A New Energy Prediction Algorithm for Solar-Powered Systems

Renewable energy sources can provide the energy requirements of resource-constrained systems due to their inherent continuous availability. Solar power is a good example of the most effective ambient energy source. In literature, it exhibits an uncontrollable but predictable manner which makes the prediction of future energy availability a critical issue. This study presents a new approach to estimate the amount of energy that will available in future, depending on the past energy generation pattern. This approach also considers the fluctuations in energy generation in the current day. It is inspired by a wellknown algorithm, namely Exponential Weighted Moving-Average (EWMA). The performance of the proposed scheme has been tested on various real-world scenarios in comparison to EWMA. The simulation results show that our algorithm provide more accurate estimation of future energy availability than EWMA.