Anomaly Detection in Renewable Energy Big Data Using Deep Learning

Abstract

This work aims to review the literature on anomaly detection (AD) in renewable energy. Due to the significance of the RE data quality and sensor performance, it is crucial to ensure that the measurement device works correctly and maintains data accuracy. The review identifies the relevant studies on big data anomaly detection in the energy field and synthesizes the related techniques. Also, the study shows a need for segmentation annotations for solar system electroluminescence imagery complicating the domain development of anomaly segmentation approaches. Consequently, most processes create machine learning (ML) models using semi-supervised techniques. Still, these approaches need more generalization regarding variation in environmental or systematic conditions. Furthermore, the studies discussed here focus on existing algorithms that used big data and AD to propose an improved analysis framework. Finally, the work presents a framework to solve the problem of identifying sensors' issues that will appear in data anomalies.