# Sky-image-based solar forecasting using deep learning with multi-location data: training models locally, globally or via transfer learning?

arXiv: https://arxiv.org/abs/2211.02108 · HTML: https://mlsanity.com/paper/2211.02108/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 3 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Deep Photovoltaic Nowcasting](https://mlsanity.com/paper/1810.06327/) (2018)
- [Benchmarking of Deep Learning Irradiance Forecasting Models from Sky Images -- an in-depth Analysis](https://mlsanity.com/paper/2102.00721/) (2021)
- [ECLIPSE : Envisioning CLoud Induced Perturbations in Solar Energy](https://mlsanity.com/paper/2104.12419/) (2021)
- [Convolutional Neural Networks applied to sky images for short-term solar irradiance forecasting](https://mlsanity.com/paper/2005.11246/) (2020)
- [SKIPP'D: a SKy Images and Photovoltaic Power Generation Dataset for Short-term Solar Forecasting](https://mlsanity.com/paper/2207.00913/) (2022)
- [SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting](https://mlsanity.com/paper/2111.14507/) (2021)
- [A Temporally Consistent Image-based Sun Tracking Algorithm for Solar Energy Forecasting Applications](https://mlsanity.com/paper/2012.01059/) (2020)
- [Girasol, a Sky Imaging and Global Solar Irradiance Dataset](https://mlsanity.com/paper/2102.07814/) (2021)
- [SkyCam: A Dataset of Sky Images and their Irradiance values](https://mlsanity.com/paper/2105.02922/) (2021)
- [A Moment in the Sun: Solar Nowcasting from Multispectral Satellite Data using Self-Supervised Learning](https://mlsanity.com/paper/2112.13974/) (2021)

## Built on by (most cited first, 2 of 2)

- [Open-Source Ground-based Sky Image Datasets for Very Short-term Solar Forecasting, Cloud Analysis and Modeling: A Comprehensive Survey](https://mlsanity.com/paper/2211.14709/) (2022)
- [SkyGPT: Probabilistic Short-term Solar Forecasting Using Synthetic Sky Videos from Physics-constrained VideoGPT](https://mlsanity.com/paper/2306.11682/) (2023)

## Abstract (arXiv)

Solar forecasting from ground-based sky images has shown great promise in reducing the uncertainty in solar power generation. With more and more sky image datasets open sourced in recent years, the development of accurate and reliable deep learning-based solar forecasting methods has seen a huge growth in potential. In this study, we explore three different training strategies for solar forecasting models by leveraging three heterogeneous datasets collected globally with different climate patterns. Specifically, we compare the performance of local models trained individually based on single datasets and global models trained jointly based on the fusion of multiple datasets, and further examine the knowledge transfer from pre-trained solar forecasting models to a new dataset of interest. The results suggest that the local models work well when deployed locally, but significant errors are observed when applied offsite. The global model can adapt well to individual locations at the cost of a potential increase in training efforts. Pre-training models on a large and diversified source dataset and transferring to a target dataset generally achieves superior performance over the other two strategies. With 80% less training data, it can achieve comparable performance as the local baseline trained using the entire dataset.