Author:
Zhang Yu,Ma Jianfeng,Zeng Cong,Li Guangyao
Abstract
Abstract
The effectiveness of photovoltaic power generation systems—a clean and renewable use of solar energy—depends on the amount of solar radiation. Consequently, solar radiation forecasting (especially short-term) is crucial for photovoltaic plants. In this paper, a hybrid convolutional neural network (CNN) and gate recurrent unit (GRU) method is proposed for short-term (10-min) solar radiation forecasting based on image and time-series data (i.e., radiation data at different times). The method aims to achieve high performance in solar radiation forecasting, which can be useful for PV plant adjustment. CNN–GRU consists of two branches. One is based on the ResNet-18 structure, which can extract features from sky images. The other is a GRU branch, which consists of three fully connected layers used for meteorological feature extraction. Experiments on a public dataset showed that our method predicts the mean absolute error better than other benchmark models. The ablation experiments demonstrated that the hybrid model performs better than a single model and, therefore, shows promise for application in solar radiation forecasting.
Subject
General Physics and Astronomy
Reference16 articles.
1. Determination of the sun area in sky camera images using radiometric data;Alonso;Energy Convers and Manag,2014
2. Solar radiation forecasting in the short- and medium- term under all sky conditions;Alonso-Montesinos;Energy,2015
3. Short and medium-term cloudiness forecasting using remote sensing techniques and sky camera imagery;Alonso;Energy,2014
4. Cloud tracking with optical flow for short-term solar forecasting;Wood-Bradley,2012
5. A low cost, edge computing, all-sky imager for cloud tracking and intra-hour irradiance forecasting;Richardson;Sustain,2017
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献