Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations

TL;DR

This paper introduces a semi-supervised deep domain adaptation method that enables accurate solar power prediction across different locations with minimal labeled data, addressing domain shift caused by weather and geographic variability.

Contribution

It proposes a source-free teacher-student deep learning framework for effective domain adaptation using limited labeled target data, improving prediction accuracy across diverse locations.

Findings

Achieved up to 11.36% accuracy improvement in California

Reduced labeled data requirement to 20% in target domain

Effective adaptation without source data using teacher-student model

Abstract

Accurate solar generation prediction is essential for proper estimation of renewable energy resources across diverse geographic locations. However, geographical and weather features vary from location to location which introduces domain shift - a major bottleneck to develop location-agnostic prediction model. As a result, a machine-learning model which can perform well to predict solar power in one location, may exhibit subpar performance in another location. Moreover, the lack of properly labeled data and storage issues make the task even more challenging. In order to address domain shift due to varying weather conditions across different meteorological regions, this paper presents a semi-supervised deep domain adaptation framework, allowing accurate predictions with minimal labeled data from the target location. Our approach involves training a deep convolutional neural network on a source location's data and adapting it to the target location using a source-free, teacher-student model configuration. The teacher-student model leverages consistency and cross-entropy loss for semi-supervised learning, ensuring effective adaptation without any source data requirement for prediction. With annotation of only $20 \%$ data in the target domain, our approach exhibits an improvement upto $11.36 \%$, $6.65 \%$, $4.92\%$ for California, Florida and New York as target domain, respectively in terms of accuracy in predictions with respect to non-adaptive approach.