Building heating load prediction method based on artificial intelligence algorithm

Abstract

The present invention belongs to the field of heating technology, and specifically relates to a method for predicting building heating load based on an artificial intelligence algorithm. The method comprises the following steps: S1. Acquiring weather data and outdoor temperature data; S2. Acquiring indoor temperature data of the user's heating demand; S3. Determining the user's heating unit area heat load index based on the outdoor temperature data and the heating demand indoor temperature data; S4. Determining the heating load corresponding to historical weather data similar to the weather data and the heating effect data on historical weather days similar to the weather data; S5. Comparing the user's required heating data with the heating data on historical weather days similar to the weather data to obtain a first correction coefficient; S6. Determining a deviation auxiliary correction coefficient of the first correction coefficient based on the weather data; S7. Determining the building heating load prediction data based on the user's heating unit area heat load index, the heating load corresponding to historical weather data similar to the weather data, the first correction coefficient, and the deviation auxiliary correction coefficient. The method of the present invention enables intelligent prediction, saves resources, and can also meet customer needs.

Description

Technical Field

[0001] The present invention relates to the field of heating technology, and in particular to a method for predicting building heating load based on an artificial intelligence algorithm. Background Art

[0002] The description of the background technology in the present invention belongs to the related technology related to the present invention and is only used to illustrate and facilitate the understanding of the invention content of the present invention. It should not be understood that the applicant explicitly believes or infers that the applicant believes that it is the prior art of the present invention on the filing date of the first application.

[0003] With the development of society and the improvement of people's living standards, people's requirements for heating are getting higher and higher. However, the current heating generally adopts extensive heating, without clear prediction of the heating load, and adopts manual control. For example, some areas rely entirely on boiler masters to control heating based on rough judgment of the weather or energy budget. Such extensive methods have many defects. For example, in warm weather, it not only wastes resources but also the temperature is too high and the user experience is not good. Moreover, when the weather is cold, the required room temperature cannot be reached, resulting in a very poor user experience, which intensifies the contradiction between users and heating companies.

[0004] It's generally accepted that the typical heating load for residential buildings is 20-30 kWh / m2 / year. This range accounts for variations in different regions and climates. For example, in cold regions or northern cities, where lower winter temperatures require more energy for heating, the heat load may be higher.

[0005] Commercial and office buildings typically have slightly higher heating loads than residential buildings. Depending on their function and usage requirements, commercial and office buildings may have heating demands ranging from 30-50 kWh / m2 / year.

[0006] New Buildings: With increasing energy conservation and environmental protection requirements and the application of new technologies, more and more new buildings are adopting high-efficiency energy-saving technologies and meeting heating needs through the comprehensive utilization of renewable energy sources such as solar energy and ground-source heat pumps. The heat load indicators of these new buildings may be lower, typically between 10-20 kWh / m2 / year. It is important to note that these values ​​are for reference only; actual heating load indicators require detailed calculation and design based on the specific building conditions and local climate conditions.

[0007] Some literature has also conducted research on heating loads. "Civil Heating Radiators" (Tsinghua University Press) mentions that the factors affecting the heating load include the heating area, the heat index per unit area, and the correction coefficient; but the correction coefficient it explains is relatively simple, and different environments and different demands will definitely have different effects on the heating load. There is no single coefficient that can meet the load caused by different demands. Therefore, there is an urgent need for an intelligent heating load prediction method to solve this problem. Summary of the Invention

[0008] The purpose of the embodiment of the present invention is to provide a building heating load prediction method based on an artificial intelligence algorithm. The method of the present invention integrates historical data, customer demand data, weather data and a correction coefficient for the impact of different weather conditions on heating demand, making the heating forecast more intelligent, saving resources while also meeting customer needs.

[0009] The object of the present invention is achieved by the following method:

[0010] A building heating load prediction method based on an artificial intelligence algorithm comprises the following steps:

[0011] S1. Obtain weather data and outdoor temperature data;

[0012] S2. Obtain the user's indoor temperature data for heating demand;

[0013] S3. Determine the user's heating load per unit area based on the outdoor temperature data and the indoor temperature data for heating demand;

[0014] S4. Based on the heating load corresponding to the historical weather data corresponding to the weather data and the heating effect data of the historical weather day corresponding to the weather data;

[0015] S5. Compare the user's required heating data with historical heating data for similar weather days to obtain a first correction coefficient;

[0016] S6. Obtain an auxiliary correction coefficient for deviation of the first correction coefficient according to weather data;

[0017] S7. Obtain building heating load forecast data based on the user's heating unit area heat load index, the heating load corresponding to historical similar weather data, the first correction coefficient, and the deviation auxiliary correction coefficient.

[0018] Furthermore, the calculation method of step S7 is:

[0019]

[0020] Among them, M 预测is the predicted value of the building heating load; K1 is the heat load index coefficient per unit area of ​​the user's heating; q is the heat load index per unit area; S is the heating area; K2 is the heating load coefficient corresponding to historical similar weather data; Q is the heating load corresponding to historical similar weather data; L1 is the first correction coefficient; L2 is the deviation auxiliary correction coefficient.

[0021] Furthermore, the values ​​of K1 and K2 are determined as follows:

[0022] K1+K2=1;

[0023] If the absolute value of F-F0 is less than or equal to 0.3 times F0, then

[0024] If the absolute value of F-F0 is greater than 0.3 times F0, then K2=0.01;

[0025] Among them, F is the historical similar weather data; F0 is the weather data.

[0026] Furthermore, the algorithm of F-F0 is as follows;

[0027] F-F0=∑N(D1-D0) i

[0028] Among them, D0 is the digitally processed data of an indicator in the weather data; D1 is the digitally processed data of an indicator in the historical weather data; N is the weight corresponding to each indicator.

[0029] Furthermore, L2 is determined as follows: weather factors that cause high humidity are defined as positive values, and weather factors that do not cause high humidity are defined as 0.

[0030] Furthermore, users can set temperature requirements according to time periods, and calculate the heating load according to different requirements in different time periods to obtain the total heating load.

[0031] The embodiments of the present invention have the following beneficial effects:

[0032] The method of the present invention integrates historical data, customer demand data, weather data and the correction coefficient of the impact of different weather conditions on heating demand, making the forecast of heating more intelligent, saving resources while meeting customer needs. DETAILED DESCRIPTION

[0033] The present application will be further described below with reference to the embodiments.

[0034] To more clearly illustrate the embodiments of the present invention or technical solutions in the prior art, different "one embodiment" or "embodiment" in the following description do not necessarily refer to the same embodiment. Different embodiments may be replaced or combined. Those skilled in the art can also derive other implementation methods based on these embodiments without inventive effort.

[0035] A building heating load prediction method based on an artificial intelligence algorithm comprises the following steps:

[0036] S1. Obtain weather data and outdoor temperature data;

[0037] S2. Obtain the user's indoor temperature data for heating demand;

[0038] S3. Determine the user's heating load per unit area based on the outdoor temperature data and the indoor temperature data for heating demand;

[0039] S4. Based on the heating load corresponding to the historical weather data corresponding to the weather data and the heating effect data of the historical weather day corresponding to the weather data;

[0040] S5. Compare the user's required heating data with historical heating data for similar weather days to obtain a first correction coefficient;

[0041] S6. Obtain an auxiliary correction coefficient for deviation of the first correction coefficient according to weather data;

[0042] S7. Obtain building heating load forecast data based on the user's heating unit area heat load index, the heating load corresponding to historical similar weather data, the first correction coefficient, and the deviation auxiliary correction coefficient.

[0043] The method of the present invention integrates historical data, customer demand data, weather data and the correction coefficient of the impact of different weather conditions on heating demand, making the forecast of heating more intelligent, saving resources while meeting customer needs.

[0044] In some embodiments, the calculation method of step S7. is:

[0045]

[0046] Among them, M 预测 is the predicted value of the building heating load; K1 is the heat load index coefficient per unit area of ​​the user's heating; q is the heat load index per unit area; S is the heating area; K2 is the heating load coefficient corresponding to historical similar weather data; Q is the heating load corresponding to historical similar weather data; L1 is the first correction coefficient; L2 is the deviation auxiliary correction coefficient.

[0047] The calculation method in the above embodiment is explained as follows: The product of qS can be used to calculate the heating load obtained based on the indoor and outdoor temperature data. However, this is only a crude and simple calculation method and only provides a general data range for determining the heating load. It is allocated to the actual heating load generated under historically similar weather conditions through different coefficients to achieve a heating load determined by combining the previous actual heating load with the heating load predicted by the existing weather data. However, these two data are obviously inaccurate and require some correction. Although K2 is calculated based on the deviation between historically similar weather data and weather data (the specific calculation method will be discussed later), the applicant found that even with this correction alone, the calculated heating load still has a certain gap with the actual heating load. After extensive research and practice, the applicant determined that a coefficient correction should be applied to the heating load on days with historically similar weather conditions. L1 is the absolute value of the ratio of the weather data on the historically similar weather day to the weather data on the current day. The problem here is that if this simple calculation correction is not satisfactory, the applicant has further corrected the first correction coefficient. The method for determining this auxiliary correction is described in detail later and will not be repeated here.

[0048] In some embodiments of the present invention, the values ​​of K1 and K2 are determined as follows:

[0049] K1+K2=1;

[0050] If the absolute value of F-F0 is less than or equal to 0.3 times F0, then

[0051] If the absolute value of F-F0 is greater than 0.3 times F0, then K2=0.01;

[0052] Among them, F is the historical similar weather data; F0 is the weather data.

[0053] Furthermore, the algorithm of F-F0 is as follows;

[0054] F-F0=∑N(D1-D0) i

[0055] Among them, D0 is the digitally processed data of an indicator in the weather data; D1 is the digitally processed data of an indicator in the historical weather data; N is the weight corresponding to each indicator.

[0056] In order to facilitate understanding of the purpose of the design of this calculation method, the following detailed explanation is given here: Weather data contains multiple data, such as cloudy, rainy, snowy, ultraviolet, light intensity and wind speed, etc. Each heating company here can determine it according to its own situation and actual heating situation, as long as the sum of each weight is reasonable and the weight item is an important factor affecting heating. Each region is different. For example, in the Northeast, there is more snow, which will obviously affect the heating effect, and its weight must be larger. In North China, there is less snow in winter and it will not accumulate for a long time, so the impact it causes is smaller, and its weight can be appropriately reduced. The applicant will not go into details here.

[0057] In some embodiments, L2 is determined as follows: weather factors that cause high humidity are defined as positive values, and weather factors that do not cause high humidity are defined as 0. It is understood that high humidity will affect the perceived temperature. For example, even if the heating temperature is always 22 degrees, the indoor temperature will also feel colder in cold and humid weather. In this case, the heating supply should be appropriately increased, which will increase the heating load. On sunny days, the indoor temperature will feel comfortable, and this correction factor can be set to 0.

[0058] In other embodiments, users can set temperature requirements according to time periods, calculate the heating load according to different requirements for different time periods, and obtain the total heating load. It is understandable that each family has different household conditions and different heat requirements, which all lead to different requirements. In the past, heating was all unified heating parameters, which users could not adjust themselves, resulting in a very poor experience. This application takes this into consideration. For example, if the user goes out to work during the day and no one is at home most of the time, the heating can be automatically reduced appropriately. At night, when the heating requirements are higher, the temperature can be set to be appropriately increased. It should be understood that the premise of this method should be that heating is charged according to volume, which is conducive to customers setting it according to their own needs, and can also reduce operating costs while saving resources without reducing the heating experience. It is intelligent and uses different heating methods for different users in different time periods according to needs, without wasting resources.

[0059] It should be noted that the above embodiments can be freely combined as needed. The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A building heating load prediction method based on artificial intelligence algorithm, characterized in that: The steps include: S1. Obtain weather data and outdoor temperature data; S2. Obtain the user's indoor temperature data for heating demand; S3. Determine the user's heating load per unit area based on the outdoor temperature data and the indoor temperature data for heating demand; S4. Based on the heating load corresponding to the historical weather data corresponding to the weather data and the heating effect data of the historical weather day corresponding to the weather data; S5. Compare the user's required heating data with historical heating data for similar weather days to obtain a first correction coefficient; S6. Obtain an auxiliary correction coefficient for deviation of the first correction coefficient according to weather data; S7. Obtain building heating load forecast data based on the user's heating load per unit area index, the heating load corresponding to historical similar weather data, the first correction coefficient, and the deviation auxiliary correction coefficient; The calculation method of step S7. is: ； in, is the predicted value of building heating load; K1 is the heat load index coefficient per unit area of ​​user heating; is the heat load index per unit area; S is the heating area; K2 is the heating load coefficient corresponding to historical similar weather data; Q is the heating load corresponding to historical similar weather data; is the first correction coefficient; L2 is the deviation auxiliary correction coefficient; The values ​​of K1 and K2 are determined as follows: K1+K2=1; like The absolute value of is less than or equal to 0.3 times, then ; like The absolute value of 0.3 times, then =0.01; Among them, F is the historical similar weather data; For weather data; F- The algorithm is as follows; = ； Among them, D0 is the digitally processed data of an indicator in the weather data; D1 is the digitally processed data of an indicator in the historical weather data; N is the weight corresponding to each indicator.

2. The method for predicting building heating load based on artificial intelligence algorithm according to claim 1 is characterized in that: L2 is determined as follows: weather factors that cause high humidity are defined as positive values, and weather factors that do not cause high humidity are defined as 0.

3. The building heating load prediction method based on artificial intelligence algorithm according to claim 1 is characterized in that: Users can set temperature requirements according to time periods, and calculate the heating load according to different requirements in different time periods to obtain the total heating load.

Images