Heating load prediction and remote control system based on Internet of Things architecture

Abstract

The invention discloses a heat supply load prediction and remote control system based on an Internet of Things architecture, which relates to the field of remote management and control and comprises a data acquisition module, a database module, a prediction module and a data processing module. The prediction module is used for predicting heat demands of the user at different times during the heat supply period; the data processing module is used for analyzing the real-time indoor temperature data, the real-time environment temperature data and the real-time parameter information to generate a heat supply execution report; according to the method, system parameter configuration required by a user under different temperature demands is speculated according to historical data, then a heat supply plan is made in combination with temperature prediction data of future weather, and finally, the temperature demand is adjusted, so that the operation accuracy of the system is improved, and relatively accurate operation parameters are configured to improve the use experience of the user; and meanwhile, energy waste caused by unscientific parameter configuration during manual system operation parameter adjustment is also reduced, and the scientificity of remote control is improved.

Description

Technical Field

[0001] The present invention relates to the field of remote management and control, and in particular to a heating load prediction and remote control system based on an Internet of Things architecture. Background Art

[0002] Heating load forecasting is an important part of the hot water heating system. It is of great significance to ensure the thermal comfort of heat users, save the investment cost of heating enterprises and reduce environmental pollution. Its combination with remote control can enable heating enterprises to monitor and control the operation status of the heating system in real time. The current heating load forecasting system is based on historical heating data of different time periods to infer future heating demand and remotely control it. Due to the uncertainty of ambient temperature changes, the prediction results deviate greatly from the actual situation and the prediction accuracy is poor. The poor prediction accuracy requires more manual participation during remote control, which also affects the reference value of remote control data in judging the operation status of the heating system. To solve this problem, a heating load forecasting and remote control system based on the Internet of Things architecture is proposed. Summary of the invention

[0003] The technical problem to be solved by the present invention is: how to solve the problem that the existing safety protection system has a single protection type, resulting in poor protection effect and bringing certain impacts on the use of the safety protection system, and provides a heating load prediction and remote control system based on the Internet of Things architecture.

[0004] The present invention solves the above technical problems through the following technical solutions, and the present invention includes a data acquisition module, a preprocessing module, a database module, a prediction module, a data processing module, a control module, and a data output module; The data acquisition module is used to collect real-time parameter information in the heating system, real-time indoor temperature data, real-time ambient temperature data, and temperature forecast data for future weather; The preprocessing module is used to receive real-time parameter information and real-time indoor temperature data, and to sort and filter the real-time parameter information and real-time indoor temperature data; The database module is used to store historical data information of various parameters in the heating system, external ambient temperature and indoor temperature; The prediction module is used to receive temperature prediction data and historical data information; by analyzing the temperature prediction data and historical data information, it predicts the user's heat demand at different times during the heating period and issues a heating plan report; The data processing module is used to receive the heating plan report, real-time indoor temperature data, real-time ambient temperature data, real-time parameter information and historical data information, and adjust the heating plan report to generate a heating execution report by analyzing the real-time indoor temperature data, real-time ambient temperature data and real-time parameter information; and analyze the real-time parameter information and historical data information to determine the operating status of the heating system, and issue a maintenance report when the operating status of the heating system is abnormal; The control module is used to receive the heating execution report and control the operating parameters of each device in the heating system to provide heating to the user; The data output module is used to receive and output heating execution reports and maintenance reports.

[0005] Preferably, the processing process of the preprocessing module is: Get real-time parameter information and real-time indoor temperature data; Classify the real-time parameter information to generate a real-time parameter data set, and classify the real-time indoor temperature data to generate a real-time indoor temperature data set; Read the data in the real-time parameter data set, filter the same data and keep one of them; read the data in the real-time indoor temperature data set, filter the same data and keep one of them.

[0006] Preferably, the historical data information includes historical ambient temperature data, historical indoor temperature data, historical heating data and historical parameter information of the heating system; the specific processing process of the prediction module is: Obtain historical indoor temperature data of users' rooms during multiple heating periods, which are Te1, Te2, Te3, ..., Ten; Calculate the average of multiple historical indoor temperature data ,make It is the standard indoor temperature required by users during heating period; Then obtain historical ambient temperature data of multiple heating periods, namely Tr1, Tr2, Tr3, ..., Trn; Calculate the temperature demand W. The specific calculation process is: ; Import different historical ambient temperature data Trn to obtain the temperature demand W at different ambient temperatures; Then import the historical parameter information Y of the heating system under different temperature demands; Establish a mapping relationship F(W)=Y between the temperature demand W and the historical parameter information Y of the heating system; Then import the temperature forecast data of future weather and obtain the temperature demand W in different time periods; The parameter information Y of the heating system in different time periods is obtained through the function mapping relationship F(W), and a heating plan report including the operating parameters of the heating system in different time periods is generated.

[0007] Preferably, the standard temperature The acquisition process also includes: Obtain historical indoor temperature data of multiple users in different regions; Calculate the average values ​​of historical indoor temperature data in different regions, which are Ti1, Ti2, Ti3, ..., Tin respectively; Calculate the difference E1 of the standard temperature. The specific calculation process is: ; When the difference E1>preset threshold Q1, a regional standard temperature value corresponding to the region is established; When the difference E1 ≤ the preset threshold Q1, the data in the area is cleared.

[0008] Preferably, the process of obtaining the temperature demand W further includes: Randomly obtain a temperature demand W; Obtain historical parameter information Y` of the heating system under the temperature demand W through the mapping relationship F(W); Obtain multiple historical indoor temperature data under historical parameter information Y', and calculate their average value Ta; Calculate historical indoor temperature data and standard temperature The specific calculation process of the deviation degree E2 is as follows: ; When the deviation E2>preset threshold Q2, obtain historical ambient temperature data under multiple historical parameter information Y' and the deviation E2≤preset threshold Q2, and calculate the average value Tb; Using the formula Calculate the temperature demand W` of the historical parameter information Y`; The temperature demand W under the historical parameter information Y' is replaced with W'.

[0009] Preferably, the specific processing process of the data processing module is: Obtain heating plan report and read heating system operation parameter Yr; Get the user's real-time indoor temperature data Ts1; Calculate the first deviation E3 of the real-time indoor temperature. The specific calculation process is as follows: ; When the first deviation E3>preset threshold Q3, multiple historical ambient temperatures under the heating system operating parameter Yr are read and their average value Tc is calculated; Collect real-time ambient temperature data Td; Calculate the second deviation E4 of the real-time ambient temperature. The specific calculation process is: ; When the second deviation E4>preset threshold Q5, the temperature demand W is adjusted to change the temperature demand W to , and generate heating execution report; When the second deviation E4 ≤ the preset threshold Q5, it is determined that the heating system is operating abnormally and a maintenance report is generated.

[0010] Preferably, the maintenance report includes a heating system maintenance report and a user end maintenance report, and the generation process of the maintenance report is: Randomly obtain sample data of real-time indoor temperature of multiple users in the user area, namely Tv1, Tv2, Tv3, ..., Tvn; Replace Ts1 with Tv1, Tv2, Tv3, ..., Tvn respectively, and use the first deviation formula to calculate the first deviation E3 of the indoor temperatures of multiple users respectively; Count the number of abnormal users U1 when the first deviation E3 in the sample data is greater than the preset threshold Q3; Then count the number of sample data U2; Calculate the proportion of abnormal users E5. The specific calculation process is as follows: E5=U1 / U2; When the proportion E5 ≥ the preset threshold Q4, a heating end maintenance report is generated; When the proportion E5 is less than the preset threshold Q4, a user-side maintenance report is generated.

[0011] Preferably, the real-time parameter information includes real-time user heating height parameters, the historical data information includes historical user heating height parameters, and the generation process of the heating end maintenance report further includes: Read the historical user heating height parameters and obtain the heating height data of multiple users, namely Ha1, Ha2, Ha3, ..., Han; Randomly obtain multiple groups of heating height data between multiple heating height data, calculate the difference between each group of heating height data, and obtain at least one minimum height difference Hb, and calculate the average value of the minimum height difference ; Then obtain the historical indoor temperature under each heating height data; Randomly extract multiple sets of heating height data and historical indoor temperatures at corresponding heights; Use preset rules to calculate each group of heating height data for each change The change of historical indoor temperature Tz; The default rules are: A group of heating height data is randomly selected, each group has two heating height data, and the two heating height data are set to be Hc1 and Hc2; Get the historical indoor temperature Tu1 when the heating height is Hc1, and the historical indoor temperature Tu2 when the heating height is Hc2; Calculate the heating height data every time it changes The change in historical indoor temperature Tz at that time, the specific calculation process is: ; Calculate each group of heating height data for each change The change of historical indoor temperature at that time, and obtain the average change of historical indoor temperature ; Obtain the user's real-time heating height parameter and read the heating height Hd; Calculate the change in indoor temperature Tm when the heating height is Hd. The specific calculation process is: ; The real-time indoor temperature data of the user is adjusted to Ts1+Tm, and the first deviation E3 is recalculated to obtain the value of the abnormal user data U1.

[0012] Preferably, the real-time parameter information also includes the inlet height of the heating pipe at the user end, and the acquisition process of the heating height Hd also includes: Obtain the entrance height of the heating pipe, take the entrance height of the heating as the reference point, measure the heating height Hd`, and replace the heating height Hd with Hd`.

[0013] Preferably, the system further comprises a service platform module, and the service platform module is used to receive and display a heating execution report and a maintenance report.

[0014] Compared with the prior art, the present invention has the following advantages: the system first infers the system parameter configuration required by the user at different temperature demands based on historical data, and then makes a heating plan in combination with the temperature forecast data of future weather, and finally adjusts the temperature demand based on the real-time temperature data, thereby improving the operating accuracy of the system and configuring more accurate operating parameters to improve the user experience; at the same time, it also reduces the energy waste caused by unscientific configuration of parameters when manually adjusting the system operating parameters, and improves the scientific nature of remote control; among them, through the analysis of the user's heating height and abnormal user data, the operating status of the heating system is judged and feedback is given, which can greatly improve the efficiency of the operation of the heating enterprise, making the system more worthy of promotion and use. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is the overall module diagram of the present invention. DETAILED DESCRIPTION

[0016] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0017] like Figure 1 As shown, this embodiment provides a technical solution: a heating load prediction and remote control system based on the Internet of Things architecture, including a data acquisition module, a preprocessing module, a database module, a prediction module, a data processing module, a control module, and a data output module; The data acquisition module is used to collect real-time parameter information in the heating system, real-time indoor temperature data, real-time ambient temperature data, and temperature forecast data for future weather; It should be noted that the indoor temperature data refers to the temperature data of the user's room, and the ambient temperature data refers to the temperature data of the user's room.

[0018] It should be noted that the temperature prediction data is future weather forecast data, which is imported into the system through the data acquisition module. The acquisition of weather forecast is an existing technology and has various acquisition channels, which will not be elaborated here.

[0019] The preprocessing module is used to receive real-time parameter information and real-time indoor temperature data, and to sort and filter the real-time parameter information and real-time indoor temperature data; The database module is used to store historical data information of various parameters in the heating system, external ambient temperature and indoor temperature; The prediction module is used to receive temperature prediction data and historical data information; by analyzing the temperature prediction data and historical data information, it predicts the user's heat demand at different times during the heating period and issues a heating plan report; The data processing module is used to receive the heating plan report, real-time indoor temperature data, real-time ambient temperature data, real-time parameter information and historical data information, and adjust the heating plan report to generate a heating execution report by analyzing the real-time indoor temperature data, real-time ambient temperature data and real-time parameter information; and analyze the real-time parameter information and historical data information to determine the operating status of the heating system, and issue a maintenance report when the operating status of the heating system is abnormal; The control module is used to receive the heating execution report and control the operating parameters of each device in the heating system to provide heating to the user; The data output module is used to receive and output heating execution reports and maintenance reports.

[0020] The system first infers the system parameter configuration required by users for different temperature demands based on historical data, then makes a heating plan based on future temperature forecast data, and finally adjusts the temperature demand based on real-time temperature data, thereby improving the system's operating accuracy and configuring more accurate operating parameters to enhance the user experience; at the same time, it also reduces the energy waste caused by unscientific configuration of parameters when manually adjusting system operating parameters, and improves the scientific nature of remote control; through the analysis of the user's heating height and abnormal user data, the operating status of the heating system is judged and feedback is given, which can greatly improve the efficiency of the heating company's operation, making the system more worthy of promotion and use.

[0021] Among them, the processing process of the preprocessing module is: Get real-time parameter information and real-time indoor temperature data; Classify the real-time parameter information to generate a real-time parameter data set, and classify the real-time indoor temperature data to generate a real-time indoor temperature data set; Read the data in the real-time parameter data set, filter the same data and keep one of them; read the data in the real-time indoor temperature data set, filter the same data and keep one of them.

[0022] The historical data information includes historical ambient temperature data, historical indoor temperature data, historical heating data and historical parameter information of the heating system; the specific processing process of the prediction module is as follows: Obtain historical indoor temperature data of users' rooms during multiple heating periods, which are Te1, Te2, Te3, ..., Ten; Calculate the average of multiple historical indoor temperature data ,make It is the standard indoor temperature required by users during heating period; It should be noted that the standard temperature is the temperature to be maintained indoors during the heating period.

[0023] Then obtain historical ambient temperature data of multiple heating periods, namely Tr1, Tr2, Tr3, ..., Trn; Calculate the temperature demand W. The specific calculation process is: ; Import different historical ambient temperature data Trn to obtain the temperature demand W at different ambient temperatures; Then import the historical parameter information Y of the heating system under different temperature demands; Establish a mapping relationship F(W)=Y between the temperature demand W and the historical parameter information Y of the heating system; Then import the temperature forecast data of future weather and obtain the temperature demand W in different time periods; The parameter information Y of the heating system in different time periods is obtained through the function mapping relationship F(W), and a heating plan report including the operating parameters of the heating system in different time periods is generated.

[0024] In this embodiment, the temperature to be maintained indoors during the heating period, i.e., the standard temperature, is inferred based on historical indoor temperature data; the temperature that needs to be adjusted to the standard temperature, i.e., the temperature demand, is determined by judging the difference between indoor and outdoor temperatures; the operating parameters of the heating system under different historical temperature demands are obtained, and a mapping relationship between the two is established; finally, the future temperature demand is inferred based on future weather, and system operating parameters under different temperature demands are formulated to formulate a heating plan report, which can more accurately predict future heating loads, make the operation of the heating system more in line with user needs, and improve the practicality of the system.

[0025] In the above embodiment, the standard temperature is obtained based on randomly selected data. Due to the different living habits of residents in different regions, the randomly obtained standard temperature is not targeted and cannot meet the living needs of different residents. To solve this problem, the following solution is proposed: Furthermore, the standard temperature The acquisition process also includes: Obtain historical indoor temperature data of multiple users in different regions; Calculate the average values ​​of historical indoor temperature data in different regions, which are Ti1, Ti2, Ti3, ..., Tin respectively; Calculate the difference E1 of the standard temperature. The specific calculation process is: ; When the difference E1>preset threshold Q1, a regional standard temperature value corresponding to the region is established; When the difference E1 ≤ the preset threshold Q1, the data in the area is cleared.

[0026] In this solution, historical indoor temperature data of users in different regions are obtained, and the difference in demand temperature in different regions is judged by comparing the indoor temperature in different regions with the average value of sample data; when the difference is too small, it indicates that the demand temperature in different regions is slightly different, and a unified standard temperature can be formulated; when the difference is large, it indicates that the demand temperature in different regions is quite different, and a targeted standard temperature needs to be formulated to meet the needs of different users; through this method, the targeted use of the system can be improved, the user comfort can be improved, and the reliability of the system can be improved.

[0027] Furthermore, the process of obtaining the temperature demand W also includes: Randomly obtain a temperature demand W; Obtain historical parameter information Y` of the heating system under the temperature demand W through the mapping relationship F(W); Obtain multiple historical indoor temperature data under historical parameter information Y', and calculate their average value Ta; Calculate historical indoor temperature data and standard temperature The specific calculation process of the deviation degree E2 is as follows: ; When the deviation E2>preset threshold Q2, obtain historical ambient temperature data under multiple historical parameter information Y' and the deviation E2≤preset threshold Q2, and calculate the average value Tb; Using the formula Calculate the temperature demand W` of the historical parameter information Y`; The temperature demand W under the historical parameter information Y' is replaced with W'.

[0028] In this embodiment, a temperature demand is randomly selected, and the system configuration parameters under the temperature demand are obtained, thereby obtaining the indoor temperature data of users of multiple systems under the configuration parameters; the indoor temperature is compared to see whether it is close to the standard temperature, so as to verify the mapping relationship between the temperature demand and the heating system parameter information; when the indoor temperature is close to the standard temperature, it indicates that the mapping relationship is relatively accurate and can be used normally; when the indoor temperature is significantly different from the standard temperature, it indicates that there is an abnormality in the mapping relationship between the temperature demand and the heating system parameter information, and the abnormal mapping relationship can be adjusted to improve the accuracy of the heating plan report.

[0029] Among them, the specific processing process of the data processing module is: Obtain heating plan report and read heating system operation parameter Yr; Get the user's real-time indoor temperature data Ts1; Calculate the first deviation E3 of the real-time indoor temperature. The specific calculation process is as follows: ; When the first deviation E3>preset threshold Q3, multiple historical ambient temperatures under the heating system operating parameter Yr are read and their average value Tc is calculated; Collect real-time ambient temperature data Td; Calculate the second deviation E4 of the real-time ambient temperature. The specific calculation process is: ; When the second deviation E4>preset threshold Q5, the temperature demand W is adjusted to change the temperature demand W to , and generate heating execution report; When the second deviation E4 ≤ the preset threshold Q5, it is determined that the heating system is operating abnormally and a maintenance report is generated.

[0030] In this embodiment, the correctness of the system operating parameters in the heating plan report is analyzed through indoor temperature data and ambient temperature data; under the premise that the indoor temperature deviates greatly from the standard temperature, when the ambient temperature deviation is large, it indicates that the weather forecast temperature in the heating plan report deviates greatly from the actual temperature, and it is necessary to recalculate the temperature demand and formulate a heating execution report; when the ambient temperature deviation is small, it indicates that the system is insufficiently heated, the heating system may be abnormal, and maintenance is required; the degree of manual intervention can be reduced, and the energy waste caused by unscientific configuration of parameters when manually adjusting the system operating parameters can be reduced, thereby improving the scientific nature of remote control.

[0031] Furthermore, the maintenance report includes a heating system maintenance report and a user-end maintenance report. The generation process of the maintenance report is as follows: Randomly obtain sample data of real-time indoor temperature of multiple users in the user area, namely Tv1, Tv2, Tv3, ..., Tvn; Replace Ts1 with Tv1, Tv2, Tv3, ..., Tvn respectively, and use the first deviation formula to calculate the first deviation E3 of the indoor temperatures of multiple users respectively; Count the number of abnormal users U1 when the first deviation E3 in the sample data is greater than the preset threshold Q3; Then count the number of sample data U2; Calculate the proportion of abnormal users E5. The specific calculation process is as follows: E5=U1 / U2; When the proportion E5 ≥ the preset threshold Q4, a heating end maintenance report is generated; When the proportion E5 is less than the preset threshold Q4, a user-side maintenance report is generated.

[0032] Determine the maintenance location in the heating system, issue corresponding maintenance reports, assist staff in maintenance work, and improve the system's operational efficiency.

[0033] In the heating system, heat will be lost during the transmission process, which is a normal state; when the user is a high-floor user, the slight fluctuation of the temperature is normal, so this data cannot be used to judge the abnormal situation of the heating system. Such data is not effective data for judging the heating system and needs to be adjusted. Therefore, the following further solutions are proposed: Furthermore, the real-time parameter information includes real-time user heating height parameters, the historical data information includes historical user heating height parameters, and the generation process of the heating end maintenance report also includes: Read the historical user heating height parameters and obtain the heating height data of multiple users, namely Ha1, Ha2, Ha3, ..., Han; Randomly obtain multiple groups of heating height data between multiple heating height data, calculate the difference between each group of heating height data, and obtain at least one minimum height difference Hb, and calculate the average value of the minimum height difference ; Then obtain the historical indoor temperature under each heating height data; Randomly extract multiple sets of heating height data and historical indoor temperatures at corresponding heights; Use preset rules to calculate each group of heating height data for each change The change of historical indoor temperature Tz; The default rules are: A group of heating height data is randomly selected, each group has two heating height data, and the two heating height data are set to be Hc1 and Hc2; Get the historical indoor temperature Tu1 when the heating height is Hc1, and the historical indoor temperature Tu2 when the heating height is Hc2; Calculate the heating height data every time it changes The change in historical indoor temperature Tz at that time, the specific calculation process is: ; Calculate each group of heating height data for each change The change of historical indoor temperature at that time, and obtain the average change of historical indoor temperature ; Obtain the user's real-time heating height parameter and read the heating height Hd; Calculate the change in indoor temperature Tm when the heating height is Hd. The specific calculation process is: ; The real-time indoor temperature data of the user is adjusted to Ts1+Tm, and the first deviation E3 is recalculated to obtain the value of the abnormal user data U1.

[0034] This embodiment uses historical data to analyze the change in indoor temperature every time the heating height data changes by one unit, and then obtains the user's height information, and adjusts the data of the first deviation E3 according to the temperature change Tm; and then determines the proportion of abnormal users E5, so as to obtain more accurate judgment data, reduce the probability of misjudgment of the heating system, and improve the reliability of system use.

[0035] The real-time parameter information also includes the inlet height of the heating pipe at the user end. The acquisition process of the heating height Hd also includes: Obtain the entrance height of the heating pipe, take the entrance height of the heating as the reference point, measure the heating height Hd`, and replace the heating height Hd with Hd`.

[0036] The system also includes a service platform module, which is used to receive and display a heating execution report and a maintenance report.

[0037] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0038] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0039] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A heating load prediction and remote control system based on the Internet of Things architecture, characterized in that: It includes data acquisition module, preprocessing module, database module, prediction module, data processing module, control module and data output module; The data acquisition module is used to collect real-time parameter information in the heating system, real-time indoor temperature data, real-time ambient temperature data, and temperature forecast data for future weather; The preprocessing module is used to receive real-time parameter information and real-time indoor temperature data, and to sort and filter the real-time parameter information and real-time indoor temperature data; The database module is used to store historical data information of various parameters in the heating system, external ambient temperature and indoor temperature; The prediction module is used to receive temperature prediction data and historical data information; by analyzing the temperature prediction data and historical data information, it predicts the user's heat demand at different times during the heating period and issues a heating plan report; The data processing module is used to receive the heating plan report, real-time indoor temperature data, real-time ambient temperature data, real-time parameter information and historical data information, and adjust the heating plan report to generate a heating execution report by analyzing the real-time indoor temperature data, real-time ambient temperature data and real-time parameter information; and analyze the real-time parameter information and historical data information to determine the operating status of the heating system, and issue a maintenance report when the operating status of the heating system is abnormal; The control module is used to receive the heating execution report and control the operating parameters of each device in the heating system to provide heating to the user; The data output module is used to receive and output heating execution reports and maintenance reports.

2. According to claim 1, a heating load prediction and remote control system based on the Internet of Things architecture is characterized by: The processing process of the preprocessing module is: Get real-time parameter information and real-time indoor temperature data; Classify the real-time parameter information to generate a real-time parameter data set, and classify the real-time indoor temperature data to generate a real-time indoor temperature data set; Read the data in the real-time parameter data set, filter the same data and keep one of them; read the data in the real-time indoor temperature data set, filter the same data and keep one of them.

3. According to the heating load prediction and remote control system based on the Internet of Things architecture as claimed in claim 1, it is characterized by: The historical data information includes historical ambient temperature data, historical indoor temperature data, historical heating data and historical parameter information of the heating system; the specific processing process of the prediction module is: Obtain historical indoor temperature data of users' rooms during multiple heating periods, which are Te1, Te2, Te3, ..., Ten; Calculate the average of multiple historical indoor temperature data ,make It is the standard indoor temperature required by users during heating period; Then obtain historical ambient temperature data of multiple heating periods, namely Tr1, Tr2, Tr3, ..., Trn; Calculate the temperature demand W. The specific calculation process is: ； Import different historical ambient temperature data Trn to obtain the temperature demand W at different ambient temperatures; Then import the historical parameter information Y of the heating system under different temperature demands; Establish a mapping relationship F(W)=Y between the temperature demand W and the historical parameter information Y of the heating system; Then import the temperature forecast data of future weather and obtain the temperature demand W in different time periods; The parameter information Y of the heating system in different time periods is obtained through the function mapping relationship F(W), and a heating plan report including the operating parameters of the heating system in different time periods is generated.

4. The heating load prediction and remote control system based on the Internet of Things architecture according to claim 3 is characterized in that: The standard temperature The acquisition process also includes: Obtain historical indoor temperature data of multiple users in different regions; Calculate the average values ​​of historical indoor temperature data in different regions, which are Ti1, Ti2, Ti3, ..., Tin respectively; Calculate the difference E1 of the standard temperature. The specific calculation process is: ； When the difference E1>preset threshold Q1, a regional standard temperature value corresponding to the region is established; When the difference E1 ≤ the preset threshold Q1, the data in the area is cleared.

5. The heating load prediction and remote control system based on the Internet of Things architecture according to claim 3 is characterized in that: The process of obtaining the temperature demand W also includes: Randomly obtain a temperature demand W; Obtain historical parameter information Y` of the heating system under the temperature demand W through the mapping relationship F(W); Obtain multiple historical indoor temperature data under historical parameter information Y', and calculate their average value Ta; Calculate historical indoor temperature data and standard temperature The specific calculation process of the deviation degree E2 is as follows: ； When the deviation E2>preset threshold Q2, obtain historical ambient temperature data under multiple historical parameter information Y' and the deviation E2≤preset threshold Q2, and calculate the average value Tb; Using the formula Calculate the temperature demand W` of the historical parameter information Y`; The temperature demand W under the historical parameter information Y' is replaced with W'.

6. A heating load prediction and remote control system based on the Internet of Things architecture according to claim 1 or 3, characterized in that: The specific processing process of the data processing module is as follows: Obtain heating plan report and read heating system operation parameter Yr; Get the user's real-time indoor temperature data Ts1; Calculate the first deviation E3 of the real-time indoor temperature. The specific calculation process is as follows: ； When the first deviation E3>preset threshold Q3, multiple historical ambient temperatures under the heating system operating parameter Yr are read and their average value Tc is calculated; Collect real-time ambient temperature data Td; Calculate the second deviation E4 of the real-time ambient temperature. The specific calculation process is: ； When the second deviation E4>preset threshold Q5, the temperature demand W is adjusted to change the temperature demand W to , and generate heating execution report; When the second deviation E4 ≤ the preset threshold Q5, it is determined that the heating system is operating abnormally and a maintenance report is generated.

7. The heating load prediction and remote control system based on the Internet of Things architecture according to claim 6 is characterized in that: The maintenance report includes a heating system maintenance report and a user end maintenance report. The generation process of the maintenance report is as follows: Randomly obtain sample data of real-time indoor temperature of multiple users in the user area, namely Tv1, Tv2, Tv3, ..., Tvn; Replace Ts1 with Tv1, Tv2, Tv3, ..., Tvn respectively, and use the first deviation formula to calculate the first deviation E3 of the indoor temperatures of multiple users respectively; Count the number of abnormal users U1 when the first deviation E3 in the sample data is greater than the preset threshold Q3; Then count the number of sample data U2; Calculate the proportion of abnormal users E5. The specific calculation process is as follows: E5=U1 / U2; When the proportion E5 ≥ the preset threshold Q4, a heating end maintenance report is generated; When the proportion E5 is less than the preset threshold Q4, a user-side maintenance report is generated.

8. The heating load prediction and remote control system based on the Internet of Things architecture according to claim 7 is characterized in that: The real-time parameter information includes the real-time user heating height parameter, and the historical data information includes the historical user heating height parameter. The generation process of the heating end maintenance report also includes: Read the historical user heating height parameters and obtain the heating height data of multiple users, namely Ha1, Ha2, Ha3, ..., Han; Randomly obtain multiple groups of heating height data between multiple heating height data, calculate the difference between each group of heating height data, and obtain at least one minimum height difference Hb, and calculate the average value of the minimum height difference ; Then obtain the historical indoor temperature under each heating height data; Randomly extract multiple sets of heating height data and historical indoor temperatures at corresponding heights; Use preset rules to calculate each group of heating height data for each change The change of historical indoor temperature at that time Tz; The default rules are: A group of heating height data is randomly selected, each group has two heating height data, and the two heating height data are set to be Hc1 and Hc2; Get the historical indoor temperature Tu1 when the heating height is Hc1, and the historical indoor temperature Tu2 when the heating height is Hc2; Calculate the heating height data every time it changes The change in historical indoor temperature Tz at that time, the specific calculation process is: ； Calculate each group of heating height data for each change The change of historical indoor temperature at that time, and obtain the average change of historical indoor temperature ; Obtain the user's real-time heating height parameter and read the heating height Hd; Calculate the change in indoor temperature Tm when the heating height is Hd. The specific calculation process is: ； The real-time indoor temperature data of the user is adjusted to Ts1+Tm, and the first deviation E3 is recalculated to obtain the value of the abnormal user data U1.

9. The heating load prediction and remote control system based on the Internet of Things architecture according to claim 8, characterized in that: The real-time parameter information also includes the inlet height of the heating pipe at the user end. The acquisition process of the heating height Hd also includes: Obtain the entrance height of the heating pipe, take the entrance height of the heating as the reference point, measure the heating height Hd`, and replace the heating height Hd with Hd`.

10. The heating load prediction and remote control system based on the Internet of Things architecture according to claim 1, characterized in that: It also includes a service platform module, which is used to receive and display a heating execution report and a maintenance report.

Images