Short-term net load forecasting method considering building photovoltaic heat transfer characteristics

Abstract

This invention provides a short-term net load forecasting method that considers the heat transfer characteristics of building rooftop photovoltaic (PV) systems. For building rooftops equipped with parallel overhead PV modules, a PV-roof integrated heat transfer model is constructed using the heat balance method. The annual heat transfer characteristics of the building's PV roof are calculated, and the daily load types for each season are classified based on the waveform characteristics of the heat transfer. Finally, using the heat transfer characteristics as input, short-term net load forecasts for each season are performed. This invention's short-term net load forecasting method considers the rooftop PV thermal effect, which has a significant impact on load fluctuations, and further subdivides daily load types based on heat transfer characteristics. It also deeply explores and characterizes the relationship between rooftop PV and building load, significantly improving the forecasting accuracy of net load for each season.

Description

Technical Field

[0001] This invention belongs to the field of building photovoltaic system technology, specifically relating to a short-term net load forecasting method that takes into account the heat transfer characteristics of building photovoltaic systems. Background Technology

[0002] In 2023, building operation energy consumption accounted for approximately 30% of global energy consumption, with central air conditioning systems accounting for about 50% of total building energy consumption, and this figure is on the rise. As national energy structures shift towards cleaner and lower-carbon models, building-integrated photovoltaics (BIPV) is developing rapidly to compensate for peak-hour electricity loads in buildings in order to achieve the goal of "building carbon reduction".

[0003] Although the primary demand for photovoltaic (PV) systems is power generation, the energy-saving contribution of building-integrated photovoltaics (BIPV) to buildings through its shading and insulation effects is increasingly attracting attention. Research by Wang Yiping et al. shows that compared to traditional exposed roofs, BIPV with ventilation gaps can reduce daily heat gain by 46% in summer due to its shading effect and good ventilation performance; in winter, BIPV can reduce indoor heat load peaks and heat loss by 5–20%. Ma Zongyao et al. focused on analyzing the shading effect of rooftop PV in summer: after installing PV on the roof, the roof heat flux decreased by 41.7%, the roof peak temperature decreased by 22.9℃, and the daily heat gain decreased by 74.84%. Bhuvad SS et al., in their annual analysis of the heat load effect of PV shading, found that although the PV shading effect increases the building's heat load in winter across all climate zones, the overall building heat load may decrease by 22.76–74.07%. These studies have identified and demonstrated the significant impact of the shading and insulation effects of BIPV on building loads in different regions and seasons, but practical applications of the energy-saving effects of BIPV are currently lacking.

[0004] Dominguez A et al. pointed out that the shading and heat insulation effects of photovoltaic modules on improving building energy efficiency and thermal comfort are particularly evident in low-rise industrial buildings with poor insulation and large surface areas. Statistics show that air conditioning load accounts for approximately 50% to 67% of the total electricity consumption of industrial buildings, and industrial buildings are favored by photovoltaic power generation developers due to their large roof areas. Espino-Reyes et al. documented significant energy-saving effects in industrial buildings with installed photovoltaic systems. For industrial buildings with a large proportion of cooling and heating loads, installing photovoltaic modules on their roofs will have a significant impact on the magnitude and fluctuation patterns of their loads. This further increases the difficulty of load forecasting for the grid dispatching side, which needs to plan and control load demand.

[0005] As photovoltaic (PV) penetration continues to increase, power companies will need to transition from forecasting actual load to forecasting the net load resulting from PV power output, which presents increasing forecasting challenges. Existing net load forecasting methods have several shortcomings, thus failing to achieve ideal forecasting accuracy in practical applications. Firstly, existing methods tend to consider only a limited range of input characteristics, typically including weather factors and single PV-related information such as temperature, air pressure, and solar radiation, while neglecting meteorological features like date, day of the week, and holidays. These non-meteorological features have a significant impact on net load. Secondly, the installation of PV systems on industrial building rooftops also significantly affects the load. Furthermore, ensuring forecasting accuracy across different seasons is also crucial.

[0006] Therefore, to solve the above problems, there is a need for a net load forecasting method that can further improve forecast accuracy. Summary of the Invention

[0007] This invention addresses the aforementioned problems and aims to provide a short-term net load forecasting method that can further improve forecasting accuracy. The invention employs the following technical solution:

[0008] This invention provides a short-term net load prediction method considering the heat transfer characteristics of building photovoltaics (PV). The method is used to predict the net load of a building with PV modules installed parallel to and suspended on its roof. A ventilation channel is formed between the roof and the PV modules. The method includes the following steps: Step S1, obtaining relevant data required for predicting the net load; Step S2, calculating the total irradiance of the sloping surface based on the relevant data; Step S3, constructing a PV-roof integrated heat transfer model, wherein the model includes the energy balance equations of the PV module components and the energy balance equations of the air within the ventilation channel. The one-dimensional unsteady-state heat conduction equation of the roof, the boundary equation of the outer surface of the roof, and the boundary equation of the inner surface of the roof; Step S4, based on the photovoltaic-roof integrated heat transfer model and the relevant data, classify the daily load types for each season, and calculate the actual load prediction results for each season in combination with the daily load types; Step S5, based on the photovoltaic-roof integrated heat transfer model and the relevant data, calculate the photovoltaic output prediction results for each season; Step S6, based on the actual load prediction results and the photovoltaic output prediction results for each season, obtain the net load prediction results for each season.

[0009] The short-term net load forecasting method considering the heat transfer characteristics of building photovoltaics provided by this invention may also have the following technical features: In step S1, the relevant data includes total solar irradiance data on the horizontal plane, direct irradiance data, diffuse irradiance data, reflected irradiance data, air temperature data, ground temperature data, wind speed data, installation data of the photovoltaic modules, characteristic data of the photovoltaic modules, structural data of the building, thermal property data of the building's roof, thermal property data of the photovoltaic modules, and indoor air conditioning setting data of the building; In step S3, the photovoltaic module includes a glass cover plate, photovoltaic cells, and a photovoltaic backsheet, and the energy balance equations of the components of the photovoltaic module include the energy balance equations of the glass cover plate, the photovoltaic cells, and the photovoltaic backsheet.

[0010] The short-term net load forecasting method considering the heat transfer characteristics of building photovoltaics provided by this invention may also have the following technical feature, wherein, in step S3, the energy balance equation of the glass cover is:

[0011]

[0012] In the formula, M g For the quality of the glass cover, C g For the specific heat of the glass cover, G t α represents the total solar irradiance on the slope. g Let ρ be the absorptivity of the glass cover to solar radiation, A be the area of ​​the glass cover, and ρ be the absorptivity of the glass cover to solar radiation. o,g h represents the reflectivity of the glass cover. c,glass T is the convective heat transfer coefficient between the glass cover and the surrounding environment. a For ambient temperature, h gc Φ is the heat transfer coefficient between the glass cover and the photovoltaic cell. r,g-s The energy balance equation for the photovoltaic cell, which represents the radiative heat exchange between the glass cover and the surrounding environment, is as follows:

[0013]

[0014] In the formula, G pv G represents the irradiance incident on the photovoltaic cell. pv =G t ·A(1-ρ o,g )(1-α g ), h gc h is the heat transfer coefficient between the photovoltaic cell and the glass cover. tc P is the heat transfer coefficient between the photovoltaic cell and the photovoltaic backsheet. c Given the output power of the photovoltaic cell, the energy balance equation of the photovoltaic backsheet is:

[0015]

[0016] In the formula, h tf ε is the convective heat transfer coefficient between the photovoltaic backsheet and the air inside the ventilation channel; t ε e Here, emissivity represents the photovoltaic backsheet and the outer surface of the roof, respectively; δ is the Stefan-Boltzmann constant, and the energy balance equation for the air within the ventilation duct is:

[0017]

[0018] In the formula, h fe Let h be the convective heat transfer coefficient between the air inside the ventilation duct and the outer surface of the roof. fe The convective heat transfer coefficient h between the photovoltaic backsheet and the air in the ventilation channel tf Same; m fr C f These represent the mass flow rate and specific heat capacity of the air within the flow channel, respectively; T fo With T fi These are the inlet and outlet temperatures of the flow channel, respectively, let T be... fo =T a And T f =(T fo +T fi The one-dimensional unsteady-state heat conduction equation for the roof is: ) / 2

[0019]

[0020] In the formula, 'a' is the thermal diffusivity of the roof material; the boundary equation of the outer surface of the roof is:

[0021]

[0022] The boundary equation for the inner surface of the roof is:

[0023]

[0024] In the formula, λ e , λ i T represents the thermal conductivity of the outer and inner surfaces of the roof, respectively. he Specify the temperature for indoor air conditioning equipment in a building, h ih The heat transfer coefficient of the inner surface of the roof.

[0025] The short-term net load forecasting method considering building photovoltaic heat transfer characteristics provided by this invention may also have the following technical features, wherein step S4 includes the following sub-steps: Step S4-1, calculating the hourly heat transfer of the roof based on the photovoltaic-roof integrated heat transfer model and the relevant data; Step S4-2, constructing a feature matrix based on the daily maximum and minimum values ​​of the hourly heat transfer, and using hierarchical clustering to classify the daily load types of each season based on the feature matrix, obtaining the daily load type labels corresponding to each season; Step S4-3, constructing the actual load input matrix for each season based on the load type labels corresponding to each season, the hourly heat transfer, and the actual load power time series; Step S4-4, predicting the actual load of each season based on the actual load input matrix corresponding to the season to be predicted using a bidirectional long short-term memory network algorithm, obtaining the actual load forecast result for the season to be predicted.

[0026] The short-term net load forecasting method considering building photovoltaic heat transfer characteristics provided by this invention may also have the following technical feature, wherein, in step S4-3, the input matrix X1 for actual load forecasting is:

[0027]

[0028] In the formula, h represents the hourly heat transfer of the roof, l represents the load type label, and S... load is the historical actual load power time series, where i is the index value of the sample point and n is the length of the historical actual load power time series.

[0029] The short-term net load forecasting method considering building photovoltaic heat transfer characteristics provided by the present invention may also have the following technical features, wherein, in step S4-2, for spring, there are five clusters; for summer, autumn and winter, there are four clusters, and a label is set for each cluster as the load type label.

[0030] The short-term net load forecasting method considering the heat transfer characteristics of building photovoltaics provided by this invention may also have the following technical features, wherein step S5 includes the following sub-steps: Step S5-1, calculating the photovoltaic cell temperature of the photovoltaic cell based on the photovoltaic-roof integrated heat transfer model and the relevant data; Step S5-2, constructing a photovoltaic output input matrix for the predicted season based on the photovoltaic cell temperature, the total irradiance of the inclined plane, relative humidity, and the photovoltaic output time series; Step S5-3, predicting the photovoltaic output of the season to be predicted using a bidirectional long short-term memory network algorithm based on the photovoltaic output input matrix corresponding to each season, and obtaining the photovoltaic output prediction results for each season.

[0031] The short-term net load forecasting method considering building photovoltaic heat transfer characteristics provided by this invention may also have the following technical feature, wherein, in step S5-2, the photovoltaic output input matrix is:

[0032]

[0033] Where, T c For the temperature of photovoltaic cells, G t S is the total irradiance of the inclined plane, H is the relative humidity; S pv This is a historical photovoltaic power output time series.

[0034] The short-term net load forecasting method considering the heat transfer characteristics of building photovoltaics provided by this invention may also have the following technical feature: in step S2, the Liu & Jordan model is used to calculate the total irradiance of the inclined plane.

[0035]

[0036] In the formula, G t G represents the total irradiance of the inclined plane. b R represents the direct irradiance on a horizontal plane. b G is the ratio of direct irradiance on the inclined plane to that on the horizontal plane. d Let θ be the horizontal diffuse irradiance, θ be the tilt angle of the photovoltaic module, G be the total horizontal irradiance, and ρ be the roof reflectivity.

[0037] Invention Function and Effect

[0038] According to the short-term net load forecasting method of the present invention, which considers the heat transfer characteristics of building photovoltaics, a photovoltaic-roof integrated heat transfer model is constructed for building roofs equipped with parallel overhead photovoltaic modules using the heat balance method. This model includes the energy balance equations of components in the photovoltaic modules, the energy balance equation of air in the ventilation ducts, the one-dimensional unsteady-state heat conduction equation of the roof, and the boundary equations of the inner and outer surfaces of the roof. Based on this model, the actual load and photovoltaic output are predicted, thereby obtaining the short-term net load forecast. Furthermore, when predicting the actual load, the daily load types for each season are classified based on the model and relevant data. That is, the method of this embodiment fully considers the roof photovoltaic thermal effect, which has a significant impact on load fluctuations, and further subdivides the daily load types according to the season, thus effectively improving the accuracy of short-term net load forecasting. Attached Figure Description

[0039] Figure 1 This is a flowchart of a short-term net load forecasting method considering building photovoltaic heat transfer characteristics in an embodiment of the present invention;

[0040] Figure 2 These are schematic cross-sectional views of two roof heat transfer models in embodiments of the present invention;

[0041] Figure 3 This is a graph showing the inner and outer surface temperatures of the two types of roofs in different seasons in the embodiments of the present invention.

[0042] Figure 4 This is a comparison diagram of the heat transfer of two roof heat transfer models in an embodiment of the present invention;

[0043] Figure 5 This is a diagram showing the effect of daily load clustering in various seasons in an embodiment of the present invention;

[0044] Figure 6 This is a graph showing the actual load forecast results for each season in this embodiment of the invention;

[0045] Figure 7 This is a temperature curve of each component of the photovoltaic module in an embodiment of the present invention;

[0046] Figure 8 This is a graph showing the photovoltaic power output prediction results for each season in the embodiments of the present invention;

[0047] Figure 9 This is a graph showing the net load forecast results for each season in an embodiment of the present invention. Detailed Implementation

[0048] To make the technical means, creative features, objectives and effects of this invention easy to understand, the following describes in detail the short-term net load prediction method of this invention that takes into account the heat transfer characteristics of building photovoltaics, in conjunction with the embodiments and accompanying drawings.

[0049] <Example>

[0050] Figure 1 This is a flowchart of the short-term net load forecasting method that considers the heat transfer characteristics of building photovoltaics in this embodiment.

[0051] like Figure 1 As shown, the method includes the following steps:

[0052] Step S1: Obtain the relevant data required for forecasting short-term net load.

[0053] Step S2: Calculate the total irradiance of the inclined plane based on relevant data.

[0054] Step S3: Construct a photovoltaic-roof integrated heat transfer model using the thermal balance method.

[0055] Step S4: Based on the photovoltaic-roof integrated heat transfer model and the aforementioned relevant data, the load types for each season are divided, and the actual load prediction results for the season to be predicted are calculated in combination with the corresponding load types.

[0056] Step S5: Based on the photovoltaic-roof integrated heat transfer model and the aforementioned relevant data, calculate the photovoltaic output prediction results for the season to be predicted.

[0057] Step S6: Based on the actual load forecast results and the photovoltaic output forecast results for the season to be predicted, obtain the net load forecast results for the season to be predicted.

[0058] The steps described above will be explained in detail below.

[0059] Step S1: Obtain the relevant data required for forecasting short-term net load.

[0060] In this embodiment, the relevant data includes horizontal solar irradiance data, air temperature data, ground temperature data, wind speed data, photovoltaic module installation data, photovoltaic module characteristic data, building structure data, building roof thermal property data, photovoltaic module thermal property data, and building indoor air conditioning setting data.

[0061] The data includes: horizontal solar irradiance data (total solar irradiance, direct irradiance, diffuse irradiance, and reflected irradiance); photovoltaic module installation data and photovoltaic module characteristic data (installation method, ventilation channel clearance, installation area, installation length, materials, thickness, and photoelectric conversion efficiency of each part of the photovoltaic module); building structure data (materials and thickness of each part of the roof); and building roof thermal property data and photovoltaic module thermal property data (thermal conductivity, density, and specific heat capacity of each part of the roof and photovoltaic modules, absorptivity and reflectivity of the photovoltaic glass cover, absorptivity of the photovoltaic cells and backsheet, absorptivity and reflectivity of the roof, and emissivity of the photovoltaic glass cover and roof).

[0062] Step S2: Calculate the total irradiance of the inclined plane based on the above-mentioned relevant data.

[0063] In this embodiment, the Liu & Jordan model is used to calculate the total irradiance of the slope, specifically based on the following formula:

[0064]

[0065] In the formula, G t G represents the total irradiance of the inclined plane. b R represents the direct irradiance on a horizontal plane. b G is the ratio of direct irradiance on the inclined plane to that on the horizontal plane. d θ is the horizontal diffuse irradiance; θ is the tilt angle of the photovoltaic module; G is the total horizontal irradiance; ρ is the roof reflectivity.

[0066] Step S3: Construct a photovoltaic-roof integrated heat transfer model using the thermal balance method.

[0067] In this embodiment, a rooftop with parallel overhead photovoltaic modules is used as an example for specific explanation.

[0068] Figure 2 These are cross-sectional schematic diagrams of the two types of roofs in this embodiment. Figure 2 (a) shows an exposed roof, corresponding to a roof heat transfer model without installed photovoltaic modules. Figure 2 (b) shows a roof with parallel overhead photovoltaic modules, corresponding to the parallel overhead photovoltaic-roof integrated heat transfer model.

[0069] like Figure 2 As shown, the roof covered with parallel, overhead photovoltaic (PV) modules can be divided into three parts from top to bottom: PV modules, ventilation channels (or ventilation gaps), and the roof itself, with air flowing within the ventilation channels. The PV modules consist of a series of stacked glass cover plates, PV cells, and PV backsheets, whose parameters are indicated by the subscripts g, c, and t in the formulas below. The parameters of the ventilation channels, the outer surface of the roof, and the inner surface of the roof are indicated by the subscripts f, e, and i, respectively. A PV-roof integrated heat transfer model is obtained by modeling this roof structure. The temperature T of each part of this model is calculated by constructing the corresponding heat balance (energy balance) equations.

[0070] The energy balance equation for the glass cover is:

[0071]

[0072] In the formula, M g For the mass of the glass cover; C g Specific heat of the glass cover; G t α represents the total solar irradiance of the inclined plane. g ρ is the absorptivity of the glass cover to solar radiation; A is the area of ​​the glass cover; o,g h is the reflectivity of the glass cover. c,glass T is the convective heat transfer coefficient between the glass cover and the surrounding environment. a ambient temperature; h gc Φ is the heat transfer coefficient between the glass cover and the photovoltaic cell; r,g-s It refers to the radiative heat exchange between the glass cover and the surrounding environment (including the surrounding air, sky, and ground).

[0073] The energy balance equation for a photovoltaic cell is:

[0074]

[0075] In the formula, G pv G represents the irradiance incident on the photovoltaic cell. pv =G t ·A(1-ρ o,g)(1-α g );h gc with h tc These are the heat transfer coefficients between the photovoltaic cell and the glass cover, and between the photovoltaic backsheet, respectively; P c Let P be the output power of the photovoltaic cell. c =G pv ·η, where η is the photoelectric conversion efficiency of the photovoltaic module.

[0076] The energy balance equation for a photovoltaic backsheet is:

[0077]

[0078] In the formula, h tf ε is the convective heat transfer coefficient between the photovoltaic backsheet and the air in the ventilation channel; t ε e δ represents the emissivity of the back panel and the outer surface of the roof, respectively; δ is the Stefan-Boltzmann constant, taken as 5.669 × 10⁻⁶. -8 W / (m 2 ·K 4 ).

[0079] The energy balance equation for the air within the ventilation duct is:

[0080]

[0081] In the formula, h fe Let h be the convective heat transfer coefficient between the air inside the flow channel and the outer surface of the roof. fe The convective heat transfer coefficient h between the photovoltaic backsheet and the air in the ventilation channel tf Same; m fr C f These represent the mass flow rate and specific heat capacity of the air within the flow channel, respectively; T fo With T fi These are the inlet and outlet temperatures of the flow channel, respectively, let T be... fo =T a And T f =(T fo +T fi ) / 2.

[0082] In the parallel overhead photovoltaic-roof integrated heat transfer model, the boundary equations for the outer and inner surfaces of the roof are as follows:

[0083]

[0084] In the formula, λ e , λ i T represents the thermal conductivity of the outer and inner surfaces of the roof, respectively. he The specified temperature for the building's indoor air conditioning equipment is set to 24°C year-round in this embodiment; h ihThe heat transfer coefficient of the inner surface of the roof.

[0085] In this embodiment, Figure 2 The exposed roof shown in (a) and Figure 2 A comparative analysis is conducted using the cross-sectional schematic diagram of the parallel overhead photovoltaic roof shown in (b). Therefore, the heat transfer equation for the exposed roof heat transfer model is also given below.

[0086] The roof heat transfer model is a one-dimensional unsteady-state heat conduction along the thickness direction of the roof, and its heat transfer equation is:

[0087]

[0088] In the formula, 'a' represents the thermal diffusivity of the roofing material. For roofs made of composite materials, the thermal diffusivity of the corresponding material is used at different thicknesses.

[0089] The boundary equations for the outer surface and the inner surface of the exposed roof are as follows:

[0090]

[0091] Step S4: Based on the photovoltaic-roof integrated heat transfer model and the aforementioned relevant data, the load types for each season are divided, and the actual load prediction results for the season to be predicted are calculated in combination with the corresponding load types.

[0092] like Figure 1 As shown, step S4 specifically includes the following sub-steps:

[0093] Step S4-1: Calculate the hourly heat transfer of the roof based on the photovoltaic-roof integrated heat transfer model and the aforementioned relevant data.

[0094] Based on the aforementioned model and relevant data, the temperatures of the outer and inner surfaces of the roof at various time points are calculated. Then, the hourly heat transfer of the roof can be calculated using the following formula: h ih (T i -T he ).

[0095] In this embodiment, the hourly heat transfer of the roof throughout the year is calculated based on relevant data for one year.

[0096] Figure 3 This is a graph showing the inner and outer surface temperatures of the two types of roofs in different seasons in this embodiment. Figure 4 This is a comparison diagram of the heat transfer of two roof heat transfer models in this embodiment of the invention.

[0097] like Figure 3 and Figure 4As shown, based on the above model and relevant data, the temperatures of the inner and outer surfaces of the roof at each time point on each day of each season can be calculated, thus obtaining a curve of the roof's inner and outer surface temperatures. It can be seen that during periods of sunshine, the temperature of the roof with photovoltaic modules installed is significantly lower than that of the bare roof. Based on this curve and parameters such as the heat transfer coefficient of the roof's inner surface, the hourly heat transfer of the roof can be further calculated. It can be seen that the roof with photovoltaic modules installed and the bare roof differ significantly in both temperature and heat transfer.

[0098] Step S4-2: Construct a feature matrix based on the daily maximum and minimum values ​​of hourly heat transfer on the roof, and use hierarchical clustering to classify the daily load types for each season based on the feature matrix to obtain the corresponding daily load type labels for each season.

[0099] In constructing the feature matrix for load clustering, using the daily maximum and minimum values ​​of hourly heat transfer (i.e., the maximum and minimum values ​​within a day) achieves the best classification results. Load classification is implemented using hierarchical clustering, and the classification effect is verified using the daily load average. Because heat transfer characteristics and load demands differ across seasons, the number of load clusters also varies.

[0100] Figure 5 This is a diagram showing the effect of daily load clustering for each season in this embodiment.

[0101] like Figure 5 As shown, based on the statistical analysis of the above-mentioned data, daytime temperature fluctuations are more frequent in spring. Consequently, spring has the most load clusters, reaching five; while the other three seasons each have four clusters. A label is assigned to each cluster as a load type label.

[0102] Step S4-3: Construct the actual load input matrix for the season to be predicted using the load type label corresponding to the season to be predicted, the hourly heat transfer of the roof, and the actual load power time series.

[0103] The actual load power time series can be obtained from the aforementioned data. The input matrix X1 for actual load forecasting is as follows:

[0104]

[0105] In the formula, h represents the hourly heat transfer of the rooftop equipped with photovoltaic modules; l represents the load type label; S load is the historical actual load power time series; i is the index value of the sample point; n is the length of the historical actual load power time series.

[0106] Step S4-4: Based on the actual load input matrix corresponding to the season to be predicted, the actual load of the season to be predicted is predicted using the Bi-LSTM (Bidirectional Long Short-Term Memory) algorithm to obtain the actual load prediction result of the season to be predicted.

[0107] That is, the above-mentioned actual load input matrix is ​​input into the trained Bi-LSTM model to obtain the corresponding output.

[0108] Figure 6 This is a graph showing the actual load forecast results for each season in this embodiment. Figure 6 In the diagram, the line corresponding to True represents the actual load obtained based on relevant data. Pre1 represents the actual load prediction result with hourly heat transfer and load type label, Pre2 represents the actual load prediction result with hourly heat transfer but no load type label, and Pre3 represents the actual load prediction result without hourly heat transfer and no load type label.

[0109] Table 1 below provides the evaluation indicators for the actual load forecast results.

[0110] Table 1 Evaluation Indicators for Actual Load Forecast Results

[0111]

[0112] In the table, RMSE is the root mean square error, and MAPE is the mean absolute percentage error.

[0113] from Figure 6 As can be seen from Table 1, the prediction accuracy of Pre1 is significantly higher than that of Pre2 and Pre3, which means that considering hourly heat transfer and setting the above load type labels helps to improve prediction accuracy.

[0114] Step S5: Calculate the predicted output of photovoltaic modules for each season based on the photovoltaic-roof integrated heat transfer model and the aforementioned relevant data.

[0115] like Figure 1 As shown, step S5 specifically includes the following sub-steps:

[0116] Step S5-1: Calculate the temperature of the photovoltaic cells in the photovoltaic module based on the photovoltaic-roof integrated heat transfer model and the above-mentioned relevant data.

[0117] Figure 7 This is a temperature curve of each component of the photovoltaic module in this embodiment.

[0118] like Figure 7As shown, during periods of sunshine, the temperature of the photovoltaic cells is very close to that of the glass cover and the photovoltaic backsheet. However, during nighttime periods without sunshine, the temperature of the photovoltaic cells is slightly higher than that of the glass cover and the photovoltaic backsheet. Furthermore, the temperature difference between the photovoltaic cells is significant in summer and winter.

[0119] Step S5-2: Based on the photovoltaic cell temperature, total irradiance on the slope, relative humidity, and photovoltaic output time series, construct the photovoltaic output input matrix X2 for the season to be predicted as follows:

[0120]

[0121] Where, T c For photovoltaic cell temperature; G t S is the total irradiance of the inclined plane; H is the relative humidity; S is the total irradiance of the inclined plane. pv This is a historical photovoltaic power output time series.

[0122] Step S5-3: Based on the photovoltaic power output input matrix corresponding to the season to be predicted, the photovoltaic power output of the season to be predicted is predicted by the Bi-LSTM algorithm to obtain the photovoltaic power output prediction result of the season to be predicted.

[0123] Figure 8 This is a graph showing the predicted photovoltaic power output for each season in this embodiment. Figure 8 In the diagram, the line corresponding to True represents the actual photovoltaic output obtained based on relevant data, Pre1 represents the photovoltaic output prediction result with photovoltaic cell temperature, and Pre2 represents the photovoltaic output prediction result without photovoltaic cell temperature.

[0124] Table 2 below provides the evaluation indicators for the photovoltaic power output prediction results.

[0125] Table 2 Evaluation Indicators for Photovoltaic Output Prediction Results

[0126]

[0127] from Figure 8 As can be seen from Table 2, the prediction accuracy of Pre1 is significantly higher than that of Pre2, which means that considering the temperature of photovoltaic cells is beneficial to improving the prediction accuracy of photovoltaic output.

[0128] Step S6: Based on the actual load forecast results and the output forecast results for each season, obtain the net load forecast results for each season.

[0129] The formula for calculating the net load forecast result is as follows:

[0130]

[0131] In the formula, The actual load forecast result obtained through step S4, The photovoltaic output prediction result is obtained through step S5.

[0132] Figure 9 This is a graph showing the net load forecast results for each season in this embodiment. Figure 9 In the diagram, the line corresponding to True represents the actual net load value obtained based on the aforementioned data. Pre1 represents the net load prediction result with hourly heat transfer, load type label, and photovoltaic cell temperature. Pre2 represents the net load prediction result with hourly heat transfer, no load type label, and photovoltaic cell temperature. Pre3 represents the net load prediction result without hourly heat transfer, load type label, or photovoltaic cell temperature.

[0133] Table 3 below provides the evaluation indicators for the net load forecast results.

[0134] Table 3 Evaluation Indicators for Net Load Forecast Results

[0135]

[0136] from Figure 9 As can be seen from Table 3, the net load prediction result of Pre1 is very close to the actual value, and its prediction accuracy is significantly higher than that of Pre2 and Pre3. That is, the method of this embodiment, which uses hourly heat transfer, load classification labels and photovoltaic cell temperature, can effectively improve the prediction accuracy of net load.

[0137] The role and effect of the embodiments

[0138] According to the short-term net load forecasting method considering the heat transfer characteristics of building photovoltaics provided in this embodiment, for building roofs equipped with parallel overhead photovoltaic modules, a photovoltaic-roof integrated heat transfer model is constructed using the heat balance method. This model includes the energy balance equations of the components in the photovoltaic modules, the energy balance equations of the air in the ventilation ducts, and the boundary equations of the inner and outer surfaces of the roof. Based on this model, the actual load and photovoltaic output are predicted, thereby obtaining the short-term net load forecasting results. Furthermore, when predicting the actual load, the daily load types for each season are classified based on the model and relevant data. That is, the method in this embodiment fully considers the roof photovoltaic thermal effect, which has a significant impact on load fluctuations, and further subdivides the daily load types according to the seasons, thus effectively improving the accuracy of short-term net load forecasting.

[0139] In the embodiment, the photovoltaic-roof integrated heat transfer model fully considers the heat transfer of the building roof equipped with parallel overhead photovoltaic modules, including the absorption and reflection of solar radiation by the glass cover, the convection and radiation heat transfer between the glass cover and the surrounding environment, the heat transfer between the glass cover and the photovoltaic cells, the heat transfer between the photovoltaic cells and the photovoltaic backsheet, the heat transfer between the photovoltaic backsheet and the air in the ventilation duct, etc. The model is detailed and complete, thus improving the accuracy of short-term net load prediction.

[0140] Furthermore, in the method of the embodiment, the annual heat transfer characteristics of the model are calculated based on meteorological data and non-meteorological data. The daily load type of each season is further classified based on the waveform characteristics of the heat transfer. Finally, the net load of each season is predicted in a short period of time using the heat transfer characteristics as input elements. By comprehensively considering multiple factors, the prediction accuracy is significantly improved.

[0141] In summary, the method in the embodiments deeply explores and characterizes the relationship between rooftop photovoltaics and building load, significantly improving the prediction accuracy of short-term net load in each season.

[0142] The above embodiments are merely illustrative of specific implementations of the present invention, and the present invention is not limited to the scope of the description of the above embodiments. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are only for illustrating the principles of the present invention. Various changes and modifications can be made to the present invention without departing from the spirit and scope thereof, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A short-term net load forecasting method considering building photovoltaic heat transfer characteristics, used to predict the net load of a building, wherein photovoltaic modules are installed on the roof of the building and are parallel to and suspended above the roof, and a ventilation channel is formed between the roof and the photovoltaic modules, characterized in that, Includes the following steps: Step S1: Obtain the relevant data required to predict the net load; Step S2: Calculate the total irradiance of the inclined plane based on the relevant data; Step S3: Construct a photovoltaic-roof integrated heat transfer model for the roof using the heat balance method. The model includes the energy balance equations of the photovoltaic module components, the energy balance equations of the air in the ventilation duct, the one-dimensional unsteady-state heat conduction equation of the roof, the boundary equations of the outer surface of the roof, and the boundary equations of the inner surface of the roof. Step S4: Based on the photovoltaic-roof integrated heat transfer model and the relevant data, the daily load types for each season are divided, and the actual load prediction results for the season to be predicted are calculated in combination with the daily load types. Step S5: Based on the photovoltaic-roof integrated heat transfer model and the relevant data, calculate the photovoltaic output prediction result for the season to be predicted. Step S6: Based on the actual load forecast result and the photovoltaic output forecast result for the season to be predicted, obtain the net load forecast result for the season to be predicted.

2. The short-term net load forecasting method considering building-integrated photovoltaic heat transfer characteristics according to claim 1, characterized in that: in, In step S1, the relevant data includes total solar irradiance data on the horizontal plane, direct irradiance data, diffuse irradiance data, reflected irradiance data, air temperature data, ground temperature data, wind speed data, installation data of the photovoltaic modules, characteristic data of the photovoltaic modules, structural data of the building, thermal property data of the building's roof, thermal property data of the photovoltaic modules, and indoor air conditioning settings data of the building. In step S3, the photovoltaic module includes a glass cover, photovoltaic cells, and a photovoltaic backsheet. The energy balance equations for the components of the photovoltaic module include the energy balance equations for the glass cover, the photovoltaic cells, and the photovoltaic backsheet.

3. The short-term net load forecasting method considering building photovoltaic heat transfer characteristics according to claim 2, characterized in that: in, In step S3, the energy balance equation for the glass cover is: In the formula, M g For the quality of the glass cover, C g For the specific heat of the glass cover, G t α represents the total solar irradiance on the slope. g Let ρ be the absorptivity of the glass cover to solar radiation, A be the area of ​​the glass cover, and ρ be the absorptivity of the glass cover to solar radiation. o,g h represents the reflectivity of the glass cover. c,glass T is the convective heat transfer coefficient between the glass cover and the surrounding environment. a For ambient temperature, h gc Φ is the heat transfer coefficient between the glass cover and the photovoltaic cell. r,g-s This is for the radiative heat exchange between the glass cover and the surrounding environment. The energy balance equation for the photovoltaic cell is: In the formula, G pv G represents the irradiance incident on the photovoltaic cell. pv =G t ·A(1-ρ o,g )(1-α g ), h gc h is the heat transfer coefficient between the photovoltaic cell and the glass cover. tc P is the heat transfer coefficient between the photovoltaic cell and the photovoltaic backsheet. c The output power of the photovoltaic cell. The energy balance equation for the photovoltaic backsheet is: In the formula, h tf ε is the convective heat transfer coefficient between the photovoltaic backsheet and the air inside the ventilation channel; t ε e δ represents the emissivity of the photovoltaic backsheet and the outer surface of the roof, respectively; δ is the Stefan-Boltzmann constant. The energy balance equation for the air within the ventilation duct is: In the formula, h fe Let h be the convective heat transfer coefficient between the air inside the ventilation duct and the outer surface of the roof. fe The convective heat transfer coefficient h between the photovoltaic backsheet and the air in the ventilation channel tf Same; m fr C f These represent the mass flow rate and specific heat capacity of the air within the flow channel, respectively; T fo With T fi These are the inlet and outlet temperatures of the flow channel, respectively, let T be... fo =T a And T f =(T fo +T fi ) / 2, The one-dimensional unsteady heat conduction equation for the roof is: In the formula, a is the thermal diffusivity of the roof material. The boundary equation for the outer surface of the roof is: The boundary equation for the inner surface of the roof is: In the formula, λ e , λ i T represents the thermal conductivity of the outer and inner surfaces of the roof, respectively. he Specify the temperature for indoor air conditioning equipment in a building, h ih The heat transfer coefficient of the inner surface of the roof.

4. The short-term net load forecasting method considering building photovoltaic heat transfer characteristics according to claim 3, Its features are: Step S4 includes the following sub-steps: Step S4-1: Calculate the hourly heat transfer of the roof based on the photovoltaic-roof integrated heat transfer model and the relevant data; Step S4-2: Construct a feature matrix based on the daily maximum and minimum values ​​of the hourly heat transfer, and use hierarchical clustering to classify the daily load types of each season based on the feature matrix to obtain the corresponding daily load type labels for each season. Step S4-3: Construct the actual load input matrix for each season using the load type label, hourly heat transfer, and actual load power time series corresponding to each season. Step S4-4: Based on the actual load input matrix corresponding to the season to be predicted, the actual load of each season is predicted using a bidirectional long short-term memory network algorithm to obtain the actual load prediction result for the season to be predicted.

5. The short-term net load forecasting method considering building-integrated photovoltaic heat transfer characteristics according to claim 4, characterized in that: in, In step S4-3, the input matrix X1 for actual load prediction is: In the formula, h represents the hourly heat transfer of the roof, l represents the load type label, and S... load is the historical actual load power time series, where i is the index value of the sample point and n is the length of the historical actual load power time series.

6. The short-term net load forecasting method considering building photovoltaic heat transfer characteristics according to claim 4, characterized in that: in, In step S4-2, for spring, the number of clusters is five. For summer, autumn, and winter, there are four clusters. Assign a label to each cluster as the load type label.

7. The short-term net load forecasting method considering building photovoltaic heat transfer characteristics according to claim 3, characterized in that: in, Step S5 includes the following sub-steps: Step S5-1: Calculate the photovoltaic cell temperature based on the photovoltaic-roof integrated heat transfer model and the relevant data; Step S5-2: Construct the photovoltaic output input matrix for the season to be predicted based on the photovoltaic cell temperature, the total irradiance of the inclined plane, the relative humidity, and the photovoltaic output time series; Step S5-3: Based on the photovoltaic output input matrix corresponding to the season to be predicted, the photovoltaic output of the season to be predicted is predicted by a bidirectional long short-term memory network algorithm to obtain the photovoltaic output prediction results for each season.

8. The short-term net load forecasting method considering building photovoltaic heat transfer characteristics according to claim 7, characterized in that: in, In step S5-2, the photovoltaic output input matrix is: In the formula, T c For the temperature of photovoltaic cells, G t S is the total irradiance of the inclined plane, H is the relative humidity; S pv This is a historical photovoltaic power output time series.

9. The short-term net load forecasting method considering building-integrated photovoltaic heat transfer characteristics according to claim 1, characterized in that: in, In step S2, the Liu & Jordan model is used to calculate the total irradiance of the slope: In the formula, G t G represents the total irradiance of the inclined plane. b R represents the direct irradiance on a horizontal plane. b G is the ratio of direct irradiance on the inclined plane to that on the horizontal plane. d Let θ be the horizontal diffuse irradiance, θ be the tilt angle of the photovoltaic module, G be the total horizontal irradiance, and ρ be the roof reflectivity.

Images