Heating demand prediction method and system based on big data acquisition

Abstract

The invention discloses a heat supply demand prediction method and system based on big data acquisition, and relates to the technical field of heat supply demand prediction, and the method comprises the steps: marking urban heat supply monitoring temperature-sensitive organisms based on correlation analysis between biological characteristic data of various urban temperature-sensitive organisms and temperature changes; building characteristic data of different areas and traffic data of different time areas are utilized to perform correlation analysis with heating records of different areas at different time, and a correlation model of building-traffic characteristics and heating demands is established; a hybrid prediction model is constructed in combination with the association between the characteristic change of the urban heating monitoring temperature-sensitive organisms and the building-traffic characteristics; and taking the biological characteristic data of the urban heating monitoring temperature-sensitive organisms in different areas as the input of the hybrid prediction model, and outputting to obtain heating demand prediction values in different areas. The prediction accuracy and the resource utilization efficiency are both improved, and scientific and dynamic decision support is provided for urban heating management.

Description

Technical Field

[0001] The present invention relates to the technical field of heating demand prediction, and in particular to a method and system for predicting heating demand based on big data collection. Background Art

[0002] With the acceleration of urbanization and the improvement of people's living standards, urban heating demand continues to grow, and energy consumption has also increased significantly. Traditional heating systems mostly adopt extensive operation modes and lack accurate heating demand forecasts, resulting in serious energy waste and high heating costs. At the same time, global climate change and frequent extreme weather have made the factors affecting heating demand more complex and changeable. In addition, there is a close connection between the urban ecological environment and heating demand, but previous research and practice have often ignored the potential indicative role of urban organisms on heating demand.

[0003] Traditional heating demand forecasting methods only consider meteorological data and historical heating data, ignoring the impact of building characteristics, traffic data, and biological factors on heating demand. At the same time, due to the lack of comprehensive coverage of multiple influencing factors and the lack of effective data correlation analysis methods, existing forecasting models are difficult to accurately capture the changing patterns of heating demand. In complex environments, the prediction error is large and cannot meet the needs of precise heating. In addition, existing technologies do not incorporate urban biological characteristics into the heating demand forecasting system, ignore the potential connection between urban thermosensitive organisms and environmental temperature and heating demand, and fail to fully explore the heating demand-related information contained in the urban ecosystem.

[0004] Therefore, in response to the above problems, there is an urgent need for a heating demand prediction method and system based on big data collection. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a method and system for predicting heating demand based on big data collection, which solves the problems of single data and poor adaptability in traditional heating demand prediction.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for predicting heating demand based on big data collection, comprising the following steps: step S1, obtaining building characteristic data of different areas, traffic data of different time areas, and biological characteristic data of various urban thermosensitive organisms; step S2, marking urban heating monitoring thermosensitive organisms based on the correlation analysis between the biological characteristic data of various urban thermosensitive organisms and temperature changes; step S3, using the building characteristic data of different areas and the traffic data of different time areas to perform correlation analysis with the heating records of different areas and times, respectively, to establish a correlation model between building-traffic characteristics and heating demand; step S4, identifying the correlation between the characteristic changes of urban heating monitoring thermosensitive organisms and building-traffic characteristics, and then combining the correlation model between building-traffic characteristics and heating demand to construct a hybrid prediction model; step S5, real-time monitoring of the biological characteristic data of urban heating monitoring thermosensitive organisms in different areas, using the biological characteristic data of urban heating monitoring thermosensitive organisms in different areas as the input of the hybrid prediction model, and outputting the predicted values of heating demand in different areas.

[0007] Furthermore, the building characteristic data includes wall thermal conductivity, roof insulation thickness, building density and shadow shielding coefficient; the traffic data in different time zones includes congestion index, ground heat storage coefficient and overpass shadow effect; and the biological characteristic data includes sound intensity attenuation coefficient, group aggregation and hair fluffiness.

[0008] Furthermore, step S2 is specifically analyzed as follows: identifying the acquisition time corresponding to the biological characteristic data and the regional temperature data, and then normalizing the biological characteristic data and the regional temperature data; for each type of biological characteristic data, based on the time series, identifying the biological characteristic change and temperature change at adjacent time points, and then identifying the sensitivity of the biological characteristics of various types of urban thermosensitive organisms to temperature changes based on the biological characteristic change and temperature change; arranging the sensitivity of each type of urban thermosensitive organism from large to small, and then marking the most sensitive urban thermosensitive organism as the urban heating monitoring thermosensitive organism.

[0009] Furthermore, step S3 is specifically analyzed as follows: based on the correlation analysis of the building characteristic data of different areas and the traffic data of different time areas with the heating records of different areas at different times, the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand are identified; considering the joint impact of building characteristics and traffic data on heating demand, the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand are integrated to construct a comprehensive correlation model between building-traffic characteristics and heating demand.

[0010] Furthermore, the specific analysis of the relationship model for identifying building characteristics and heating demand and the relationship model for traffic data and heating demand is as follows: for the relationship model between building characteristics and heating demand, the building characteristic data is used as the independent variable and the heating record data is used as the dependent variable, and a multiple linear regression algorithm is used to construct a relationship model for obtaining building characteristics and heating demand, and the model parameters of the preliminary relationship model are determined by the least squares method; for the relationship model between traffic data and heating demand, the traffic data is used as the independent variable and the heating record data is used as the dependent variable, and a multiple linear regression algorithm is used to determine the model parameters based on the least squares method, and a relationship model for obtaining traffic data and heating demand is established.

[0011] Furthermore, step S4 is specifically analyzed as follows: for the marked urban heating monitoring thermosensitive organisms, the relationship model between the changes in the characteristics of the thermosensitive organisms and the building-traffic characteristics is determined; the relationship model between the changes in the characteristics of the thermosensitive organisms and the building-traffic characteristics is substituted into the association model between the building-traffic characteristics and the heating demand to obtain a hybrid prediction model. The specific hybrid prediction model is used to predict the heating demand of each area based on the characteristic change data of the urban heating monitoring thermosensitive organisms.

[0012] Furthermore, the specific analysis of determining the relationship model between changes in thermosensitive biological characteristics and building-traffic characteristics is as follows: based on the urban heating monitoring of thermosensitive organisms at adjacent time points with time series identification marks, the changes in biological characteristic data of thermosensitive organisms are formed to form thermosensitive biological characteristic change data; the parameter changes of building characteristic data and traffic data at adjacent time points are respectively identified to obtain building-traffic characteristic change data, and then the thermosensitive biological characteristic change data is used as the independent variable and the building-traffic characteristic change data as the dependent variable to obtain the relationship model between changes in thermosensitive biological characteristics and building-traffic characteristics.

[0013] Furthermore, step S5 is specifically analyzed as follows: monitoring temperature-sensitive organisms for marked urban heating in different areas, collecting their biological characteristic data in real time, and performing time synchronization on the biological characteristic data collected in real time; inputting the collected biological characteristic data into the hybrid prediction model, and the model determines the heating demand prediction values of different areas based on the internal parameters and functional relationships, and then visualizing the heating demand prediction values of different areas and transmitting them to the heating management department.

[0014] A heating demand prediction system based on big data collection applies the above-mentioned heating demand prediction method based on big data collection, including: a data acquisition module for acquiring building characteristic data of different regions, traffic data of different time zones, and biological characteristic data of various types of urban thermosensitive organisms; a thermosensitive organism identification module for marking urban heating monitoring thermosensitive organisms based on the correlation analysis between the biological characteristic data of various types of urban thermosensitive organisms and temperature changes; a correlation model construction module for using the building characteristic data of different regions and the traffic data of different time zones to perform correlation analysis with the heating records of different regions and different times, respectively, to establish a correlation model between building-traffic characteristics and heating demand; a hybrid prediction model construction module for identifying the correlation between the characteristic changes of urban heating monitoring thermosensitive organisms and building-traffic characteristics, and then combining the correlation model between building-traffic characteristics and heating demand to construct a hybrid prediction model; a heating demand prediction module for real-time monitoring of the biological characteristic data of urban heating monitoring thermosensitive organisms in different regions, using the biological characteristic data of urban heating monitoring thermosensitive organisms in different regions as input to the hybrid prediction model, and outputting predicted values of heating demand in different regions.

[0015] The present invention has the following beneficial effects:

[0016] This method and system for predicting heating demand based on big data collection integrates building characteristics, traffic data and thermosensitive biological characteristics, breaking the limitation of traditional reliance on meteorological data and building a more comprehensive prediction model; by real-time monitoring of changes in the characteristics of urban thermosensitive organisms, the potential impact of the natural environment on heating demand is captured, and the sensitivity and accuracy of the prediction are improved; thermosensitive biological characteristics are strongly correlated with climate change, and the model can be adjusted in real time to adapt to extreme weather or seasonal fluctuations, reducing prediction deviations; localized models are established based on differences in building density, traffic flow and biological characteristics in different regions to avoid a "one-size-fits-all" prediction method; based on the prediction results, the heating intensity and time period can be adjusted in advance to avoid waste or shortage of resources and improve energy utilization efficiency; accurate prediction reduces idling or overload operation of the heating system, extends equipment life and reduces maintenance costs; uses thermosensitive biological characteristics as a reference to reduce dependence on artificial meteorological data, embodying the concept of harmonious coexistence between man and nature.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for predicting heating demand based on big data collection in the present invention.

[0019] Figure 2 This is a structural diagram of a heating demand prediction system based on big data collection in the present invention. DETAILED DESCRIPTION

[0020] The embodiment of the present application achieves a dual improvement in prediction accuracy and resource utilization efficiency through a heating demand prediction method and system based on big data collection, providing scientific and dynamic decision-making support for urban heating management.

[0021] The overall approach to the problems in the embodiments of this application is as follows:

[0022] Based on big data collection technology, we comprehensively collect building characteristic data from different regions, traffic data from different time zones, and biological characteristic data of various urban thermosensitive organisms. By analyzing the correlation between the biological characteristics of urban thermosensitive organisms and temperature changes, we screen out organisms that are sensitive to temperature and can be used for heating monitoring. We establish correlation models between building-traffic characteristics and heating demand, as well as correlation models between changes in the characteristics of thermosensitive organisms monitored in urban heating and building-traffic characteristics. We then construct a hybrid prediction model to achieve accurate prediction of heating demand in different regions, providing a scientific basis for the optimal scheduling of heating systems and the rational allocation of energy.

[0023] See also Figure 1 , an embodiment of the present invention provides a technical solution: a method for predicting heating demand based on big data collection, comprising the following steps: step S1, acquiring building characteristic data of different areas, traffic data of different time areas, and biological characteristic data of various urban thermosensitive organisms; step S2, marking urban heating monitoring thermosensitive organisms based on the correlation analysis between the biological characteristic data of various urban thermosensitive organisms and temperature changes; step S3, using the building characteristic data of different areas and the traffic data of different time areas to perform correlation analysis with the heating records of different areas at different times, and establishing a correlation model between building-traffic characteristics and heating demand; step S4, identifying the correlation between the characteristic changes of urban heating monitoring thermosensitive organisms and building-traffic characteristics, and then combining the correlation model between building-traffic characteristics and heating demand to construct a hybrid prediction model; step S5, real-time monitoring of the biological characteristic data of urban heating monitoring thermosensitive organisms in different areas, using the biological characteristic data of urban heating monitoring thermosensitive organisms in different areas as input of the hybrid prediction model, and outputting the predicted values of heating demand in different areas.

[0024] Specifically, building characteristic data include wall thermal conductivity, roof insulation thickness, building density and shadow shielding coefficient; traffic data in different time zones include congestion index, ground heat storage coefficient and overpass shadow effect; biological characteristic data include sound intensity attenuation coefficient, group aggregation and hair fluffiness.

[0025] In this embodiment, the thermal conductivity of the wall represents the ability of the wall material to conduct heat and is a key indicator for measuring the thermal insulation performance of the wall. The lower the thermal conductivity, the better the thermal insulation performance of the wall, the slower the indoor heat loss, and the corresponding lower the heating demand. It is obtained through two methods: laboratory testing and on-site testing. During laboratory testing, samples are taken from the wall material and measured using a thermal conductivity meter. On-site testing uses non-destructive testing techniques, such as the heat flow meter method, the hot box method, etc., to directly measure the surface of the building wall. The numerical value of the wall thermal conductivity directly reflects the thermal conductivity of the material, and the specific value is obtained through measurement and calculation.

[0026] The thickness of the roof insulation layer directly affects the thermal insulation effect of the roof. The thicker the thickness, the better the thermal insulation performance, which reduces the loss of indoor heat through the roof, thereby reducing heating demand. The original design thickness can be obtained by consulting the architectural design drawings. The actual thickness can also be directly measured through on-site surveys using measuring tools (such as steel tape measures, laser rangefinders, etc.), or with the help of Building Information Modeling (BIM) technology, accurate data can be obtained in the virtual model, and specific values can be directly measured and recorded in meters or millimeters.

[0027] Building density refers to the ratio of the total area of buildings in a certain area to the total area of the area, reflecting the density of buildings in the area. The higher the building density, the more complex the mutual shading and heat exchange between buildings, which will affect the heat dissipation and heat gain of buildings, and thus affect the heating demand. It is calculated using geographic information system (GIS) data, combined with satellite remote sensing imagery and building census data, through image recognition and data analysis. It can also be determined through on-site surveys to count the number of buildings and the area they occupy. It is expressed as a percentage and is calculated by calculating the ratio of the total building area to the total area of the area.

[0028] The shadow shielding coefficient is used to measure the degree to which buildings or other objects block the lighting and sunshine of the target building. Shadow shielding will reduce the solar radiation heat received by the building, affect the indoor temperature, and thus affect the heating demand. Based on GIS technology and 3D modeling software, the location, height, orientation and other parameters of the building are input to simulate the sunlight exposure and calculate the shadow shielding coefficient. It can also be calculated through on-site observation, recording the shadow coverage and duration in different time periods, and combining relevant formulas. It is generally a dimensionless value with a value range of 0-1, where 0 means no shielding and 1 means complete shielding. The specific value is obtained through simulation calculation or observation formula.

[0029] The congestion index reflects the degree of traffic congestion in a certain area or road section within a specific time. Traffic congestion can cause vehicles to stagnate, and the continuous operation of the engine will generate heat, affecting the surrounding temperature. At the same time, the detention of people will also change the heat demand in the area, thereby affecting the heating demand. The congestion index is calculated through data analysis and algorithm by collecting vehicle speed, flow and other data through traffic monitoring systems (such as road cameras, radar monitoring equipment), or using the real-time location and driving data of navigation software users, and referring to traffic flow statistics released by the transportation department. It is usually a dimensionless value, and different calculation methods correspond to different value ranges. For example, the degree of congestion is divided into unimpeded (0-2), basically unimpeded (2-4), light congestion (4-6), moderate congestion (6-8), and severe congestion (8-10). The larger the value, the higher the congestion level.

[0030] The ground heat storage coefficient indicates the ground's ability to store and release heat. The larger the ground heat storage coefficient, the more heat it releases at night after absorbing solar radiation during the day, and the stronger its regulating effect on the surrounding temperature. This will affect indoor and outdoor heat exchange, and thus affect heating demand. The heat storage coefficient can be calculated by measuring the thermophysical properties of soil or ground materials on the spot, such as thermal conductivity, specific heat capacity and other parameters, in combination with relevant formulas. Thermal response testing technology can also be used to bury temperature sensors in the ground to monitor ground temperature changes and infer the heat storage coefficient. Specific values are obtained through measurement and calculation.

[0031] The shadow effect of an elevated bridge specifically refers to the fact that the elevated bridge blocks sunlight, changing the light conditions on the ground and surrounding buildings, causing the temperature in the shadow area to drop, affecting the thermal environment in the area, and thus affecting the heating demand; using GIS technology and 3D modeling software, the position, height, direction and angle of sunlight of the elevated bridge are simulated to calculate the shadow coverage and degree of impact; through on-site observation, the position, area and changes of the shadow of the elevated bridge in different time periods can also be recorded; the shadow coverage area ratio or the temperature reduction value of the shadow area is used for quantification, and the specific values are obtained through simulation calculations or on-site observation measurements.

[0032] The sound attenuation coefficient reflects the degree of intensity reduction of sound during its propagation due to factors such as the medium and environment. The sound intensity generated by the activities and communications of some thermosensitive organisms will change with temperature. The sound attenuation coefficient can be used as one of the indicators of the response of organisms to temperature changes, indirectly reflecting the impact of environmental temperature changes on organisms, and thus related to heating needs. Acoustic measuring instruments (such as sound level meters, spectrum analyzers, etc.) are used to monitor and record the sounds emitted by thermosensitive organisms in real time under different environmental conditions, analyze the attenuation of sound intensity with propagation distance, and calculate the sound attenuation coefficient.

[0033] Group aggregation refers to the degree of aggregation of thermosensitive biological groups within a certain spatial range. Temperature changes will affect the activity habits and behavioral patterns of organisms. When the temperature is unsuitable, organisms may aggregate to regulate their body temperature or obtain better living conditions. Therefore, group aggregation can be used as an indicator of the sensitivity of organisms to temperature changes and has a potential correlation with heating needs. Through on-site observation, video monitoring and other methods, the number and distribution of individual organisms in a certain area can be counted. Image recognition technology can also be used to analyze the images of biological groups taken to calculate group aggregation. It can be quantified by the number of individual organisms per unit area or the aggregation index based on image analysis (a dimensionless value calculated by an algorithm, where the larger the value, the higher the aggregation).

[0034] Hair fluffiness is a way for thermosensitive organisms to regulate their body temperature. When the temperature drops, the hair of the organism will become fluffy, forming an insulating layer to reduce heat loss. When the temperature rises, the hair will be relatively close to the body. Therefore, hair fluffiness reflects the adaptation of the organism to temperature changes and is related to the ambient temperature and heating needs. The state of the organism's hair is recorded through close-up on-site observation and high-definition image capture. Image processing and analysis technology are used to extract the morphological characteristics of the hair and calculate the fluffiness of the hair. A dimensionless numerical value is used to set different levels (such as 0-10 points) to indicate the fluffiness of the hair, with 0 indicating hair close to the body and 10 indicating extremely fluffy hair. It can also be quantified by calculating the rate of change of hair coverage area.

[0035] Specifically, step S2 is specifically analyzed as follows: identifying the acquisition time corresponding to the biological characteristic data and the regional temperature data, and then normalizing the biological characteristic data and the regional temperature data; for each type of biological characteristic data, based on the time series, identifying the biological characteristic change and temperature change at adjacent time points, and then identifying the sensitivity of the biological characteristics of various types of urban thermosensitive organisms to temperature changes based on the biological characteristic change and temperature change; arranging the sensitivity of each type of urban thermosensitive organism from large to small, and then marking the most sensitive urban thermosensitive organism as the urban heating monitoring thermosensitive organism.

[0036] In this implementation plan, the specific steps for identifying sensitivity based on changes in biological characteristics and temperature are as follows: after obtaining biological characteristic data and regional temperature data at the corresponding time, check data integrity, remove outliers, and fill missing values using interpolation methods (such as linear interpolation and cubic spline interpolation); use the minimum-maximum normalization method to normalize the biological characteristic data and temperature data to the [0,1] interval to eliminate dimensional effects; for each type of biological characteristic data and temperature data, calculate the changes at adjacent time points based on the time series, and then take the absolute value to avoid positive and negative offsets, sum and average to obtain the overall sensitivity. An example of a specific calculation expression for sensitivity is: in Indicates the change in biological characteristics per unit temperature change, Δp j Indicates the change in biological characteristic data, Δt j Indicates the temperature change.

[0037] By systematically analyzing the correlation between biological characteristic data and temperature changes, and using sensitivity as the screening standard, we can accurately find urban thermosensitive organisms that are most sensitive to temperature changes, ensure that the marked urban heating monitoring thermosensitive organisms can effectively reflect environmental temperature changes, and provide a reliable basis for heating demand forecasting; combine biological characteristic data with temperature data for analysis, explore the response patterns of organisms to temperature changes, incorporate biological factors into heating demand forecasting, enrich the forecasting dimensions, enhance the correlation between the forecasting model and actual environmental changes, and improve the accuracy of heating demand forecasting; break through the limitations of traditional heating demand forecasting that only relies on physical environmental data, and innovatively start from the perspective of biological characteristics to open up new ways for heating demand forecasting, which will help to discover potential temperature-heating demand influence relationships and improve heating demand forecasting theories and methods.

[0038] Specifically, step S3 is analyzed as follows: based on the correlation analysis of the building characteristic data of different areas and the traffic data of different time areas with the heating records of different areas at different times, the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand are identified; considering the joint impact of building characteristics and traffic data on heating demand, the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand are integrated to construct a comprehensive correlation model between building-traffic characteristics and heating demand.

[0039] The specific analysis of identifying the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand is as follows: for the relationship model between building characteristics and heating demand, the building characteristic data is used as the independent variable and the heating record data is used as the dependent variable. The multiple linear regression algorithm is used to construct a relationship model between building characteristics and heating demand, and the model parameters of the preliminary relationship model are determined by the least squares method; for the relationship model between traffic data and heating demand, the traffic data is used as the independent variable and the heating record data is used as the dependent variable. The multiple linear regression algorithm is used to determine the model parameters based on the least squares method, and a relationship model between traffic data and heating demand is established.

[0040] In this implementation plan, the steps for constructing the relationship model between building characteristics and heating demand are as follows: collecting building characteristic data (wall thermal conductivity, roof insulation thickness, building density, and shadow shielding coefficient) from different areas and heating record data from the corresponding areas and time periods, cleaning the data to remove outliers and missing values, and using normalization to unify the data scale; using the processed building characteristic data as the independent variable X b, represented as a vector X b =[x b1 ,x b2 ,x b3 ,x b4 ], where x b1 is the thermal conductivity of the wall, x b2 is the thickness of the roof insulation layer, x b3 is the building density, x b4 The shadow shielding coefficient and heating record data are used as the dependent variable Y to construct a multiple linear regression model: Construct a preliminary multiple linear regression model Y b =β0+β1x b1 +β2x b2 +β3x b3 +β4x b4 +∈, where β0 is a constant term, β1,β2,β3,β4 are model parameters, and ∈ is an error term; the least squares method is used to solve the model parameters, with the goal of minimizing the sum of squares of the errors between the predicted value and the actual value, that is, where Y i is the actual heating record value of the ith time, is the i-th predicted value, and n is the number of samples; by solving the optimization problem, the determined model parameters β0, β1, β2, β3, and β4 are obtained, thereby establishing a relationship model between building characteristics and heating demand.

[0041] The steps for building a relationship model between traffic data and heating demand are as follows: collect traffic data (congestion index, ground heat storage coefficient and overpass shadow effect) in different time zones and heating record data in the corresponding areas and time zones. Similarly, data cleaning and normalization are performed; the processed traffic data is used as the independent variable X t , represented as vector X t =[x t1 ,x t2 ,x t3 ], where x t1 is the congestion index, x t2 is the ground heat storage coefficient, x t3 Construct a multiple linear regression model for the shadow effect of the viaduct; heating record data is used as the dependent variable: Construct a multiple linear regression model Y t =γ0+γ1x t1 +γ2x t2 +γ3x t3 +δ, where γ0 is a constant term, γ1, γ2, γ3 are model parameters, and δ is an error term; using the least squares method, by minimizing To determine the model parameters γ0, γ1, γ2, γ3, and establish the relationship model between traffic data and heating demand.

[0042] The specific steps for constructing a comprehensive association model between building-traffic characteristics and heating demand are as follows: considering the joint impact of building characteristics and traffic data on heating demand, dividing historical data for training and testing through methods such as cross-validation, and adjusting the weights w of the relationship model between building characteristics and heating demand. b and the weight w of the relationship model between traffic data and heating demand t , and satisfy w b +w t =1, which minimizes the prediction error of the comprehensive model on the test set; the example of the association model expression is:

[0043] Y h =f h (X c )=ω b Y b +ω t Y t , X c is the building-traffic feature data vector, Y h Heating demand data.

[0044] Relationship models are constructed for building characteristics and traffic data and heating demand respectively, fully considering the impact of these two factors on heating demand. Compared with traditional single-factor or small-factor modeling, it can more accurately capture the changing pattern of heating demand in complex environments and improve the accuracy of prediction; by constructing a relationship model, the quantitative relationship between various parameters of building characteristics and various parameters of traffic data and heating demand is clearly displayed, which helps to deeply understand the mechanism of the effect of different factors on heating demand and provide a theoretical basis for the optimization and regulation of the heating system; the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand are integrated to construct a comprehensive correlation model, which can take into account the common impact of building characteristics and traffic data on heating demand and the synergistic effect between them, make the model more in line with the actual situation, and enhance the practicality and reliability of the model; the correlation analysis and model construction based on big data provide data-driven decision support for heating management departments.

[0045] Specifically, step S4 is analyzed as follows: for the marked urban heating monitoring thermosensitive organisms, the relationship model between the changes in the characteristics of the thermosensitive organisms and the building-traffic characteristics is determined; the relationship model between the changes in the characteristics of the thermosensitive organisms and the building-traffic characteristics is substituted into the association model between the building-traffic characteristics and the heating demand to obtain a hybrid prediction model. The specific hybrid prediction model is used to predict the heating demand of each area based on the characteristic change data of the urban heating monitoring thermosensitive organisms.

[0046] The specific analysis to determine the relationship model between changes in thermosensitive biological characteristics and building-traffic characteristics is as follows: based on the time series identification mark, the changes in the biological characteristic data of thermosensitive organisms at adjacent time points of urban heating monitoring are used to form thermosensitive biological characteristic change data; the parameter changes of building characteristic data and traffic data at adjacent time points are identified respectively to obtain building-traffic characteristic change data, and then the thermosensitive biological characteristic change data are used as independent variables and the building-traffic characteristic change data as dependent variables to fit the relationship model between changes in thermosensitive biological characteristics and building-traffic characteristics.

[0047] In this embodiment, the temperature-sensitive biological characteristic change data is used as the independent variable X w (X w is a vector containing the change in sound intensity attenuation coefficient, group aggregation, and hair fluffiness), and the building-traffic characteristic change data is used as the dependent variable Y c (Y c is a vector containing the changes in the building-traffic characteristics such as the change in wall thermal conductivity and the change in the thickness of the roof insulation layer). The model parameters are solved by the least squares method using a multivariate linear regression algorithm to minimize the sum of squares of the errors between the predicted building-traffic characteristics and the actual values, that is, (where Y ci is the actual building-traffic characteristic change value of the i-th, is the i-th predicted value, n is the number of samples), and the relationship model Y between the changes in the characteristics of thermosensitive organisms and building-traffic characteristics is obtained. c =f c (X w ).

[0048] Correlation model Y between known building-traffic characteristics and heating demand h =f h (X c ), the relationship model between the changes in temperature-sensitive biological characteristics and building-traffic characteristics Y c =f c (X w ) is substituted into the correlation model between building-traffic characteristics and heating demand to obtain a hybrid prediction model, that is, firstly through Y c =f c (X w ) Data of temperature-sensitive biological characteristics changes X w Predict the change in building-traffic characteristics Y c , and then Y c Substitute Y h =f h (X c ), the final hybrid prediction model Y is obtained h =f h (f c (Xw )), the model establishes a predictive relationship between the characteristic changes of thermosensitive organisms monitored in urban heating and the heating demand of each region.

[0049] Traditional heating demand forecasting focuses primarily on physical environmental factors. This innovative approach incorporates data on changes in the characteristics of thermosensitive organisms monitored in urban heating systems, providing a new perspective on forecasting from a bioecological perspective. Thermosensitive organisms are sensitive to changes in ambient temperature, and changes in their characteristics can proactively reflect these fluctuations. Combined with building and traffic data, the forecasting model more comprehensively captures factors influencing heating demand, significantly improving forecast accuracy. Time series analysis of data changes allows real-time tracking of dynamic changes in the characteristics of thermosensitive organisms, building characteristics, and traffic data. Urban environments are complex and volatile, such as changes in building density due to new construction, adjustments to congestion indices due to traffic planning, and changes in the concentration of thermosensitive organisms due to seasonal migration. The model can promptly respond to these changes, adjusting forecast results and enhancing its adaptability to complex real-world scenarios. By establishing a relationship model between changes in the characteristics of thermosensitive organisms and building-traffic characteristics, and substituting this relationship into a model linking building-traffic characteristics with heating demand, a hybrid forecasting model is constructed. This process deeply explores the potential connections between biological, building, and traffic factors, demonstrating the mechanisms by which these multiple factors synergistically influence heating demand. This makes the model more relevant to actual urban environments and provides a more scientific basis for decision-making in optimizing heating system scheduling.

[0050] Specifically, step S5 is specifically analyzed as follows: monitoring temperature-sensitive organisms for marked urban heating in different areas, collecting their biological characteristic data in real time, and performing time synchronization on the biological characteristic data collected in real time; inputting the collected biological characteristic data into the hybrid prediction model, and the model determines the heating demand prediction values of different areas based on the internal parameters and functional relationships, and then visualizing the heating demand prediction values of different areas and transmitting them to the heating management department.

[0051] In this implementation plan, by collecting biological characteristic data of thermosensitive organisms for urban heating monitoring in real time in different areas and performing time synchronization, it is possible to obtain real-time information on the immediate response of organisms to changes in ambient temperature. The characteristic changes of thermosensitive organisms can be used as "biological indicators" of ambient temperature fluctuations. Combined with the hybrid prediction model, it can quickly capture the impact of environmental changes on heating demand. Compared with the traditional fixed-cycle prediction method, it can achieve dynamic and accurate prediction of heating demand, avoid prediction lag problems caused by environmental changes, and improve the timeliness and accuracy of the prediction; the accurate heating demand prediction value is visualized and transmitted to the heating management department, and the heating demand situation in different areas is displayed in the form of intuitive and easy-to-understand charts and graphs, helping managers to quickly understand the temporal and spatial distribution characteristics and changing trends of heating demand. This visual information presentation method provides strong data support for heating management departments to formulate scientific and reasonable heating scheduling plans and energy allocation plans, making the decision-making process more efficient and accurate, and reducing the subjectivity and blindness of human decision-making; based on real-time and accurate heating demand forecasts, heating management departments can adjust the operating parameters of the heating system according to actual needs, such as heating temperature, heating time, etc., avoiding energy waste caused by excessive heating, and preventing insufficient heating from affecting the quality of life of residents, realizing on-demand energy supply, thereby effectively improving energy utilization efficiency, reducing the operating costs of the heating system, helping to achieve energy conservation and emission reduction goals, and promoting urban heating to develop in a green and low-carbon direction.

[0052] See also Figure 2 , a heating demand prediction system based on big data collection, applying the above-mentioned heating demand prediction method based on big data collection, including: a data acquisition module, used to obtain building characteristic data of different areas, traffic data of different time areas and biological characteristic data of various urban thermosensitive organisms; a thermosensitive organism determination module, used to mark urban heating monitoring thermosensitive organisms based on the correlation analysis between the biological characteristic data of various urban thermosensitive organisms and temperature changes; an association model construction module, used to use the building characteristic data of different areas and the traffic data of different time areas to perform correlation analysis with the heating records of different areas and different times, and establish a correlation model between building-traffic characteristics and heating demand; a hybrid prediction model construction module, used to identify the correlation between the characteristic changes of urban heating monitoring thermosensitive organisms and building-traffic characteristics, and then combine the correlation model of building-traffic characteristics and heating demand to construct a hybrid prediction model; a heating demand prediction module, used to monitor the biological characteristic data of urban heating monitoring thermosensitive organisms in different areas in real time, use the biological characteristic data of urban heating monitoring thermosensitive organisms in different areas as input of the hybrid prediction model, and output the predicted value of heating demand in different areas.

[0053] In summary, this application has at least the following effects:

[0054] By comprehensively considering multi-source data such as building characteristics, traffic data and biological characteristics, and through correlation analysis and hybrid model construction, the factors affecting heating demand and their interrelationships can be more comprehensively captured, significantly improving the accuracy of heating demand forecasts; accurate heating demand forecasts can help heating management departments rationally plan energy supply, avoid oversupply or undersupply of energy, achieve efficient energy utilization, and reduce heating costs and carbon emissions; the innovative introduction of urban temperature-sensitive biological characteristic data provides a new perspective and data dimension for heating demand forecasting, enriching the research methods and theoretical system of heating demand forecasting; real-time monitoring of temperature-sensitive biological characteristic data and dynamic updating of the prediction model enable the heating demand forecasting system to quickly adapt to environmental changes, and improve the adaptability and stability of the heating system under complex and changing conditions.

[0055] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods or systems. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to the flowcharts and structure diagrams of the methods and systems according to the embodiments of the present invention. It should be understood that each process and combination of modules in the flowcharts and structure diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate the instructions for implementing the processes in the flowcharts. Figure 1 process or processes and structures Figure 1 A device that specifies functionality within a module or modules.

[0057] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 process or processes and structures Figure 1 Functionality specified in a module or modules.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 process or processes and structures Figure 1 Steps for specifying functionality in a module or multiple modules.

[0059] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0060] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for predicting heating demand based on big data collection, characterized in that: The following steps are involved: Step S1, obtaining building characteristic data of different areas, traffic data of different time zones, and biological characteristic data of various urban temperature-sensitive organisms; Step S2: Based on the correlation analysis between the biological characteristic data of various urban thermosensitive organisms and temperature changes, the thermosensitive organisms for urban heating monitoring are marked; Step S3, using the building characteristic data of different areas and the regional traffic data at different times to perform correlation analysis with the heating records of different areas at different times, to establish a correlation model between building-traffic characteristics and heating demand; Step S4, identifying the correlation between the characteristic changes of thermosensitive organisms monitored in urban heating and building-traffic characteristics, and then combining the correlation model between building-traffic characteristics and heating demand to construct a hybrid prediction model; Step S5: real-time monitoring of biological characteristic data of thermosensitive organisms in urban heating monitoring in different regions, using the biological characteristic data of thermosensitive organisms in urban heating monitoring in different regions as input of the hybrid prediction model, and outputting predicted values of heating demand in different regions.

2. The method for predicting heating demand based on big data collection according to claim 1, characterized in that: The building characteristic data includes wall thermal conductivity, roof insulation thickness, building density and shadow shielding coefficient; the traffic data in different time zones includes congestion index, ground heat storage coefficient and overpass shadow effect; and the biological characteristic data includes sound intensity attenuation coefficient, group aggregation and hair fluffiness.

3. The method for predicting heating demand based on big data collection according to claim 1, characterized in that: Step S2 is specifically analyzed as follows: identifying the acquisition time of the biometric data and the regional temperature data, and then normalizing the biometric data and the regional temperature data; For each biological characteristic data, based on the time series, the changes in biological characteristics and temperature at adjacent time points are identified. Then, based on the changes in biological characteristics and temperature, the sensitivity of the biological characteristics of various urban thermosensitive organisms to temperature changes is identified. The sensitivity of each urban thermosensitive organism is arranged from large to small, and the urban thermosensitive organism with the greatest sensitivity is marked as the urban heating monitoring thermosensitive organism.

4. The method for predicting heating demand based on big data collection according to claim 1, characterized in that: The specific analysis in step S3 is as follows: based on the correlation analysis of the building characteristic data of different areas and the traffic data of different time areas with the heating records of different areas and different time areas, the relationship model between the building characteristics and the heating demand and the relationship model between the traffic data and the heating demand are identified; Considering the joint impact of building characteristics and traffic data on heating demand, the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand are integrated to construct a comprehensive association model between building-traffic characteristics and heating demand.

5. The method for predicting heating demand based on big data collection according to claim 4, characterized in that: The specific analysis of the relationship model between building characteristics and heating demand and the relationship model between traffic data and heating demand is as follows: for the relationship model between building characteristics and heating demand, the building characteristic data is used as the independent variable and the heating record data is used as the dependent variable. A multiple linear regression algorithm is used to construct a relationship model between building characteristics and heating demand, and the model parameters of the preliminary relationship model are determined by solving the least squares method. For the relationship model between traffic data and heating demand, traffic data is used as the independent variable and heating record data as the dependent variable. The multiple linear regression algorithm is used to determine the model parameters based on the least squares method to establish the relationship model between traffic data and heating demand.

6. The method for predicting heating demand based on big data collection according to claim 1, characterized in that: The specific analysis of step S4 is as follows: monitoring thermosensitive organisms for marked urban heating and determining a relationship model between changes in thermosensitive organism characteristics and building-traffic characteristics; The relationship model between changes in thermosensitive organism characteristics and building-traffic characteristics is substituted into the association model between building-traffic characteristics and heating demand to obtain a hybrid prediction model. The specific hybrid prediction model is used to predict the heating demand of each region based on the characteristic change data of thermosensitive organisms monitored by urban heating.

7. The method for predicting heating demand based on big data collection according to claim 6, characterized in that: The specific analysis of the relationship model between the change of thermosensitive biological characteristics and building-traffic characteristics is as follows: based on the time series identification mark, the urban heating monitors the change of biological characteristic data of thermosensitive organisms at adjacent time points to form thermosensitive biological characteristic change data; The parameter changes of building characteristic data and traffic data at adjacent time points were identified respectively to obtain the building-traffic characteristic change data. Then, the thermosensitive biological characteristic change data were used as the independent variable and the building-traffic characteristic change data as the dependent variable to fit the relationship model between the thermosensitive biological characteristic change and the building-traffic characteristic.

8. The method for predicting heating demand based on big data collection according to claim 1, characterized in that: Step S5 is specifically analyzed as follows: monitoring temperature-sensitive organisms for marked urban heating in different areas, collecting their biological characteristic data in real time, and performing time synchronization on the collected biological characteristic data in real time; The collected biological characteristic data is input into the hybrid prediction model. The model determines the heating demand forecast values of different areas based on the internal parameters and functional relationships, and then visualizes the heating demand forecast values of different areas and transmits them to the heating management department.

9. A heating demand prediction system based on big data collection, applying the heating demand prediction method based on big data collection according to any one of claims 1 to 8, characterized in that: include: The data acquisition module is used to obtain building characteristic data of different areas, traffic data of different time zones, and biological characteristic data of various urban temperature-sensitive organisms; Thermosensitive organism identification module is used to identify thermosensitive organisms for urban heating monitoring based on the correlation analysis between the biological characteristic data of various urban thermosensitive organisms and temperature changes; The correlation model building module is used to use the building characteristic data of different areas and the traffic data of different time zones to conduct correlation analysis with the heating records of different areas and time zones, and establish a correlation model between building-traffic characteristics and heating demand; A hybrid prediction model building module is used to identify the correlation between changes in the characteristics of thermosensitive organisms monitored in urban heating and building-traffic characteristics, and then combine the correlation model between building-traffic characteristics and heating demand to build a hybrid prediction model; The heating demand prediction module is used to monitor the biological characteristic data of thermosensitive organisms monitored by urban heating in different regions in real time, use the biological characteristic data of thermosensitive organisms monitored by urban heating in different regions as the input of the hybrid prediction model, and output the predicted values of heating demand in different regions.

Images