Forecasting solar radiation during dust storms using deep learning
Author:
- B. RavindraBRB. Ravindra
Preprint
Abstract
Dust storms are common in arid zones on the earth and others planets such as Mars. The impact of dust storms on solar radiation has significant implications for solar power plants and autonomous vehicles powered by solar panels. This paper deals with the analysis of solar radiation and power output of a rooftop photovoltaic plant during a dust storm and proposes a forecasting methodology using deep learning network. The increased aerosol content due to dust storms increases the diffuse component of the solar radiation. This effect persists for a long duration and can impact the quality of forecasting of solar radiation. Deep learning networks that capture long range structure can improve the quality of solar radiation forecasting during dust storms. These results can help explain the sudden drop in power output of solar plants due to dust storms originating in another continent. They can shed light on mysterious cleaning events in autonomous vehicles powered by solar panels to be used in space missions.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Recurrent Neural Networks for Multivariate Time Series with Missing ValuesScientific Reports, 2018
- The impact of climate change on photovoltaic power generation in EuropeNature Communications, 2015
- Irradiance forecasts based on an irradiance monitoring network, cloud motion, and spatial averagingSolar Energy, 2015
- Characteristics of recent dust storms over the Indian region using real time multi-satellite observations from the direct broadcast receiving system at IMDAdvances In Space Research, 2013
- The physics of wind-blown sand and dustReports on Progress in Physics, 2012
- A scaling theory for the size distribution of emitted dust aerosols suggests climate models underestimate the size of the global dust cycleProceedings of the National Academy of Sciences, 2010
- Difference in the Wind Speeds Required for Initiation versus Continuation of Sand Transport on Mars: Implications for Dunes and Dust StormsPhysical Review Letters, 2010
- Modeling and prediction of chaotic systems with artificial neural networksInternational Journal for Numerical Methods in Fluids, 2009