Existing old residential area low-carbon transformation potential rapid evaluation method in combination with convolutional neural network

Abstract

The invention provides an existing old residential district low-carbon transformation potential rapid evaluation method in combination with a convolutional neural network, and belongs to the technical field of building photovoltaic integration, and the method comprises the steps: firstly building a three-dimensional digital city model; based on the three-dimensional digital city model, calculating old residential district city morphological indexes, establishing a building energy consumption simulation model and a BIPV simulation model, and performing numerical simulation; according to a numerical simulation result, carbon emission conversion calculation of old residential area BIPV low-carbon transformation is carried out; establishing an association database of the urban morphological indexes of the old residential districts, the building energy consumption, the BIPV potential and the building carbon emission; carrying out the training, verification and testing of a CNN algorithm, and judging the low-carbon transformation potential of the urban old residential district BIPV; compared with traditional energy-saving measures such as pipeline transformation and external wall heat preservation, the method for implementing BIPV transformation on the old community is beneficial to improving the energy self-sufficiency capacity of a building, promoting transformation and upgrading of the old community and remarkably reducing urban carbon emission.

Description

Technical Field

[0001] The present invention belongs to the technical field of building integrated photovoltaics, and specifically relates to a method for quickly evaluating the low-carbon transformation potential of existing old residential areas by combining convolutional neural networks. Background Art

[0002] The problem of high carbon emissions accompanying urban development is becoming increasingly prominent. With the continuous advancement of urban construction and the deepening of renovation in China, the use of solar renewable energy can significantly reduce traditional energy consumption and building operation carbon emissions. As major energy consumers, old urban residential areas have an urgent need for low-carbon transformation. Currently, traditional centralized heating and hot water systems are still commonly used in old residential areas, and the low-carbon transformation methods are limited to traditional methods such as pipeline renovation and exterior wall renovation, with limited potential for energy efficiency improvement; while photovoltaic renovation projects often rely on empirical judgment, lacking applicability and pertinence, resulting in difficult-to-guarantee renovation effects, affecting overall efficiency, and causing waste of resources.

[0003] Therefore, exploring a more efficient and accurate low-carbon transformation evaluation method is of great significance for old residential areas. As an emerging technology with extensive practice, building integrated photovoltaics (BIPV) shows higher operability and popularization potential compared with other low-carbon transformation means. Summary of the Invention

[0004] Based on the above background, the present invention proposes a method for quickly evaluating the low-carbon transformation potential of existing old residential areas by combining convolutional neural networks. By combining deep learning algorithms, an intelligent evaluation model based on building form and spatial characteristics is constructed, which can quickly identify the low-carbon transformation potential of old residential areas and effectively provide scientific guidance for renovation.

[0005] The present invention is realized through the following technical solutions:

[0006] A method for quickly evaluating the low-carbon transformation potential of existing old residential areas by combining convolutional neural networks:

[0007] The method specifically includes the following steps:

[0008] Step 1: Use satellite remote sensing data and a modeling platform to establish a three-dimensional digital city model;

[0009] Step 2: Calculate the urban form indicators of the old residential area based on the three-dimensional digital city model;

[0010] Step 3: Use meteorological station data to establish a building energy consumption simulation model and a BIPV simulation model for numerical simulation;

[0011] Step 4: According to the numerical simulation results, perform carbon emission conversion calculation for the BIPV low-carbon transformation of the old residential area;

[0012] Step 5: Establish a four - correlation database of urban form indicators, building energy consumption, BIPV potential, and building carbon emissions in old residential areas;

[0013] Step 6: Based on the database, conduct training, validation, and testing of the CNN algorithm to judge the potential of BIPV low - carbon transformation in old urban residential areas.

[0014] Furthermore, in Step 1, it includes:

[0015] Step 1.1, Obtain high - resolution satellite remote sensing data, where the satellite remote sensing data includes the target old residential area and its surrounding areas;

[0016] Step 1.2, Import the obtained satellite remote sensing data into the modeling platform, and use the geographic information processing tools in the platform to process the image data;

[0017] Step 1.3, According to the ground object features in the image data, use the 3D modeling function of the modeling platform to conduct 3D modeling of buildings, roads, and green spaces in the city, and construct a 3D digital city model including the old residential area.

[0018] Furthermore, in Step 2,

[0019] The urban form indicators of the old residential area include: building density, average building height, building orientation, building height fluctuation value, sky view factor, enclosure index, volume index, and block interface openness ratio.

[0020] Furthermore, in Step 3,

[0021] Obtain meteorological station data for at least one year as environmental parameters during simulation;

[0022] For building energy consumption simulation, record the energy consumption values of buildings in different seasons and different time periods, including building heating, cooling, lighting, and equipment energy consumption, set the simulation time range and step size, and use the Energy Use Intensity (EUI) to evaluate the energy performance of buildings;

[0023] For BIPV simulation, based on the BIPV system of CIGS thin - film solar cells, set the simulation time range and step size to be consistent with the building energy consumption simulation, and use the solar power generation intensity to represent the solar power generation potential of the rooftop photovoltaic system.

[0024] Furthermore, in Step 4,

[0025] From the output results of the building energy consumption simulation model in step 3, extract the annual cooling energy consumption per unit area, lighting energy consumption, equipment energy consumption of each building in the old residential area, and the annual heating energy consumption per unit area. According to the regional information, find the average carbon emission factor and coal energy carbon emission factor of the corresponding regional power grid, calculate the annual coal carbon emission per unit area and the annual electricity carbon emission per unit area, and obtain the total annual carbon emission per unit area of the old residential area.

[0026] Furthermore, in step 6,

[0027] Extract data from the database established in step 5, and divide it into a training set, a validation set, and a test set;

[0028] Construct a CNN model and use the training set for training. During the training process, define a loss function to measure the difference between the model prediction value and the true value; use the validation set data to verify the model. Calculate the accuracy of the model on the validation set, optimize and adjust the model; finally, use the test set to test the trained model, and judge the reliability of the model by calculating the coefficient of determination R 2 and the root mean square error RMSE of the training set, test set, and validation set.

[0029] Furthermore, the evaluation method further includes:

[0030] Step 7: Use visualization software to draw the BIPV low-carbon transformation potential map of the renovated old urban residential area;

[0031] According to the prediction results of the CNN model in step 6, classify the BIPV low-carbon transformation potential of different regions in the old residential area, and set different colors or symbols to represent regions with different potential levels.

[0032] A rapid evaluation system for the low-carbon transformation potential of existing old residential areas combined with convolutional neural networks:

[0033] The evaluation system includes an urban modeling module, a data simulation module, a carbon emission conversion module, and a transformation potential evaluation module;

[0034] The urban modeling module uses satellite remote sensing data and a modeling platform to establish a three-dimensional digital city model;

[0035] The data simulation module calculates the urban form indicators of the old residential area based on the three-dimensional digital city model; uses meteorological station data to establish a building energy consumption simulation model and a BIPV simulation model for numerical simulation;

[0036] The carbon emission conversion module performs carbon emission conversion calculations for the BIPV low-carbon transformation of the old residential area according to the numerical simulation results;

[0037] The potential evaluation module establishes a four - correlation database of urban form indicators, building energy consumption, BIPV potential, and building carbon emissions in old residential areas; based on the database, training, verification, and testing of the CNN algorithm are carried out to judge the potential of BIPV low - carbon transformation in old urban residential areas.

[0038] An electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above - mentioned method are implemented.

[0039] A computer - readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps of the above - mentioned method are implemented.

[0040] Advantages of the present invention

[0041] Compared with the prior art, the rapid evaluation method for the low - carbon transformation potential of existing old residential areas combined with a convolutional neural network of the present invention has the following advantages:

[0042] 1. Improve the utilization rate of urban renewable energy: The implementation of BIPV (Building Integrated Photovoltaic) transformation in old communities proposed by the present invention, compared with traditional energy - saving measures such as pipeline transformation and external wall insulation, helps to improve the energy self - sufficiency ability of buildings, promotes the transformation and upgrading of old residential areas, and significantly reduces urban carbon emissions.

[0043] 2. Rapidly evaluate the potential of BIPV low - carbon transformation in old communities: The rapid evaluation model for BIPV transformation in old communities constructed by the present invention can help decision - makers quickly judge the potential of low - carbon transformation in old urban residential areas. This evaluation method also has reference significance for the low - carbon construction and renewal of other functional - type buildings such as schools and industrial parks.

[0044] 3. Improve the accuracy and efficiency of evaluation: The present invention combines a convolutional neural network. Compared with traditional methods, image data has the characteristics of easy acquisition, large amount of information, and strong difference, which is convenient for training deep - learning algorithms with simulation results and can effectively enhance the accuracy of building photovoltaic performance prediction. Description of the drawings

[0045] Figure 1 It is a schematic flow chart of the method of the present invention. Detailed implementation manners

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] In the following embodiments, the experimental methods used are all conventional methods unless otherwise specified. The materials, reagents, methods, and instruments used are all conventional materials, reagents, methods, and instruments in this field and can be obtained by those skilled in the art through commercial channels without special instructions.

[0048] A rapid assessment method for the low-carbon transformation potential of existing old residential areas combined with convolutional neural networks:

[0049] Step 1: Use satellite remote sensing data and a modeling platform to establish a three-dimensional digital city model;

[0050] Step 1.1, Obtain high-resolution satellite remote sensing data, and the satellite remote sensing data includes the target old residential area and a certain range of areas around it;

[0051] Step 1.2, Select a suitable modeling platform, import the obtained satellite remote sensing data into the modeling platform for processing; for example, correct the remote sensing data through a GIS (Geographic Information Processing System) platform, and import the processed data into a Rhino three-dimensional digital modeling platform;

[0052] Step 1.3, According to the ground object characteristics in the image data, use the three-dimensional modeling function of the modeling platform to perform three-dimensional modeling on elements such as buildings, roads, and green spaces in the city.

[0053] For buildings, information such as the outline, number of floors, and geographical coordinates of the buildings needs to be included to construct a three-dimensional digital city model containing the old residential area;

[0054] Step 2: Based on the three-dimensional digital city model in Step 1, calculate the urban form indicators of the old residential area;

[0055] The urban form indicators of the old residential area include: building density, average building height, building orientation, building height fluctuation value, sky view factor, enclosure index, volume index, and block interface openness ratio.

[0056] The calculation formulas and descriptions of the form indicators in Step 2 are shown in Table 1:

[0057]

[0058] Table 1 Urban form indicators of old residential areas and their calculation formulas

[0059] Step 3, Use meteorological station data to establish a building energy consumption simulation model and a BIPV simulation model for numerical simulation;

[0060] Obtain meteorological station data of typical sample meteorological data corrected by the average value of meteorological data in the past ten years (in years) as the environmental parameters during simulation;

[0061] For building energy consumption simulation, record the energy consumption values of the building in different seasons and at different times, including the heating, cooling, lighting, and equipment energy consumption of the building. Set the time range and step size of the simulation, and use the Energy Use Intensity (EUI) to evaluate the energy performance of the building;

[0062] For BIPV simulation, for a BIPV system based on CIGS thin-film solar cells, set the time range and step size of the simulation to be consistent with the building energy consumption simulation, and use the solar power generation intensity to represent the solar power generation potential of the rooftop PV system.

[0063] Building energy consumption simulation formula:

[0064]

[0065] In the formula is the sum of the convective internal loads, represents the convective heat transfer from the surface of the zone, represents the heat transfer between the mixed zones, m inf C p (T ∞ -T z ) represents the heat transfer from the outside air. Among them, Q sys is the output of the air conditioning system, and Q storage is the energy saved in the zone air.

[0066] Energy consumption evaluation formula

[0067] The present invention uses the Energy Use Intensity (EUI) to evaluate the energy performance of the building. EUI represents the energy consumption per unit area of the building in a year. The sources of energy consumption considered include the heating, cooling, lighting, and equipment energy consumption of the building. EUI is calculated by the following formula:

[0068]

[0069] In the formula, EUI is the energy use intensity (kWh / m 2 ), E H is the heating energy consumption (kWh), E C is the cooling energy consumption (kWh), E L is the building lighting energy consumption (kWh), E E is the building equipment energy consumption (kWh), and A is the total building floor area (m 2 ).

[0070] BIPV simulation formula:

[0071] In the present invention, a BIPV system using copper indium gallium selenide (CIGS) thin-film solar cells is adopted. According to existing methods and research reports, the present invention calculates using the following conservative values. Considering the installation of other service equipment such as air conditioners on the building facades and roofs and the limitations of the photovoltaic module layout, the coverage rate of photovoltaic panels on the building monomer wall is defined as 70%. The loss efficiency of the photovoltaic system is 20%. The average production efficiency of commercial components of CIGS photovoltaic technology is between 12% and 15%. The conversion efficiency of the photovoltaic cell is set to 12%. Since the energy consumption evaluation index and subsequent carbon emission analysis are both calculated per unit building area, the solar energy generation intensity (SEGI) is used to represent the solar energy generation potential of the rooftop photovoltaic system. The calculation method is shown in the following formula

[0072]

[0073] In the formula, SEGI is the solar energy generation intensity (kWh / m 2 ), I is the annual solar radiation intensity on the surface of the photovoltaic cell (kWh / m 2 ), K E is the conversion efficiency of the photovoltaic cell (%), K s is the loss efficiency of the photovoltaic system (%), A P is the net area of the photovoltaic panel (m 2 ), A is the total building floor area (m 2 )

[0074] Step 4: According to the numerical simulation results in Step 3, perform the carbon emission conversion calculation for the low-carbon transformation of the old residential area with BIPV;

[0075] From the output results of the building energy consumption simulation model in Step 3, extract the annual cooling energy consumption per unit area, lighting energy consumption, equipment energy consumption of each building in the old residential area, and the annual heating energy consumption per unit area. According to the regional information, find the average carbon emission factor and coal energy carbon emission factor of the corresponding regional power grid, calculate the annual carbon emissions per unit area of coal combustion and the annual carbon emissions per unit area of electric energy, and obtain the total annual carbon emissions per unit area of the old residential area.

[0076] Carbon emission calculation formula:

[0077] The present invention uses the emission factor method to carry out the carbon emission quantification research and calculates according to the "Standard for Calculating Building Carbon Emissions" (GB / T 51366-2019). Substitute the selected evaluation indicators into the calculation formula for the building operation stage to obtain the following formula:

[0078] C = CO 2C + CO 2E = (E cooling + E lighting + E equipment ) EFE +E heating EF C

[0079] In the formula, C is the total annual carbon emissions per unit area (kgCO2e);

[0080] CO 2C ——The annual carbon emissions from coal per unit area (kgCO2e);

[0081] CO 2E ——The annual carbon emissions from electricity per unit area (kgCO2e);

[0082] E cooling 、E lighting 、E equipment ——The annual cooling energy consumption, lighting energy consumption, and equipment energy consumption per unit area (kWh);

[0083] E heating ——The annual heating energy consumption per unit area (GJ);

[0084] EF E 、EF C ——The average carbon emission factor of the regional power grid and the carbon emission factor of coal energy (kgCO2e / kWh, kgCO2e / GJ).

[0085] In the present invention, the carbon emission factors mainly refer to the "Standard for Calculating Building Carbon Emissions". The carbon emission factor of the power grid adopts the value in the "Research Report on Building Energy Consumption and Carbon Emissions in China (2021)" published by the Energy Consumption Statistics Committee of the China Building Energy Conservation Association in 2021.

[0086] Step 5: Establish a four-correlation database for the urban form indicators, building energy consumption, BIPV potential, and building carbon emissions of old residential areas;

[0087] In the selected database management system, create four main data tables, which are respectively used to store the urban form indicator data, building energy consumption data, BIPV potential data, and building carbon emission data of old residential areas;

[0088] Among them, the stored urban form indicator data of old residential areas includes building density, plot ratio, building height distribution, greening rate, etc.

[0089] The building energy consumption data includes the building energy consumption data in different seasons and different time periods.

[0090] The BIPV potential data includes BIPV power generation power, power generation amount, power generation efficiency, etc.

[0091] The building carbon emission data includes the annual coal carbon emission per unit area, the annual electricity carbon emission per unit area in Step 4, and the total annual carbon emission per unit area of the old residential areas.

[0092] Step 6: Based on the database, conduct the training, validation, and testing of the CNN algorithm;

[0093] Extract data from the database established in Step 5 and divide it into a training set, a validation set, and a testing set according to the ratio of 70%, 15%, and 15%.

[0094] Build a CNN model and use the training set for training. During the training process, define a loss function to measure the difference between the predicted value and the true value of the model; use the validation set data to verify the model. Calculate the accuracy of the model on the validation set and optimize and adjust the model; finally, use the testing set to test the trained model, and judge the reliability of the model by calculating the determination coefficient R 2 and the root mean square error RMSE of the training set, the testing set, and the validation set.

[0095] Step 7: Use visualization software to draw the potential map of the BIPV low-carbon transformation of the old urban residential areas.

[0096] According to the prediction results of the CNN model in Step 6, classify the BIPV low-carbon transformation potential of different regions in the old residential areas, and set different colors or symbols to represent the regions with different potential levels.

[0097] A rapid assessment system for the low-carbon transformation potential of existing old residential areas combined with convolutional neural networks:

[0098] The assessment system includes an urban modeling module, a data simulation module, a carbon emission conversion module, and a transformation potential assessment module;

[0099] The urban modeling module uses satellite remote sensing data and a modeling platform to establish a three-dimensional digital city model;

[0100] The data simulation module calculates the urban form indicators of the old residential areas based on the three-dimensional digital city model; uses the meteorological station data to establish a building energy consumption simulation model and a BIPV simulation model for numerical simulation;

[0101] The carbon emission conversion module conducts carbon emission conversion calculations for the BIPV low-carbon transformation of the old residential areas according to the numerical simulation results;

[0102] The potential assessment module establishes a four-way association database of the urban form indicators, building energy consumption, BIPV potential, and building carbon emissions of the old residential areas; based on the database, conducts the training, validation, and testing of the CNN algorithm to judge the BIPV low-carbon transformation potential of the old urban residential areas.

[0103] An electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0104] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the steps of the above method are implemented.

[0105] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM). It should be noted that the memory of the method described in the present invention is intended to include, but not limited to, these and any other suitable types of memory.

[0106] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire, such as coaxial cable, optical fiber, digital subscriber line (DSL), or wirelessly, such as infrared, wireless, microwave, etc. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, data center, etc., that includes one or more integrated available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, magnetic tape, an optical medium, such as a high-definition digital video disc (DVD), or a semiconductor medium, such as a solid-state disk (SSD), etc.

[0107] In the implementation process, the steps of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by the hardware processor or completed by the combination of the hardware and software modules in the processor. The software module can be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0108] It should be noted that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method embodiments can be completed by the integrated logic circuit in the hardware of the processor or instructions in software form. The above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0109] The above has introduced in detail a method for quickly evaluating the low-carbon transformation potential of existing old residential areas in combination with convolutional neural networks, and has elaborated on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A rapid evaluation method for the low-carbon transformation potential of existing old residential areas combined with convolutional neural networks, characterized in that: The method specifically includes the following steps: Step 1: Use satellite remote sensing data and a modeling platform to establish a three-dimensional digital city model; Step 2: Calculate the urban form indicators of old residential areas based on the three-dimensional digital city model; Step 3: Use meteorological station data to establish a building energy consumption simulation model and a BIPV simulation model for numerical simulation; Step 4: According to the numerical simulation results, perform carbon emission conversion calculations for the BIPV low-carbon transformation of old residential areas; Step 5: Establish a four-correlation database of urban form indicators, building energy consumption, BIPV potential, and building carbon emissions for old residential areas; Step 6: Based on the database, perform training, verification, and testing of the CNN algorithm to judge the BIPV low-carbon transformation potential of urban old residential areas.

2. The evaluation method according to claim 1, wherein: In Step 1, it includes: Step 1.1, Obtain high-resolution satellite remote sensing data, where the satellite remote sensing data includes the target old residential area and its surrounding areas; Step 1.2, Import the obtained satellite remote sensing data into the modeling platform, and use the geographic information processing tools in the platform to process the image data; Step 1.3, According to the ground object characteristics in the image data, use the three-dimensional modeling function of the modeling platform to perform three-dimensional modeling of buildings, roads, and green spaces in the city, and construct a three-dimensional digital city model including the old residential area.

3. The evaluation method according to claim 2, characterized in that: In Step 2, The urban form indicators of the old residential area include: building density, average building height, building orientation, building height floating value, sky view factor, enclosure index, volume index, and block interface openness ratio.

4. The evaluation method according to claim 3, wherein: In Step 3, Obtain at least one year of meteorological station data as the environmental parameters during simulation; For building energy consumption simulation, record the energy consumption values of buildings in different seasons and different time periods, including heating, cooling, lighting, and equipment energy consumption of the building, set the simulation time range and step size, and use the Energy Use Intensity (EUI) to evaluate the energy performance of the building; For BIPV simulation, based on the BIPV system of CIGS thin-film solar cells, set the simulation time range and step size to be consistent with the building energy consumption simulation, and use the solar power generation intensity to represent the solar power generation potential of the rooftop photovoltaic system.

5. The evaluation method according to claim 4, wherein: In Step 4, Extract the annual cooling energy consumption per unit area, lighting energy consumption, equipment energy consumption, and annual heating energy consumption per unit area of each building in the old residential area from the output results of the building energy consumption simulation model in Step 3. According to the regional information, find the average carbon emission factor of the regional power grid and the carbon emission factor of coal energy, and calculate the annual carbon emissions per unit area of coal combustion and the annual carbon emissions per unit area of electric energy to obtain the total annual carbon emissions per unit area of the old residential area.

6. The evaluation method according to claim 5, characterized in that: In Step 6, Extract data from the database established in Step 5 and divide it into a training set, a validation set, and a test set; Construct a CNN model and use the training set for training. During the training process, define a loss function to measure the difference between the model prediction value and the true value; Use the validation set data to validate the model. Calculate the accuracy of the model on the validation set and optimize and adjust the model. Finally, use the test set to test the trained model, and judge the reliability of the model by calculating the coefficient of determination R 2 and the root mean square error RMSE.

7. The evaluation method according to claim 6, wherein: The evaluation method further includes: Step 7: Use visualization software to draw a map of the BIPV low-carbon transformation potential of the renovated urban old residential area; According to the prediction results of the CNN model in step 6, the BIPV low-carbon transformation potential of different regions in old residential areas is graded, and different colors or symbols are set for regions with different potential levels.

8. An evaluation system for rapidly evaluating the low-carbon transformation potential of existing old residential areas combined with a convolutional neural network according to any one of claims 1 to 7, characterized in that: The evaluation system includes an urban modeling module, a data simulation module, a carbon emission conversion module, and a transformation potential evaluation module; The urban modeling module uses satellite remote sensing data and a modeling platform to establish a three-dimensional digital city model; The data simulation module calculates the urban form indicators of old residential areas based on the three-dimensional digital city model; uses meteorological station data to establish a building energy consumption simulation model and a BIPV simulation model for numerical simulation; The carbon emission conversion module performs carbon emission conversion calculations for the BIPV low-carbon transformation of old residential areas according to the numerical simulation results; The potential evaluation module establishes a four-way association database of urban form indicators, building energy consumption, BIPV potential, and building carbon emissions in old residential areas; based on the database, conducts training, verification, and testing of the CNN algorithm to judge the BIPV low-carbon transformation potential of urban old residential areas.

9. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium for storing computer instructions, characterized in that, The computer instructions implement the steps of the method according to any one of claims 1 to 7 when executed by the processor.

Images