Continuous optimization heat supply load prediction method and system based on big data analysis learning

Abstract

The invention relates to the field of heat supply heat load operation adjustment, and provides a continuous optimization heat supply load prediction method and system based on big data analysis learning, and the method comprises the steps: S1, configuring a data interface on a real-time library service module to receive real-time and historical operation data, the operation data comprises meteorological information data, heat exchange station heat load and room temperature qualification rate; and S2, preprocessing the collected operation data through a data processing module integrated on the heat supply platform service module, and analyzing the preprocessed operation data through an analysis algorithm stored in a relation module to determine a predicted heat load value of a next control period. The heat supply platform is combined, the big data analysis technology is used for learning and analyzing historical heat supply network operation data, proper correction and adjustment are carried out, the heat load of the heat supply system is effectively predicted, the method is closely combined with actual operation, prediction accuracy is remarkably improved, the operation process is simplified, energy use is optimized, and the operation efficiency and the system response speed are improved.

Description

Technical Field

[0001] The present invention relates to the field of heating thermal load operation regulation, and in particular to a method and system for continuously optimizing heating load prediction based on big data analysis and learning. Background Art

[0002] The prediction of heat load of heating system is an important part of heating system planning and the basis of its economical and efficient operation. Accurate prediction of heat load can provide strong data support for the operation and management of heating system, thus reasonably guiding the operation and regulation management. Current prediction technology mainly relies on complex mathematical models and formulas. Although these methods are feasible in theory, in practical applications, due to the complexity of the model and the delay in responding to external variables, the prediction is often not accurate or the scope of application is limited. Therefore, it is particularly important to develop a prediction method that is both accurate and easy to implement. Summary of the invention

[0003] In view of the above problems, the present invention proposes a method and system for continuously optimizing heating load prediction based on big data analysis and learning. By comprehensively utilizing historical and real-time meteorological data, heating system performance data, and user demand changes, dynamic prediction and real-time adjustment of heating load are achieved, solving the problems of high complexity, insufficient prediction accuracy, and poor practicality in existing heat load prediction methods. The above invention object of the present invention is achieved through the following technical solutions: The present invention provides a method for continuously optimizing heating load prediction based on big data analysis and learning, comprising: Step S1: configuring a data interface on the real-time library service module to receive real-time and historical operation data, the operation data including meteorological information data, heat load of the heat exchange station and room temperature qualification rate; Step S2: pre-processing the collected operation data through the data processing module integrated in the heating platform service module, and analyzing the pre-processed operation data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle; Among them, the pre-processed operating data is analyzed by the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle, including, based on the real-time collected operating data, statistics of the corrected converted comprehensive outdoor temperature, heat exchange station heat load and room temperature qualification rate under different meteorological information; based on different meteorological information and converted comprehensive outdoor temperature, the next control cycle searches and locates the weather category, and adopts the principle of minimum converted comprehensive outdoor temperature difference to find similar meteorological information conditions to obtain the corresponding predicted heat load value.

[0004] Furthermore, in step S2, the operation data is preprocessed by the data processing module integrated in the heating platform service module, including validity processing of the operation data, including removing the operation data within a preset time after the operation adjustment of the heating network, and standardizing, detecting outliers and cleaning the operation data.

[0005] Furthermore, in step S2, based on the real-time collected operating data, the corrected converted comprehensive outdoor temperature, heat load of the heat exchange station and room temperature pass rate under different meteorological information are counted, including real-time statistics of heat load of the heat exchange station and room temperature pass rate under different meteorological information, and calculating the converted comprehensive outdoor temperature through a conversion correction algorithm, wherein the meteorological information includes weather type, temperature and wind speed.

[0006] Furthermore, in step S2, the conversion correction algorithm is: When the current wind speed is lower than the baseline wind speed, the comprehensive outdoor temperature T is converted to the actual outdoor temperature t; When the current wind speed is between the baseline wind speed and the increasing wind speed threshold, the calculation formula for the converted comprehensive outdoor temperature T is: ;in, is the baseline wind speed, v is the current wind speed; When the current wind speed reaches the increasing wind speed threshold but does not exceed the medium wind speed threshold, the calculation formula for the converted comprehensive outdoor temperature T is: ,in, is the increasing wind speed threshold, b is the basic adjustment value, c and d are the relevant adjustment coefficients of wind speed increment; When the current wind speed exceeds the medium wind speed threshold and reaches high wind speed, the calculation formula for converting the comprehensive outdoor temperature T is: , k is the preset fixed reduction value for high wind speed.

[0007] Further, in step S2, based on different meteorological information and the converted comprehensive outdoor temperature, the next control cycle searches for similar meteorological information conditions based on the search and positioning weather category, and adopts the principle of minimum converted comprehensive outdoor temperature difference to obtain the corresponding predicted heat load value, including: Set an expected value of the room temperature pass rate to evaluate whether the heating effect of the current heat exchange station meets expectations; The judgment is made based on the room temperature qualification rate under the same meteorological information conditions; When the room temperature pass rate reaches or exceeds the expected value, the predicted heat load is set to the historical heat exchange station heat load under similar meteorological information conditions; When the room temperature pass rate does not reach the expected value, the predicted heat load is set to the heat load of the heat exchange station under similar meteorological information conditions plus an adjustment value β, and the adjustment value β is the heat load used for adjustment when the room temperature pass rate exceeds the expected value.

[0008] Furthermore, similar meteorological information conditions refer to the historical heat load of the heat exchange station with the smallest comprehensive outdoor temperature difference under the same weather type.

[0009] Furthermore, it also includes step S3: sending the predicted heat load value to the heating control system as a basis for heating load regulation; at the same time, the heating control system adjusts the operating parameters of the heat exchange station according to the received predicted heat load value and feeds back the operating data to the real-time library service module.

[0010] Based on the same inventive concept, the present invention also provides a continuous optimization heating load prediction system based on big data analysis and learning, which adopts the continuous optimization heating load prediction method as mentioned above, including: The real-time library service module is used to configure the data interface to receive real-time and historical operation data, including meteorological information data, heat load of the heat exchange station, and room temperature qualification rate; A relation module for storing an analysis algorithm for analyzing the preprocessed operation data; The data processing module is used to pre-process the collected operating data, and analyze the pre-processed operating data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle; wherein, the pre-processed operating data is analyzed through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle, including, based on the real-time collected operating data, statistics of the corrected converted comprehensive outdoor temperature, heat exchange station heat load and room temperature qualification rate under different meteorological information; based on different meteorological information and converted comprehensive outdoor temperature, the next control cycle searches for the weather category according to the minimum converted comprehensive outdoor temperature difference principle to find similar meteorological information conditions to obtain the corresponding predicted heat load value.

[0011] Furthermore, the data processing module includes: A data preprocessing unit is used to process the operation data for validity, including removing the operation data within a preset time after the operation adjustment of the heating network, and standardizing, detecting and cleaning the operation data for abnormal values; A data statistics unit is used for collecting operation data in real time, and counting the corrected converted comprehensive outdoor temperature, heat load of the heat exchange station and qualified rate of room temperature under different meteorological information, further including real-time counting of heat load of the heat exchange station and qualified rate of room temperature under different meteorological information, and calculating the converted comprehensive outdoor temperature through a conversion correction algorithm, wherein the meteorological information includes weather type, temperature and wind speed; The data analysis unit is used to set an expected value of the room temperature pass rate, which is used to evaluate whether the heating effect of the current heat exchange station meets expectations; the judgment is made based on the room temperature pass rate under the same meteorological information conditions; when the room temperature pass rate reaches or exceeds the expected value, the predicted heat load is set to the historical heat exchange station heat load under similar meteorological information conditions; when the room temperature pass rate does not reach the expected value, the predicted heat load is set to the heat load of the heat exchange station under similar meteorological information conditions plus an adjustment value β, and the adjustment value β is the heat load used to adjust when the room temperature pass rate exceeds the expected value.

[0012] Furthermore, it also includes a data feedback module, which is used to send the predicted heat load value to the heating control system as a basis for heating load regulation; at the same time, the heating control system adjusts the operating parameters of the heat exchange station according to the received predicted heat load value and feeds back the operating data to the real-time library service module.

[0013] Compared with the prior art, the present invention has at least one of the following beneficial effects: The present invention combines the heating platform, uses big data analysis technology to learn and analyze historical heating network operation data, and makes appropriate corrections and adjustments to effectively predict the heat load of the heating system, which is closely integrated with actual operations. Its ideas are novel and simple, and its practicality is strong. It significantly improves the prediction accuracy, simplifies the operation process and optimizes energy use, thereby improving the operation efficiency and system response speed. (1) The big data analysis learning method is used to predict the heating load. Compared with traditional mathematical models or statistical methods, it can more accurately process and analyze complex data and improve the accuracy of prediction. This method can better adapt to environmental changes and dynamic changes in user needs. (2) It realizes real-time prediction of heating load, can quickly respond to external meteorological changes and changes in internal load demand, and timely adjust heating parameters to ensure efficient operation of the heating system. At the same time, accurate load prediction helps to reasonably arrange the output of heat sources, avoid the problem of overheating or insufficient heating, and reduce energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flowchart of the steps of the method for continuously optimizing heating load prediction based on big data analysis and learning of the present invention; Figure 2 This is a system schematic diagram of the continuous optimization heating load prediction system based on big data analysis and learning of the present invention; Figure 3 The statistical table of heat load and room temperature qualification rate of the heat exchange station under different meteorological information in the embodiment of the present invention; Figure 4 This is a table of learning rules for data statistical analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution 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 part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0017] First embodiment In modern heating systems, heat load forecasting is one of the key technologies to ensure the economic and efficient operation of the system. Accurate heat load forecasting can help operators optimize heating plans and regulation strategies, thereby minimizing energy consumption and maximizing user comfort. However, the heat load forecasting methods currently used are mainly based on traditional mathematical modeling techniques, including but not limited to linear regression models, time series analysis, and complex artificial neural networks. Although these methods provide solutions to a certain extent, they also have many limitations. Specifically, the existing heat load forecasting technology for heating systems mainly relies on complex mathematical models, which not only increases the difficulty of operation and limits the use of non-professionals, but also often cannot accurately adapt to rapidly changing meteorological conditions and user needs due to the lack of versatility and adaptability of the models, resulting in low prediction accuracy. In addition, these technologies fail to effectively utilize a large amount of real-time data generated, so that the potential value of data resources is not fully explored, thereby affecting the practicality and market adaptability of the technology. Therefore, it is necessary to develop a new forecasting method to solve these problems of existing methods and provide a more efficient, accurate and user-friendly heat load forecasting solution.

[0018] Based on this, the inventor, based on in-depth thinking and analysis of the defects of the existing technology, came up with the idea of ​​solving these problems by combining the heating information operation and management platform and adopting big data analysis technology. This method can make full use of historical and real-time data, learn the patterns in the data and make appropriate corrections and adjustments, which not only simplifies the operation process and improves the real-time and accuracy of the prediction, but also enhances the adaptability and practicality of the system, thereby more effectively supporting the economic and efficient operation of the heating system. The specific implementation methods are as follows: like Figure 1As shown, the present invention provides a method for continuously optimizing heating load prediction based on big data analysis and learning, comprising: Step S1: configuring a data interface on the real-time library service module to receive real-time and historical operation data, i.e., historical heating system data source, the operation data including meteorological information data, heat load of the heat exchange station, and room temperature qualification rate; Step S2: pre-processing the collected operation data through the data processing module integrated in the heating platform service module, and analyzing the pre-processed operation data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle; Among them, the pre-processed operating data is analyzed by the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle, including, based on the real-time collected operating data, statistics of the corrected converted comprehensive outdoor temperature, heat exchange station heat load and room temperature qualification rate under different meteorological information; based on different meteorological information and converted comprehensive outdoor temperature, the next control cycle searches and locates the weather category, and adopts the principle of minimum converted comprehensive outdoor temperature difference to find similar meteorological information conditions to obtain the corresponding predicted heat load value.

[0019] Among them, in step S2, the operation data is preprocessed by the data processing module integrated in the heating platform service module, including validity processing of the operation data, including removing the operation data within a preset time after the operation adjustment of the heating network, and standardizing, detecting outliers and cleaning the operation data.

[0020] Specifically, the data processing module integrated in the heating platform service module realizes the validity processing of the operating data source. Due to the lag of the heating system, the data within 2 hours after the heating network operation adjusts the heat load is removed to ensure that the heating network is stable. The specific operation method includes time window filtering of the data. By setting a specific time window, such as removing the data within 2 hours after the adjustment, the data used for analysis and prediction is more representative and stable.

[0021] At the same time, in step S2, based on the real-time collected operation data, the corrected converted comprehensive outdoor temperature, heat load of the heat exchange station and room temperature qualified rate under different meteorological information are counted, including real-time statistics of heat load and room temperature qualified rate of the heat exchange station under different meteorological information, and calculating the converted comprehensive outdoor temperature through a conversion correction algorithm, wherein the meteorological information includes weather type, temperature and wind speed, and the converted comprehensive outdoor temperature is to convert the wind force, an important influencing factor of the heat load, into the outdoor temperature through certain reasonable rules, and the conversion correction algorithm is: ①When the current wind speed is lower than the baseline wind speed, the comprehensive outdoor temperature T is converted to the actual outdoor temperature t; ②When the current wind speed is between the baseline wind speed and the increasing wind speed threshold, the calculation formula for the converted comprehensive outdoor temperature T is: ;in, is the baseline wind speed, v is the current wind speed; ③When the current wind speed reaches the increasing wind speed threshold but does not exceed the medium wind speed threshold, the calculation formula for converting the comprehensive outdoor temperature T is: ,in, is the increasing wind speed threshold, b is the basic adjustment value, c and d are the relevant adjustment coefficients of wind speed increment; ④ When the current wind speed exceeds the medium wind speed threshold and reaches high wind speed, the calculation formula for converting the comprehensive outdoor temperature T is: , k is the preset fixed reduction value for high wind speed.

[0022] Specifically, if Figure 3 As shown, the heat load and room temperature qualification rate of the heat exchange station under different meteorological information are counted, including weather such as sunny, cloudy, rainy and snowy days, room temperature t, wind force or wind speed v, converted comprehensive outdoor temperature T, heat load Q of the heat exchange station and room temperature qualification rate G; according to the above correction algorithm, for example: Wherein, t is the outside temperature, v is the wind speed, and T is the converted comprehensive outdoor temperature.

[0023] As shown in the formula, when the wind speed , within this baseline wind speed range, the wind has little effect on the perceived temperature, so no adjustment is made to the raw temperature t; In this increasing wind speed range, as the wind speed increases, it has a moderate effect on the perceived temperature. Therefore, v-2 in the formula represents the direct linear negative effect of the wind speed exceeding 2m / s on the temperature; when the wind speed In this medium wind speed range, the wind speed has a more significant effect on the perceived temperature, so the adjustment formula includes not only a basic adjustment value of 3, but also a growth factor ,Right now , where v-5 represents the part exceeding 5m / s, and 0.2 is an empirical coefficient, which expresses the trend of increasing wind speed affecting temperature. When the wind speed is high, the high wind speed preset fixed impairment value is directly subtracted from the temperature.

[0024] Further, in step S2, based on different meteorological information and the converted comprehensive outdoor temperature, the next control cycle searches for similar meteorological information conditions based on the search and positioning weather category, and adopts the principle of minimum converted comprehensive outdoor temperature difference to obtain the corresponding predicted heat load value, including: Set an expected value of the room temperature pass rate to evaluate whether the heating effect of the current heat exchange station meets expectations; The judgment is made based on the room temperature qualification rate under the same meteorological information conditions; When the room temperature pass rate reaches or exceeds the expected value, the predicted heat load is set to the historical heat exchange station heat load under similar meteorological information conditions; when the room temperature pass rate does not reach the expected value, the predicted heat load is set to the heat exchange station heat load under similar meteorological information conditions plus an adjustment value β, which is the heat load used for adjustment when the room temperature pass rate exceeds the expected value. Among them, similar meteorological information conditions refer to the historical heat exchange station heat load with the smallest comprehensive outdoor temperature difference under the same weather type. Specifically, if Figure 4 As shown in the figure, if the room temperature qualification rate G is greater than or equal to 95%, the predicted heat load under the same conditions in the next cycle is assigned to Q; if G is less than 95%, the predicted heat load under the same conditions in the next cycle is assigned to Q+β, where β is an adjustment value determined by the operator based on the room temperature qualification rate and experience, and the setting range of β is 1%-5% of the heat load. In addition, considering factors such as the particle and accuracy of meteorological forecasts, the thermal after-effect of the heat exchange station pipe network, etc., different cycles of various learning rules of 1h, 2h and 4h are set, and learning knowledge bases corresponding to 0.5h, 1h, 2h and 4h are established. In addition, the learning prediction searches the data statistics learning rule table based on the weather and the converted comprehensive outdoor temperature in the next cycle to obtain the predicted heat load. At the same time, based on the predicted load obtained by the learning algorithm of the heating operation management platform, it is linked with the heating control system (DCS / PLC), and the predicted data is sent to the control system to provide a basis for adjusting the load output of the heat exchange station, and the operation data is collected and obtained in real time, and the learning algorithm knowledge base is continuously enriched and improved to provide a guarantee for improving the prediction and providing accurate optimal operation load. By comparing and analyzing the predicted heat load operation effects of the learning algorithms under different cycles, we can obtain the analytical learning prediction algorithm that meets the property conditions of the environmental object, and then continue to learn and improve the knowledge base and guide the control optimization operation of the heat exchange station.

[0025] Furthermore, it also includes step S3: sending the predicted heat load value to the heating control system as a basis for heating load regulation; at the same time, the heating control system adjusts the operating parameters of the heat exchange station according to the received predicted heat load value and feeds back the operating data to the real-time library service module.

[0026] In summary, the heating load prediction method based on big data analysis and learning proposed in the present invention shows significant advantages and improvements compared with the existing technology. First, the method integrates the rich data resources collected by the heating platform system and uses advanced big data analysis technology to realize dynamic prediction and real-time adjustment of the heat load, simplify the operation process, and improve the practicality and applicability of the method. Secondly, the present invention uses the room temperature qualification rate, a key heating effect indicator, as the basis for heat load correction, which enhances the reliability of the prediction and allows the system to make online corrections based on real-time data, so as to adapt to actual operating conditions more accurately. Finally, with the accumulation and analysis of more and more data, the present invention can continuously optimize the prediction model, improve the accuracy of heat load prediction, and ensure the efficiency and economy of the operation of the heating system. Therefore, the present invention is not only technologically advanced, but also in line with the trend of modern heating systems towards intelligent and data-driven management, and has broad application prospects and practical value.

[0027] Second embodiment Based on the same inventive concept, Figure 2 As shown, the present invention also provides a continuous optimization heating load prediction system based on big data analysis and learning, and the hardware system implemented by the system consists of: a heating platform, a real-time module, and a relationship module. Among them, the real-time library module is used for real-time data storage and docking with historical data sources, including meteorological information data, heat load data, room temperature pass rate and other data; the relationship library module is used to store parameter relationship information and statistical learning tables; the heating platform is the core of the big data analysis and learning prediction method, and has built-in rules, methods and programs for data processing, analysis and load prediction. The continuous optimization heating load prediction method as described above is adopted, including, The real-time library service module is used to configure the data interface to receive real-time and historical operation data, including meteorological information data, heat load of the heat exchange station, and room temperature qualification rate; A relation module for storing an analysis algorithm for analyzing the preprocessed operation data; The data processing module is used to pre-process the collected operating data, and analyze the pre-processed operating data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle; wherein, the pre-processed operating data is analyzed through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle, including, based on the real-time collected operating data, statistics of the corrected converted comprehensive outdoor temperature, heat exchange station heat load and room temperature qualification rate under different meteorological information; based on different meteorological information and converted comprehensive outdoor temperature, the next control cycle searches for the weather category according to the minimum converted comprehensive outdoor temperature difference principle to find similar meteorological information conditions to obtain the corresponding predicted heat load value.

[0028] Furthermore, the data processing module includes: A data preprocessing unit is used to process the operation data for validity, including removing the operation data within a preset time after the operation adjustment of the heating network, and standardizing, detecting and cleaning the operation data for abnormal values; A data statistics unit is used for collecting operation data in real time, and counting the corrected converted comprehensive outdoor temperature, heat load of the heat exchange station and qualified rate of room temperature under different meteorological information, further including real-time counting of heat load of the heat exchange station and qualified rate of room temperature under different meteorological information, and calculating the converted comprehensive outdoor temperature through a conversion correction algorithm, wherein the meteorological information includes weather type, temperature and wind speed; The data analysis unit is used to set an expected value of the room temperature pass rate, which is used to evaluate whether the heating effect of the current heat exchange station meets expectations; the judgment is made based on the room temperature pass rate under the same meteorological information conditions; when the room temperature pass rate reaches or exceeds the expected value, the predicted heat load is set to the historical heat exchange station heat load under similar meteorological information conditions; when the room temperature pass rate does not reach the expected value, the predicted heat load is set to the heat load of the heat exchange station under similar meteorological information conditions plus an adjustment value β, and the adjustment value β is the heat load used to adjust when the room temperature pass rate exceeds the expected value.

[0029] Furthermore, it also includes a data feedback module, which is used to send the predicted heat load value to the heating control system as a basis for heating load regulation; at the same time, the heating control system adjusts the operating parameters of the heat exchange station according to the received predicted heat load value and feeds back the operating data to the real-time library service module.

[0030] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

[0031] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

Claims

1. A method for continuously optimizing heating load prediction based on big data analysis and learning, characterized in that: include, Step S1: configuring a data interface on the real-time library service module to receive real-time and historical operation data, wherein the operation data includes meteorological information data, heat load of the heat exchange station, and room temperature qualification rate; Step S2: pre-processing the collected operation data through the data processing module integrated in the heating platform service module, and analyzing the pre-processed operation data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle; Among them, the analysis algorithm stored in the relationship module is used to analyze the pre-processed operating data to determine the predicted heat load value of the next control cycle, including, based on the operating data collected in real time, statistics of the corrected converted comprehensive outdoor temperature, the heat load of the heat exchange station and the room temperature pass rate under different meteorological information; based on the different meteorological information and the converted comprehensive outdoor temperature, the next control cycle is based on the search and positioning weather category, and the principle of the minimum converted comprehensive outdoor temperature difference is adopted to find similar meteorological information conditions to obtain the corresponding predicted heat load value.

2. The method for continuously optimizing heating load prediction according to claim 1, characterized in that: In step S2, the operating data is preprocessed by the data processing module integrated on the heating platform service module, further including validity processing of the operating data, including removing the operating data within a preset time after the heating network operation is adjusted, and standardizing, detecting outliers and cleaning the operating data.

3. The method for continuously optimizing heating load prediction according to claim 1, characterized in that: In step S2, based on the operating data collected in real time, the corrected converted comprehensive outdoor temperature, the heat load of the heat exchange station and the room temperature pass rate under different meteorological information are counted, further including real-time statistics of the heat load of the heat exchange station and the room temperature pass rate under different meteorological information, and calculating the converted comprehensive outdoor temperature through a conversion correction algorithm, wherein the meteorological information includes weather type, temperature and wind speed.

4. The method for continuously optimizing heating load prediction according to claim 3 is characterized in that: In step S2, the conversion correction algorithm is: When the current wind speed is lower than the baseline wind speed, the converted comprehensive outdoor temperature T is the actual outdoor temperature t; When the current wind speed is between the baseline wind speed and the increasing wind speed threshold, the calculation formula for the converted comprehensive outdoor temperature T is: ; wherein said is the baseline wind speed, and v is the current wind speed; When the current wind speed reaches the increasing wind speed threshold but does not exceed the medium wind speed threshold, the calculation formula for the converted comprehensive outdoor temperature T is, , Among them, the is the increasing wind speed threshold, b is the basic adjustment value, c and d are the relevant adjustment coefficients of the wind speed increment; When the current wind speed exceeds the medium wind speed threshold and reaches a high wind speed, the calculation formula for converting the comprehensive outdoor temperature T is: , k is the preset fixed reduction value for high wind speed.

5. The method for continuously optimizing heating load prediction according to claim 4, characterized in that: In step S2, based on the different meteorological information and the converted comprehensive outdoor temperature, the next control cycle searches for similar meteorological information conditions according to the search and positioning weather category and adopts the principle of minimum converted comprehensive outdoor temperature difference to obtain the corresponding predicted heat load value, further including: An expected value of the room temperature pass rate is set to evaluate whether the heating effect of the current heat exchange station meets expectations; The judgment is made based on the room temperature pass rate under the same meteorological information conditions; When the room temperature pass rate reaches or exceeds the expected value, the predicted heat load is set to the historical heat exchange station heat load under similar meteorological information conditions; When the room temperature pass rate does not reach the expected value, the predicted heat load is set to the heat load of the heat exchange station under the similar meteorological information conditions plus an adjustment value β, and the adjustment value β is the heat load used for adjustment when the room temperature pass rate exceeds the expected value.

6. The method for continuously optimizing heating load prediction according to claim 5, characterized in that: The similar meteorological information condition is the historical heat exchange station heat load with the smallest converted comprehensive outdoor temperature difference under the same weather type.

7. The method for continuously optimizing heating load prediction according to claim 6, characterized in that: It also includes step S3: sending the predicted heat load value to the heating control system as a basis for heating load regulation; at the same time, the heating control system adjusts the operating parameters of the heat exchange station according to the received predicted heat load value and feeds back the operating data to the real-time library service module.

8. A continuous optimization heating load prediction system based on big data analysis and learning, using the continuous optimization heating load prediction method according to any one of claims 1 to 7, characterized in that: include, A real-time library service module is used to configure a data interface to receive real-time and historical operation data, wherein the operation data includes meteorological information data, heat load of the heat exchange station, and room temperature qualification rate; A relationship module, used for storing an analysis algorithm for analyzing the pre-processed operation data; A data processing module is used to pre-process the collected operating data, and analyze the pre-processed operating data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle; wherein, the analysis of the pre-processed operating data through the analysis algorithm stored in the relationship module to determine the predicted heat load value of the next control cycle includes, based on the operating data collected in real time, statistics on the corrected converted comprehensive outdoor temperature, the heat load of the heat exchange station and the room temperature pass rate under different meteorological information; based on the different meteorological information and the converted comprehensive outdoor temperature, the next control cycle is based on the search and positioning weather category, and adopts the principle of the minimum converted comprehensive outdoor temperature difference to find similar meteorological information conditions to obtain the corresponding predicted heat load value.

9. The continuous optimization heating load prediction system according to claim 8, characterized in that: The data processing module comprises: A data preprocessing unit, used for performing validity processing on the operation data, including removing the operation data within a preset time after the operation adjustment of the heating network, and performing standardization, abnormal value detection and cleaning on the operation data; A data statistics unit is used for collecting the operating data in real time, and counting the corrected converted comprehensive outdoor temperature, the heat load of the heat exchange station and the qualified rate of the room temperature under different meteorological information, further comprising: counting the heat load of the heat exchange station and the qualified rate of the room temperature under different meteorological information in real time, and calculating the converted comprehensive outdoor temperature through a conversion correction algorithm, wherein the meteorological information includes weather type, temperature and wind speed; The data analysis unit is used to set an expected value of the room temperature pass rate, which is used to evaluate whether the heating effect of the current heat exchange station meets expectations; the judgment is made based on the room temperature pass rate under the same meteorological information conditions; when the room temperature pass rate reaches or exceeds the expected value, the predicted heat load is set to the historical heat exchange station heat load under similar meteorological information conditions; when the room temperature pass rate does not reach the expected value, the predicted heat load is set to the heat load of the heat exchange station under the similar meteorological information conditions plus an adjustment value β, and the adjustment value β is the heat load used to adjust when the room temperature pass rate exceeds the expected value.

10. The continuous optimization heating load forecasting system according to claim 9, characterized in that: It also includes a data feedback module, which is used to send the predicted heat load value to the heating control system as a basis for heating load regulation; at the same time, the heating control system adjusts the operating parameters of the heat exchange station according to the received predicted heat load value and feeds back the operating data to the real-time library service module.

Images