Detection and Optimization of Photovoltaic Arrays’ Tilt Angles Using Remote Sensing Data
Source abstract
Abstract
Maximizing the energy output of photovoltaic (PV) systems is becoming increasingly important. Consequently, numerous approaches have been developed over the past few years that utilize remote sensing data to predict or map solar potential. However, they primarily address hypothetical scenarios, and few focus on improving existing installations. This paper presents a novel method for optimizing the tilt angles of existing PV arrays by integrating Very High Resolution (VHR) satellite imagery and airborne Light Detection and Ranging (LiDAR) data. At first, semantic segmentation of VHR imagery using a deep learning model is performed in order to detect PV modules. The segmentation is refined using a Fine Optimization Module (FOM). LiDAR data are used to construct a 2.5D grid to estimate the modules’ tilt (inclination) and aspect (orientation) angles. The modules are grouped into arrays, and tilt angles are optimized using a Simulated Annealing (SA) algorithm, which maximizes simulated solar irradiance while accounting for shadowing, direct, and anisotropic diffuse irradiances. The method was validated using PV systems in Maribor, Slovenia, achieving a 0.952 F1-score for module detection (using FT-UnetFormer with SwinTransformer backbone) and an estimated electricity production error of below 6.7%. Optimization results showed potential energy gains of up to 4.9%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Solar Radiation and Photovoltaics · Photovoltaic System Optimization Techniques · Photovoltaic Systems and Sustainability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, Slovenia
Faculty of Energy Technology, University of Maribor, 2000 Maribor, Slovenia
Funding
Slovenian Research And Innovation Agency
References (58)
Show source-provided references
1. Review of geographic information systems-based rooftop solar photovoltaic potential estimation approaches at urban scales10.1016/j.apenergy.2021.116817 ↗
2. Power quality experimental analysis of grid-connected photovoltaic systems in urban distribution networks10.1016/j.energy.2017.05.088 ↗
3. Petrie, G., and Toth, C.K. (2018). Airborne and spaceborne laser profilers and scanners. Topographic Laser Ranging and Scanning, CRC Press.10.1201/9781315154381-3 ↗
4. Physical, geographical, technical, and economic potential for the optimal configuration of photovoltaic systems using a digital surface model and optimization method10.1016/j.energy.2021.122971 ↗
5. SPAN: An open-source plugin for photovoltaic potential estimation of individual roof segments using point cloud data10.1016/j.renene.2023.119022 ↗
6. Automatic identification of utilizable rooftop areas in digital surface models for photovoltaics potential assessment10.1016/j.apenergy.2021.118033 ↗
7. High-resolution spatiotemporal assessment of solar potential from remote sensing data using deep learning10.1016/j.renene.2023.119868 ↗
8. Optimisation for large-scale photovoltaic arrays’ placement based on Light Detection And Ranging data10.1016/j.apenergy.2020.114592 ↗
9. Rooftop segmentation and optimization of photovoltaic panel layouts in digital surface models10.1016/j.compenvurbsys.2023.102026 ↗
10. A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata10.1038/s41597-023-01951-4 ↗
11. A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection from Aerial Images10.1109/ACCESS.2023.3275435 ↗
12. SolarNet: A convolutional neural network-based framework for rooftop solar potential estimation from aerial imagery
13. Chen, Z., Kang, Y., Sun, Z., Wu, F., and Zhang, Q. (2022). Extraction of Photovoltaic Plants Using Machine Learning Methods: A Case Study of the Pilot Energy City of Golmud, China. Remote Sens., 14.10.3390/rs14112697 ↗
14. Understanding rooftop PV panel semantic segmentation of satellite and aerial images for better using machine learning10.1016/j.adapen.2021.100057 ↗
15. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany. Proceedings, Part III 18.
16. Roofpedia: Automatic mapping of green and solar roofs for an open roofscape registry and evaluation of urban sustainability10.1016/j.landurbplan.2021.104167 ↗
17. The automatic segmentation of residential solar panels based on satellite images: A cross learning driven U-Net method10.1016/j.asoc.2020.106283 ↗
18. GeoAI for detection of solar photovoltaic installations in the Netherlands10.1016/j.egyai.2021.100111 ↗
19. SP-RAN: Self-paced residual aggregated network for solar panel mapping in weakly labeled aerial images
20. Deep solar PV refiner: A detail-oriented deep learning network for refined segmentation of photovoltaic areas from satellite imagery
21. PVNet: A novel semantic segmentation model for extracting high-quality photovoltaic panels in large-scale systems from high-resolution remote sensing imagery
22. Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv.
23. Hu, J., Shen, L., Albanie, S., Sun, G., and Wu, E. (2019). Squeeze-and-Excitation Networks. arXiv.10.1109/CVPR.2018.00745 ↗
24. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017, January 4–9). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11231 ↗
25. Assessment of the large-scale extraction of photovoltaic (PV) panels with a workflow based on artificial neural networks and algorithmic postprocessing of vectorization results
26. TransPV: Refining photovoltaic panel detection accuracy through a vision transformer-based deep learning model10.1016/j.apenergy.2023.122282 ↗
27. Photovoltaic panel extraction from very high-resolution aerial imagery using region—Line primitive association analysis and template matching10.1016/j.isprsjprs.2018.04.010 ↗
28. Solar photovoltaic module detection using laboratory and airborne imaging spectroscopy data10.1016/j.rse.2021.112692 ↗
29. Developing a deep learning-based layer-3 solution for thermal infrared large-scale photovoltaic module inspection from orthorectified big UAV imagery data
30. Advances and prospects on estimating solar photovoltaic installation capacity and potential based on satellite and aerial images10.1016/j.rser.2023.113276 ↗
31. 3D-PV-Locator: Large-scale detection of rooftop-mounted photovoltaic systems in 3D10.1016/j.apenergy.2021.118469 ↗
32. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
33. Ravishankar, R., AlMahmoud, E., Habib, A., and de Weck, O.L. (2022). Capacity Estimation of Solar Farms Using Deep Learning on High-Resolution Satellite Imagery. Remote Sens., 15.10.3390/rs15010210 ↗
34. A framework to estimate generating capacities of PV systems using satellite imagery segmentation10.1016/j.engappai.2023.106186 ↗
35. Chen, Y., Lin, G., Li, S., Bourahla, O., Wu, Y., Wang, F., Feng, J., Xu, M., and Li, X. (2020, January 13–19). Banet: Bidirectional aggregation network with occlusion handling for panoptic segmentation. Proceedings of the IEEE/CVF Conference on Computer vision And Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00385 ↗
36. Hu, M., Li, Y., Fang, L., and Wang, S. (2021, January 20–25). A2-FPN: Attention aggregation based feature pyramid network for instance segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01509 ↗
37. A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images
38. MANet: A multi-level aggregation network for semantic segmentation of high-resolution remote sensing images10.1080/01431161.2022.2073795 ↗
39. UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery10.1016/j.isprsjprs.2022.06.008 ↗
40. Building the component tree in quasi-linear time10.1109/TIP.2006.877518 ↗
41. Gharibi, H., and Habib, A. (2018). True orthophoto generation from aerial frame images and LiDAR data: An update. Remote Sens., 10.10.3390/rs10040581 ↗
42. Kavran, D., Mongus, D., and Lukač, N. (2024, January 17–19). Buildings, Approximate True Orthophoto Construction From Satellite Imagery Using Semantic Segmentation and the ICP Algorithm. Proceedings of the 2024 International Conference on Computer, Information and Telecommunication Systems (CITS), Girona, Spain.10.1109/CITS61189.2024.10608032 ↗
43. Boulch, A., Puy, G., and Marlet, R. (December, January 30). FKAConv: Feature-kernel alignment for point cloud convolution. Proceedings of the Asian Conference on Computer Vision, Kyoto, Japan.
44. Obtaining a best fitting plane through 3D georeferenced data10.1016/j.jsg.2004.12.004 ↗
45. DBSCAN revisited, revisited: Why and how you should (still) use DBSCAN10.1145/3068335 ↗
46. Simulated annealing10.1214/ss/1177011077 ↗
47. Delahaye, D., Chaimatanan, S., and Mongeau, M. (2019). Simulated annealing: From basics to applications. Handbook of Metaheuristics, Springer.10.1007/978-3-319-91086-4_1 ↗
48. Novel GPU-accelerated high-resolution solar potential estimation in urban areas by using a modified diffuse irradiance model10.1016/j.apenergy.2023.122129 ↗
49. Duffie, J.A., Beckman, W.A., and Blair, N. (2020). Solar Engineering of Thermal Processes, Photovoltaics and Wind, John Wiley & Sons, Inc.
50. Hall, I., Prairie, R., Anderson, H., and Boes, E. (1978). Generation of a Typical Meteorological Year, Sandia Labs.. Technical Report.
51. Solar position algorithm for solar radiation applications10.1016/j.solener.2003.12.003 ↗
52. Modeling daylight availability and irradiance components from direct and global irradiance10.1016/0038-092X(90)90055-H ↗
53. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE conference on computer vision and pattern recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
54. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
55. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11–17). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00986 ↗
56. A new simplified version of the Perez diffuse irradiance model for tilted surfaces10.1016/S0038-092X(87)80031-2 ↗
57. nasapower: A NASA POWER global meteorology, surface solar energy and climatology data client for R10.21105/joss.01035 ↗
58. Aghenta, L.O., and Iqbal, M.T. (2019, January 5–8). Development of an IoT based open source SCADA system for PV system monitoring. Proceedings of the 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE), Edmonton, AB, Canada.10.1109/CCECE.2019.8861827 ↗