Arabian Journal for Science and Engineering
https://doi.org/10.1007/s13369-020-05140-y
RESEARCH ARTICLE-ELECTRICAL ENGINEERING
Data Normalisation-Based Solar Irradiance Forecasting Using Artificial
Neural Networks
Isha Arora
1
· Jaimala Gambhir
1
· Tarlochan Kaur
1
Received: 21 January 2020 / Accepted: 11 November 2020
© King Fahd University of Petroleum & Minerals 2020
Abstract
Due to continual day-to-day increase in electricity demand, and hazardous and critical threats of fossil fuels to the environment,
researchers are scrutinizing over substitute energy sources. Solar radiation intensity prediction is essential for conducting
various research work in the emerging field of Renewable Energy Sources (RESs). This paper has presented development
of monthly averaged solar radiation intensity prediction model by employing Artificial Neural Network (ANN) algorithm.
Various meteorological parameters have been considered over period of 2 years to execute forecasting for Chandigarh, India.
Different normalisation techniques such as min-max, decimal and z-score have been utilised to normalise database. Structure
and parameter learning of ANNs has been carried out. Comparative analysis has been done to select optimal architecture
based on different performance evaluation measures such as mean square error (MSE), mean absolute percentage error
(MAPE), mean absolute error (MAE), and correlation coefficient ( R-value) and training time. The network topology with
least forecasting errors, higher R-value has been found to be optimum and further simulated for predicting monthly averaged
solar radiation intensity for Chandigarh region.
Keywords ANN · Data Normalisation · Forecasting · Meteorological Parameters · RESs · Training
List of Abbreviations
RESs Renewable Energy Sources
ANN Artificial Neural Network
MSE Mean Square Error
MAPE Mean Absolute Percentage Error
MAE Mean Absolute Error
R-value Co-relation Coefficient
PV Photovoltaic
GHI Global Horizontal Irradiance
NN Neural Networks
FFD Feed Forward Neural Network
ENN Elman Neural Network
NWP Numerical Weather Prediction
ARMA Auto Regressive Moving Average model
RMSE Root-Mean-Square Error
PSO Particle Swarm Optimisation
nRMSE Normalised Root-Mean-Square Error
B Isha Arora
ishaarora.phdele17@pec.edu.in
1
Punjab Engineering College, Chandigarh, India
MODIS Moderate Resolution Imaging
Spectroradiometer
GA Genetic Algorithm
1 Introduction
Ever increasing electricity demands, swiftly exhausting fossil
fuels, rapid industrialisation and globalisation of society, and
rising environmental concerns has witnessed shift towards
non-conventional energy resources for wide-scaled energy
production. These renewable resources are derived from nat-
urally existing sources such as solar, wind, hydro, fuel cells,
tidal and biomass energy that are easily replenishable.
Sun is a clean, green, safe, environmental friendly energy
source that is inexhaustible. Solar energy is major contrib-
utor in renewable energy integration with power grid. The
amount of solar energy reaching Earth’s surface each hour is
sufficient to meet electricity demands of the entire population
for entire year [1]. The amount of Solar energy striking the
Earth’s surface is about 6000 times to that of present global
utilisation of energy, as well as majority of it, is still unutilised
[2]. Solar generation technologies is undergoing remarkable
123