SolarTformer: A Transformer Based Deep Learning Approach for Short Term Solar Power Forecasting

2026-04-27

AI Summary

This study addresses the challenge of insufficient accuracy in short-term solar power forecasting by introducing, for the first time, the Transformer architecture to this task. Leveraging its self-attention mechanism, the proposed model effectively captures both temporal dependencies and spatial variations in solar irradiance, while incorporating power plant metadata to enhance generalization. Within a unified framework, the method achieves high-precision predictions across diverse sites and seasons, demonstrating consistently superior robustness and generalization performance compared to existing models under varied weather conditions—including clear skies and overcast days.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Large Vision Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Accurate forecasting of solar power output is essential for efficient integration of renewable energy into the grid. In this study, an attention-based deep learning model, inspired by transformer architecture, is used for short-term solar power forecasting. Our proposed model, "SolarTformer", is designed to predict solar power output from meteorological data. Unlike traditional models, SolarTformer leverages self-attention mechanisms to effectively capture temporal dependencies and spatial variability in solar irradiance. In addition, the proposed methodology includes feeding power station-specific metadata into the model, which helps to generalize between power stations located at different locations and with different panel configurations and in different seasons. Our experiments demonstrate that SolarTformer significantly outperforms previous models on the same data set. In particular, the model exhibits strong performance on both clear and cloudy days, indicating high robustness and generalizability. These findings highlight the potential of attention-based architectures in enhancing the accuracy of solar forecasting, contributing to a more reliable management of renewable energy.

Problem

• solar power forecasting
• short-term forecasting
• renewable energy integration
• temporal dependencies
• spatial variability

Innovation

• Transformer
• self-attention
• solar power forecasting
• metadata integration
• spatiotemporal modeling