H
Haixiang Zang
Researcher at Hohai University
Publications - 147
Citations - 2331
Haixiang Zang is an academic researcher from Hohai University. The author has contributed to research in topics: Wind power & Electric power system. The author has an hindex of 19, co-authored 130 publications receiving 1317 citations. Previous affiliations of Haixiang Zang include Southeast University.
Papers
More filters
Journal ArticleDOI
Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations
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.
Journal ArticleDOI
Hybrid method for short-term photovoltaic power forecasting based on deep convolutional neural network
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.
Journal ArticleDOI
Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning
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.
Journal ArticleDOI
A robust optimization approach for integrated community energy system in energy and ancillary service markets
TL;DR: A day-ahead scheduling strategy for the integrated community energy system in a joint energy and ancillary service markets and simulations of a real regional multi-energy system demonstrate the effectiveness and applicability of the proposed model.
Journal ArticleDOI
Residential load forecasting based on LSTM fusing self-attention mechanism with pooling
TL;DR: In this paper, the authors proposed a novel day-ahead residential load forecasting method based on feature engineering, pooling, and a hybrid deep learning model, where feature engineering is performed using two-stage preprocessing on data from each user, i.e., decomposition and multi-source input dimension reconstruction.