Deep Learning Based Multistep Solar Forecasting for PV Ramp-Rate Control Using Sky Images

Abstract

Solar forecasting is one of the most promising approaches to address the intermittent photovoltaic (PV) power generation by providing predictions before upcoming ramp events. In this article, a novel multistep forecasting (MSF) scheme is proposed for PV power ramp-rate control (PRRC). This method utilizes an ensemble of deep ConvNets without additional time series models (e.g., recurrent neural network (RNN) or long short-term memory) and exogenous variables, thus more suitable for industrial applications. The MSF strategy can make multiple predictions in comparison with a single forecasting point produced by a conventional method while maintaining the same high temporal resolution. Besides, stacked sky images that integrate temporal–spatial information of cloud motions are used to further improve the forecasting performance. The results demonstrate a favorable forecasting accuracy in comparison to the existing forecasting models with the highest skill score of 17.7%. In the PRRC application, the MSF-based PRRC can detect more ramp-rates violations with a higher control rate of 98.9% compared with the conventional forecasting-based control. Thus, the PV generation can be effectively smoothed with less energy curtailment on both clear and cloudy days using the proposed approach.