Heat supply regulation and control method based on edge cloud cooperative computing and related device

Abstract

The invention discloses a heat supply regulation and control method based on side cloud cooperative computing and a related device, and relates to the technical field of comprehensive energy heat supply, real-time data is obtained and then input into a current heat supply control model, and after control parameters are obtained and sent to a local side to be executed, the indoor temperature reaches a target value of the indoor temperature. The current heat supply control model is obtained by selecting the preset modeling algorithm for training according to the characteristics of the current historical meteorological data and the current historical room temperature data stored in the cloud platform and the current historical local operation data of the local side, and the training data of the model is comprehensive compared with the training data in the prior art; the method is a prediction modeling algorithm selected based on characteristics of historical data. Therefore, the method can be used for training different heat supply systems and establishing adaptive current heat supply control models with relatively high control precision.

Description

Technical Field

[0001] The present application relates to the field of integrated energy heating technology, and in particular to a heating control method and related devices based on edge-cloud collaborative computing. Background Art

[0002] Traditional centralized heating systems generally rely on the built-in heating curve in the local control system to calculate the target control parameters. However, due to the differences between different heating systems, it is difficult for there to be exactly the same heating system. The built-in heating curve in the local control system cannot adapt well to other heating systems except the heating system adapted to the heating curve. Moreover, in the actual heating process, the heating system can only use the outdoor temperature as the input condition and rely on a single heating curve to calculate the heating target value, with the heating target value as the output parameter. The heating curve cannot be corrected autonomously (manual correction is required), and does not take into account the outdoor weather, such as sunny, cloudy, rainy, snowy, etc., outdoor wind speed, user behavior habits and other factors that affect the heating effect. This will lead to problems such as low heating control accuracy, poor indoor comfort, and high energy consumption. Summary of the invention

[0003] In view of the above problems, this application provides a heating control method and related devices based on edge-cloud collaborative computing to achieve the purpose of improving the accuracy of heating control. The specific scheme is as follows:

[0004] The first aspect of the present application provides a heating control method based on edge-cloud collaborative computing, including:

[0005] Obtain real-time data; real-time data includes real-time meteorological data, real-time room temperature data and real-time local operation data on the local side;

[0006] The real-time meteorological data, the real-time room temperature data and the real-time local operation data on the local side are input into the current heating control model obtained from the cloud platform to obtain control parameters; the current heating control model is a model trained by the cloud platform using a predictive modeling algorithm selected from a predictive modeling algorithm set, and the predictive modeling algorithm is selected based on the amount of current historical data stored on the cloud platform and the proportion of the range of the current historical data relative to the range of preset influencing factors, and the preset influencing factors are various influencing factors that affect the heating effect of the current heating control model; the current historical data includes the current historical meteorological data, the current historical room temperature data and the current historical local operation data on the local side;

[0007] The control parameters are sent to the local side so that the local control system on the local side executes the control parameters to make the indoor temperature reach the target value of the indoor temperature.

[0008] In a possible implementation, the method further includes:

[0009] Responding to the model correction instruction sent by the cloud platform;

[0010] Obtain historical meteorological data, historical room temperature data and local historical operation data;

[0011] Sending historical meteorological data, historical room temperature data and historical operation data of the local side to the cloud platform, so that the cloud platform can correct the current heating control model based on the historical meteorological data, historical room temperature data and historical operation data of the local side;

[0012] The revised heating control model is received, and the revised heating control model is used as the current heating control model.

[0013] In a possible implementation, the prediction modeling algorithm includes a time series analysis algorithm, a regression analysis algorithm, and a neural network algorithm; the selection process of the prediction modeling algorithm in the current heating control model includes:

[0014] When the amount of current historical data stored in the cloud platform is lower than a first preset threshold, a time series analysis algorithm is selected for training to obtain a current heating control model;

[0015] When the amount of current historical data stored in the cloud platform is higher than a first preset threshold, and the proportion of the range of the current historical data relative to the range of the preset influencing factors is lower than a preset second threshold, a regression analysis algorithm is selected for training to obtain the current heating control model;

[0016] When the amount of current historical data stored in the cloud platform is higher than the first preset threshold, and the proportion of the range of the current historical data relative to the preset influencing factor range is higher than the preset second threshold, the neural network algorithm is selected for training to obtain the current heating control model.

[0017] In a possible implementation, obtaining real-time data includes:

[0018] Obtain real-time meteorological data from the meteorological website, real-time room temperature data from the cloud platform, and real-time local operation data of the local control system from the local side; the real-time room temperature data is obtained by the cloud platform from the room temperature data collector and sent to the edge side.

[0019] In a possible implementation, the method further includes:

[0020] Monitor the size of control parameters;

[0021] When the change range of the control parameter exceeds the preset change threshold, the control parameter is output according to the preset maximum change upper limit of the control parameter, and a prompt message is generated and sent to the supervisor side.

[0022] A second aspect of the present application provides a heating control device based on edge-cloud collaborative computing, comprising:

[0023] Acquisition unit, heating control unit and sending unit; wherein:

[0024] An acquisition unit, used to acquire real-time data; the real-time data includes real-time meteorological data, real-time room temperature data and real-time local operation data on the local side;

[0025] A heating control unit, used for inputting real-time meteorological data, real-time room temperature data and real-time local operation data on the local side into a current heating control model obtained from a cloud platform to obtain control parameters; the current heating control model is a model trained by the cloud platform using a predictive modeling algorithm selected from a predictive modeling algorithm set, the predictive modeling algorithm is selected based on the amount of current historical data stored on the cloud platform, and the proportion of the range of the current historical data relative to the range of preset influencing factors, the preset influencing factors are various influencing factors that affect the heating effect of the current heating control model; the current historical data includes current historical meteorological data, current historical room temperature data and current historical local operation data on the local side;

[0026] The sending unit is used to send the control parameters to the local side, so that the local control system on the local side executes the control parameters to make the indoor temperature reach the target value of the indoor temperature.

[0027] In a possible implementation, it further includes a model correction unit;

[0028] A model correction unit, used to respond to a model correction instruction sent by the cloud platform;

[0029] Obtain historical meteorological data, historical room temperature data and local historical operation data;

[0030] Sending historical meteorological data, historical room temperature data and historical operation data of the local side to the cloud platform, so that the cloud platform can correct the current heating control model based on the historical meteorological data, historical room temperature data and historical operation data of the local side;

[0031] The revised heating control model is received, and the revised heating control model is used as the current heating control model.

[0032] A third aspect of the present application provides a heating control device based on edge-cloud collaborative computing, comprising at least one processor and a memory connected to the processor, wherein:

[0033] The memory is used to store computer programs;

[0034] The processor is used to execute the computer program so that the electronic device can implement the heating control method based on edge-cloud collaborative computing as described in any one of the above.

[0035] The fourth aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the heating control method based on edge-cloud collaborative computing as described in any one of the above.

[0036] The fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement a heating control method based on edge-cloud collaborative computing as described in any one of the above.

[0037] Through the above technical solution, the heat supply control method and related devices based on edge-cloud collaborative computing provided by the present application obtain real-time data and input it into the current heat supply control model, obtain the control parameters and send them to the local side for execution, and then the indoor temperature reaches the target value of the indoor temperature. The current heat supply control model in the present application is trained by selecting a preset modeling algorithm based on the characteristics of the current historical meteorological data, the current historical room temperature data and the current historical local operation data stored on the cloud platform. The training data of the model is more comprehensive than the training data in the known technology, and it is a predictive modeling algorithm selected based on the characteristics of historical data. It can be seen that the present application can train and establish an adaptive current heat supply control model with higher control accuracy for different heating systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0039] Figure 1 A schematic diagram of a flow chart of a heating control method based on edge-cloud collaborative computing provided in this application;

[0040] Figure 2 A flow chart showing an example of a method for controlling heat supply based on edge-cloud collaborative computing provided in this application;

[0041] Figure 3 A schematic diagram of the structure of a heating control device based on edge-cloud collaborative computing provided in this application;

[0042] Figure 4 A schematic diagram of the structure of the heating control equipment based on edge-cloud collaborative computing provided in this application. DETAILED DESCRIPTION

[0043] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0044] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0045] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0046] With the development of technology, a local PLC (Programmable Logic Controller) control system is basically built during the construction of a heating system. By inputting the outdoor temperature, the target water supply temperature is calculated according to the built-in heating curve in the local control system to control the local system equipment. The control of the local control system is reliable and stable, and can realize the start and stop control of local equipment and the setting of heating parameters. Therefore, most existing heating systems use local control.

[0047] However, the heating systems in actual applications are generally different: different factors such as building insulation, building type, heating system flow, terminal form, and project location will produce different heating systems. Specifically, factors such as building insulation, building type, and building orientation will affect the load of the heating system. Under the same water supply flow, the greater the load, the higher the temperature required. It can be seen that the water supply flow will affect the transmission and distribution of heat; correspondingly, under the same load requirements, the greater the water supply flow, the lower the temperature. In addition, different terminal forms will also affect the heating. The heating required for the air-conditioning terminal, radiator terminal, and floor radiation are all different. It is understandable that due to the differences between the various heating systems, it is difficult to encounter exactly the same system. Therefore, the built-in heating curve in the local control system cannot be applied to various heating systems with differences.

[0048] It should be noted that the centralized heating system is a very complex system. Its heating load demand is affected by external factors such as outdoor meteorological parameters, internal factors such as indoor people's living habits and internal loads, as well as the heat storage capacity of the building and the delay in transmission and distribution. Therefore, it is difficult to establish an accurate mathematical model. Moreover, in the actual heating process, the input condition of the mathematical model is only the outdoor temperature. The heating target value is calculated based on a single heating curve that cannot be corrected and needs to be manually corrected. It does not consider factors that may affect the heating effect, such as outdoor weather and user behavior habits. As a result, problems such as low control accuracy of the overall heating, poor indoor comfort, and high energy consumption occur in known technologies.

[0049] In order to solve the above problems, this application proposes a heating control method and related devices based on edge-cloud collaborative computing.

[0050] Optional, see Figure 1 , a flow chart of a heating control method based on edge-cloud collaborative computing provided in this application.

[0051] It should be noted that the execution subject of the specific embodiment provided by the present application is the edge side, which includes an edge side calculator. The edge side calculator is mainly used to obtain the operation data of the local control system from the local control system on the local side, obtain meteorological data from the meteorological website or meteorological station, and also to transmit the operation data and meteorological data to the cloud platform. The cloud platform is mainly used to receive and store the operation data and meteorological data of the local control system sent from the edge calculator, and also receives and stores the room temperature data sent from the room temperature data collector.

[0052] like Figure 1 As shown in the figure, the heat supply control method based on edge-cloud collaborative computing includes the following steps:

[0053] Step 101: Acquire real-time meteorological data, real-time room temperature data, and real-time local operation data on the local side.

[0054] It should be noted that real-time meteorological data is mainly obtained from meteorological websites, and meteorological data includes but is not limited to weather conditions, outdoor wind speed, outdoor temperature, outdoor humidity, solar illumination, etc.; real-time room temperature data is mainly obtained from the cloud platform, and room temperature data includes but is not limited to indoor temperature and indoor humidity. Specifically, the real-time room temperature data in the cloud platform is mainly obtained from the room temperature data collector; the real-time local operation data on the local side is mainly obtained from the local control system on the local side, and the local operation data includes but is not limited to the primary side water supply temperature, the primary side return water temperature, the primary side circulation flow, the secondary side water supply temperature, the secondary side return water temperature, the secondary side circulation flow and instantaneous heating supply, etc.

[0055] Optionally, real-time meteorological data is obtained from a meteorological website, real-time room temperature data is obtained from a cloud platform, and real-time local operation data of a local control system is obtained from the local side.

[0056] Step 102: input the real-time meteorological data, real-time room temperature data and real-time local operation data on the local side into the current heating control model obtained from the cloud platform to obtain control parameters; the current heating control model is a model trained by the cloud platform using a predictive modeling algorithm selected from a predictive modeling algorithm set, and the predictive modeling algorithm is selected based on the amount of local data stored on the cloud platform and the proportion of the data range relative to the range of preset influencing factors. The preset influencing factors are the various influencing factors that affect the heating effect of the current heating control model.

[0057] It should be noted that the current heating control model is trained on the cloud platform. The training process of the current heating control model can be:

[0058] Step 1: Acquisition of current historical data.

[0059] The current historical data mainly includes the current historical meteorological data, the current historical operation data of the local control system and the current historical room temperature data.

[0060] The edge side calculator on the edge side obtains the current historical meteorological data, the current historical operating data of the local control system on the local side, and the current historical room temperature data sent to the edge side calculator by the cloud platform. Specifically, the edge side calculator has a remote communication function, including but not limited to: field bus, WIFI, 4G, IOT, GPRS, RS485, etc.; the edge side calculator has a data storage function, and the data storage time is not less than 24 hours. When the communication interruption is restored, the edge side controller can upload the data during the communication interruption to the cloud; when the cloud platform and the edge side calculator are disconnected, the edge calculator will calculate the control parameters according to the latest heating control model sent by the cloud platform.

[0061] Step 2: Clean and process these current historical data.

[0062] The abnormal data in these current historical data mainly include continuous abnormal data and intermittent abnormal data.

[0063] The general means of processing abnormal data are: eliminating continuous abnormal data; using the correlation between data to correct intermittent abnormal data.

[0064] Take abnormal water supply temperature as an example:

[0065] Specifically, the water supply temperature can be calculated based on the instantaneous heat supply, circulation flow and return water temperature. The calculation formula can be:

[0066]

[0067] in, is the instantaneous heat supply, in kJ; is the specific heat capacity of water, which is equal to 4.1868 kJ / (℃×kg) by default; is the flow rate, in kg / s; is the return water temperature in °C.

[0068] Step 3: According to the data characteristics of the current historical data, a matching prediction modeling algorithm is selected from the prediction modeling algorithm set to train the current heating control model.

[0069] It should be noted that the prediction modeling algorithm includes but is not limited to time series analysis algorithm, regression analysis algorithm and neural network algorithm; the data characteristics of the current historical data include the amount of current historical data and the proportion of the range of the current historical data relative to the range of the preset influencing factors. Specifically, the selection rules of the prediction modeling algorithm are:

[0070] When the amount of current historical data stored in the cloud platform is lower than the preset first threshold, the time series analysis algorithm is selected to train the current heating control model, that is, when the amount of current historical data is relatively small, the time series analysis algorithm is selected from the prediction modeling algorithm for model training. It can be understood that if the amount of current historical data is relatively small, it cannot meet the conditions for training the model with the regression analysis algorithm and the neural network algorithm, so the time series analysis algorithm that can train the current heating control model with a small amount of data is used for model training;

[0071] When the amount of current historical data stored in the cloud platform is higher than a first preset threshold, and the range of the current historical data relative to the range of the influencing factors is lower than a preset second preset threshold, a regression analysis algorithm is selected for training to obtain the current heating control model.

[0072] The preset influencing factors are various influencing factors that affect the heating effect of the current heating control model, including but not limited to water supply temperature, outdoor temperature, outdoor weather, etc. The proportion of the range of the preset influencing factors represents the proportion of the range of the current historical data in the range of the historical data in the current heating control system. The proportion of the range of the preset influencing factors can also be referred to as how much the range of the current historical data involves the range of the preset influencing factors.

[0073] Taking outdoor temperature as an example, the outdoor temperature range during the heating period is from -20°C to +15°C, while the current historical outdoor temperature data only has outdoor temperature data from -20°C to -10°C, and there is almost no or very little outdoor temperature data in other ranges, which indicates that the range of the current historical data of the influencing factor of outdoor temperature data is small relative to the range of the preset influencing factor. It is understandable that the preset second threshold includes a defined value of the pre-set division ratio for each preset influencing factor.

[0074] That is, when the amount of current historical data is large and the preset influencing factors are relatively few, the regression analysis algorithm is used for model training. It is understandable that even if the amount of current historical data is large, but the preset influencing factors are relatively few, the conditions for training the neural network algorithm model are still not met.

[0075] When the amount of current historical data stored in the cloud platform is higher than the first preset threshold, and the range of the current historical data relative to the range of the influencing factors is higher than the preset second preset threshold, the neural network algorithm is selected for training to obtain the current heating control model. That is, when the amount of current historical data is large and there are many preset influencing factors, the conditions for training the neural network algorithm model are met.

[0076] Step 4: Use the prediction modeling algorithm selected from the prediction modeling algorithm set to train and obtain the current heating control model.

[0077] Specifically, the current heating control model is trained to take indoor temperature as the control target, outdoor air temperature, outdoor weather, pollution conditions, water supply temperature, return water temperature, indoor temperature and other data as input parameters, and water supply temperature and flow rate as output parameters.

[0078] It should be noted that the current heating control model may be a unit equation or a multivariate equation, that is, the model may be one equation or multiple equations. When there are multiple equations, each equation corresponds to a different input parameter range.

[0079] Moreover, both the input parameters and output parameters of the current heating control model are configurable.

[0080] For the configuration of input parameters, you can customize the model input parameters through the cloud platform based on the current status of the heating system to which the current heating control model is applied. You can choose to input only a single parameter of outdoor temperature; you can also choose to input multiple parameters such as outdoor temperature and outdoor weather. The default input parameter is outdoor temperature.

[0081] For the configuration of output parameters, it is possible to customize the model output parameters through the cloud platform based on the current status of the heating system to which the current heating control model is to be applied. The water supply temperature and flow rate on the primary and secondary sides are the target control parameters. You can choose to output only one parameter, either the water supply temperature or the flow rate, or you can choose to output both the water supply temperature and the flow rate.

[0082] In addition, the control accuracy and self-learning parameters of the current heating control model can also be configured. Specifically, the cloud platform can customize the upper and lower limits of the deviation between the indoor temperature and the indoor temperature target value, the upper limit of the cumulative over-limit time, and the upper limit of the continuous over-limit time. When the deviation between the actual indoor temperature value and the indoor temperature target value exceeds the upper limit of the deviation for a continuous time that exceeds the upper limit of the continuous over-limit time, or the continuous cumulative over-limit time since the last model correction exceeds the upper limit of the cumulative over-limit time, the cloud will perform self-learning to correct the model. The default upper limit of the deviation between the indoor temperature and the target value is ±1°C, the upper limit of the cumulative over-limit time is 12 hours, and the upper limit of the continuous over-limit time is 2 hours.

[0083] Exemplarily, the calculation formula for the deviation between the indoor temperature and the indoor temperature target value may be:

[0084]

[0085] in, is the deviation between the indoor temperature and the indoor temperature target value, in °C; is the average indoor temperature in °C. The granularity of the indoor temperature value is consistent with the frequency of control parameter issuance. is the target indoor temperature in °C.

[0086] Optionally, the correction process of the current heating control model is described from the perspective of the edge side:

[0087] 1> Respond to the model correction instruction sent by the cloud platform.

[0088] Specifically, when the deviation between the actual indoor temperature value and the indoor temperature target value exceeds the upper limit of the deviation for a continuous time that exceeds the upper limit of the continuous excess time, or the continuous cumulative excess time since the last model correction exceeds the upper limit of the cumulative excess time, the cloud platform will send a model correction instruction to the edge side calculator on the edge side.

[0089] 2> Obtain historical meteorological data, historical room temperature data and historical operation data on the local side.

[0090] After receiving the model correction instruction, the edge side calculator starts to obtain historical meteorological data, historical room temperature data and historical operation data on the local side.

[0091] 3> Send the historical meteorological data, historical room temperature data and historical operation data of the local side to the cloud platform, so that the cloud platform can correct the current heating control model based on the historical meteorological data, historical room temperature data and historical operation data of the local side.

[0092] The edge side calculator sends the historical meteorological data, historical room temperature data and historical operation data of the local side to the cloud platform. The cloud platform corrects the current heating control model based on the above historical meteorological data, historical room temperature data and historical operation data of the local side, and sends the corrected heating control model to the edge side calculator.

[0093] 4> Receive the revised heating control model, and use the revised heating control model as the current heating control model.

[0094] The edge-side calculator receives the revised heating control model and uses the revised heating control model as the current heating control model.

[0095] Next, the control frequency configuration of the current heating control model is introduced: users can configure the time interval for sending control parameters of the edge side calculator in the cloud as needed, such as sending control parameters once every hour.

[0096] From then on, the training process of the current heating control model is completed, and the current heating control model is obtained.

[0097] Afterwards, the current heating control model can be sent to the edge side computer, which stores and deploys the model sent by the cloud platform.

[0098] Optionally, real-time meteorological data, real-time room temperature data and real-time local operation data on the local side are input into a pre-trained current heating control model to obtain control parameters.

[0099] Specifically, the control parameters may include water supply temperature and flow rate.

[0100] Step 103: Send the control parameters to the local side, so that the local control system on the local side executes the control parameters to make the indoor temperature reach the target value of the indoor temperature.

[0101] Optionally, the control parameters are sent to a local control system, which adjusts the control parameters of the device so that the temperature reaches the indoor temperature target value.

[0102] Specifically, after the local side receives the target value parameters such as water supply temperature and flow rate sent by the edge side controller, the local control system adjusts the operating parameters of the equipment, such as the boiler outlet water temperature, valve opening, water pump frequency, etc.

[0103] At the same time, the local control system will upload the operating parameters to the edge computer.

[0104] It should also be noted that the current heating control model can configure the upper limit of the change of the output parameters to avoid excessive changes in the output parameters that affect the stable operation of the heating system.

[0105] Optionally, the current heating control model monitors the size of the output control parameter by itself. When the change range of the control parameter exceeds the preset change threshold, the control parameter is output according to the preset maximum change upper limit of the control parameter, and a prompt message is generated and sent to the supervisor side.

[0106] Specifically, in order to avoid the current heating control model output parameters being too large and affecting the system operation, the maximum change upper limit of the heating system output parameters is customized. When the absolute value of the difference between the output parameter setting value and the current actual parameter is greater than the upper limit, the target parameter is output according to the maximum change upper limit, and the relevant personnel are notified through messages.

[0107] You can also configure the upper limit of the control parameters sent by the current heating control model at a time, and customize the upper limit of the single heating control parameter sending to avoid excessive changes in heating system parameters and affect the stable operation of the heating system. For example, if the upper limit of the single system control parameter sending of the water supply temperature is set to 2°C, the current water supply temperature is 40°C, and the target water supply temperature is 44°C, then the target value is achieved by sending control parameters twice, which are 42°C and 44°C respectively.

[0108] In summary, the heating control method based on edge-cloud collaborative computing provided by the present application obtains real-time data and inputs it into the current heating control model, obtains control parameters and sends them to the local side for execution, and then the indoor temperature reaches the target value of the indoor temperature. The current heating control model in the present application is trained by selecting a preset modeling algorithm based on the characteristics of the current historical meteorological data, the current historical room temperature data and the current historical local operation data stored on the cloud platform. The training data of the model is more comprehensive than the training data in the known technology, and it is a predictive modeling algorithm selected based on the characteristics of historical data. It can be seen that the present application can train and establish adaptive current heating control models with higher control accuracy for different heating systems.

[0109] Optional, see Figure 2 , a flow chart of an example method for heat supply control based on edge-cloud collaborative computing provided in this application.

[0110] like Figure 2 As shown, the heating control method based on edge-cloud collaborative computing is implemented based on the cloud, edge calculator, meteorological website, meteorological station and local control system.

[0111] Among them, meteorological websites and weather stations are mainly used to provide meteorological data for edge computers.

[0112] The edge calculator is mainly responsible for obtaining meteorological data from meteorological websites and meteorological stations, obtaining the operating data of the local control system from the local control system, and obtaining the model from the cloud. It automatically calculates the water supply temperature and flow target values ​​based on the input conditions and current operating parameters, and then sends the water supply temperature and flow target values ​​to the local control system for parameter control.

[0113] The cloud can store and manage collected data, clean data, process abnormal or missing data, and further analyze and process the processed data. Taking indoor temperature as the target, it uses AI self-learning algorithms to autonomously train and optimize models, and sends the trained or optimized models to edge computers.

[0114] This application trains the model based on data such as outdoor meteorological parameters, historical operating data, and indoor temperature. The model is continuously corrected by judging the difference between the indoor temperature and the indoor temperature target value, and the model and the room temperature target value are sent to the edge side controller. The edge side controller obtains the future outdoor meteorological parameters, calculates the target values ​​of the temperature and flow, and sends them to the local control system. It should be noted that the indoor target value is determined based on the actual situation of the comprehensive consideration project.

[0115] The above introduces the heating control method based on edge-cloud collaborative computing provided by the embodiment of the present application. The following will introduce a device for executing the above-mentioned heating control method based on edge-cloud collaborative computing.

[0116] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of the heating control device based on edge-cloud collaborative computing provided in this application. Figure 3 As shown, the device comprises:

[0117] Acquisition unit 10, heating control unit 20 and sending unit 30; wherein:

[0118] The acquisition unit 10 is used to acquire real-time data; the real-time data includes real-time meteorological data, real-time room temperature data and real-time local operation data of the local side;

[0119] The heating control unit 20 is used to input the real-time meteorological data, the real-time room temperature data and the real-time local operation data of the local side into the current heating control model obtained from the cloud platform to obtain control parameters; the current heating control model is a model trained by the cloud platform using a prediction modeling algorithm selected from the prediction modeling algorithm set, and the prediction modeling algorithm is selected based on the amount of current historical data stored in the cloud platform and the proportion of the range of the current historical data relative to the range of the preset influencing factors, and the preset influencing factors are various influencing factors that affect the heating effect of the current heating control model; the current historical data includes the current historical meteorological data, the current historical room temperature data and the current historical local operation data of the local side;

[0120] The sending unit 30 is used to send the control parameters to the local side, so that the local control system on the local side executes the control parameters to make the indoor temperature reach the target value of the indoor temperature.

[0121] In one embodiment, the device further comprises a model correction unit;

[0122] A model correction unit, used to respond to a model correction instruction sent by the cloud platform;

[0123] Obtain historical meteorological data, historical room temperature data and local historical operation data;

[0124] Sending historical meteorological data, historical room temperature data and historical operation data of the local side to the cloud platform, so that the cloud platform can correct the current heating control model based on the historical meteorological data, historical room temperature data and historical operation data of the local side;

[0125] The revised heating control model is received, and the revised heating control model is used as the current heating control model.

[0126] In one embodiment, the prediction modeling algorithm in the heating control unit 20 includes a time series analysis algorithm, a regression analysis algorithm, and a neural network algorithm; the selection process of the prediction modeling algorithm in the current heating control model includes:

[0127] When the amount of current historical data stored in the cloud platform is lower than a first preset threshold, a time series analysis algorithm is selected for training to obtain a current heating control model;

[0128] When the amount of current historical data stored in the cloud platform is higher than a first preset threshold, and the proportion of the range of the current historical data relative to the range of the preset influencing factors is lower than a preset second threshold, a regression analysis algorithm is selected for training to obtain the current heating control model;

[0129] When the amount of current historical data stored in the cloud platform is higher than the first preset threshold, and the proportion of the range of the current historical data relative to the preset influencing factor range is higher than the preset second threshold, the neural network algorithm is selected for training to obtain the current heating control model.

[0130] In one implementation, the acquisition unit 10 is specifically configured to:

[0131] Obtain real-time meteorological data from the meteorological website, real-time room temperature data from the cloud platform, and real-time local operation data of the local control system from the local side; the real-time room temperature data is obtained by the cloud platform from the room temperature data collector and sent to the edge side.

[0132] In one embodiment, the apparatus further comprises a model monitoring unit;

[0133] A model monitoring unit, specifically used to monitor the size of control parameters;

[0134] When the change range of the control parameter exceeds the preset change threshold, the control parameter is output according to the preset maximum change upper limit of the control parameter, and a prompt message is generated and sent to the supervisor side.

[0135] The embodiment of the present application also provides a heating control device based on edge-cloud collaborative computing. Figure 4 As shown, it shows a structural schematic diagram of a heating control device based on edge-cloud collaborative computing suitable for implementing the present application. The heating control device based on edge-cloud collaborative computing in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 4 The heating control device based on edge-cloud collaborative computing shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0136] like Figure 4 As shown, the heating control device based on edge-cloud collaborative computing may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the heating control device based on edge-cloud collaborative computing is powered on, various programs and data required for the operation of the heating control device based on edge-cloud collaborative computing are also stored in RAM 603. The processing device 601, ROM 602 and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0137] Typically, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a memory card, a hard disk, etc.; and communication devices 609. The communication device 609 can allow the heating control device based on edge-cloud collaborative computing to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The edge-cloud collaborative computing-based heating control device with various devices is shown, but it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0138] Also provided in an embodiment of the present application is a computer program product including computer-readable instructions. When the computer-readable instructions are executed on a heating control device based on edge-cloud collaborative computing, the heating control device based on edge-cloud collaborative computing enables the heating control device based on edge-cloud collaborative computing to implement any one of the heating control methods based on edge-cloud collaborative computing provided in the embodiments of the present application.

[0139] A computer-readable storage medium is also provided in an embodiment of the present application, which carries one or more computer programs. When one or more computer programs are executed by a heating control device based on edge-cloud collaborative computing, the heating control device based on edge-cloud collaborative computing can implement any one of the heating control methods based on edge-cloud collaborative computing provided in the embodiments of the present application.

[0140] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0141] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0142] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0143] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A heating control method based on edge-cloud collaborative computing, characterized in that: Applied to the edge side, including: Acquire real-time data; the real-time data includes real-time meteorological data, real-time room temperature data and real-time local operation data on the local side; The real-time meteorological data, real-time room temperature data and real-time local operation data on the local side are input into the current heating control model obtained from the cloud platform to obtain control parameters; the current heating control model is a model trained by the cloud platform using a predictive modeling algorithm selected from a predictive modeling algorithm set, and the predictive modeling algorithm is selected based on the amount of current historical data stored in the cloud platform and the proportion of the range of the current historical data relative to the range of preset influencing factors, and the preset influencing factors are various influencing factors that affect the heating effect of the current heating control model; the current historical data includes current historical meteorological data, current historical room temperature data and current historical local operation data on the local side; The control parameters are sent to the local side, so that the local control system of the local side executes the control parameters to make the indoor temperature reach the target value of the indoor temperature.

2. The heat supply control method based on edge-cloud collaborative computing according to claim 1 is characterized in that: Also includes: Responding to a model modification instruction sent by the cloud platform; Obtain historical meteorological data, historical room temperature data and local historical operation data; Sending the historical meteorological data, the historical room temperature data and the historical operation data on the local side to the cloud platform, so that the cloud platform corrects the current heating control model based on the historical meteorological data, the historical room temperature data and the historical operation data on the local side; The modified heating control model is received, and the modified heating control model is used as the current heating control model.

3. The method for heat supply control based on edge-cloud collaborative computing according to claim 1 is characterized in that: The prediction modeling algorithm includes a time series analysis algorithm, a regression analysis algorithm and a neural network algorithm; the selection process of the prediction modeling algorithm in the current heating control model includes: When the amount of the current historical data stored in the cloud platform is lower than a first preset threshold, selecting the time series analysis algorithm for training to obtain the current heating control model; When the amount of the current historical data stored in the cloud platform is higher than the first preset threshold, and the proportion of the range of the current historical data relative to the preset influencing factor range is lower than the preset second threshold, the regression analysis algorithm is selected for training to obtain the current heating control model; When the amount of the current historical data stored in the cloud platform is higher than the first preset threshold, and the proportion of the range of the current historical data relative to the preset influencing factor range is higher than the preset second threshold, the neural network algorithm is selected for training to obtain the current heating control model.

4. The method for heat supply control based on edge-cloud collaborative computing according to claim 1 is characterized in that: The obtaining of real-time data includes: The real-time meteorological data is obtained from the meteorological website, the real-time room temperature data is obtained from the cloud platform, and the real-time local operation data of the local control system is obtained from the local side; the real-time room temperature data is obtained by the cloud platform from the room temperature data collector and sent to the edge side.

5. The method for heat supply control based on edge-cloud collaborative computing according to claim 1 is characterized in that: Also includes: Monitoring the magnitude of the control parameter; When the change range of the control parameter exceeds the preset change threshold, the control parameter is output according to the preset maximum change upper limit of the control parameter, and a prompt message is generated and sent to the supervisor side.

6. A heating control device based on edge-cloud collaborative computing, characterized in that: include: Acquisition unit, heating control unit and sending unit; wherein: The acquisition unit is used to acquire real-time data; the real-time data includes real-time meteorological data, real-time room temperature data and real-time local operation data on the local side; The heating control unit is used to input the real-time meteorological data, real-time room temperature data and real-time local operation data on the local side into the current heating control model obtained from the cloud platform to obtain control parameters; the current heating control model is a model trained by the cloud platform using a predictive modeling algorithm selected from a predictive modeling algorithm set, and the predictive modeling algorithm is selected based on the amount of current historical data stored in the cloud platform and the proportion of the range of the current historical data relative to the range of preset influencing factors, and the preset influencing factors are various influencing factors that affect the heating effect of the current heating control model; the current historical data includes current historical meteorological data, current historical room temperature data and current historical local operation data on the local side; The sending unit is used to send the control parameter to the local side, so that the local control system of the local side executes the control parameter to make the indoor temperature reach the target value of the indoor temperature.

7. The heat supply control device based on edge-cloud collaborative computing according to claim 6 is characterized in that: Also includes a model correction unit; The model correction unit is used to respond to the model correction instruction sent by the cloud platform; Obtain historical meteorological data, historical room temperature data and local historical operation data; Sending the historical meteorological data, the historical room temperature data and the historical operation data on the local side to the cloud platform, so that the cloud platform corrects the current heating control model based on the historical meteorological data, the historical room temperature data and the historical operation data on the local side; The modified heating control model is received, and the modified heating control model is used as the current heating control model.

8. The heating control equipment based on edge-cloud collaborative computing is characterized by: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the heating control method based on edge-cloud collaborative computing as described in any one of claims 1 to 5.

9. A computer program product, characterized in that It includes computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the heating control method based on edge-cloud collaborative computing as described in any one of claims 1 to 5.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the heating control method based on edge-cloud collaborative computing as described in any one of claims 1 to 5.

Images