobbies, etc. The third process 803 is a check, that is, a check based on predetermined execution conditions, such as a downgrade process if the target control strategy does not meet the predetermined execution conditions. The third process 803 can be referred to above.

[0145] Figure 9 is a schematic structural block diagram of a control device of a heating and ventilation system according to an embodiment of the present disclosure.

[0146] As shown in Figure 9 , the control device 900 of the heating and ventilation system can include a processing module 910, a strategy determination module 920 and a control module 930.

[0147] The processing module 910 is configured to process a plurality of candidate control strategies and environmental information by using a simulation environment model to obtain a plurality of energy consumption indicators respectively corresponding to the plurality of candidate control strategies; wherein the heating and ventilation system includes a plurality of devices, the candidate control strategy represents a candidate control mode for the plurality of devices, and the energy consumption indicator represents the energy consumption generated by running the heating and ventilation system based on the candidate control strategy; wherein the simulation environment model represents the relationship between the device information of the plurality of devices, the environmental information and the device energy consumption.

[0148] The strategy determination module 920 is configured to determine the candidate control strategy corresponding to the minimum energy consumption indicator among the plurality of candidate control strategies as the target control strategy.

[0149] The control module 930 is configured to control the operation state of the HVAC system according to the target control strategy.

[0150] According to another embodiment of the present disclosure, the HVAC system includes a plurality of sub-devices, the simulation environment model includes a plurality of first sub-models corresponding to the plurality of sub-devices respectively, and the input-output relationship between the plurality of first sub-models is determined based on the connection relationship and the heat conduction direction between the plurality of sub-devices.

[0151] According to another embodiment of the present disclosure, the plurality of sub-devices include a chilled water pump and a chiller, the plurality of first sub-models include a chilled water pump sub-model and a chiller sub-model, and the processing module includes a first processing sub-module and a second processing sub-module, the first processing sub-module is configured to input the environment information into the chilled water pump sub-model, the chilled water pump sub-model outputs the operation frequency of the chilled water pump and the chilled water pump energy consumption sub-index, and the second processing sub-module is configured to input the environment information and the operation frequency of the chilled water pump into the chiller sub-model, the chiller sub-model outputs the outlet water temperature of the chiller and the chiller energy consumption sub-index.

[0152] According to another embodiment of the present disclosure, the plurality of sub-devices further include a cooling water pump and a cooling tower, the plurality of first sub-models further include a cooling water pump sub-model and a cooling tower sub-model, and the processing module further includes a third processing sub-module and a fourth processing sub-module, the third processing sub-module is configured to input the environment information into the cooling tower sub-model, the cooling tower sub-model outputs the operation frequency of the cooling tower and the cooling tower energy consumption sub-index, and the fourth processing sub-module is configured to input the environment information and the operation frequency of the cooling tower into the cooling water pump sub-model, the cooling water pump sub-model outputs the operation frequency of the cooling water pump and the cooling water pump energy consumption sub-index.

[0153] According to another embodiment of the present disclosure, the simulation environment model includes a second sub-model and a third sub-model, the second sub-model represents the relationship between the device information of the plurality of devices, the environment information, and the intermediate state variable, and the third sub-model represents the relationship between the intermediate state variable and the device energy consumption, the intermediate state variable represents the device information of the plurality of devices changing with the control strategy, and the processing module includes a fifth processing sub-module and a sixth processing sub-module, the fifth processing sub-module is configured to input the candidate control strategy into the second sub-model, the second sub-model outputs the intermediate state variable, and the sixth processing sub-module is configured to input the intermediate state variable into the third sub-model, and the third sub-model outputs the energy consumption index.

[0154] According to another embodiment of the present disclosure, the HVAC system comprises at least one heat exchange unit, the simulation environment model comprises at least one fourth sub-model corresponding to the at least one heat exchange unit respectively, and the fourth sub-model represents the relationship between the device information, the intermediate state variable, the environment information and the device energy consumption of the plurality of devices; the processing module comprises: a seventh processing sub-module configured to, for the fourth sub-model corresponding to a target heat exchange unit in the plurality of heat exchange units, input the candidate control strategy for the target heat exchange unit, the intermediate state variable and the environment information into the fourth sub-model, and output the energy consumption index for the target heat exchange unit by the fourth sub-model.

[0155] According to another embodiment of the present disclosure, the control strategy comprises a test frequency for a water pump in the HVAC system; and the device further comprises: an acquisition module, a test information obtaining module, a verification module and a model determining module. The acquisition module is configured to acquire a candidate model; the test information obtaining module is configured to input the test frequency and the environment information into the candidate model, and the candidate model outputs test information for the water pump, the test information comprising at least one of a test flow value and a test power value; the verification module is configured to determine whether the candidate model satisfies a predetermined verification condition according to the test frequency and the test information; and the model determining module is configured to determine the candidate model as the simulation environment model in a case where it is determined that the candidate model satisfies the predetermined verification condition.

[0156] According to another embodiment of the present disclosure, the predetermined verification condition comprises at least one of: a linear relationship between the test flow value and the test frequency; parameters of a first straight line being consistent with parameters of a second straight line, the first straight line being fitted based on the test flow value and the test frequency, and the second straight line being fitted based on historical flow values and historical operating frequencies of the water pump; a cubic relationship between the test power value and the test frequency; and parameters of a first curve being consistent with parameters of a second curve, the first curve being fitted based on the test power value and the test frequency, and the second curve being fitted based on historical power values and historical operating frequencies of the water pump.

[0157] According to another embodiment of the present disclosure, the control module comprises: a verification sub-module and an adjustment sub-module. The verification sub-module is configured to determine whether the target control strategy satisfies a predetermined execution condition; and the adjustment sub-module is configured to adjust the operating state of the HVAC system to a predetermined operating state in a case where it is determined that the target control strategy does not satisfy the predetermined execution condition.

[0158] According to another embodiment of the present disclosure, the predetermined execution condition comprises at least one of: the target control strategy comprising target values of N adjustment parameters for the HVAC system, each adjustment parameter corresponding to a predetermined numerical range; target values of at least M adjustment parameters being within the corresponding predetermined numerical range, a ratio of M to N being greater than or equal to a predetermined ratio; 1≤M≤N, M and N being integers; and a change rate between the target control strategy and a previous control strategy executed by the HVAC system being greater than or equal to a change rate threshold.

[0159] According to another embodiment of the present disclosure, the processing module comprises: an eighth processing submodule, configured to, for each candidate control strategy of the plurality of candidate control strategies of the current moment, process the candidate control strategy of the current moment, the environment information of the current moment, the control strategy of at least one preceding moment, the environment information of at least one preceding moment, and the energy consumption index of at least one preceding moment by using the simulation environment model, to obtain the energy consumption index corresponding to the candidate control strategy of the current moment.

[0160] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved all comply with relevant laws and regulations and do not violate public order and good customs.

[0161] In the technical solution of the present disclosure, the authorization or consent of the user is obtained before the user personal information is acquired or collected.

[0162] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, comprising at least one processor; and a memory connected with the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the control method of the heating and ventilation system.

[0163] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to perform the control method of the heating and ventilation system.

[0164] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the control method of the heating and ventilation system.

[0165] Figure 10 is a structural block diagram of an electronic device for implementing the control method of the heating and ventilation system according to the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections, and their functions, as well as their implementation, are merely examples and are not intended to limit the implementations described herein and / or claimed.

[0166] As Figure 10As shown, the device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded into a random access memory (RAM) 1003 from a storage unit 1008. Various programs and data required for the operation of the device 1000 can also be stored in the RAM 1003. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0167] A plurality of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a magnetic disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0168] The computing unit 1001 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1001 performs various methods and processes described above, such as the control method of a heating system. For example, in some embodiments, the control method of a heating system can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the control method of a heating system described above can be performed. Alternatively, in other embodiments, the computing unit 1001 can be configured to perform the control method of a heating system by any other appropriate means, such as by means of firmware.

[0169] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0170] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0171] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0173] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0174] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0175] It should be understood that various forms of flow shown above can be used, re-ordered, added to, or deleted from without departing from the spirit of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0176] The specific embodiments described above have been shown by way of example, and someone skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement, and improvement within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A control method of a heating and ventilation system, comprising: processing a plurality of candidate control strategies and environment information by using a simulation environment model to obtain a plurality of energy consumption indexes corresponding to the plurality of candidate control strategies respectively, wherein the heating and ventilation system comprises a plurality of devices, the candidate control strategy represents a candidate control mode for the plurality of devices, and the energy consumption index represents energy consumption generated by running the heating and ventilation system based on the candidate control strategy; determining a candidate control strategy corresponding to a minimum energy consumption index in the plurality of candidate control strategies as a target control strategy; and controlling a running state of the heating and ventilation system according to the target control strategy, comprising: determining whether the target control strategy meets a predetermined execution condition, and adjusting the running state of the heating and ventilation system to a predetermined running state in a case where it is determined that the target control strategy does not meet the predetermined execution condition; wherein the simulation environment model represents a relationship between device information of the plurality of devices, environment information and device energy consumption. The heating and ventilation system comprises a plurality of sub-devices, and the simulation environment model comprises a plurality of first sub-models corresponding to the plurality of sub-devices respectively, and an input-output relationship between the plurality of first sub-models is determined based on a connection relationship and a heat conduction direction between the plurality of sub-devices. The plurality of sub-devices comprise a chilled water pump and a chiller, the plurality of first sub-models comprise a chilled water pump sub-model and a chiller sub-model, and the processing of the plurality of candidate control strategies and the environment information by using the simulation environment model to obtain the plurality of energy consumption indexes corresponding to the plurality of candidate control strategies respectively comprises: inputting the environment information into the chilled water pump sub-model, and outputting a running frequency of the chilled water pump and a chilled water pump energy consumption sub-index by the chilled water pump sub-model; and inputting the environment information and the running frequency of the chilled water pump into the chiller sub-model, and outputting a chilled water outlet temperature of the chiller and a chiller energy consumption sub-index by the chiller sub-model. The plurality of sub-devices further comprise a cooling water pump and a cooling tower, the plurality of first sub-models further comprise a cooling water pump sub-model and a cooling tower sub-model, and the processing of the plurality of candidate control strategies and the environment information by using the simulation environment model to obtain the plurality of energy consumption indexes corresponding to the plurality of candidate control strategies respectively further comprises: inputting the environment information into the cooling tower sub-model, and outputting a running frequency of the cooling tower and a cooling tower energy consumption sub-index by the cooling tower sub-model; and inputting the environment information and the running frequency of the cooling tower into the cooling water pump sub-model, and outputting a running frequency of the cooling water pump and a cooling water pump energy consumption sub-index by the cooling water pump sub-model. The simulation environment model comprises a second sub-model and a third sub-model, the second sub-model represents a relationship between device information of the plurality of devices, environment information and intermediate state variables, the third sub-model represents a relationship between the intermediate state variables and device energy consumption, and the intermediate state variables represent device information of the plurality of devices changing with the control strategy.

2. The method of claim 1, wherein, The processing of the plurality of candidate control strategies and the environment information by using the simulation environment model to obtain the plurality of energy consumption indexes corresponding to the plurality of candidate control strategies respectively comprises:

3. The method of claim 2, wherein, ​ ​ ​ 4. The method of claim 3, wherein, ​ ​ ​ 5. The method of claim 1, wherein, ​ ​ inputting the candidate control strategy into the second sub-model, the second sub-model outputting an intermediate state variable; and inputting the intermediate state variable into the third sub-model, the third sub-model outputting the energy consumption index.

6. The method of claim 1, wherein, The HVAC system comprises at least one heat exchange unit, and the simulation environment model comprises at least one fourth sub-model corresponding to the at least one heat exchange unit respectively, the fourth sub-model representing a relationship between device information of the plurality of devices, an intermediate state variable, environment information, and device energy consumption; The processing of the plurality of candidate control strategies and the environment information by the simulation environment model to obtain the plurality of energy consumption indexes corresponding to the plurality of candidate control strategies comprises: For the fourth sub-model corresponding to a target heat exchange unit of the at least one heat exchange unit, inputting the candidate control strategy for the target heat exchange unit, the intermediate state variable, and the environment information into the fourth sub-model, and the fourth sub-model outputting an energy consumption index for the target heat exchange unit.

7. The method of claim 1, wherein, The candidate control strategy comprises a test frequency for a water pump in the HVAC system; the method further comprises: obtaining a candidate model; inputting the test frequency and the environment information into the candidate model, the candidate model outputting test information for the water pump, the test information comprising at least one of a test flow value and a test power value; determining whether the candidate model meets a predetermined checking condition according to the test frequency and the test information; and determining the candidate model as the simulation environment model if it is determined that the candidate model meets the predetermined checking condition.

8. The method of claim 7, wherein, The predetermined checking condition comprises at least one of: a linear relationship between the test flow value and the test frequency; parameters of a first straight line are consistent with parameters of a second straight line, the first straight line being fitted based on the test flow value and the test frequency, and the second straight line being fitted based on historical flow values and historical operating frequencies of the water pump; a cubic relationship between the test power value and the test frequency; and parameters of a first curve are consistent with parameters of a second curve, the first curve being fitted based on the test power value and the test frequency, and the second curve being fitted based on historical power values and historical operating frequencies of the water pump. The predetermined execution condition comprises at least one of:

9. The method of claim 1, wherein, The target control strategy comprises target values of N adjustment parameters of the HVAC system, each adjustment parameter corresponding to a predetermined numerical range; target values of at least M adjustment parameters are within the corresponding predetermined numerical range, and the ratio of M to N is greater than or equal to a predetermined ratio; 1≤M≤N, M and N are integers; and a change rate between the target control strategy and a previous control strategy that has been executed by the HVAC system is greater than or equal to a change rate threshold. The processing of the plurality of candidate control strategies and the environment information by the simulation environment model to obtain the plurality of energy consumption indexes corresponding to the plurality of candidate control strategies comprises:

10. The method of any one of claims 1 to 9, wherein, ​ For each of the plurality of candidate control strategies at the current time, the simulation environment model is used to process the candidate control strategy at the current time, the environment information at the current time, the control strategy at the at least one previous time, the environment information at the at least one previous time, and the energy consumption indicator at the at least one previous time, to obtain the energy consumption indicator corresponding to the candidate control strategy at the current time.

11. A control device of a heating and ventilation system, comprising: a processing module configured to use a simulation environment model to process a plurality of candidate control strategies and environment information to obtain a plurality of energy consumption indicators corresponding to the plurality of candidate control strategies respectively; wherein the heating and ventilation system comprises a plurality of devices, the candidate control strategies represent candidate control manners for the plurality of devices, and the energy consumption indicators represent energy consumption generated by running the heating and ventilation system based on the candidate control strategies; a strategy determination module configured to determine a candidate control strategy corresponding to a minimum energy consumption indicator in the plurality of candidate control strategies as a target control strategy; and a control module configured to control a running state of the heating and ventilation system according to the target control strategy; wherein the simulation environment model represents a relationship between device information, environment information, and device energy consumption of the plurality of devices; wherein the control module comprises: a verification submodule configured to determine whether the target control strategy satisfies a predetermined execution condition; and an adjustment submodule configured to adjust the running state of the heating and ventilation system to a predetermined running state in a case where it is determined that the target control strategy does not satisfy the predetermined execution condition.

12. The apparatus of claim 11, wherein, The heating and ventilation system comprises a plurality of sub-devices, and the simulation environment model comprises a plurality of first sub-models corresponding to the plurality of sub-devices respectively, and input-output relationships between the plurality of first sub-models are determined based on a connection relationship and a heat conduction direction between the plurality of sub-devices.

13. The apparatus of claim 12, wherein, The plurality of sub-devices comprise a chilled water pump and a chiller, the plurality of first sub-models comprise a chilled water pump sub-model and a chiller sub-model, and the processing module comprises: a first processing submodule configured to input the environment information into the chilled water pump sub-model, and the chilled water pump sub-model outputs a running frequency of the chilled water pump and a chilled water pump energy consumption sub-indicator; and a second processing submodule configured to input the environment information and the running frequency of the chilled water pump into the chiller sub-model, and the chiller sub-model outputs a chilled water outlet temperature of the chiller and a chiller energy consumption sub-indicator.

14. The apparatus of claim 13, wherein, The plurality of sub-devices further comprise a cooling water pump and a cooling tower, the plurality of first sub-models further comprise a cooling water pump sub-model and a cooling tower sub-model, and the processing module further comprises: a third processing submodule configured to input the environment information into the cooling tower sub-model, and the cooling tower sub-model outputs a running frequency of the cooling tower and a cooling tower energy consumption sub-indicator; and a fourth processing submodule configured to input the environment information and the running frequency of the cooling tower into the cooling water pump sub-model, and the cooling water pump sub-model outputs a running frequency of the cooling water pump and a cooling water pump energy consumption sub-indicator.

15. The apparatus of claim 11, wherein, The simulation environment model comprises a second sub-model and a third sub-model, the second sub-model representing a relationship between device information, environment information and intermediate state variables of the plurality of devices, and the third sub-model representing a relationship between the intermediate state variables and device energy consumption, the intermediate state variables representing device information of the plurality of devices varying with the control strategy; the processing module comprises: a fifth processing sub-module configured to input the candidate control strategy into the second sub-model, the second sub-model outputting intermediate state variables; and a sixth processing sub-module configured to input the intermediate state variables into the third sub-model, the third sub-model outputting the energy consumption index.

16. The apparatus of claim 11, wherein, The HVAC system comprises at least one heat exchange unit, and the simulation environment model comprises at least one fourth sub-model corresponding to the at least one heat exchange unit respectively, the fourth sub-model representing a relationship between device information, intermediate state variables, environment information and device energy consumption of the plurality of devices; the processing module comprises: a seventh processing sub-module configured to, for the fourth sub-model corresponding to a target heat exchange unit of the at least one heat exchange unit, input the candidate control strategy, intermediate state variables and environment information for the target heat exchange unit into the fourth sub-model, the fourth sub-model outputting an energy consumption index for the target heat exchange unit.

17. The apparatus of claim 11, wherein, The candidate control strategy comprises a test frequency for a water pump in the HVAC system; the device further comprises: an acquisition module configured to acquire a candidate model; a test information obtaining module configured to input the test frequency and environment information into the candidate model, the candidate model outputting test information for the water pump, the test information comprising at least one of a test flow value and a test power value; a verification module configured to determine, according to the test frequency and the test information, whether the candidate model satisfies a predetermined verification condition; and a model determining module configured to, in a case where it is determined that the candidate model satisfies the predetermined verification condition, determine the candidate model as the simulation environment model.

18. The apparatus of claim 17, wherein, The predetermined verification condition comprises at least one of: a linear relationship between the test flow value and the test frequency; parameters of a first straight line being consistent with parameters of a second straight line, the first straight line being fitted based on the test flow value and the test frequency, and the second straight line being fitted based on historical flow values and historical operating frequencies of the water pump; a cubic relationship between the test power value and the test frequency; and parameters of a first curve being consistent with parameters of a second curve, the first curve being fitted based on the test power value and the test frequency, and the second curve being fitted based on historical power values and historical operating frequencies of the water pump. The predetermined execution condition comprises at least one of:

19. The apparatus of claim 11, wherein, the target control strategy comprising target values of N adjustment parameters of the HVAC system, each adjustment parameter corresponding to a predetermined numerical range; target values of at least M adjustment parameters being within corresponding predetermined numerical ranges, a ratio of M to N being greater than or equal to a predetermined ratio; 1≤M≤N, M and N being integers; and ​ A change rate between the target control strategy and a previous control strategy executed by the HVAC system is greater than or equal to a change rate threshold.

20. The apparatus of any of claims 11 to 19, wherein, The processing module comprises: An eighth processing submodule is configured to, for each candidate control strategy of the plurality of candidate control strategies of the current time, process the candidate control strategy of the current time, the environmental information of the current time, the control strategy of at least one previous time, the environmental information of at least one previous time, and the energy consumption index of at least one previous time by using the simulation environment model, to obtain the energy consumption index corresponding to the candidate control strategy of the current time. 21.An electronic device comprising: at least one processor; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 10.

22. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1 to 10. 23.A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 10.

24. A heating and ventilation apparatus comprising: the HVAC system and the electronic device of claim 21.

Images