Comparison of artificial intelligence and empirical models for estimation of daily diffuse solar radiation in North China Plain. (25th May 2017)

• Record Type: Journal Article
• Authors: Feng, Yu; Cui, Ningbo; Zhang, Qingwen; Zhao, Lu; Gong, Daozhi
• Is Part Of: International journal of hydrogen energy. Volume 42:Number 21(2017)
• Page Start: 14418
• Page End: 14428
• Publication Date: 2017-05-25
• Subjects: Diffuse solar radiation -- Extreme learning machine -- Backpropagation neural networks -- Random forests -- Generalized regression neural networks -- North China Plain; Hydrogen as fuel -- Periodicals; Hydrogène (Combustible) -- Périodiques; Hydrogen as fuel; Periodicals; 665.81
• DOI: 10.1016/j.ijhydene.2017.04.084
• Languages: English
• ISSNs: 0360-3199

Abstract

Abstract: Accurate diffuse solar radiation (Hd ) data is highly crucial for the development and utilization of solar energy technologies. However, due to expensive cost and technology requirements, measurements of Hd are not available in many regions of North China Plain (NCP), where the diffuse and direct solar radiation are affected by severe particulate pollution. Thus, development of models for precisely estimating Hd is indeed essential in NCP. On this account, the present studies proposed four artificial intelligence models, including the extreme learning machine (ELM), backpropagation neural networks optimized by genetic algorithm (GANN), random forests (RF), and generalized regression neural networks (GRNN), for estimating daily Hd at two meteorological stations of NCP. Daily global solar radiation and sunshine duration along with the estimated extraterrestrial radiation and maximum possible sunshine duration were selected as model inputs to train the models. Meanwhile, the proposed AI models were compared with the empirical Iqbal model to test their performance using measured Hd data. The results indicated that the ELM, GANN, RF, and GRNN models all performed much better than the empirical Iqbal model for estimating daily Hd . All the models underestimated Hd for both stations, with average relative error ranging from −5.8% to −5.4% for AI models and 19.1% for Iqbal model in Beijing, −5.9% to −4.3% and −26.9% in Zhengzhou, respectively. Generally, GANN model had the best accuracy, and ELM ranked next, followed by RF and GRNN models. The ELM model had a slightly poorer performance but the highest computation speed, and both the GANN and ELM models could be highly recommended to estimate daily Hd in NCP of China. Highlights: ELM, GANN, RF, and GRNN models are proposed for daily diffuse solar radiation estimation. The proposed AI models are compared against Iqbal mode. The AI models have much better performance than Iqbal model. GANN model are found to perform better than the ELM, followed by RF and GRNN models.