Open AccessReview of the PV Electricity Production Estimate under the Effect of Climatic Disturbances and Sunspots by Using Deep-Learning Tools
Author(s) -
Afef Ben Othman,
Ayoub El Ouni,
Mongi Besbes
Publication year - 2020
Publication title -
journal of solar energy research updates
Language(s) - English
Resource type - Journals
ISSN - 2410-2199
DOI - 10.31875/2410-2199.2020.07.8
Subject(s) - cloud cover , environmental science , meteorology , productivity , climate change , clarity , satellite , insolation , climate model , electricity generation , sunspot , cloud computing , electricity , computer science , climatology , power (physics) , geography , engineering , geology , economics , macroeconomics , aerospace engineering , oceanography , chemistry , operating system , biochemistry , quantum mechanics , magnetic field , physics , electrical engineering
The mathematical models used in the estimation of GHI on the Earth's surface are inconvenient because they always assume that the sky clarity index is constant. Hence, these models are often confronted with long-period empirical ground measurements that may exceeds 11 years. The impact of cloud cover on an electric power generation site is a very critical parameter for installing a solar power plant and evaluating its productivity. The state of knowledge about the sun influence, the greenhouse effect on climate change, and cloud occurrence can’t be described in a mathematical or numerical model.Therefore, in this paper, we propose the use of Deep-Learning techniques to predict any site’s productivity by analyzing its potential insolation. We also suggest the analysis of the ground and satellite- based measurements collected over 30 years. We propose the estimation of future climate change affecting cloud cover.