Search

Solar energy captured by solar photovoltaic (PV) systems has great potential to meet the high demand for renewable energy sources in urban areas. A photovoltaic noise barrier (PVNB) system, which integrates a PV system with a noise barrier, is a promising source for harvesting solar energy to overcome the problem of having limited land available for solar panel installations. When estimating the solar PV potential at the city scale, it is difficult to identify sites for installing solar panels. A computational framework is proposed for estimating the solar PV potential of PVNB systems based on both existing and planned noise barrier sites. The proposed computational framework can identify suitable sites for installing photovoltaic panels. A deep learning-based method is used to detect existing noise barrier sites from massive street-view images. The planned noise barrier sites are identified with urban policies. Based on the existing and planned sites of noise barriers in Nanjing, the annual solar PV potentials in 2019 are 29,137 MW h and 113,052 MW h, respectively. The estimation results show that the potential PVNB systems based on the existing and planned noise barrier in 2019 have the potential installed capacity of 14.26 MW and 57.24 MW, with corresponding potential annual power generation of 4662 MW h and 18,088 MW h, respectively. • A photovoltaic noise barrier system is promising source for harvesting solar energy. • Detect existing noise barrier from street-view images with 96.22% accuracy. • Solar PV potentials of existing and planned noise barriers are estimated. • Installed capacity of proposed PVNB systems reach 14.26 MW and 57.24 MW. • Potential annual power generation are 4662 MW h and 18,088 MW h. [ABSTRACT FROM AUTHOR]

• A framework for city-scale rooftop solar PV potential estimation was developed. • Labor cost of deep learning was significantly reduced with proposed spatial optimization sampling strategy. • Rooftop extraction model was proved to be robust in districts with different architectural styles and land use. • 311,853 GWh rooftop solar PV potential was estimated for Nanjing in 2019. • 330.36 km2 rooftop area and 66 GW installed capacity were estimated for Nanjing. The estimation of rooftop solar photovoltaic (PV) potential is crucial for policymaking around sustainable energy plans. But it is difficult to accurately estimate the availability of rooftop area for solar radiation on a city-scale. In this study, a generic framework for estimating the rooftop solar PV potential on a city-scale using publicly available high-resolution satellite images is proposed. A deep learning-based method is developed to extract the rooftop area with image semantic segmentation automatically. A spatial optimization sampling strategy is developed to solve the labor-intensive problem when training the rooftop extraction model based on prior knowledge of urban and rural spatial layout and land use. In the case study of Nanjing, China, the labor cost on preparing the dataset for training the rooftop extraction model has been reduced by about 80% with the proposed spatial optimization sampling strategy. Meanwhile, the robustness of the rooftop extraction model in districts with different architectural styles and land use has been improved. The total rooftop area extracted was 330.36 km2, and the overall accuracy reached 0.92. The estimation results show that Nanjing has significant potential for rooftop-mounted PV installations, and the potential installed capacity reached 66 GW. The annual rooftop solar PV potential was approximately 311,853 GWh, with a corresponding estimated power generation of 49,897 GWh in 2019. [ABSTRACT FROM AUTHOR]