A novel solar energy predictor for communicating sensors

International audienceSolar energy harvesting constitutes an attractive solution to provide energy for communicating objects. Theadvantage of this energy over other forms of renewable energy is that the available solar power can be predicted withreasonable accuracy, which allows the implementation of efficient power management techniques. Nevertheless, harvestedsolar energy comes from a non-controllable source. Therefore, the prediction of the solar radiation and energy availability is acritical issue, as the amount of the harvested energy may vary over time. In this study, a novel solar radiation and energypredictor (Solar Energy Predictor for Communicating Sensors: SEPCS) is proposed. This prediction model uses past energyobservations to forecast future energy availability in short term. To assess the performance of the proposed algorithm, authorsused database providing the solar radiation evolution for one year. Then, a comparative performance evaluation shows that theSEPCS predictor significantly outperforms the state-of-the-art energy predictors, by decreasing the average prediction errorfrom 28 to 6.5%