Environmental control system control method and device and environmental control system

Abstract

The invention discloses an environment control system control method and device and an environment control system, and belongs to the field of environment control systems. The environmental control system control method comprises the following steps: acquiring target load data corresponding to an environmental control system; inputting the target load data and the acquired AHU mixed wind temperature at the first acquisition moment into a global coordination optimization model, and acquiring an optimization parameter set corresponding to a second acquisition moment and output by the global coordination optimization model; the global coordination optimization model is deployed at a cloud end; establishing an optimization parameter model based on the optimization parameter set; and deploying the optimization parameter model to the field controller, so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model. According to the control method of the environmental control system, the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform are set to be mutually independent, and only short-frequency data interaction exists between the optimization parameter model and the global coordination optimization model, so that the operation stability of the controller is remarkably improved, the implementation is relatively high, and the robustness is high.

Description

Technical Field

[0001] The present application belongs to the field of environmental control systems, and in particular, relates to an environmental control system control method, device and environmental control system. Background Art

[0002] The environmental control system of public buildings needs to control the water system and the wind system. In the related technology, the wind system and the water system are mainly controlled separately to achieve stable control of the system. However, this method easily causes a mismatch between the supply and demand of cooling capacity, thereby increasing the energy consumption of the system and making the control effect poor. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes an environmental control system control method, device and environmental control system, which significantly improves the stability of the controller operation on the basis of ensuring the best matching of cooling supply and demand, has strong feasibility and high robustness, low development difficulty, and is easy to implement in actual projects.

[0004] In a first aspect, the present application provides a method for controlling an environmental control system, the method comprising:

[0005] Obtain target load data corresponding to the environmental control system;

[0006] Input the target load data and the AHU mixed air temperature obtained at the first collection time into a global coordination optimization model, and obtain an optimization parameter set corresponding to the second collection time output by the global coordination optimization model; the global coordination optimization model is deployed in the cloud;

[0007] Establishing an optimization parameter model based on the optimization parameter set;

[0008] Deploying the optimization parameter model to a field controller, so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model;

[0009] The second collection time is a collection time after the first collection time.

[0010] According to the environmental control system control method of the present application, the wind system and the water system are controlled as a whole, and the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform are set to be independent of each other. Only short-frequency data interaction exists between the two, which reduces the requirements for the communication environment between the cloud and the controller, and has low requirements for on-site hardware. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, the development difficulty is low, and it is easy to implement in actual projects.

[0011] According to an embodiment of the present application, the step of obtaining target load data corresponding to the environmental control system includes:

[0012] Inputting the first parameter into the load prediction model, and obtaining the first load data of the environmental control system at the second collection time predicted by the load prediction model; wherein the load prediction model is obtained by training based on the sample key parameters;

[0013] The first load data is determined as the target load data.

[0014] According to an embodiment of the present application, before inputting the first parameter into the load prediction model to obtain the first load data of the environmental control system at the second collection time predicted by the load prediction model, the method further includes:

[0015] When the time interval between the last training of the load forecasting model and that of the last training exceeds the target training period, the load forecasting model is updated.

[0016] According to one embodiment of the present application, the first parameter includes the outdoor dry-bulb temperature corresponding to the second collection time, the main water supply temperature corresponding to the first collection time, and the second load data of the environmental control system corresponding to the first collection time; the outdoor dry-bulb temperature is predicted based on actual temperature information.

[0017] According to one embodiment of the present application, the global coordinated optimization model is trained and modeled through the following steps:

[0018] Randomly combine any parameters in the sample load parameter set and the AHU mixed air temperature parameter set to obtain multiple sample parameter combinations;

[0019] Each of the sample parameter combinations and constraint conditions is input into the global coordinated optimization model to solve the optimization parameter set corresponding to the minimum value of the first predicted energy consumption data under each of the sample parameter combinations.

[0020] According to one embodiment of the present application, the method further includes:

[0021] Acquire actual energy consumption data at the first collection moment;

[0022] Inputting the equipment operation data into the environmental control equipment model to obtain second predicted energy consumption data predicted by the environmental control equipment model;

[0023] When the difference between the actual energy consumption data and the second predicted energy consumption data exceeds a target threshold, the global coordinated optimization model is updated.

[0024] According to one embodiment of the present application, the environmental control equipment model includes: a chiller model, a refrigeration pump model and an AHU model.

[0025] According to an embodiment of the present application, inputting the equipment operation data into the environmental control equipment model to obtain the second predicted energy consumption data predicted by the environmental control equipment model includes:

[0026] Inputting the equipment operation data into the AHU model, and obtaining the AHU water flow and fan energy consumption data output by the AHU model;

[0027] determining a chilled water flow rate based on the AHU water flow rate;

[0028] The chilled water flow is input into the chiller model and the freezing pump model respectively, and the chiller energy consumption data output by the chiller model and the freezing pump energy consumption data output by the freezing pump model are obtained.

[0029] According to an embodiment of the present application, deploying the optimization parameter model to a field controller so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model includes:

[0030] Obtaining a first optimization parameter and a first optimization algorithm corresponding to the second acquisition moment output by the optimization parameter model;

[0031] The target control variable is controlled based on the first optimization parameter and the first optimization algorithm.

[0032] In a second aspect, the present application provides an environmental control system control device, the device comprising:

[0033] A first processing module is used to obtain target load data corresponding to the environmental control system;

[0034] The second processing module is used to input the target load data and the AHU mixed air temperature obtained at the first collection time into the global coordination optimization model, and obtain the optimization parameter set corresponding to the second collection time output by the global coordination optimization model; the global coordination optimization model is deployed in the cloud;

[0035] A third processing module, used for establishing an optimization parameter model based on the optimization parameter set;

[0036] a fourth processing module, configured to deploy the optimization parameter model to a field controller, so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model;

[0037] The second collection time is a collection time after the first collection time.

[0038] According to the environmental control system control device of the present application, the wind system and the water system are controlled as a whole, and the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform are set to be independent of each other. Only short-frequency data interaction exists between the two, which reduces the requirements for the communication environment between the cloud and the controller, and has low requirements for on-site hardware. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, the development difficulty is low, and it is easy to implement in actual projects.

[0039] In a third aspect, the present application provides an environmental control system, comprising:

[0040] Water systems;

[0041] Wind system;

[0042] Cloud / Edge Platform;

[0043] A field controller, wherein the field controller and the cloud / edge platform are electrically connected to the water system and the wind system respectively, and the field controller controls the water system and the wind system based on the environmental control system control method as described in the first aspect.

[0044] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the environmental control system control method as described in the first aspect above is implemented.

[0045] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the environmental control system control method as described in the first aspect above.

[0046] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0047] By controlling the wind system and the water system as a whole, and setting the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform to be independent of each other, there is only short-frequency data interaction between the two, which reduces the communication environment requirements between the cloud and the controller, and has low requirements for on-site hardware. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, the development difficulty is low, and it is easy to implement in actual projects.

[0048] Furthermore, by inputting the predicted first load data of the next moment into the global coordinated optimization model to obtain the first optimization parameters and the first optimization algorithm to adjust the control parameters of the system in advance, the environmental control system can quickly reach the optimal operating state and effectively improve the control efficiency and control effect.

[0049] Furthermore, by establishing a global coordination optimization model for the key equipment of the environmental control system, an optimization algorithm is used to obtain the optimization parameter model with the lowest energy consumption of the environmental control system under different working conditions, and the obtained optimization parameter model is deployed to the local controller, so that the local controller can optimize the host water outlet temperature and AHU supply air temperature setting values ​​in real time according to the load forecast results and the collected operating data, so as to achieve continuous optimal operation of the system energy efficiency, simple and fast operation, and low design cost.

[0050] Furthermore, by judging whether it is necessary to update the global coordination optimization model through the accumulated error between the energy consumption predicted by the global coordination optimization model and the actual energy consumption within a certain period of time, so as to update the coefficients of the controller optimization parameter model, the precision and accuracy of the optimization parameter model deployed in the controller can be effectively guaranteed, thereby improving the control effect.

[0051] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0053] Figure 1 It is one of the flow charts of the environmental control system control method provided in the embodiment of the present application;

[0054] Figure 2 This is the second flow chart of the environmental control system control method provided in the embodiment of the present application;

[0055] Figure 3 This is the third flow chart of the environmental control system control method provided in the embodiment of the present application;

[0056] Figure 4 This is the fourth flow chart of the environmental control system control method provided in the embodiment of the present application;

[0057] Figure 5 This is the fifth flow chart of the environmental control system control method provided in the embodiment of the present application;

[0058] Figure 6 This is the sixth flow chart of the environmental control system control method provided in the embodiment of the present application;

[0059] Figure 7 is a schematic diagram of the structure of the environmental control system control device provided in an embodiment of the present application;

[0060] Figure 8 It is a structural schematic diagram of the environmental control system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0062] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0063] In the following, in conjunction with the accompanying drawings, the environmental control system control method, environmental control system control device, environmental control system, electronic device and readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0064] The environmental control system control method may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0065] The environmental control system control method provided in the embodiment of the present application may be executed by the environmental control system, or an electronic device connected to the environmental control system for communication, or a functional module or functional entity in the electronic device that can implement the environmental control system control method. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The environmental control system control method provided in the embodiment of the present application is described below by taking the electronic device as the execution subject as an example.

[0066] like Figure 1 As shown, the environmental control system control method includes: step 110, step 120, step 130 and step 140.

[0067] Step 110, obtaining target load data corresponding to the environmental control system;

[0068] In this step, the environmental control system includes an air system (air conditioning terminal) and a water system (air conditioning refrigeration room).

[0069] The water system may include: a chilled water system and a cooling water system.

[0070] The chilled water system is used to transport the cold energy generated by the cold source equipment (chiller) to the air conditioning terminal through the power device (chiller water pump); the cooling water system is used to transport the condensation heat generated by the chiller to the cooling tower through the power device (cooling water pump), exchange heat with the air in the cooling tower, and transfer the waste heat to the outside.

[0071] The wind system can include air handling units (AHU) and fan coil units and other air handling equipment. The end that provides cooling for public areas such as platforms and station halls is called a large system, and the end that provides cooling for staff and equipment rooms is called a small system.

[0072] It is understandable that the wind system and the water system are coupled with each other, and there is a trade-off in energy consumption.

[0073] The target load data may be the current actual load value of the environmental control system, or may be the predicted load value of the environmental control system at the next collection time.

[0074] In some embodiments, obtaining target load data corresponding to the environmental control system may include:

[0075] Inputting the first parameter into the load prediction model, obtaining the first load data of the environment control system at the second acquisition time predicted by the load prediction model; wherein the load prediction model is obtained by training based on the sample key parameters;

[0076] The first load data is determined as the target load data.

[0077] In this embodiment, the second collection moment may be the next collection moment.

[0078] The first load data is the predicted system load value of the environmental control system at the next collection time.

[0079] The first load data is used to perform feedforward control on the environmental control system.

[0080] like Figure 2 The example shows the load forecast result (i.e., the first load data) and the actual load data (i.e., the second load data) of a subway environmental control system for one week.

[0081] The load forecasting model is pre-trained based on sample key parameters and sample forecasting loads corresponding to the sample key parameters.

[0082] Among them, the key parameters of the sample may include: outdoor dry-bulb temperature at the next moment of the sample, main pipe water supply temperature at the current moment of the sample, and system load at the current moment of the sample;

[0083] The sample predicted load may be the outdoor dry-bulb temperature at the next moment of the sample, the main water supply temperature at the current moment of the sample, and the system load corresponding to the next moment of the sample under the effect of the system load at the current moment of the sample.

[0084] The load forecasting model may be any achievable model type, for example, a multivariate linear regression model, etc., and this application does not limit this.

[0085] Among them, the multivariate linear regression model has low computational complexity and occupies less memory in the controller, and can be applied in most PLCs and DDCs on the market.

[0086] It should be noted that the load forecasting model can be deployed on the field controller, and the load forecasting model and the global coordination optimization model are independent of each other.

[0087] The load forecasting model can be regularly trained and updated by the cloud or edge based on historical operating data, and the updated parameters can be sent to the load forecasting model to update the load forecasting model. The specific updating method will be described in the following embodiments and will not be elaborated here.

[0088] During the research and development process, the inventors discovered that in related technologies, feedback control is often used for optimization control, that is, the optimal control parameters are calculated after the current actual system load is known. Affected by the hysteresis characteristics of the environmental control system, this feedback control can easily lead to a mismatch between cooling demand and supply, thereby affecting the control result, making the final control result not the optimal state of the system.

[0089] In the present application, the first load data at the next moment is obtained through algorithm prediction, and subsequent parameter optimization is performed based on the predicted load data, which can reduce the impact of hysteresis on the control effect and enable the environmental control system to quickly reach the optimal operating state.

[0090] According to the environmental control system control method provided in the embodiment of the present application, by using the predicted first load data at the next moment as the target load data to adjust the control parameters of the system in advance, the environmental control system can quickly reach the optimal operating state, effectively improving the control efficiency and control effect.

[0091] like Figure 3 As shown, in some embodiments, the first parameter may include the outdoor dry-bulb temperature corresponding to the second collection time, the main pipe water supply temperature corresponding to the first collection time, and the second load data of the environmental control system corresponding to the first collection time; the outdoor dry-bulb temperature is predicted based on the actual temperature information.

[0092] In this embodiment, the first acquisition moment is the previous acquisition moment of the second acquisition moment. For example, when the second acquisition moment is the next acquisition moment, the first acquisition moment may be the current acquisition moment.

[0093] The outdoor dry-bulb temperature corresponding to the second collection time is predicted based on the actual temperature information.

[0094] Continue to refer Figure 3 The actual temperature information may include: the outdoor dry-bulb temperature within the target time period one day before the first collection time, the maximum outdoor dry-bulb temperature one day before, the minimum outdoor dry-bulb temperature one day before, the maximum outdoor dry-bulb temperature of the weather forecast on the day of the first collection time, the minimum outdoor dry-bulb temperature of the weather forecast on the day of the first collection time, and the outdoor dry-bulb temperature at the first collection time, etc.

[0095] The target time period can be user-defined, such as set to 24 hours, etc., and this application does not limit it.

[0096] In the actual implementation process, the outdoor dry-bulb temperature corresponding to the second collection moment can be predicted based on a pre-trained neural network model, or the outdoor dry-bulb temperature corresponding to the second collection moment can be predicted based on a table lookup method, or it can be predicted in other feasible ways, which is not limited in this application.

[0097] The main pipe water supply temperature corresponding to the first collection time and the second load data of the environmental control system corresponding to the first collection time can be obtained from the current time data collected by the BMS.

[0098] In the present application, the first load data at the next moment is predicted by the outdoor dry-bulb temperature at the next moment, the main water supply temperature at the current moment, and the system load at the current moment. The first load data is used to perform feedforward control on the environmental control system, and the control parameters of the equipment can be adjusted in advance, so that the system can quickly reach the optimal operating state.

[0099] Step 120: input the target load data and the AHU mixed air temperature obtained at the first acquisition time into the global coordination optimization model, and obtain the optimization parameter set corresponding to the second acquisition time output by the global coordination optimization model; the global coordination optimization model is deployed in the cloud;

[0100] In this step, the second collection time may be the next collection time of the first collection time.

[0101] The target load data is the predicted load data corresponding to the next collection time (ie, the first load data), or may be the current actual load data (ie, the second load data).

[0102] AHU mixed air temperature is the mixed air temperature of the air handling unit.

[0103] The global coordinated optimization model is deployed in the cloud.

[0104] Of course, in other embodiments, the global coordinated optimization model can also be deployed at the edge, such as at an Internet of Things controller, which is not limited in this application.

[0105] The global coordinated optimization model is used to generate the best optimization parameter set based on the input target load data and AHU mixed air temperature to optimize the control algorithm.

[0106] like Figure 4 As shown, the global coordinated optimization model is trained based on the sample load parameter set, the sample AHU mixed air temperature parameter set and the constraint conditions.

[0107] The global coordinated optimization model can be any type of model.

[0108] The sample load parameter set includes multiple sample load parameters, and the sample AHU mixed air temperature parameter set includes multiple AHU mixed air temperature parameters.

[0109] In some embodiments, a sample load parameter set may include: a maximum load value and a minimum load value.

[0110] During the actual execution process, at least one intermediate load parameter within the boundary can be obtained based on the first unit interval with the maximum load value and the minimum load value as the boundary. The first unit interval can be based on user customization, such as setting it to 50 or 30, etc., which is not limited in this application.

[0111] For example, the sample load parameter set may be set to: [50, 100, 150, …, 500] RT, where 50 RT is the lower limit load for a single host and 500 RT is the rated load for two hosts.

[0112] The sample AHU mixed air temperature parameter set may include: a maximum AHU mixed air temperature and a minimum AHU mixed air temperature.

[0113] During the actual implementation process, at least one intermediate AHU mixed air temperature parameter within the boundary can be obtained based on the second unit interval with the maximum AHU mixed air temperature and the minimum AHU mixed air temperature. The second unit interval can be based on user customization, such as setting it to 0.5°C or 0.2°C, etc., which is not limited in this application.

[0114] For example, the sample AHU mixed air temperature parameter set may be set to: [26, 26.5, 27, ..., 29]°C, where 26°C is the minimum value of the actual project AHU mixed air temperature, and 29°C is the maximum value of the actual project AHU mixed air temperature.

[0115] Constraints can be user-defined, such as determined based on actual project control requirements, and this application does not limit this.

[0116] For example, in some embodiments, the constraint condition can be determined by combining a sample load parameter set and an AHU mixed air temperature parameter set as operating condition parameters with the goal of minimizing energy consumption.

[0117] Step 130: establishing an optimization parameter model based on the optimization parameter set;

[0118] In this step, the optimization parameter model is used to enable the field controller to achieve the best control effect, that is, to achieve the optimal energy efficiency of the environmental control system by simultaneously optimizing the wind side and water side control parameters.

[0119] The optimization parameter model is deployed on the field controller, and the optimization parameter model and the global coordination optimization model are independent of each other.

[0120] In the actual implementation process, step 130 may include: establishing an optimization parameter model based on the optimization parameter set and the corresponding operating condition parameters.

[0121] In this embodiment, the first load data at the next moment is obtained through algorithm prediction, and the predicted load data is input into the global coordination optimization model, and the feedback control is converted into feedforward control. The control parameters of the equipment can be adjusted in advance so that the environmental control system can quickly reach the optimal operating state, effectively improve the control efficiency, and make the control effect reach the optimal state of the system.

[0122] Continue to refer Figure 4 In some embodiments, the global coordinated optimization model can be trained and modeled through the following steps:

[0123] Randomly combine any parameters in the sample load parameter set and the AHU mixed air temperature parameter set to obtain multiple sample parameter combinations;

[0124] Each sample parameter combination and constraint condition is input into the global coordinated optimization model to solve the optimal parameter set corresponding to the minimum value of the first predicted energy consumption data under each sample parameter combination.

[0125] In this embodiment, the constraint condition can be determined by combining the sample load parameter set and the AHU mixed air temperature parameter set as operating condition parameters with the goal of minimizing energy consumption.

[0126] The method for determining the sample load parameter set and the AHU mixed air temperature parameter set has been described above and will not be repeated here.

[0127] In some embodiments, the constraints may be expressed as follows:

[0128] min P sys =P chiler +P pump +P AHU =f(Q,T chw,out ,Tsa ,T ma )

[0129]

[0130] Among them, min P sys is the minimum predicted energy consumption data; P chiler is the energy consumption data of the chiller; P pump is the energy consumption data of the refrigeration pump; P AHU is the fan energy consumption data; Q is the load data at the next collection time; T chw,out T is the chilled water outlet temperature; che,out is the chilled water inlet temperature; T sa is the AHU supply air temperature; T ma is the chiller temperature; T che,out,min and T che,out,max T chw,out The minimum and maximum values ​​of T sa,min and T sa,max T sa The minimum and maximum values ​​of r w,min is the minimum chilled water flow ratio; r a,min is the minimum air volume ratio; where T chw,out The minimum and maximum values ​​of T sa The minimum and maximum values ​​of the minimum chilled water flow ratio r w,min And the minimum air volume ratio r a,min It can be based on user customization, such as determined according to the actual control requirements of different projects, and this application does not limit it.

[0131] In some embodiments, after obtaining the optimization parameter set corresponding to the minimum value of the first predicted energy consumption data, an optimization parameter model can also be established based on the sample parameter combination corresponding to the minimum first predicted energy consumption data and the optimization parameter set corresponding to the minimum first predicted energy consumption data.

[0132] After obtaining the optimization parameter set through the global coordinated optimization model, an optimization parameter model can be established based on the optimization parameter set and the corresponding operating condition parameters.

[0133] Continue to refer Figure 4 , in the actual execution process, the sample load parameter set and the sample AHU mixed air temperature parameter set can be randomly combined to obtain a sample operating condition parameter set of the global coordinated optimization algorithm, and the sample operating condition parameter set includes multiple sample operating condition parameter combinations;

[0134] Set the constraints of the optimization model, including upper and lower limits of chilled water outlet temperature, upper and lower limits of AHU supply air temperature, and upper and lower limits of chilled water flow rate;

[0135] The obtained sample operating condition parameter set and constraint conditions are input into the global coordinated optimization model, and the optimization algorithm is used to solve the minimum energy consumption of the environmental control system under different sample operating condition parameter combinations, and the optimal control parameter set corresponding to the minimum energy consumption is output;

[0136] Among them, optimization algorithms include but are not limited to nonlinear programming, genetic algorithms, and simulated annealing algorithms;

[0137] The optimal control parameter set includes: optimized chilled water outlet temperature and optimized AHU supply air temperature, etc.

[0138] According to the obtained optimal control parameter set, the correlation between the optimal control parameter set and the sample operating condition parameter combination corresponding to the minimum energy consumption is analyzed, and an optimization parameter model is established based on the multivariate linear regression equation.

[0139] In some embodiments, the optimization parameter model may be represented as follows:

[0140] T chw,out,opt =g(Q,T a,in )

[0141] T sa,opt =h(Q,T a,in )

[0142] Among them, T chw,out,opt is the optimized chilled water outlet temperature; T sa,opt is the optimized AHU supply air temperature; Q is the load data at the next moment; T a,in is the AHU inlet wet bulb temperature.

[0143] According to the environmental control system control method provided in the embodiment of the present application, a global coordination optimization model is established for the key equipment of the environmental control system, and an optimization algorithm is used to obtain the optimization parameter set with the lowest energy consumption of the environmental control system under different working conditions to establish an optimization parameter model, so that the optimization parameter model is deployed in the local controller, so that the local controller can optimize the main unit outlet water temperature and AHU supply air temperature setting values ​​in real time according to the load forecast results and the collected working condition data, so as to achieve continuous optimal operation of the system energy efficiency, simple and fast operation, and low design cost.

[0144] Step 140: deploy the optimization parameter model to the field controller, so that the field controller can control the target control variable at the second acquisition moment based on the optimization parameter model.

[0145] In this step, the target control variable is a variable controlled by the field controller, including the control variable corresponding to the wind system and the control variable corresponding to the water system.

[0146] The controlled equipment corresponding to the target control variable may include: chillers, AHUs, refrigeration pumps, etc.

[0147] The optimization parameter model may be any type of model, such as a multivariate linear regression model, etc., and this application does not limit this.

[0148] Among them, the multivariate linear regression model has low computational complexity and occupies less memory in the controller, and can be applied in most PLCs and DDCs on the market.

[0149] After the optimization parameter model is obtained, the optimization parameter model may be deployed to the field controller so that the field controller can control the target control variable at the second acquisition moment based on the optimization parameter model.

[0150] The field controller is the core device of the environmental control system architecture, which is used to optimize the distribution of control parameters and the upload of operating data of controlled equipment.

[0151] In some embodiments, step 140 may include:

[0152] Obtaining a first optimization parameter and a first optimization algorithm corresponding to a second acquisition time output by the optimization parameter model;

[0153] Based on the first optimization parameter and the first optimization algorithm, the target control variable is controlled.

[0154] In this embodiment, the first optimization parameter is the best control parameter corresponding to the field controller in the environmental control system.

[0155] The first optimization parameter may include: optimized AHU inlet wet bulb temperature and optimized AHU load, etc.

[0156] The first optimization algorithm is used to characterize the correlation between the first optimization parameter and the optimal operating condition parameter corresponding to the field controller.

[0157] Based on the optimization parameter model deployed on the field controller, the first optimization parameter and the first optimization algorithm corresponding to the optimized second acquisition moment can be obtained.

[0158] After obtaining the first optimization parameters and the first optimization algorithm corresponding to the second acquisition moment, the first optimization parameters and the first optimization algorithm can be deployed to the field controller to control the target control variable at the second acquisition moment, and based on the actual control result at the second acquisition moment, the first optimization parameters and the first optimization algorithm corresponding to the third acquisition moment are predicted; wherein the third acquisition moment is the next acquisition moment of the second acquisition moment.

[0159] For example, in the actual execution process, the controller calculates the predicted load at the next moment through the load prediction model based on the system load at the current moment, the difference between the main water supply temperature and the set temperature, and the outdoor dry-bulb temperature at the next moment.

[0160] The optimization parameter model then calculates the optimal set of settings for the next moment (including the optimized outlet water temperature of the host and the optimized supply air temperature of the AHU, etc.) based on the predicted load at the next moment output by the load prediction model and the collected AHU mixed air temperature, and sends it to the on-site equipment.

[0161] Repeat the above steps at the next moment.

[0162] like Figure 5 As shown, the architecture of the global coordinated optimization model of the present application may include: controlled devices, controllers, gateways, and cloud platforms, etc.

[0163] Among them, the gateway realizes the functions of uploading local collected data to the cloud and sending data to the cloud platform.

[0164] The controlled equipment mainly includes: chillers, AHU and refrigeration pumps, and the control parameters include: chilled water outlet temperature and AHU supply air temperature.

[0165] The controller is the core device of the entire control system architecture, and plays the role of optimizing the distribution of control parameters and uploading of operating data of controlled devices.

[0166] An optimization parameter model is deployed in the controller, and the model coefficients can be updated through the cloud platform.

[0167] The cloud platform is deployed with a global coordination optimization model, which outputs the set of optimization parameters with the lowest system energy consumption under different working conditions, obtains the regression equation coefficients of the optimization parameters and working condition parameters, and sends the coefficients to the optimization parameter model of the controller.

[0168] This architecture deploys the optimization control model in a dispersed manner on the cloud platform and the controller. The cloud platform is mainly responsible for training and updating the model and algorithm, and uses cloud computing power to solve relatively complex modeling and optimization tasks. The controller is mainly responsible for calculating the optimal control parameters of the environmental control system, with fast calculation speed and small memory usage, meeting the real-time and reliability requirements of on-site control. The cloud platform has a short downlink data cycle and will not put pressure on controller communication. Even if the communication network is interrupted, it will not affect the independent operation of the controller. The inventor has verified through multiple experiments that this control architecture can be applied to almost all building controllers on the market.

[0169] During the research and development process, the inventors also discovered that in the related technologies, the traditional control strategy is to control the wind system and the water system separately. Although this can ensure stable system control, it also causes a mismatch between cooling supply and demand, leading to an increase in system energy consumption. To solve the above problems, the current common solution in the industry is to optimize the control of the wind system and the water system as a whole, establish a simulation model of the HVAC equipment on the cloud or edge, and use optimization algorithms to optimize different working conditions, and send the optimized parameters to the controller regularly. However, this method requires support from a cloud platform or edge device with powerful computing power, and the cloud / edge communicates frequently with the controller, which has an adverse effect on the stable operation of the controller, making it difficult to be truly applied and promoted in actual projects.

[0170] In this application, by controlling the wind system and the water system as a whole and fully considering the mutual coupling characteristics between the wind system and the water system, the cooling supply and demand under the final control can be optimally matched, effectively reducing the system energy consumption and achieving a higher control effect.

[0171] In addition, by setting the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform to be independent of each other, there is only short-frequency data interaction between the cloud and the controller, which makes the communication environment requirements between the cloud and the controller relatively low. Even if the on-site network is interrupted, it will not affect the normal operation of the controller model. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, which is easy to implement in actual projects.

[0172] According to the environmental control system control method provided in the embodiment of the present application, the wind system and the water system are controlled as a whole, and the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform are set to be independent of each other. Only short-frequency data interaction exists between the two, which reduces the requirements for the communication environment between the cloud and the controller, and has low requirements for on-site hardware. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, the development difficulty is low, and it is easy to implement in actual projects.

[0173] The following is an explanation of the updating method of the load forecasting model.

[0174] like Figure 6 As shown, in some embodiments, before step 110, the method may further include:

[0175] When the time interval between the last training of the load forecasting model and that of the last training exceeds the target training period, the load forecasting model is updated.

[0176] In this embodiment, the target training cycle can be based on user customization, such as being set to 2 training cycles or 3 training cycles, etc., which is not limited in this application.

[0177] Updating the load forecast model may include:

[0178] Update sample key parameters;

[0179] The load forecasting model is trained based on the updated sample key parameters.

[0180] During the actual execution process, it can be determined whether the last load forecasting model training time interval exceeds the target training cycle.

[0181] If the target training cycle is exceeded, the load forecasting model is retrained, and the training database is added with data from the new training cycle. After the training is completed, the controller load forecasting model coefficients are updated, and the controller is sent the daily weather forecast data (daily maximum and minimum temperatures) for the next training cycle.

[0182] After obtaining the updated load prediction model, the first parameter is input into the updated load prediction model to obtain the first load data of the environmental control system at the second collection time predicted by the updated load prediction model.

[0183] If the target training cycle is not exceeded, the first parameter can be directly input into the load prediction model to obtain the first load data of the environment control system at the second collection time predicted by the load prediction model.

[0184] According to the environmental control system control method provided in the embodiment of the present application, the load prediction model is updated by updating the timing coefficient, which is simple and convenient to operate and can effectively ensure the update frequency to improve the precision and accuracy of the load prediction model.

[0185] The updating method of the global coordinated optimization model is described below.

[0186] Continue to refer Figure 6 In some embodiments, the method may further include:

[0187] Obtaining actual energy consumption data at the first collection moment;

[0188] Inputting the equipment operation data into the environmental control equipment model to obtain second predicted energy consumption data predicted by the environmental control equipment model;

[0189] When the difference between the actual energy consumption data and the second predicted energy consumption data exceeds the target threshold, the global coordinated optimization model is updated.

[0190] In this embodiment, the target threshold may be user-defined, which is not limited in this application.

[0191] The second predicted energy consumption data is energy consumption data predicted based on the environmental control equipment model.

[0192] In some embodiments, the difference may be a difference between the actual energy consumption data and the second predicted energy consumption data.

[0193] In some embodiments, the difference degree may also be a cumulative value of differences between a plurality of actual energy consumption data and a plurality of second predicted energy consumption data.

[0194] For example, during the actual execution process, based on the equipment operation data obtained at the current collection time, the actual energy consumption data of the environmental control system at the current collection time is determined, and the cumulative error between the actual energy consumption data and the second predicted energy consumption data predicted by the environmental control equipment model is compared to see whether it exceeds the target threshold.

[0195] If the cumulative error exceeds the target threshold, it is considered that the accuracy of the global coordinated optimization model has decreased, and the global coordinated optimization model is retrained, and new operating data is added to the training database. After the training is completed, the controller optimization parameter model coefficients are updated.

[0196] If the cumulative error does not exceed the target threshold, it is further determined whether the load forecasting model needs to be updated.

[0197] In some embodiments, the environmental control equipment model may include: a chiller model, a refrigeration pump model, and an AHU model.

[0198] In this embodiment, the environmental control equipment model is an overall control model obtained by integrating the wind system and the water system.

[0199] Environmental control equipment models may include: chiller model, refrigeration pump model and AHU model.

[0200] Among them, the chiller model is the model corresponding to the chiller.

[0201] The refrigeration pump model is the model corresponding to the cooling water pump.

[0202] The AHU model is the model corresponding to the air handling unit.

[0203] In some embodiments, inputting the equipment operation data into the environmental control equipment model to obtain the second predicted energy consumption data predicted by the environmental control equipment model may include:

[0204] Input the equipment operation data into the AHU model, and obtain the AHU water flow and fan energy consumption data output by the AHU model;

[0205] Determine the chilled water flow based on the AHU water flow;

[0206] The chilled water flow is input into the chiller model and the refrigeration pump model respectively, and the energy consumption data of the chiller output by the chiller model and the energy consumption data of the refrigeration pump output by the refrigeration pump model are obtained.

[0207] In this embodiment, the fan energy consumption data, the chiller energy consumption data and the refrigeration pump energy consumption data are all second predicted energy consumption data.

[0208] The input of the AHU model may include a first operating condition parameter and a control parameter, wherein:

[0209] The first operating condition parameters may include: AHU load, inlet dry bulb temperature, inlet relative humidity, etc.;

[0210] Control parameters may include: supply air temperature, etc.

[0211] The output of the AHU model can include: AHU water flow and fan energy consumption, etc.

[0212] In some embodiments, the AHU model may be represented as follows:

[0213] Q AHU =f(M a ,M w ,T a,in ,T chw,out )

[0214] P AHU =f(freq AHU ,P AHU,des )

[0215] Among them, Q AHU is the AHU load, r q is the AHU chilled water flow ratio, Ma is the AHU air volume, T a,in is the AHU inlet wet bulb temperature, T che,out is the AHU chilled water temperature; M w is the AHU water flow; P AHU is the AHU power, freq AHU is the AHU fan frequency, P AHU,des is the rated power of the AHU fan.

[0216] The chilled water flow can be calculated based on the total AHU water flow.

[0217] The chilled water flow rate can be used as an input parameter for the chiller pump model and the chiller plant model.

[0218] The input of the chiller model may include a second operating condition parameter and a process parameter, wherein:

[0219] The second operating condition parameter may include: cooling water inlet temperature and main engine load, etc.;

[0220] Process parameters may include: chilled water flow rate and chilled water return temperature, etc.

[0221] In some embodiments, the chiller model may behave as follows:

[0222] COP=f(T cw,out ,T chw,out ,PLR)

[0223] Where PLR ​​is the partial load rate of the chiller; T cw,out T is the return water temperature of the main cooling water of the chiller; chw,out is the chilled water outlet temperature; CAP is the rated load of the chiller; P des is the rated power of the chiller; r p is the power correction coefficient; b0~b5 are the regression coefficients.

[0224] Outputs from the chiller model may include chiller energy consumption.

[0225] The input of the chilled water pump model may include the chilled water flow rate, and the output of the chilled water pump model may include the chilled water pump energy consumption.

[0226] In some embodiments, the freeze pump model may be represented as follows:

[0227] P pump =f(freq pump ,P pump,dex )

[0228] Among them, P pump is the chilled water pump power; freq pump is the chilled water pump frequency; P pump,des Rated power of the refrigeration pump.

[0229] According to the environmental control system control method provided in the embodiment of the present application, the cumulative error value between the energy consumption predicted by the environmental control equipment model and the actual energy consumption within a certain period of time is used to determine whether the global coordination optimization model needs to be updated, so as to update the coefficients of the controller optimization parameter model. This can effectively ensure the precision and accuracy of the optimization parameter model deployed in the controller, thereby improving the control effect.

[0230] The environmental control system control method provided in the embodiment of the present application can be executed by an environmental control system control device. In the embodiment of the present application, the environmental control system control device provided in the embodiment of the present application is described by taking the environmental control system control device executing the environmental control system control method as an example.

[0231] The embodiment of the present application also provides an environmental control system control device.

[0232] like Figure 7As shown, the environmental control system control device includes: a first processing module 710 , a second processing module 720 , a third processing module 730 and a fourth processing module 740 .

[0233] The first processing module 710 is used to obtain target load data corresponding to the environmental control system;

[0234] The second processing module 720 is used to input the target load data and the AHU mixed air temperature obtained at the first collection time into the global coordination optimization model, and obtain the optimization parameter set corresponding to the second collection time output by the global coordination optimization model; the global coordination optimization model is deployed in the cloud;

[0235] The third processing module 730 is used to establish an optimization parameter model based on the optimization parameter set;

[0236] The fourth processing module 740 is used to deploy the optimization parameter model to the field controller, so that the field controller controls the target control variable at the second acquisition time based on the optimization parameter model;

[0237] The second collection time is a collection time after the first collection time.

[0238] According to the environmental control system control device provided in the embodiment of the present application, the wind system and the water system are controlled as a whole, and the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud platform are set to be independent of each other. Only short-frequency data interaction exists between the two, which reduces the requirements for the communication environment between the cloud and the controller, and has low requirements for on-site hardware. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, the development difficulty is low, and it is easy to be implemented in actual projects.

[0239] In some embodiments, the first processing module 710 may also be used to:

[0240] Inputting the first parameter into the load prediction model, obtaining the first load data of the environment control system at the second acquisition time predicted by the load prediction model; wherein the load prediction model is obtained by training based on the sample key parameters;

[0241] The first load data is determined as the target load data.

[0242] In some embodiments, the device may also include a fourth processing module for updating the load prediction model before inputting the first parameter into the load prediction model and obtaining the first load data of the environmental control system predicted by the load prediction model at the second collection moment, when the time interval between the load prediction model and the last training of the load prediction model exceeds the target training cycle.

[0243] In some embodiments, the second processing module 720 may also be used to:

[0244] Randomly combine any parameters in the sample load parameter set and the AHU mixed air temperature parameter set to obtain multiple sample parameter combinations;

[0245] Each sample parameter combination and constraint condition is input into the global coordinated optimization model to solve the optimal parameter set corresponding to the minimum value of the first predicted energy consumption data under each sample parameter combination.

[0246] In some embodiments, the apparatus may further include a fifth processing module, configured to:

[0247] Obtaining actual energy consumption data at the first collection moment;

[0248] Inputting the equipment operation data into the environmental control equipment model to obtain second predicted energy consumption data predicted by the environmental control equipment model;

[0249] When the difference between the actual energy consumption data and the second predicted energy consumption data exceeds the target threshold, the global coordinated optimization model is updated.

[0250] In some embodiments, the fifth processing module may also be used to:

[0251] Input the equipment operation data into the AHU model, and obtain the AHU water flow and fan energy consumption data output by the AHU model;

[0252] Determine the chilled water flow based on the AHU water flow;

[0253] The chilled water flow is input into the chiller model and the refrigeration pump model respectively, and the energy consumption data of the chiller output by the chiller model and the refrigeration pump energy consumption data output by the refrigeration pump model are obtained.

[0254] In some embodiments, the fourth processing module 740 may also be used to:

[0255] Obtaining a first optimization parameter and a first optimization algorithm corresponding to a second acquisition time output by the optimization parameter model;

[0256] Based on the first optimization parameter and the first optimization algorithm, the target control variable is controlled.

[0257] The environmental control system control device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc. It can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., and the embodiment of the present application does not make specific limitations.

[0258] The environmental control system control device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0259] The environmental control system control device provided in the embodiment of the present application can achieve Figures 1 to 6 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0260] In some embodiments, Figure 8 As shown, an embodiment of the present application also provides an environmental control system.

[0261] The environmental control system includes: water system, wind system, field controller and cloud / edge platform.

[0262] Among them, the environmental control system is communicated with the cloud / edge platform.

[0263] The field controller and the cloud / edge platform are electrically connected to the water system and the wind system respectively, and the field controller controls the water system and the wind system based on the environmental control system control method described in any of the above embodiments.

[0264] According to the environmental control system provided in the embodiment of the present application, the wind system and the water system are controlled as a whole, and the optimization parameter model corresponding to the controller and the global coordination optimization model corresponding to the cloud / edge platform are set to be independent of each other. Only short-frequency data interaction exists between the two, which reduces the requirements for the communication environment between the cloud and the controller, and has low requirements for on-site hardware. On the basis of ensuring the best match between cooling supply and demand, the stability of the controller operation is significantly improved, the feasibility is strong and the robustness is high, the development difficulty is low, and it is easy to implement in actual projects.

[0265] The embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned environmental control system control method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0266] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0267] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned environmental control system control method when executed by a processor.

[0268] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0269] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned environmental control system control method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0270] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0271] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0272] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0273] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0274] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0275] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for controlling an environmental control system, characterized in that: include: Obtain target load data corresponding to the environmental control system; Input the target load data and the AHU mixed air temperature obtained at the first collection time into a global coordination optimization model, and obtain an optimization parameter set corresponding to the second collection time output by the global coordination optimization model; the global coordination optimization model is deployed in the cloud; Establishing an optimization parameter model based on the optimization parameter set; Deploying the optimization parameter model to a field controller, so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model; The second collection time is a collection time after the first collection time.

2. The environmental control system control method according to claim 1, characterized in that: The obtaining of target load data corresponding to the environmental control system includes: Inputting the first parameter into the load prediction model, and obtaining the first load data of the environmental control system at the second collection time predicted by the load prediction model; wherein the load prediction model is obtained by training based on the sample key parameters; The first load data is determined as the target load data.

3. The environmental control system control method according to claim 2, characterized in that: Before inputting the first parameter into the load prediction model to obtain the first load data of the environmental control system at the second collection time predicted by the load prediction model, the method further includes: When the time interval between the last training of the load forecasting model and that of the last training exceeds the target training period, the load forecasting model is updated.

4. The environmental control system control method according to claim 2, characterized in that: The first parameter includes the outdoor dry-bulb temperature corresponding to the second collection time, the main pipe water supply temperature corresponding to the first collection time, and the second load data of the environmental control system corresponding to the first collection time; the outdoor dry-bulb temperature is predicted based on actual temperature information.

5. The environmental control system control method according to any one of claims 1 to 4, characterized in that: The global coordinated optimization model is trained and modeled through the following steps: Randomly combine any parameters in the sample load parameter set and the AHU mixed air temperature parameter set to obtain multiple sample parameter combinations; Each of the sample parameter combinations and constraint conditions is input into the global coordinated optimization model to solve the optimization parameter set corresponding to the minimum value of the first predicted energy consumption data under each of the sample parameter combinations.

6. The environmental control system control method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire actual energy consumption data at the first collection moment; Inputting the equipment operation data into the environmental control equipment model to obtain second predicted energy consumption data predicted by the environmental control equipment model; When the difference between the actual energy consumption data and the second predicted energy consumption data exceeds a target threshold, the global coordinated optimization model is updated.

7. The environmental control system control method according to claim 6, characterized in that: The environmental control equipment model includes: a chiller model, a refrigeration pump model and an AHU model.

8. The environmental control system control method according to claim 7, characterized in that: The step of inputting the equipment operation data into the environmental control equipment model to obtain the second predicted energy consumption data predicted by the environmental control equipment model includes: Inputting the equipment operation data into the AHU model, and obtaining the AHU water flow and fan energy consumption data output by the AHU model; determining a chilled water flow rate based on the AHU water flow rate; The chilled water flow is input into the chiller model and the freezing pump model respectively, and the chiller energy consumption data output by the chiller model and the freezing pump energy consumption data output by the freezing pump model are obtained.

9. The environmental control system control method according to any one of claims 1 to 4, characterized in that: The step of deploying the optimization parameter model to a field controller so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model includes: Obtaining a first optimization parameter and a first optimization algorithm corresponding to the second acquisition moment output by the optimization parameter model; The target control variable is controlled based on the first optimization parameter and the first optimization algorithm.

10. A control device for an environmental control system, characterized in that: include: A first processing module is used to obtain target load data corresponding to the environmental control system; The second processing module is used to input the target load data and the AHU mixed air temperature obtained at the first collection time into the global coordination optimization model, and obtain the optimization parameter set corresponding to the second collection time output by the global coordination optimization model; the global coordination optimization model is deployed in the cloud; A third processing module, used for establishing an optimization parameter model based on the optimization parameter set; a fourth processing module, configured to deploy the optimization parameter model to a field controller, so that the field controller controls the target control variable at the second acquisition moment based on the optimization parameter model; The second collection time is a collection time after the first collection time.

11. An environmental control system, characterized in that: include: Water systems; Wind system; Cloud / edge platform; A field controller, wherein the field controller and the cloud / edge platform are electrically connected to the water system and the wind system respectively, and the field controller controls the water system and the wind system based on the environmental control system control method according to any one of claims 1 to 9.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the environmental control system control method as described in any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the environmental control system control method as described in any one of claims 1 to 9 is implemented.

Images