Environment control method, system, apparatus, electronic device, and storage medium

Abstract

The present application provides an environment control method, system, device, electronic equipment and storage medium, wherein the method comprises: acquiring measured environment data at at least one time point including the current time point; inputting the measured environment data into a prediction model to obtain predicted environment data at the next time point under each control strategy output by the prediction model; the prediction model is determined based on sample measured environment data at each time point under a sample control strategy; determining a target control strategy from each control strategy based on running energy consumption data under each control strategy, and difference data between predicted environment data under each control strategy and preset environment threshold data; and performing environment control based on the target control strategy. The method, system, device, electronic equipment and storage medium provided by the present application can effectively achieve energy saving on the premise of meeting the actual environment control demand.

Description

Technical Field

[0001] This invention relates to the field of environmental control technology, and in particular to an environmental control method, system, device, electronic device, and storage medium. Background Technology

[0002] Currently, data centers equipped with large-scale computer clusters have become one of the major energy-consuming locations. Physical cooling of computer clusters is a crucial foundation for maximizing their performance. High-power central air conditioning and fresh air systems are common physical cooling methods for large-scale computer clusters.

[0003] In existing technologies, the environmental control schemes based on central air conditioning and fresh air equipment in traditional large computer clusters not only lack flexibility but also struggle to achieve optimal energy-saving effects. Summary of the Invention

[0004] This invention provides an environmental control method, system, device, electronic device, and storage medium to address the shortcomings of existing environmental control technologies based on central air conditioning and fresh air equipment, which not only lack flexibility but also struggle to achieve optimal energy-saving effects.

[0005] This invention provides an environmental control method, comprising:

[0006] Acquire measured environmental data at at least one moment, including the current moment;

[0007] The measured environmental data is input into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model; the prediction model is determined based on the sample measured environmental data for each time step under the sample control strategy.

[0008] Based on the operating energy consumption data under each control strategy, and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy, the target control strategy is determined from each control strategy.

[0009] Environmental control is performed based on the aforementioned target control strategy.

[0010] According to an environmental control method provided by the present invention, the step of determining a target control strategy from various control strategies based on operating energy consumption data under each control strategy and the difference data between predicted environmental data and preset environmental threshold data under each control strategy includes:

[0011] From the various control strategies, candidate control strategies are determined that the predicted environmental data satisfies the environmental control rules. These candidate control strategies are used as the environmental control rules, which are determined based on the preset environmental threshold data.

[0012] Based on the operating energy consumption data under each candidate control strategy, and the difference between the predicted environmental data and the preset environmental threshold data under each candidate control strategy, the target control strategy is determined from each candidate control strategy.

[0013] According to an environmental control method provided by the present invention, the step of determining a target control strategy from among the candidate control strategies based on the operating energy consumption data under each candidate control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each candidate control strategy includes:

[0014] With the goal of minimizing the weighted sum of the operating energy consumption data and the difference data, a target control strategy is determined from each candidate control strategy based on the operating energy consumption data and the difference data under each candidate control strategy.

[0015] According to an environmental control method provided by the present invention, the step of inputting the measured environmental data into a prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model includes:

[0016] The weather forecast data and / or the actual control strategy at at least one time, including the current time, and the measured environmental data are input into the prediction model to obtain the predicted environmental data for the next time under each control strategy output by the prediction model.

[0017] According to an environmental control method provided by the present invention, the measured environmental data includes at least one of the following: environmental data at the dynamic environment point, environmental data at the air conditioning outlet, and environmental data at the air conditioning return air point.

[0018] The present invention also provides an environmental control system, including a gateway device, a redundant control device, and an environmental conditioning device, wherein the gateway device and the redundant control device are respectively connected to the environmental conditioning device, and the gateway device is connected to the redundant control device.

[0019] The gateway device is used to determine the target control strategy and control the environmental control device based on the target control strategy;

[0020] The redundant control device is used to determine the operating status of the gateway device, and when the operating status is faulty, determine the target control strategy, and control the environmental control device based on the target control strategy;

[0021] The target control strategy is determined based on the environmental control method described above.

[0022] According to the environmental control system provided by the present invention, the redundant control device includes:

[0023] The status determination unit is used to determine that the operating status is faulty when receiving a handshake signal sent periodically by the gateway device and failing to receive the handshake signal after a timeout.

[0024] An environmental control unit is used to determine the target control strategy when the operating state is faulty, and to control the environmental conditioning equipment based on the target control strategy.

[0025] The present invention also provides an environmental control device, comprising:

[0026] The data acquisition unit is used to acquire measured environmental data at at least one moment, including the current moment.

[0027] The data prediction unit is used to input the measured environmental data into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model; the prediction model is determined based on the sample measured environmental data for each time step under the sample control strategy.

[0028] The strategy determination unit is used to determine the target control strategy from each control strategy based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy.

[0029] An environmental control unit is used to perform environmental control based on the target control strategy.

[0030] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the environmental control method as described above.

[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the environmental control method as described above.

[0032] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the environmental control method as described above.

[0033] The environmental control method, system, device, electronic equipment, and storage medium provided by this invention determine the target control strategy for environmental control based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy. This effectively achieves energy saving while meeting the actual environmental control requirements. Furthermore, the prediction model is determined based on the sample measured environmental data at each time step under the sample control strategy. Applying the prediction model to the prediction of environmental data can improve the accuracy of the prediction and ensure the reliability of subsequent environmental control. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0035] Figure 1 This is one of the flowcharts illustrating the environmental control method provided by the present invention;

[0036] Figure 2 This is a flowchart illustrating step 130 in the environmental control method provided by the present invention;

[0037] Figure 3 This is a flowchart illustrating the search method for the bundle search tree provided by the present invention;

[0038] Figure 4 This is a schematic diagram of the structure of the environmental control system provided by the present invention;

[0039] Figure 5 This is a schematic diagram of the redundant control device provided by the present invention;

[0040] Figure 6 This is the second schematic diagram of the environmental control method provided by the present invention;

[0041] Figure 7 This is a schematic diagram of the structure of the environmental control device provided by the present invention;

[0042] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0044] This invention provides an environmental control method. Figure 1 This is one of the flowcharts illustrating the environmental control method provided by the present invention, such as... Figure 1 As shown, the method includes:

[0045] Step 110: Obtain measured environmental data at at least one time, including the current time.

[0046] Specifically, measured environmental data at at least one moment, including the current moment, can be obtained. Here, measured environmental data refers to environmental data that is actually measured. Environmental data can be temperature data, humidity data, or both. The acquisition of measured environmental data can rely on temperature sensors, humidity sensors, etc., that are pre-deployed in the space.

[0047] The measured environmental data at at least one moment may include only the measured environmental data at the current moment, or it may include both the measured environmental data at the current moment and the measured environmental data at multiple historical moments prior to the current moment. For example, if a moment is determined every 5 minutes, the measured environmental data at at least one moment may be the measured environmental data at 6 moments over a half-hour period, including the current moment.

[0048] Step 120: Input the measured environmental data into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model; the prediction model is determined based on the measured environmental data of the samples at each time step under the sample control strategy.

[0049] Specifically, the prediction model can predict environmental data under various control strategies based on the input measured environmental data, and then output the predicted environmental data for the next time step under each control strategy.

[0050] Before this step, the prediction model needs to be trained. During training, the actual measured environmental data at each time point under the sample control strategy can be obtained. This can be achieved by using the actual measured environmental data from multiple historical time points prior to a given time point under the sample control strategy as input to the prediction model. The model then predicts the environmental data at that specific time point under the sample control strategy. The degree of difference between the predicted environmental data and the actual measured environmental data at that time point is used as the loss function to iterate the model's parameters. It can be understood that the greater the difference between the predicted environmental data and the actual measured environmental data at the same time point under the same control strategy, the larger the loss function; conversely, the smaller the difference, the smaller the loss function. Here, the sample control strategy can be any of the various control strategies.

[0051] In the application phase of the predictive model, after acquiring measured environmental data at at least one moment, including the current moment, this data can be input into the predictive model. The model then uses this data to predict the environmental data, thereby obtaining the predicted environmental data for the next moment under each control strategy. Here, each control strategy refers to the control actions applied to a series of devices such as air conditioners and fresh air systems; these actions can include stopping cooling, normal cooling, or strong cooling. The control strategy can be a unified control action applied to all the aforementioned devices as a whole, or it can be a control action applied to each individual device within all the aforementioned devices.

[0052] Step 130: Based on the operating energy consumption data under each control strategy, and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy, determine the target control strategy from each control strategy.

[0053] Step 140: Perform environmental control based on the target control strategy.

[0054] Specifically, after obtaining the predicted environmental data for the next moment under each control strategy output by the prediction model, the target control strategy can be determined from each control strategy based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data under each control strategy and the preset environmental threshold data.

[0055] The operating energy consumption data here is used to reflect the operating energy consumption of a series of devices such as air conditioners and fresh air equipment under the control strategy. For example, it can be the total electricity required or the total power per unit time.

[0056] The preset environmental threshold data here refers to the pre-set environmental threshold data, specifically the maximum or minimum value of environmental data that meets the environmental control requirements. The environmental threshold data here can be temperature threshold data, humidity threshold data, or both temperature threshold data and humidity threshold data.

[0057] The difference data here reflects the size of the gap between the predicted environmental data and the actual environmental control requirements. For example, if the actual environmental control requirement is to keep the temperature below 25 degrees Celsius, the smaller the difference between the predicted environmental data and the preset environmental threshold data, i.e., 25 degrees Celsius, the smaller the gap between the predicted environmental data and the actual environmental control requirements. The larger the difference between the predicted environmental data and 25 degrees Celsius, the larger the gap between the predicted environmental data and the actual environmental control requirements.

[0058] Understandably, the difference data can also reflect the operating energy consumption under various control strategies. The smaller the difference data, the less additional operating energy is consumed to meet the actual environmental control requirements; the larger the difference data, the greater the additional operating energy is consumed to meet the actual environmental control requirements.

[0059] Therefore, by combining the operating energy consumption data under each control strategy, as well as the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy, a target control strategy can be selected. Specifically, in the selection process, to achieve energy saving, the control strategy with low operating energy consumption data and small difference data can be prioritized. Thus, from the perspectives of both the operating energy consumption of the control strategy itself and the energy consumption to meet the actual environmental control requirements, the target control strategy with the best energy saving effect can be selected.

[0060] Finally, after determining the target control strategy, environmental control can be carried out based on the target control strategy, thereby achieving the reliability of environmental control.

[0061] The method provided in this invention determines the target control strategy for environmental control based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy. This effectively achieves energy saving while meeting the actual environmental control requirements. Furthermore, the prediction model is determined based on the measured environmental data of the samples at each time step under the sample control strategy. Applying the prediction model to the prediction of environmental data can improve the accuracy of the prediction and ensure the reliability of subsequent environmental control.

[0062] Based on the above embodiments, Figure 2 This is a flowchart illustrating step 130 of the environmental control method provided by the present invention, as shown below. Figure 2 As shown, step 130 includes:

[0063] Step 131: Determine candidate control strategies from the various control strategies in which the predicted environmental data satisfies the environmental control rules, and use these candidate control strategies as the environmental control rules determined based on the preset environmental threshold data;

[0064] Step 132: Based on the operating energy consumption data under each candidate control strategy, and the difference data between the predicted environmental data and the preset environmental threshold data under each candidate control strategy, determine the target control strategy from each candidate control strategy.

[0065] Specifically, environmental control rules refer to the requirement that the predicted environmental data under each control strategy should be less than or greater than a preset environmental threshold. The specific requirements can be determined based on the actual environment and control needs. For example, in winter when indoor temperatures are low, the predicted environmental data under each control strategy should be greater than the preset environmental threshold; in summer when indoor temperatures are high, the predicted environmental data under each control strategy should be less than the preset environmental threshold. Considering that some candidate control strategies may not meet the environmental control rules, these strategies can be screened first to obtain candidate control strategies whose predicted environmental data meets the environmental control rules. These candidate control strategies are the strategies that may subsequently be used as the target control strategy.

[0066] After obtaining candidate control strategies, a target control strategy can be determined from among them based on the operating energy consumption data under each candidate control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each candidate control strategy. For example, the candidate control strategy with the smallest weighted sum of the operating energy consumption data under each candidate control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each candidate control strategy can be used as the target control strategy.

[0067] The method provided in this invention reduces the computational load required for screening control strategies and improves the efficiency of determining the target control strategy by performing a two-stage screening of control strategies.

[0068] Based on the above embodiments, step 132 includes:

[0069] With the goal of minimizing the weighted sum of the operating energy consumption data and the difference data, a target control strategy is determined from each candidate control strategy based on the operating energy consumption data and the difference data under each candidate control strategy.

[0070] Specifically, the target control strategy can be determined based on the minimum weighted sum of operating energy consumption data and difference data under each candidate control strategy, using the operating energy consumption data and difference data under each candidate control strategy as the objective. The formula is as follows:

[0071] min{U t+i J = aW + bTEMP

[0072] stX t+i (Predicted environmental data) ≤ Preset environmental threshold data

[0073] Among them, U t+i Here, J represents the various candidate control strategies, J is the weighted sum of the operating energy consumption data and the difference data under each candidate control strategy, W is the operating energy consumption data under each candidate control strategy, TEMP is the difference data between the predicted environmental data and the preset environmental threshold data under each candidate control strategy, and X is the difference data between each candidate control strategy and the predicted environmental threshold data. t+i (Predicted environment data) refers to the predicted environment data under each candidate control strategy at time i below time t. a and b are weight coefficients. Here, a and b can be added together to 1, a and b can both be 1 or both are 0.5, etc. The embodiments of the present invention do not make specific limitations in this regard.

[0074] The specific process of determining the target control strategy from various candidate control strategies can be as follows: First, calculate the weighted sum of the energy consumption data and the difference data under each candidate control strategy, and then select the candidate control strategy corresponding to the minimum value. Second, calculate the optimal solution of the above formula using algorithms such as greedy search or bundle search. The details are as follows:

[0075] First, a Beam Search Tree is constructed, and the tree nodes are expanded using a prediction model. This beam search improves upon the greedy search by expanding the search space and making it easier to obtain the global optimum.

[0076] During the search of the bundle search tree, solutions that violate the constraints are filtered out. When the bundle search tree stops growing, the optimal candidate control strategy, i.e. the target control strategy, is found by backtracking.

[0077] Figure 3 This is a flowchart illustrating the search method for the bundle search tree provided by the present invention, as shown below. Figure 3 As shown, the method includes:

[0078] First, construct the root node at time x_t, and then store the root node in the list of nodes to be processed, `nodes`. Let i = 1, where i represents the next i-th time step. Here, each node reflects the predicted environment data under a candidate control policy at a given time step.

[0079] When i≤m, calculate the predicted environment data for the next time step corresponding to the node in nodes, expand the possible child nodes of nodes, and take all the newly obtained child nodes as new nodes, then increment i, and repeat the above process.

[0080] When i > m, calculate the optimal cost of the internal nodes in the tree based on the leaf nodes at the termination time. Then, return the candidate control strategy with the minimum optimal cost among the root child nodes. Here, the candidate control strategy is the target control strategy. The cost here refers to the energy consumption data under each control strategy.

[0081] The method provided in this embodiment of the invention uses a bundle search tree to solve for the target control strategy, which expands the search space, makes it easier to obtain the global optimal solution, and further improves the efficiency of determining the target control strategy.

[0082] Based on the above embodiments, step 120 includes:

[0083] The weather forecast data and / or the actual control strategy at at least one time, including the current time, and the measured environmental data are input into the prediction model to obtain the predicted environmental data for the next time under each control strategy output by the prediction model.

[0084] Specifically, weather forecast data affects the predicted environmental data for the next moment under various control strategies. For example, when the weather forecast data is high, such as when the weather forecast data is 40 degrees Celsius, the predicted environmental data for the next moment under each control strategy will decrease accordingly; when the weather forecast data is low, such as when the weather forecast data is 2 degrees Celsius, the predicted environmental data for the next moment under each control strategy will increase accordingly. Here, weather forecast data refers to the weather forecast data for the current moment, which can be temperature forecast data, humidity forecast data, or both temperature forecast data and humidity forecast data. This embodiment of the invention does not specifically limit this.

[0085] The actual control strategy at at least one moment, including the current moment, will also affect the predicted environmental data for the next moment under each control strategy. For example, if the actual control strategy at the current moment is strong cooling, the temperature drops faster because strong cooling makes the next control strategy normal cooling, thus saving energy.

[0086] Weather forecast data and / or actual control strategies at at least one time, including the current time, along with measured environmental data, can be input into the prediction model to obtain the predicted environmental data for the next time time under each control strategy output by the prediction model.

[0087] That is, weather forecast data and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model; alternatively, the actual control strategy for at least one time step, including the current time step, and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model; and furthermore, weather forecast data and / or the actual control strategy for at least one time step, including the current time step, and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model. Here, the actual control strategy refers to the actual control actions on a series of equipment such as air conditioners and fresh air systems.

[0088] For example, obtaining the predicted environment data for each time point after the current time based on the prediction model can be achieved using the following formula:

[0089] X(t+1)=f(X(t),U(t),...,P)

[0090] X(t+2)=f(X(t+1),U(t+1),...,P) ......

[0092] X(t+i-1)=f(X(t+i-1),U(t+i-1),...,P)

[0093] Where P is the weather forecast data, U is the actual control strategy, X is the measured environmental data, t is the current time, and i is the next i-th time after the current time t.

[0094] The method provided in this invention can input weather forecast data into a prediction model, and adjust the model according to different weather forecast data to obtain the predicted environmental data for the next moment under various control strategies, thereby improving the flexibility of environmental control. At the same time, it can further reduce the energy consumption of environmental control and save a lot of energy resources.

[0095] Based on the above embodiments, the measured environmental data includes at least one of the following: environmental data at the dynamic environment point, environmental data at the air conditioning outlet, and environmental data at the air conditioning return air outlet.

[0096] Specifically, measured environmental data refers to environmental data obtained through actual measurement. Measured environmental data may include environmental data at the dynamic environment point, environmental data at the air conditioning outlet, or environmental data at the dynamic environment point, air conditioning outlet, and air conditioning return air outlet. This embodiment of the invention does not specifically limit this.

[0097] The environmental data at the environmental monitoring system here refers to the environmental data at the environmental monitoring system, which is a system that centrally monitors the power equipment and environmental variables in various computer rooms.

[0098] The method provided in this invention includes at least one of the following environmental data: environmental data at the dynamic environment, environmental data at the air conditioning outlet, and environmental data at the air conditioning return air outlet. In particular, when at least two of these data are included, on-site measurements are taken from different locations to ensure the accuracy of the measured environmental data.

[0099] Based on any of the above embodiments, the present invention provides an environmental control system. Figure 4 This is a schematic diagram of the environmental control system provided by the present invention, as shown below. Figure 4 As shown, the environmental control system includes a gateway device 410, a redundant control device 420, and an environmental conditioning device 430. The gateway device 410 and the redundant control device 420 are respectively connected to the environmental conditioning device 430, and the gateway device 410 is connected to the redundant control device 420.

[0100] The gateway device 410 is used to determine the target control strategy and control the environmental control device 430 based on the target control strategy;

[0101] The redundant control device 420 is used to determine the operating status of the gateway device, and when the operating status is a fault, determine the target control strategy, and control the environmental control device 430 based on the target control strategy.

[0102] The target control strategy is determined based on the environmental control method.

[0103] Specifically, the environmental control system may include a gateway device 410, a redundant control device 420, and an environmental conditioning device 430. The gateway device 410 and the redundant control device 420 are respectively connected to the environmental conditioning device 430, and the gateway device 410 is connected to the redundant control device 420. Here, the environmental conditioning device 430 is a device used for environmental control, which may be an air conditioner, a fresh air system, or both. This embodiment of the invention does not specifically limit this.

[0104] The gateway device 410 can be a 4G gateway device, a 5G gateway device, or an Ethernet gateway device; this embodiment of the invention does not specifically limit it in this regard.

[0105] When the gateway device 410 is working normally, and the cloud server and the gateway device 410 are connected normally, the cloud server can send the target control policy to the gateway device 410. The gateway device 410 controls the environmental adjustment device 430 based on the received target control policy. Alternatively, if the cloud server and the gateway device 410 are disconnected, the gateway device 410 can determine the target control policy on its own and control the environmental adjustment device 430 based on the self-determined target control policy.

[0106] In related technologies, once the network device 410 malfunctions, it can no longer control the environmental control device 430. The environmental control device 430 becomes uncontrollable and continues to operate according to the original control strategy, deviating from the environmental changes that occur over time, resulting in energy waste and failure to meet actual environmental control needs.

[0107] To address this issue, in this embodiment of the invention, a redundant control device 420 is added to the environmental control system. The redundant control device 420 is connected to the gateway device 410 to monitor the operating status of the gateway device 410. Thus, when a fault is detected in the operation of the gateway device 410, the redundant control device 420 can take over the control of the environmental conditioning device 430. The redundant control device 420 determines the target control strategy and controls the environmental conditioning device 430 based on the target control strategy.

[0108] Here, the target control strategy determined by the cloud server, gateway device 410, or redundant control device 420 can all be obtained based on the environmental control method provided in the above embodiments. The specific determination method will not be elaborated here.

[0109] The system provided in this embodiment of the invention adds a redundant control device, which is used to determine the target control strategy when the gateway device is in a faulty state, and control the environmental conditioning device based on the target control strategy. This solves the problem of the environmental conditioning device going out of control due to the failure of the gateway device and ensures the effectiveness of environmental control.

[0110] Based on the above embodiments, Figure 5 This is a schematic diagram of the redundant control device provided by the present invention, as shown below. Figure 5 As shown, the redundant control device 420 includes:

[0111] The status determination unit 510 is used to determine that the operating status is faulty when it receives a handshake signal sent periodically by the gateway device 410 and fails to receive the handshake signal after a timeout.

[0112] The environmental control unit 520 is used to determine the target control strategy when the operating state is faulty, and to control the environmental conditioning device 430 based on the target control strategy.

[0113] Specifically, the redundancy control device 420 may include a status determination unit 510 and an environment control unit 520. The status determination unit 510 is used to receive handshake signals sent periodically by the gateway device 410, and to determine that the operating status is faulty if no handshake signal is received within a timeout period. The handshake signal here refers to the signal used for communication between the gateway device 410 and the redundancy control device 420 using a communication protocol.

[0114] For example, the gateway device 410 can send a handshake signal to the status determination unit 510 every 2 minutes. If the status determination unit 510 does not receive a handshake signal within 2 minutes, it determines that the operating status of the gateway device 410 is faulty.

[0115] The environmental control unit 520 here is used to determine a target control strategy when the operating state is faulty, and to control the environmental conditioning equipment based on the target control strategy. For example, when the gateway device 410 is faulty, the environmental control unit 520 can determine the target control strategy from among the candidate control strategies based on the weighted sum of the operating energy consumption data and the difference data, with the goal of minimizing the weighted sum of the operating energy consumption data and the difference data under each candidate control strategy, and control the environmental conditioning equipment 430 based on the target control strategy. The environmental conditioning equipment here can be an air conditioner, a fresh air system, or both; this embodiment of the invention does not specifically limit this.

[0116] Based on any of the above embodiments Figure 6 This is the second flowchart illustrating the environmental control method provided by the present invention, as shown below. Figure 6 As shown, the method includes:

[0117] Step 610 involves acquiring measured environmental data at at least one moment, including the current moment. Here, measured environmental data refers to environmental data obtained through actual measurement. The environmental data can be temperature data, humidity data, or both. The measured environmental data can be environmental data at the dynamic environment point, air conditioning outlet environmental data, or air conditioning return air outlet environmental data; this embodiment of the invention does not specifically limit the specific data in this regard.

[0118] Step 620: Weather forecast data and / or actual control strategies at at least one time, including the current time, and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time under each control strategy output by the prediction model.

[0119] That is, weather forecast data and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model; alternatively, the actual control strategy for at least one time step, including the current time step, and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model; furthermore, weather forecast data and / or the actual control strategy for at least one time step, including the current time step, and measured environmental data can be input into the prediction model to obtain the predicted environmental data for the next time step under various control strategies output by the prediction model. The prediction model here is determined based on sample measured environmental data for each time step under sample control strategies. The actual control strategy here refers to the actual control actions on a series of equipment such as air conditioners and fresh air systems.

[0120] Step 630: Candidate control strategies that predict environmental data that meet environmental control rules can be determined from various control strategies. These candidate control strategies are strategies that may be used as target control strategies in the future. The environmental control rules are determined based on preset environmental threshold data.

[0121] Step 640: The target control strategy can be determined from the candidate control strategies based on the weighted sum of the operating energy consumption data and the difference data, with the goal of minimizing the weighted sum of the operating energy consumption data and the difference data under each candidate control strategy.

[0122] Step 650 allows for environmental control based on a target control strategy.

[0123] The environmental control device provided by the present invention is described below. The environmental control device described below and the environmental control method described above can be referred to in correspondence.

[0124] Based on any of the above embodiments Figure 7 This is a schematic diagram of the environmental control device provided by the present invention, as shown below. Figure 7 As shown, the environmental control device includes:

[0125] The data acquisition unit 710 is used to acquire measured environmental data at at least one moment, including the current moment.

[0126] The data prediction unit 720 is used to input the measured environmental data into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model; the prediction model is determined based on the sample measured environmental data for each time step under the sample control strategy.

[0127] The strategy determination unit 730 is used to determine the target control strategy from each control strategy based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy.

[0128] The environmental control unit 740 is used to perform environmental control based on the target control strategy.

[0129] The device provided in this invention determines the target control strategy for environmental control based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy. This effectively achieves energy saving while meeting the actual environmental control requirements. Furthermore, the prediction model is determined based on the sample measured environmental data at each time step under the sample control strategy. Applying the prediction model to the prediction of environmental data can improve the accuracy of the prediction and ensure the reliability of subsequent environmental control.

[0130] Based on any of the above embodiments, the strategy determination unit specifically includes:

[0131] A candidate control strategy unit is used to determine, from the various control strategies, a candidate control strategy in which the predicted environment data satisfies the environment control rule, and the environment control rule is determined based on the preset environment threshold data.

[0132] The target control strategy unit is used to determine the target control strategy from among the candidate control strategies based on the operating energy consumption data under each candidate control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each candidate control strategy.

[0133] Based on any of the above embodiments, the target control strategy unit specifically includes:

[0134] With the goal of minimizing the weighted sum of the operating energy consumption data and the difference data, a target control strategy is determined from each candidate control strategy based on the operating energy consumption data and the difference data under each candidate control strategy.

[0135] Based on any of the above embodiments, the data prediction unit specifically includes:

[0136] The weather forecast data and / or the actual control strategy at at least one time, including the current time, and the measured environmental data are input into the prediction model to obtain the predicted environmental data for the next time under each control strategy output by the prediction model.

[0137] Based on any of the above embodiments, the measured environmental data includes at least one of the following: environmental data at the dynamic environment point, environmental data at the air conditioning outlet, and environmental data at the air conditioning return air point.

[0138] Figure 8 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 8 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute an environmental control method. This method includes: acquiring measured environmental data at at least one moment, including the current moment; inputting the measured environmental data into a prediction model to obtain predicted environmental data for the next moment under each control strategy output by the prediction model; the prediction model is determined based on sample measured environmental data at each moment under sample control strategies; determining a target control strategy from each control strategy based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data under each control strategy and preset environmental threshold data; and performing environmental control based on the target control strategy.

[0139] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0140] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the environmental control method provided by the above methods. The method includes: acquiring measured environmental data at at least one moment, including the current moment; inputting the measured environmental data into a prediction model to obtain predicted environmental data for the next moment under each control strategy output by the prediction model; the prediction model is determined based on the sample measured environmental data at each moment under the sample control strategy; determining a target control strategy from each control strategy based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data under each control strategy and the preset environmental threshold data; and performing environmental control based on the target control strategy.

[0141] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the environmental control methods provided by the above methods. The method includes: acquiring measured environmental data at at least one moment, including the current moment; inputting the measured environmental data into a prediction model to obtain predicted environmental data for the next moment under each control strategy output by the prediction model; the prediction model is determined based on sample measured environmental data at each moment under sample control strategies; determining a target control strategy from each control strategy based on operating energy consumption data under each control strategy and the difference data between the predicted environmental data under each control strategy and preset environmental threshold data; and performing environmental control based on the target control strategy.

[0142] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0143] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An environmental control method, characterized in that, include: Acquire measured environmental data at at least one moment, including the current moment; The measured environmental data is input into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model; the prediction model is determined based on the sample measured environmental data for each time step under the sample control strategy. Based on the operating energy consumption data under each control strategy, and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy, the target control strategy is determined from each control strategy; the difference data is used to reflect the size of the gap between the predicted environmental data and the actual environmental control requirements. Environmental control is performed based on the aforementioned target control strategy; The determination of the target control strategy from each control strategy based on the operating energy consumption data under each control strategy, and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy, includes: From the various control strategies, candidate control strategies are determined that the predicted environmental data satisfies the environmental control rules. These candidate control strategies are used as the environmental control rules, which are determined based on the preset environmental threshold data. Based on the operating energy consumption data under each candidate control strategy, and the difference between the predicted environmental data and the preset environmental threshold data under each candidate control strategy, the target control strategy is determined from each candidate control strategy.

2. The environmental control method according to claim 1, characterized in that, The process of determining the target control strategy from among the candidate control strategies based on the operating energy consumption data under each candidate control strategy, and the difference data between the predicted environment data and the preset environment threshold data under each candidate control strategy, includes: With the goal of minimizing the weighted sum of the operating energy consumption data and the difference data, a target control strategy is determined from each candidate control strategy based on the operating energy consumption data and the difference data under each candidate control strategy.

3. The environmental control method according to any one of claims 1 to 2, characterized in that, The step of inputting the measured environmental data into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model includes: The weather forecast data and / or the actual control strategy at at least one time, including the current time, and the measured environmental data are input into the prediction model to obtain the predicted environmental data for the next time under each control strategy output by the prediction model.

4. The environmental control method according to any one of claims 1 to 2, characterized in that, The measured environmental data includes at least one of the following: environmental data at the dynamic environment point, environmental data at the air conditioning outlet, and environmental data at the air conditioning return air outlet.

5. An environmental control system, characterized in that, It includes a gateway device, a redundancy control device, and an environmental control device, wherein the gateway device and the redundancy control device are respectively connected to the environmental control device, and the gateway device is connected to the redundancy control device; The gateway device is used to determine the target control strategy and control the environmental control device based on the target control strategy; The redundant control device is used to determine the operating status of the gateway device, and when the operating status is faulty, determine the target control strategy, and control the environmental control device based on the target control strategy; The target control strategy is determined based on the environmental control method as described in any one of claims 1 to 4.

6. The environmental control system according to claim 5, characterized in that, The redundant control device includes: The status determination unit is used to determine that the operating status is faulty when receiving a handshake signal sent periodically by the gateway device and failing to receive the handshake signal after a timeout. An environmental control unit is used to determine the target control strategy when the operating state is faulty, and to control the environmental conditioning equipment based on the target control strategy.

7. An environmental control device, characterized in that, include: The data acquisition unit is used to acquire measured environmental data at at least one moment, including the current moment. The data prediction unit is used to input the measured environmental data into the prediction model to obtain the predicted environmental data for the next time step under each control strategy output by the prediction model; the prediction model is determined based on the sample measured environmental data for each time step under the sample control strategy. The strategy determination unit is used to determine the target control strategy from each control strategy based on the operating energy consumption data under each control strategy and the difference data between the predicted environmental data and the preset environmental threshold data under each control strategy; the difference data is used to reflect the size of the gap between the predicted environmental data and the actual environmental control requirements. An environmental control unit is used to perform environmental control based on the target control strategy. The strategy determination unit is specifically used for: From the various control strategies, candidate control strategies are determined that the predicted environmental data satisfies the environmental control rules. These candidate control strategies are used as the environmental control rules, which are determined based on the preset environmental threshold data. Based on the operating energy consumption data under each candidate control strategy, and the difference between the predicted environmental data and the preset environmental threshold data under each candidate control strategy, the target control strategy is determined from each candidate control strategy.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the environmental control method as described in any one of claims 1 to 4.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the environmental control method as described in any one of claims 1 to 4.

Images