Solar Power Generation Forecasting via Multimodal Feature Fusion (Student Abstract)


  • Eul Ka Chungbuk National University
  • Seungeun Go Chungbuk National University
  • Minjin Kwak Chungbuk National University
  • Jeong-Hun Kim Bigdata Research Institute, Chungbuk National University
  • Aziz Nasridinov Chungbuk National University



Multimodal Learning, Multi-modal Vision, Segmentation, Computer Vision


Solar power generation has recently been in the spotlight as global warming continues to worsen. However, two significant problems may hinder solar power generation, considering that solar panels are installed outside. The first is soiling, which accumulates on solar panels, and the second is a decrease in sunlight owing to bad weather. In this paper, we will demonstrate that the solar power generation forecasting can increase when considering soiling and sunlight information. We first introduce a dataset containing images of clean and soiled solar panels, sky images, and weather information. For accurate solar power generation forecasting, we propose a new multimodal model that aggregates various features related to weather, soiling, and sunlight. The experimental results demonstrated the high accuracy of our proposed multimodal model.



How to Cite

Ka, E., Go, S., Kwak, M., Kim, J.-H., & Nasridinov, A. (2024). Solar Power Generation Forecasting via Multimodal Feature Fusion (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23530-23532.