A method, system and medium for intelligent prediction of heating management in a thermal power station

Abstract

The present application provides a method, system and medium for intelligent prediction of heating management of a thermal power station. The method includes: obtaining historical data of heating load, historical weather data and date type data of a preset time period of the thermal power station, and then classifying and calculating to obtain historical data of effective type heating load, training a heating management prediction model based on historical data of effective type heating load and historical weather data, processing the predicted weather data and predicted date type data to obtain a heating load impact index, obtaining a predicted heating impact level after threshold comparison and querying to obtain an impact weight coefficient, and then obtaining the predicted heating load data of the thermal power station, and finally obtaining the heating adjustment status through threshold comparison of the heating difference index; thus, the technology of intelligent prediction of heating management is realized by processing the historical data of effective type heating load, the heating load impact index, the heating impact prediction level and the predicted heating load data in combination with the threshold comparison.

Description

Technical Field

[0001] The present application relates to the field of heat supply management, and more specifically, to an intelligent prediction method, system and medium for heat supply management of a thermal power station. Background Art

[0002] There are many influencing factors in the heating management of thermal power stations. Through the analysis of past history, it is found that weather factors and date types are the two main influencing factors on heating management. In the heating process, accurate prediction of heating load is crucial to achieve efficient and energy-saving heating. Traditional heating load prediction methods often fail to fully consider the influence of weather factors and date type factors, resulting in low prediction accuracy. With the development of intelligent technology, a more accurate and adaptable intelligent prediction method for heating management of thermal power stations is needed.

[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0004] The purpose of this application is to provide an intelligent prediction method, system and medium for heat supply management of a thermal power station, which can achieve faster and more accurate recommendation of regional hot products through calculation and threshold comparison of commodity heat index and hot product matching recommendation index.

[0005] The present application also provides a method for intelligent prediction of heat supply management of a thermal power station, comprising the following steps:

[0006] Obtain historical data of heating load, historical weather data and date type data for a preset time period of the heating station;

[0007] Classify the heating load historical data according to the date type data to obtain type heating load historical data, and calculate to obtain effective type heating load historical data;

[0008] A heating management prediction model is obtained by training according to the effective type heating load historical data and historical weather data;

[0009] Obtain forecast weather data and forecast date type data, and obtain a heating load impact index according to the forecast weather data and forecast date type data;

[0010] Compare the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and query a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model;

[0011] After obtaining the corresponding effective type of heating load historical data according to the forecast date type data, the forecast heating load data of the thermal power station is obtained by combining the influence weight coefficient and the forecast weather data through the heat management forecast model;

[0012] The heating difference index is obtained by processing the predicted heating load data and the preset real-time heating load data, and the heating difference index is compared with the preset heating difference index threshold. After the heating adjustment status is obtained, the heating station is adjusted for heating.

[0013] Optionally, in the intelligent prediction method for heat supply management of a heat supply station described in the present application, the obtaining of historical data of heat supply load, historical weather data and date type data of a preset time period of the heat supply station specifically includes:

[0014] Obtain the historical data of heating load and historical weather data of the thermal power station during the preset time period, the historical weather data includes temperature data, humidity data, wind speed data and sunshine duration data;

[0015] Get the date type data of the preset time period of the thermal power station, including working day data, public holiday data or holiday data.

[0016] Optionally, in the intelligent prediction method for heat supply management of a thermal power station described in the present application, classifying the heating load historical data according to the date type data to obtain type heating load historical data, and calculating to obtain effective type heating load historical data, specifically includes:

[0017] Classifying the heating load historical data according to the date type data to obtain type heating load historical data, including working day heating load historical data, holiday heating load historical data and holiday heating load historical data;

[0018] According to the working day heating load historical data, the holiday heating load historical data and the holiday heating load historical data, average values ​​are respectively calculated to obtain the effective working day heating load historical data, the effective holiday heating load historical data and the effective holiday heating load historical data.

[0019] Optionally, in the intelligent prediction method for heat supply management of a thermal power station described in the present application, the obtaining of predicted weather data and predicted date type data, and obtaining a heating load impact index according to the predicted weather data and predicted date type data, specifically includes:

[0020] Obtain forecast weather data, including forecast temperature data, forecast humidity data, forecast wind speed data, and forecast sunshine duration data;

[0021] Get forecast date type data, including forecast working day data, forecast public holiday data or forecast holiday data;

[0022] The predicted temperature data, predicted humidity data, predicted wind speed data and predicted sunshine duration data are combined with the predicted date type data and processed by a preset heating load impact assessment model to obtain a heating load impact index.

[0023] Optionally, in the intelligent prediction method for heat supply management of a thermal power station described in the present application, the heating load impact index is compared with a preset heating load impact index threshold to obtain a heating impact prediction level, and a preset heating impact level database is queried according to the heating impact prediction level to obtain a corresponding impact weight coefficient in the heating management prediction model, specifically including:

[0024] Comparing the heating load impact index with a heating load impact index threshold to obtain a heating impact prediction level, including a first-level weak impact, a second-level medium impact, or a third-level strong impact;

[0025] Extracting a first threshold and a second threshold according to the heating load impact index threshold, wherein the first threshold is greater than the second threshold;

[0026] comparing the heating load impact index with the first threshold and the second threshold;

[0027] If the heating load impact index is greater than the first threshold, the heating impact prediction level is level 3 strong impact;

[0028] If the heating load impact index is greater than the second threshold and less than or equal to the first threshold, the heating impact prediction level is a secondary medium impact;

[0029] If the heating load impact index is less than or equal to the second threshold, the heating impact prediction level is a first-level weak impact;

[0030] According to the heating impact prediction level, the preset heating impact level database is queried to obtain the corresponding impact weight coefficient, and the weight impact coefficient includes the weather weight impact coefficient and the date type weight impact coefficient.

[0031] Optionally, in the intelligent prediction method for heat supply management of a thermal power station described in the present application, after obtaining the corresponding valid type of heating load historical data according to the predicted date type data, the predicted heating load data of the thermal power station is obtained by processing the heating management prediction model in combination with the influence weight coefficient and the predicted weather data, specifically including:

[0032] According to the prediction date type data, the corresponding effective type heating load historical data is obtained;

[0033] Determine the corresponding characteristic coefficient of the heat supply management prediction model according to the influence weight coefficient, and generate the heat supply management prediction weight model in combination with the characteristic coefficient;

[0034] The predicted weather data and the effective type heating load historical data are input into the heating management prediction weight model for processing to obtain the predicted heating load data of the heating station.

[0035] Optionally, in the intelligent prediction method for heat supply management of a heat supply station described in the present application, the heat supply difference index is obtained according to the predicted heat supply load data and the preset real-time heat supply load data, the heat supply difference index is compared with the preset heat supply difference index threshold, and the heat supply adjustment of the heat supply station is performed after the heat supply adjustment status is obtained, specifically including:

[0036] Divide the predicted heating load data by the real-time heating load data to obtain a heating difference index;

[0037] Comparing the heating difference index with a preset heating difference index threshold to obtain a heating adjustment status of the heating station;

[0038] Extracting a third threshold and a fourth threshold according to the heating difference index threshold, wherein the third threshold is greater than the fourth threshold;

[0039] comparing the heating difference index with the third threshold and the fourth threshold;

[0040] If the heating difference index is greater than the third threshold, the heating adjustment condition is to increase the heating energy;

[0041] If the heating difference index is greater than the fourth threshold value and less than or equal to the third threshold value, the heating adjustment condition is to maintain the heating energy;

[0042] If the heating difference index is less than or equal to the fourth threshold, the heating adjustment condition is to reduce heating energy.

[0043] In a second aspect, the present application provides a heat supply management intelligent prediction system for a heat supply station, the system comprising: a memory and a processor, the memory storing a program of an intelligent prediction method for heat supply management of a heat supply station, and the program of the intelligent prediction method for heat supply management of a heat supply station is executed by the processor to implement the following steps:

[0044] Obtain historical data of heating load, historical weather data and date type data for a preset time period of the heating station;

[0045] Classify the heating load historical data according to the date type data to obtain type heating load historical data, and calculate to obtain effective type heating load historical data;

[0046] A heating management prediction model is obtained by training according to the effective type heating load historical data and historical weather data;

[0047] Obtain forecast weather data and forecast date type data, and obtain a heating load impact index according to the forecast weather data and forecast date type data;

[0048] Compare the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and query a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model;

[0049] After obtaining the corresponding effective type of heating load historical data according to the forecast date type data, the forecast heating load data of the thermal power station is obtained by combining the influence weight coefficient and the forecast weather data through the heat management forecast model;

[0050] The heating difference index is obtained by processing the predicted heating load data and the preset real-time heating load data, and the heating difference index is compared with the preset heating difference index threshold. After the heating adjustment status is obtained, the heating station is adjusted for heating.

[0051] Optionally, in the intelligent prediction system for heat supply management of a heat supply station, the obtaining of historical data on heat supply load, historical weather data and date type data for a preset time period of the heat supply station specifically includes:

[0052] Obtain the historical data of heating load and historical weather data of the thermal power station during the preset time period, the historical weather data includes temperature data, humidity data, wind speed data and sunshine duration data;

[0053] Get the date type data of the preset time period of the thermal power station, including working day data, public holiday data or holiday data.

[0054] In the third aspect, the present application also provides a readable storage medium, which stores a program for an intelligent prediction method for heat supply management of a thermal power station. When the program for an intelligent prediction method for heat supply management of a thermal power station is executed by a processor, the steps of an intelligent prediction method for heat supply management of a thermal power station as described in any of the above items are implemented.

[0055] As can be seen from the above, the application provides a method, system and medium for intelligent prediction of heating management of a thermal power station. The method obtains the historical data of heating load, historical weather data and date type data of a preset time period of the thermal power station, and then classifies and calculates to obtain the historical data of effective type heating load, trains the heating management prediction model according to the historical data of effective type heating load and historical weather data, obtains the heating load impact index according to the processing of the predicted weather data and the predicted date type data, obtains the predicted heating impact level after threshold comparison and obtains the influence weight coefficient by query, and then obtains the predicted heating load data of the thermal power station, and finally obtains the heating adjustment status by threshold comparison of the heating difference index; thus, the technology of intelligent prediction of heating management is realized by processing the historical data of effective type heating load, the heating load impact index, the heating impact prediction level and the predicted heating load data in combination with the threshold comparison.

[0056] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A flow chart of an intelligent prediction method for heat supply management of a thermal power station provided in an embodiment of the present application;

[0059] Figure 2 A flowchart of obtaining historical data of heating load, historical weather data and date type data of a method for intelligent prediction of heating management of a heating power station provided in an embodiment of the present application;

[0060] Figure 3 A flowchart of obtaining historical data of effective type heating loads in a method for intelligent prediction of heating management of a thermal power station provided in an embodiment of the present application;

[0061] Figure 4 A flow chart of obtaining a heating load impact index in a method for intelligent prediction of heating management in a thermal power station provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0063] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0064] Please refer to Figure 1 , Figure 1 Flow chart of the intelligent prediction method for heat supply management of a heat supply station in some embodiments of the present application. The intelligent prediction method for heat supply management of a heat supply station is used in a terminal device, such as a computer, a mobile phone, etc. The intelligent prediction method for heat supply management of a heat supply station comprises the following steps:

[0065] S11, obtaining heating load historical data, historical weather data and date type data of a preset time period of the heating station;

[0066] S12, classifying the heating load historical data according to the date type data to obtain type heating load historical data, and calculating to obtain effective type heating load historical data;

[0067] S13, training a heating management prediction model according to the historical data of effective type heating load and historical weather data;

[0068] S14, obtaining forecast weather data and forecast date type data, and obtaining a heating load impact index according to the forecast weather data and the forecast date type data;

[0069] S15, comparing the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and querying a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model;

[0070] S16, after obtaining the corresponding effective type of heating load historical data according to the predicted date type data, the predicted heating load data of the thermal power station is obtained by processing the heating management prediction model in combination with the influence weight coefficient and the predicted weather data;

[0071] S17. Obtain a heating difference index based on the predicted heating load data and the preset real-time heating load data, compare the heating difference index with a preset heating difference index threshold, and adjust the heating of the thermal power station after obtaining the heating adjustment status.

[0072] It should be noted that when conducting a heat supply management forecast for a thermal power station, it is necessary to conduct the forecast based on an analysis of past historical data. First, the historical data of the heat supply load, historical weather data, and date type data for a preset time period are obtained. The historical data of the heat supply load is classified according to the date type for easier analysis. The historical data of the type of heat supply load fluctuates, but in order to better reflect the heat supply load, the effective type of heat supply load historical data is calculated, and then the heat supply management forecast model is trained. Then, the heat supply load impact index is obtained based on the predicted weather data and the predicted date type data. The heat supply impact forecast level is determined based on the heat supply load impact index, and then the impact weight coefficient is obtained by querying. Then, the predicted heat supply load data of the thermal power station is calculated, and finally, the heat supply of the thermal power station is adjusted after the heat supply difference index is determined. Among them, in the heat supply management forecast model obtained through training, the impact weight coefficient changes according to the corresponding heat supply impact forecast level. The impact weight coefficients corresponding to different heat supply impact forecast levels are different, but one heat supply impact forecast level corresponds to one impact weight coefficient.

[0073] Please refer to Figure 2 , Figure 2 The present invention provides a flow chart of a method for intelligently predicting heating management of a heating station to obtain historical heating load data, historical weather data, and date type data. According to an embodiment of the present invention, the method of obtaining historical heating load data, historical weather data, and date type data for a preset time period of a heating station specifically includes:

[0074] S21, obtaining historical data of heating load and historical weather data of the thermal power station for a preset time period, where the historical weather data includes temperature data, humidity data, wind speed data, and sunshine duration data;

[0075] S22. Obtain date type data of a preset time period of the thermal power station, including working day data, public holiday data or holiday data.

[0076] It should be noted that the heat supply management forecast of the thermal power station must first be based on the analysis of historical heat supply management data. The analysis based on historical data can be more accurate. The preset time period can be customized according to user needs. In this embodiment, the preset time period is a heating cycle; the sunshine duration data refers to the sunshine duration data in a day; because different date types have different heating requirements, the date type must also be considered. The public holiday data refers to the weekends of each week, and holidays refer to national statutory holidays; in this embodiment, the date type data is taken in binary, the working day data is 01, the public holiday data is 10, and the holiday data is 11.

[0077] Please refer to Figure 3 , Figure 3 It is a flowchart of obtaining effective type heating load historical data of a heating station heating management intelligent prediction method provided by an embodiment of the present application. According to an embodiment of the present invention, the heating load historical data is classified according to the date type data to obtain type heating load historical data, and the effective type heating load historical data is calculated, specifically including:

[0078] S31, classifying the heating load historical data according to the date type data to obtain type heating load historical data, including working day heating load historical data, holiday heating load historical data and holiday heating load historical data;

[0079] S32. Calculate average values ​​according to the working day heating load historical data, the holiday heating load historical data and the holiday heating load historical data to obtain effective working day heating load historical data, effective holiday heating load historical data and effective holiday heating load historical data.

[0080] It should be noted that since the heating load is different under different date types, in order to better distinguish and more accurately predict, the obtained heating load historical data will be classified according to the date type. After classification, separate analysis and prediction will be more accurate. After classification, the type heating load historical data is obtained. The type heating load historical data fluctuates. In order to better and more stably reflect the data, the average value is taken as the effective type heating load historical data.

[0081] Please refer to Figure 4 , Figure 4 The flowchart of obtaining effective type heating load historical data of a heating station heating management intelligent prediction method provided by an embodiment of the present application. According to an embodiment of the present invention, obtaining predicted weather data and predicted date type data, and obtaining a heating load impact index according to the predicted weather data and predicted date type data processing specifically includes:

[0082] S41, obtaining predicted weather data, including predicted temperature data, predicted humidity data, predicted wind speed data, and predicted sunshine duration data;

[0083] S42, obtaining forecast date type data, including forecast working day data, forecast public holiday data or forecast holiday data;

[0084] S43, obtaining a heating load impact index by processing the predicted temperature data, predicted humidity data, predicted wind speed data, and predicted sunshine duration data in combination with the predicted date type data through a preset heating load impact assessment model.

[0085] It should be noted that in order to predict the heating management, it is necessary to obtain the weather data and date type data of the date to be predicted. In order to determine the influence of the weather data and date type data and further obtain the heating impact prediction level, the predicted weather data and predicted date type data are processed to obtain the heating load impact index. The heating load impact index reflects the influence of the weather data and date type data of the date on the heating management to a certain extent. The calculation formula of the heating load impact index in the heating load impact assessment model is:

[0086] ;

[0087] in, is the heating load impact index, , , , , They are respectively predicted temperature data, predicted humidity data, predicted wind speed data, predicted sunshine duration data, and predicted date type data. , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset heating management intelligent prediction platform of the thermal power station);

[0088] The heating load impact assessment model is obtained by training a large amount of historical data, and the heating load impact index can be calculated through this model.

[0089] According to an embodiment of the present invention, the heating load impact index is compared with a preset heating load impact index threshold to obtain a heating impact prediction level, and a preset heating impact level database is queried according to the heating impact prediction level to obtain a corresponding impact weight coefficient in the heating management prediction model, specifically including:

[0090] Comparing the heating load impact index with a heating load impact index threshold to obtain a heating impact prediction level, including a first-level weak impact, a second-level medium impact, or a third-level strong impact;

[0091] Extracting a first threshold and a second threshold according to the heating load impact index threshold, wherein the first threshold is greater than the second threshold;

[0092] comparing the heating load impact index with the first threshold and the second threshold;

[0093] If the heating load impact index is greater than the first threshold, the heating impact prediction level is level 3 strong impact;

[0094] If the heating load impact index is greater than the second threshold and less than or equal to the first threshold, the heating impact prediction level is a secondary medium impact;

[0095] If the heating load impact index is less than or equal to the second threshold, the heating impact prediction level is a first-level weak impact;

[0096] According to the heating impact prediction level, the preset heating impact level database is queried to obtain the corresponding impact weight coefficient, and the weight impact coefficient includes the weather weight impact coefficient and the date type weight impact coefficient.

[0097] It should be noted that after determining the heating impact prediction level according to the heating load impact index, the impact weight coefficient in the heating management prediction model is determined according to the heating impact prediction level. The first-level weak impact means that the weather data and date type data have a weak impact on the heating, and the impact weight coefficient is small; the second-level medium impact means that the weather data and date type data have a general impact on the heating, and the impact weight coefficient is medium in size; in this embodiment, the heating load impact index threshold is set to: [0,0.35], the heating impact prediction level is the first-level weak impact; (0.35, 0.7], the heating impact prediction level is the second-level medium impact; (0.7, 1]; the heating impact prediction level is the third-level strong impact; when the heating load impact index is 0.9, the heating impact prediction level is the third-level strong impact; the heating impact level database contains the heating impact prediction level, as well as the weather weight impact coefficient and the date type weight impact coefficient corresponding to the heating impact prediction level, and the weather weight impact coefficient and the date type weight impact coefficient correspond to the characteristic coefficient in the heating management prediction model.

[0098] According to an embodiment of the present invention, after obtaining the corresponding valid type heating load historical data according to the predicted date type data, the predicted heating load data of the thermal power station is obtained by processing the heating management prediction model in combination with the influence weight coefficient and the predicted weather data, specifically including:

[0099] According to the prediction date type data, the corresponding effective type heating load historical data is obtained;

[0100] Determine the corresponding characteristic coefficient of the heat supply management prediction model according to the influence weight coefficient, and generate the heat supply management prediction weight model in combination with the characteristic coefficient;

[0101] The predicted weather data and the effective type heating load historical data are input into the heating management prediction weight model for processing to obtain the predicted heating load data of the heating station.

[0102] It should be noted that, after first obtaining the historical data of effective type heating load according to the matching of the forecast date type data, the corresponding characteristic coefficient in the heating management forecast model is determined according to the influence weight coefficient, and then the heating management forecast weight model with determined characteristic coefficient is obtained; the heating management forecast weight model refers to the heating management forecast model with determined characteristic coefficient, and the forecast weather data and the historical data of effective type heating load are input into the heating management forecast model to obtain the forecast heating load data.

[0103] According to an embodiment of the present invention, the heating difference index is obtained according to the predicted heating load data and the preset real-time heating load data, the heating difference index is compared with the preset heating difference index threshold, and the heating adjustment status is obtained and the heating station is adjusted for heating, specifically including:

[0104] Divide the predicted heating load data by the real-time heating load data to obtain a heating difference index;

[0105] Comparing the heating difference index with a preset heating difference index threshold to obtain a heating adjustment status of the heating station;

[0106] Extracting a third threshold and a fourth threshold according to the heating difference index threshold, wherein the third threshold is greater than the fourth threshold;

[0107] comparing the heating difference index with the third threshold and the fourth threshold;

[0108] If the heating difference index is greater than the third threshold, the heating adjustment condition is to increase the heating energy;

[0109] If the heating difference index is greater than the fourth threshold value and less than or equal to the third threshold value, the heating adjustment condition is to maintain the heating energy;

[0110] If the heating difference index is less than or equal to the fourth threshold, the heating adjustment condition is to reduce heating energy.

[0111] It should be noted that if the predicted heating load data is not much different from the real-time heating load data, and is within the preset allowable range, the heating station does not need to be adjusted. Otherwise, it will be adjusted. In order to more intuitively judge whether adjustment is needed, the heating difference index is first calculated. The calculation formula of the heating difference index is:

[0112] ;

[0113] in, is the heating difference index, To predict heating load data, is the real-time heating load data; the heating difference index is compared with the preset heating difference index threshold to obtain the heating adjustment status of the thermal power station; in this example, the third threshold is 0.1 and the fourth threshold is -0.1; that is, when the heating difference index is greater than 0.1, the heating adjustment status is to increase the heating energy; when the heating difference index is greater than -0.1 and less than or equal to 0.1, the heating adjustment status is to maintain the heating energy; when the heating difference index is less than or equal to -0.1, the heating adjustment status is to reduce the heating energy; the specific increase or decrease amount is the absolute value of the predicted heating load data minus the real-time heating load data.

[0114] The present invention also discloses a heat supply management intelligent prediction system for a heat supply station, comprising a memory and a processor, wherein the memory stores a heat supply management intelligent prediction method program for a heat supply station, and when the heat supply management intelligent prediction method program for a heat supply station is executed by the processor, the following steps are implemented:

[0115] Obtain historical data of heating load, historical weather data and date type data for a preset time period of the heating station;

[0116] Classify the heating load historical data according to the date type data to obtain type heating load historical data, and calculate to obtain effective type heating load historical data;

[0117] A heating management prediction model is obtained by training according to the effective type heating load historical data and historical weather data;

[0118] Obtain forecast weather data and forecast date type data, and obtain a heating load impact index according to the forecast weather data and forecast date type data;

[0119] Compare the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and query a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model;

[0120] After obtaining the corresponding effective type of heating load historical data according to the forecast date type data, the forecast heating load data of the thermal power station is obtained by combining the influence weight coefficient and the forecast weather data through the heat management forecast model;

[0121] The heating difference index is obtained by processing the predicted heating load data and the preset real-time heating load data, and the heating difference index is compared with the preset heating difference index threshold. After the heating adjustment status is obtained, the heating station is adjusted for heating.

[0122] It should be noted that when conducting a heat supply management forecast for a thermal power station, it is necessary to conduct the forecast based on an analysis of past historical data. First, the historical data of the heat supply load, historical weather data, and date type data for a preset time period are obtained. The historical data of the heat supply load is classified according to the date type for easier analysis. The historical data of the type of heat supply load fluctuates, but in order to better reflect the heat supply load, the effective type of heat supply load historical data is calculated, and then the heat supply management forecast model is trained. Then, the heat supply load impact index is obtained based on the predicted weather data and the predicted date type data. The heat supply impact forecast level is determined based on the heat supply load impact index, and then the impact weight coefficient is obtained by querying. Then, the predicted heat supply load data of the thermal power station is calculated, and finally, the heat supply of the thermal power station is adjusted after the heat supply difference index is determined. Among them, in the heat supply management forecast model obtained through training, the impact weight coefficient changes according to the corresponding heat supply impact forecast level. The impact weight coefficients corresponding to different heat supply impact forecast levels are different, but one heat supply impact forecast level corresponds to one impact weight coefficient.

[0123] According to an embodiment of the present invention, the acquisition of heating load historical data, historical weather data and date type data of a preset time period of a thermal power station specifically includes:

[0124] Obtain the historical data of heating load and historical weather data of the thermal power station during the preset time period, the historical weather data includes temperature data, humidity data, wind speed data and sunshine duration data;

[0125] Get the date type data of the preset time period of the thermal power station, including working day data, public holiday data or holiday data.

[0126] It should be noted that the heat supply management forecast of the thermal power station must first be based on the analysis of historical heat supply management data. The analysis based on historical data can be more accurate. The preset time period can be customized according to user needs. In this embodiment, the preset time period is a heating cycle; the sunshine duration data refers to the sunshine duration data in a day; because different date types have different heating requirements, the date type must also be considered. The public holiday data refers to the weekends of each week, and holidays refer to national statutory holidays; in this embodiment, the date type data is taken in binary, the working day data is 01, the public holiday data is 10, and the holiday data is 11.

[0127] According to an embodiment of the present invention, the classifying the heating load historical data according to the date type data to obtain the type heating load historical data, and calculating to obtain the effective type heating load historical data, specifically includes:

[0128] Classifying the heating load historical data according to the date type data to obtain type heating load historical data, including working day heating load historical data, holiday heating load historical data and holiday heating load historical data;

[0129] According to the working day heating load historical data, the holiday heating load historical data and the holiday heating load historical data, average values ​​are respectively calculated to obtain the effective working day heating load historical data, the effective holiday heating load historical data and the effective holiday heating load historical data.

[0130] It should be noted that since the heating load is different under different date types, in order to better distinguish and more accurately predict, the obtained heating load historical data will be classified according to the date type. After classification, separate analysis and prediction will be more accurate. After classification, the type heating load historical data is obtained. The type heating load historical data fluctuates. In order to better and more stably reflect the data, the average value is taken as the effective type heating load historical data.

[0131] According to an embodiment of the present invention, the obtaining of the forecast weather data and the forecast date type data, and obtaining the heating load impact index according to the forecast weather data and the forecast date type data, specifically includes:

[0132] Obtain forecast weather data, including forecast temperature data, forecast humidity data, forecast wind speed data, and forecast sunshine duration data;

[0133] Get forecast date type data, including forecast working day data, forecast public holiday data or forecast holiday data;

[0134] The predicted temperature data, predicted humidity data, predicted wind speed data and predicted sunshine duration data are combined with the predicted date type data and processed by a preset heating load impact assessment model to obtain a heating load impact index.

[0135] It should be noted that in order to predict the heating management, it is necessary to obtain the weather data and date type data of the date to be predicted. In order to determine the influence of the weather data and date type data and further obtain the heating impact prediction level, the predicted weather data and predicted date type data are processed to obtain the heating load impact index. The heating load impact index reflects the influence of the weather data and date type data of the date on the heating management to a certain extent. The calculation formula of the heating load impact index in the heating load impact assessment model is:

[0136] ;

[0137] in, is the heating load impact index, , , , , They are respectively predicted temperature data, predicted humidity data, predicted wind speed data, predicted sunshine duration data, and predicted date type data. , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset heating management intelligent prediction platform of the thermal power station);

[0138] The heating load impact assessment model is obtained by training a large amount of historical data, and the heating load impact index can be calculated through this model.

[0139] According to an embodiment of the present invention, the heating load impact index is compared with a preset heating load impact index threshold to obtain a heating impact prediction level, and a preset heating impact level database is queried according to the heating impact prediction level to obtain a corresponding impact weight coefficient in the heating management prediction model, specifically including:

[0140] Comparing the heating load impact index with a heating load impact index threshold to obtain a heating impact prediction level, including a first-level weak impact, a second-level medium impact, or a third-level strong impact;

[0141] Extracting a first threshold and a second threshold according to the heating load impact index threshold, wherein the first threshold is greater than the second threshold;

[0142] comparing the heating load impact index with the first threshold and the second threshold;

[0143] If the heating load impact index is greater than the first threshold, the heating impact prediction level is level 3 strong impact;

[0144] If the heating load impact index is greater than the second threshold and less than or equal to the first threshold, the heating impact prediction level is a secondary medium impact;

[0145] If the heating load impact index is less than or equal to the second threshold, the heating impact prediction level is a first-level weak impact;

[0146] According to the heating impact prediction level, the preset heating impact level database is queried to obtain the corresponding impact weight coefficient, and the weight impact coefficient includes the weather weight impact coefficient and the date type weight impact coefficient.

[0147] It should be noted that after determining the heating impact prediction level according to the heating load impact index, the impact weight coefficient in the heating management prediction model is determined according to the heating impact prediction level. The first-level weak impact means that the weather data and date type data have a weak impact on the heating, and the impact weight coefficient is small; the second-level medium impact means that the weather data and date type data have a general impact on the heating, and the impact weight coefficient is medium in size; in this embodiment, the heating load impact index threshold is set to: [0,0.35], the heating impact prediction level is the first-level weak impact; (0.35, 0.7], the heating impact prediction level is the second-level medium impact; (0.7, 1]; the heating impact prediction level is the third-level strong impact; when the heating load impact index is 0.9, the heating impact prediction level is the third-level strong impact; the heating impact level database contains the heating impact prediction level, as well as the weather weight impact coefficient and the date type weight impact coefficient corresponding to the heating impact prediction level, and the weather weight impact coefficient and the date type weight impact coefficient correspond to the characteristic coefficient in the heating management prediction model.

[0148] According to an embodiment of the present invention, after obtaining the corresponding valid type heating load historical data according to the predicted date type data, the predicted heating load data of the thermal power station is obtained by processing the heating management prediction model in combination with the influence weight coefficient and the predicted weather data, specifically including:

[0149] According to the prediction date type data, the corresponding effective type heating load historical data is obtained;

[0150] Determine the corresponding characteristic coefficient of the heat supply management prediction model according to the influence weight coefficient, and generate the heat supply management prediction weight model in combination with the characteristic coefficient;

[0151] The predicted weather data and the effective type heating load historical data are input into the heating management prediction weight model for processing to obtain the predicted heating load data of the heating station.

[0152] It should be noted that, after first obtaining the historical data of effective type heating load according to the matching of the forecast date type data, the corresponding characteristic coefficient in the heating management forecast model is determined according to the influence weight coefficient, and then the heating management forecast weight model with determined characteristic coefficient is obtained; the heating management forecast weight model refers to the heating management forecast model with determined characteristic coefficient, and the forecast weather data and the historical data of effective type heating load are input into the heating management forecast model to obtain the forecast heating load data.

[0153] According to an embodiment of the present invention, the heating difference index is obtained according to the predicted heating load data and the preset real-time heating load data, the heating difference index is compared with the preset heating difference index threshold, and the heating adjustment status is obtained and the heating station is adjusted for heating, specifically including:

[0154] Divide the predicted heating load data by the real-time heating load data to obtain a heating difference index;

[0155] Comparing the heating difference index with a preset heating difference index threshold to obtain a heating adjustment status of the heating station;

[0156] Extracting a third threshold and a fourth threshold according to the heating difference index threshold, wherein the third threshold is greater than the fourth threshold;

[0157] comparing the heating difference index with the third threshold and the fourth threshold;

[0158] If the heating difference index is greater than the third threshold, the heating adjustment condition is to increase the heating energy;

[0159] If the heating difference index is greater than the fourth threshold value and less than or equal to the third threshold value, the heating adjustment condition is to maintain the heating energy;

[0160] If the heating difference index is less than or equal to the fourth threshold, the heating adjustment condition is to reduce heating energy.

[0161] It should be noted that if the predicted heating load data is not much different from the real-time heating load data, and is within the preset allowable range, the heating station does not need to be adjusted. Otherwise, it will be adjusted. In order to more intuitively judge whether adjustment is needed, the heating difference index is first calculated. The calculation formula of the heating difference index is:

[0162] ;

[0163] in, is the heating difference index, To predict heating load data, is the real-time heating load data; the heating difference index is compared with the preset heating difference index threshold to obtain the heating adjustment status of the thermal power station; in this example, the third threshold is 0.1 and the fourth threshold is -0.1; that is, when the heating difference index is greater than 0.1, the heating adjustment status is to increase the heating energy; when the heating difference index is greater than -0.1 and less than or equal to 0.1, the heating adjustment status is to maintain the heating energy; when the heating difference index is less than or equal to -0.1, the heating adjustment status is to reduce the heating energy; the specific increase or decrease amount is the absolute value of the predicted heating load data minus the real-time heating load data.

[0164] A third aspect of the present invention provides a readable storage medium, which includes a program for an intelligent prediction method for heat supply management in a thermal power station. When the program for the intelligent prediction method for heat supply management in a thermal power station is executed by a processor, the steps of an intelligent prediction method for heat supply management in a thermal power station as described in any one of the above items are implemented.

[0165] The present invention discloses an intelligent prediction method, system and medium for heat supply management of a thermal power station. The method obtains the historical data of heat supply load, historical weather data and date type data of a preset time period of the thermal power station, and then classifies and calculates to obtain the effective type heat supply load historical data. The heat supply management prediction model is trained according to the effective type heat supply load historical data and historical weather data. The heat supply load impact index is obtained according to the predicted weather data and predicted date type data. The heat supply impact prediction level is obtained through threshold comparison and the influence weight coefficient is obtained through query, and then the predicted heat supply load data of the thermal power station is obtained. Finally, the heat supply adjustment status is obtained through threshold comparison of the heat supply difference index. Thus, the technology of intelligent prediction of heat supply management is realized by processing the effective type heat supply load historical data, the heat supply load impact index, the heat supply impact prediction level and the predicted heat supply load data in combination with the threshold comparison.

[0166] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0167] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0168] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0169] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0170] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. An intelligent prediction method for heat supply management of a thermal power station, characterized in that: include: Obtain historical data of heating load, historical weather data and date type data for a preset time period of the heating station; Classify the heating load historical data according to the date type data to obtain type heating load historical data, and calculate to obtain effective type heating load historical data; A heating management prediction model is obtained by training according to the effective type heating load historical data and historical weather data; Obtain forecast weather data and forecast date type data, and obtain a heating load impact index according to the forecast weather data and forecast date type data; Compare the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and query a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model; After obtaining the corresponding effective type of heating load historical data according to the forecast date type data, the forecast heating load data of the thermal power station is obtained by combining the influence weight coefficient and the forecast weather data through the heat management forecast model; The heating difference index is obtained by processing the predicted heating load data and the preset real-time heating load data, and the heating difference index is compared with the preset heating difference index threshold value. After the heating adjustment status is obtained, the heating station is adjusted for heating; The calculation formula of heating load impact index is: ； in, is the heating load impact index, , , , , They are respectively predicted temperature data, predicted humidity data, predicted wind speed data, predicted sunshine duration data, and predicted date type data. , , , , is the preset characteristic coefficient; The calculation formula of heating difference index is: ； in, is the heating difference index, To predict heating load data, It is real-time heating load data.

2. The intelligent prediction method for heat supply management of a thermal power station according to claim 1 is characterized in that: The obtaining of the heating load historical data, historical weather data and date type data of the preset time period of the thermal power station specifically includes: obtaining the heating load historical data and historical weather data of the preset time period of the thermal power station, the historical weather data including temperature data, humidity data, wind speed data and sunshine duration data; Get the date type data of the preset time period of the thermal power station, including working day data, public holiday data or holiday data.

3. The intelligent prediction method for heat supply management of a thermal power station according to claim 2 is characterized in that: The step of classifying the heating load history data according to the date type data to obtain type heating load history data, and calculating and obtaining effective type heating load history data, specifically includes: classifying the heating load history data according to the date type data to obtain type heating load history data, including working day heating load history data, holiday heating load history data, and holiday heating load history data; According to the working day heating load historical data, the holiday heating load historical data and the holiday heating load historical data, average values ​​are respectively calculated to obtain the effective working day heating load historical data, the effective holiday heating load historical data and the effective holiday heating load historical data.

4. The intelligent prediction method for heat supply management of a thermal power station according to claim 3 is characterized in that: The step of obtaining the forecast weather data and the forecast date type data, and obtaining the heating load impact index according to the forecast weather data and the forecast date type data, specifically includes: obtaining the forecast weather data, including forecast temperature data, forecast humidity data, forecast wind speed data, and forecast sunshine duration data; Get forecast date type data, including forecast working day data, forecast public holiday data or forecast holiday data; The predicted temperature data, predicted humidity data, predicted wind speed data and predicted sunshine duration data are combined with the predicted date type data and processed by a preset heating load impact assessment model to obtain a heating load impact index.

5. The intelligent prediction method for heat supply management of a thermal power station according to claim 4 is characterized in that: The step of comparing the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and querying a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model, specifically includes: comparing the heating load impact index with a heating load impact index threshold to obtain a heating impact prediction level, including a first-level weak impact, a second-level medium impact, or a third-level strong impact; Extracting a first threshold and a second threshold according to the heating load impact index threshold, wherein the first threshold is greater than the second threshold; comparing the heating load impact index with the first threshold and the second threshold; If the heating load impact index is greater than the first threshold, the heating impact prediction level is level 3 strong impact; If the heating load impact index is greater than the second threshold and less than or equal to the first threshold, the heating impact prediction level is a secondary medium impact; If the heating load impact index is less than or equal to the second threshold, the heating impact prediction level is a first-level weak impact; According to the heating impact prediction level, the preset heating impact level database is queried to obtain the corresponding impact weight coefficient, and the weight impact coefficient includes the weather weight impact coefficient and the date type weight impact coefficient.

6. The intelligent prediction method for heat supply management of a thermal power station according to claim 5 is characterized in that: After obtaining the corresponding effective type heating load historical data according to the predicted date type data, the predicted heating load data of the thermal power station is obtained by processing the heating management prediction model in combination with the influence weight coefficient and the predicted weather data, specifically including: obtaining the corresponding effective type heating load historical data according to the predicted date type data; Determine the corresponding characteristic coefficient of the heat supply management prediction model according to the influence weight coefficient, and generate the heat supply management prediction weight model in combination with the characteristic coefficient; The predicted weather data and the effective type heating load historical data are input into the heating management prediction weight model for processing to obtain the predicted heating load data of the heating station.

7. The intelligent prediction method for heat supply management of a thermal power station according to claim 6 is characterized in that: The method of obtaining a heating difference index according to the predicted heating load data and the preset real-time heating load data, comparing the heating difference index with the preset heating difference index threshold, and adjusting the heating of the thermal power station after obtaining the heating adjustment status specifically includes: subtracting the predicted heating load data from the real-time heating load data and dividing the result by the real-time heating load data to obtain the heating difference index; Comparing the heating difference index with a preset heating difference index threshold to obtain a heating adjustment status of the heating station; Extracting a third threshold and a fourth threshold according to the heating difference index threshold, wherein the third threshold is greater than the fourth threshold; comparing the heating difference index with the third threshold and the fourth threshold; If the heating difference index is greater than the third threshold, the heating adjustment condition is to increase the heating energy; If the heating difference index is greater than the fourth threshold value and less than or equal to the third threshold value, the heating adjustment condition is to maintain the heating energy; If the heating difference index is less than or equal to the fourth threshold, the heating adjustment condition is to reduce heating energy.

8. An intelligent prediction system for heat supply management of a thermal power station, characterized in that: The method comprises a memory and a processor, wherein the memory comprises a program of an intelligent prediction method for heat supply management of a heat supply station, and when the program of the intelligent prediction method for heat supply management of a heat supply station is executed by the processor, the following steps are implemented: obtaining historical data of heating load, historical weather data and date type data of a preset time period of the heat supply station; Classify the heating load historical data according to the date type data to obtain type heating load historical data, and calculate to obtain effective type heating load historical data; A heating management prediction model is obtained by training according to the effective type heating load historical data and historical weather data; Obtain forecast weather data and forecast date type data, and obtain a heating load impact index according to the forecast weather data and forecast date type data; Compare the heating load impact index with a preset heating load impact index threshold to obtain a heating impact prediction level, and query a preset heating impact level database according to the heating impact prediction level to obtain a corresponding impact weight coefficient in a heating management prediction model; After obtaining the corresponding effective type of heating load historical data according to the forecast date type data, the forecast heating load data of the thermal power station is obtained by combining the influence weight coefficient and the forecast weather data through the heat management forecast model; The heating difference index is obtained by processing the predicted heating load data and the preset real-time heating load data, and the heating difference index is compared with the preset heating difference index threshold value. After the heating adjustment status is obtained, the heating station is adjusted for heating; The calculation formula of heating load impact index is: ； in, is the heating load impact index, , , , , They are respectively predicted temperature data, predicted humidity data, predicted wind speed data, predicted sunshine duration data, and predicted date type data. , , , , is the preset characteristic coefficient; The calculation formula of heating difference index is: ； in, is the heating difference index, To predict heating load data, It is real-time heating load data.

9. The intelligent prediction system for heat supply management of a thermal power station according to claim 8, characterized in that: The obtaining of the heating load historical data, historical weather data and date type data of the preset time period of the thermal power station specifically includes: obtaining the heating load historical data and historical weather data of the preset time period of the thermal power station, the historical weather data including temperature data, humidity data, wind speed data and sunshine duration data; Get the date type data of the preset time period of the thermal power station, including working day data, public holiday data or holiday data.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a program of an intelligent prediction method for heat supply management of a thermal power station. When the program of an intelligent prediction method for heat supply management of a thermal power station is executed by a processor, the steps of the intelligent prediction method for heat supply management of a thermal power station as described in any one of claims 1 to 7 are implemented.

Images