A Lightweight Short-Term Photovoltaic Power Prediction for Edge Computing

To meet the needs for energy savings in Internet of Things (IoT) systems, solar energy has been increasingly exploited to serve as a green and renewable source to allow systems to better operate in an energy-efficient way. In this respect, accurate PV power output prediction is a prerequisite for any energy saving scheme employed in these systems. In this work, we propose a unified training framework combined with the LightGBM algorithm to obtain a prediction model, which can provide short-term predictions of PV power output. Compared with the training in a single powerful machine, our proposed framework is more energy-efficient and fits into devices with limited computation and storage resources. The experimental results show that our proposed framework is superior to other benchmark machine learning algorithms.