Zhinong Wei

TL;DR: This study addresses this issue by proposing a spatiotemporal correlation model based on deep learning that has advantages over the other models considered and provides a good alternative for short-term solar radiation prediction.

TL;DR: The hybrid model has been verified by forecasting the output power of PV arrays with diverse capacities in various hourly timescales, which demonstrates its superiority over commonly used methods.

TL;DR: A novel day-ahead PV power forecasting approach based on deep learning based on two novel deep convolutional neural networks, which involves historical PV power series, meteorological elements and numerical weather prediction is proposed and validated.

TL;DR: Based on the analysis of commutation failure prevention, an approach of direct current value setting is proposed, the selections of parameters in calculating process are CFPREV-based in order to implement it conveniently, and the dc current predictive control strategy is applied by modifying the conventional control system at the inverter as mentioned in this paper.

TL;DR: In this paper, a probabilistic energy flow framework of integrated electrical and gas systems is initially proposed considering correlated varying energy demands and wind power, and a multilinear method is specially designed to produce a deterministic energy flow solution for each sample generated by Monte Carlo simulation (MCS).