Search

This paper presents a new hybrid approach for Global Solar Radiation (GSR) prediction problems, based on deep learning approaches. Predictive models are useful ploys in solar energy industries to optimize the performance of photovoltaic power systems. Specifically, in this work we develop a new 4-phase hybrid CXGBRFR framework, which includes a deep learning Convolutional Neural Network, an Extreme Gradient Boosting with Random Forest Regression, and a Harris Hawks Optimization for initial feature selection. The proposed system has been tested in a problem of daily GSR prediction at six solar farms in Australia. Data from three global climate models (GCM) (CSIRO-BOM ACCESS1-0, MOHC Hadley-GEM2-CC and MRI MRI-CGCM3) have been considered as predictive (input) variables for the proposed approach. The variables from these GCMs contain enough information to obtain an accurate prediction of the GSR at each solar farm. The performance of the proposed approach is compared against different deep and shallows learning approaches: Deep Belief Network, Deep Neural Network, Artificial Neural Network, Extreme Learning Machine and Multivariate Auto-Regressive Spline models. We show that the proposed approach exhibits an excellent performance in GSR prediction, against all alternative approaches in all solar farms considered. [Display omitted] • We develop hybrid deep learning model to predict solar radiation • We optimize the algorithm with Harris Hawks, gradient boosting and random forest • We adopt global climate model and observed predictors as learning model inputs • We build an expert system with relevant knowledge in context of solar application • Our methods benefit solar photovoltaic power monitoring in solar engineering problems. [ABSTRACT FROM AUTHOR]

• MERRA-2 outperforms CAMS in capturing seasonal dust, consistent with Himawari-8 observations. • Dust emissions and depositions in Australia peak at 1.4 gm−2 during Spring-Summer. • Seasonal soiling show reductions in energy of ∼3% near the Lake Eyre Basin. • Rainfall bursts remove soiling of 3 gm−2 at solar farms, improving energy yield by 9%. Dust plays a vital role in the Earth's climate system and can also modulate solar energy yield from photovoltaics due to soiling and it also impacts concentrated solar power outputs by up to 30%. Research examining decreased energy production on solar panels due to dust accumulation is limited. This is particularly important for dry arid regions of Australia, which are prone to dust storms. Thus, this paper examines the dust characteristics over Australia by comparing two reanalysis products, the Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2) and the Copernicus Atmosphere Monitoring Service (CAMS) with the satellite data (Himawari-8) to ascertain the capabilities of the reanalysis products in capturing dust cycles over Australia. The results are then used to explore the seasonal variability and trends in the radiative impacts, emissions, and depositions of dust. The energy reductions from seasonal averaged dust accumulations without natural removal or cleaning and later the impact of soiling with removal from precipitation bursts on selected operational solar farms are presented. Results show that MERRA-2 outperforms CAMS in capturing Dust Aerosol Optical Depth (AOD) near the Lake Eyre Basin in all seasons, consistent with satellite observations. The radiative trends showed contrasting differences during the Spring and Summer, whereas seasonal dust emissions and depositions peaked at 1.4 gm−2. Similarly, seasonal dust accumulations without natural removal on panels showed significant reductions in the energy of up to 3% around the Lake Eyre Basin, but most operational solar farms in Australia depicted energy reductions of 8–9% due to accumulated dust of up to 2.5–3 gm−2, which was naturally removed from regular seasonal rainfall bursts. [ABSTRACT FROM AUTHOR]

• Deep learning hybrid model is proposed for solar radiation prediction. • Convolutional network is used to extract features for solar radiation. • Long Short-Term Memory is used for prediction of solar radiation. • Deep learning hybrid model outperforms all comparative models. • The model can be adopted as a decision-support tool in solar energy simulation. This paper designs a hybridized deep learning framework that integrates the Convolutional Neural Network for pattern recognition with the Long Short-Term Memory Network for half-hourly global solar radiation (GSR) forecasting. The Convolution network is applied to robustly extract data input features from predictive variables (i.e., statistically significant antecedent inputs) while Long Short-Term Memory absorbs them for prediction. Half-hourly GSR for Alice Springs (Australia: 01 January 2006 to 31 August 2018) are extracted with stationarity checks applied via unit-root and mutual information test to capture antecedent GSR values required to forecast future GSR. The proposed hybrid model is benchmarked with standalone models as well as other Deep Learning, Single Hidden Layer and Tree based models. The results show that the benchmarked models are not able to generate satisfactory GSR predictions and the proposed hybrid model outperforms all other counterparts. The hybrid model registers superior results with over 70% of predictive errors lying below ±10 Wm−2 and outperforms the benchmark model for 1-Day half-hourly GSR prediction with low Relative Root Mean Square Error (≈1.515%), Mean Absolute Percentage Error (≈4.672%) and Absolute Percentage Bias (≈1.233%). This study ascertains that a proposed hybrid model based on a convolution network framework can accurately predict GSR and enable energy availability to be regularly monitored over multi-step horizons when coupled with a low latency Long Short-Term Memory network. Furthermore, it also concludes that the proposed model can have practical implications in forecasting GSR , capitalizing its versatility as a stratagem in monitoring solar powered systems by integrating freely available solar radiation into a real power grid system. [ABSTRACT FROM AUTHOR]