Citation: Malakar, S.; Goswami, S.;
Ganguli, B.; Chakrabarti, A.; Roy, S.S.;
Boopathi, K.; Rangaraj, A.G.
Deep-Learning-Based Adaptive
Model for Solar Forecasting Using
Clustering. Energies 2022, 15, 3568.
https://doi.org/10.3390/en15103568
Academic Editors: Luis
Hernández-Callejo, Sergio
Nesmachnow and Sara Gallardo
Saavedra
Received: 24 March 2022
Accepted: 19 April 2022
Published: 13 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Deep-Learning-Based Adaptive Model for Solar Forecasting
Using Clustering
Sourav Malakar
1,
*
,†
, Saptarsi Goswami
2,†
, Bhaswati Ganguli
3
, Amlan Chakrabarti
1
, Sugata Sen Roy
3
,
K. Boopathi
4
and A. G. Rangaraj
4
1
A.K. Choudhury School of Information Technology, University of Calcutta, Kolkata 700073, India;
achakra12@yahoo.com
2
Bangabasi Morning College, University of Calcutta, Kolkata 700073, India; sgakc@caluniv.ac.in
3
Department of Statistics, University of Calcutta, Kolkata 700073, India; bgstat@gmail.com (B.G.);
sugatasr@gmail.com (S.S.R.)
4
National Institute of Wind Energy (NIWE), The Ministry of New and Renewable Energy,
Government of India, New Delhi 110003, India; boopathi.niwe@nic.in (K.B.); rangaraj.niwe@nic.in (A.G.R.)
* Correspondence: sourav.xaviers@gmail.com
† These authors contributed equally to this work.
Abstract:
Accurate short-term solar forecasting is challenging due to weather uncertainties associated
with cloud movements. Typically, a solar station comprises a single prediction model irrespective of
time and cloud condition, which often results in suboptimal performance. In the proposed model,
different categories of cloud movement are discovered using K-medoid clustering. To ensure broader
variation in cloud movements, neighboring stations were also used that were selected using a dynamic
time warping (DTW)-based similarity score. Next, cluster-specific models were constructed. At the
prediction time, the current weather condition is first matched with the different weather groups
found through clustering, and a cluster-specific model is subsequently chosen. As a result, multiple
models are dynamically used for a particular day and solar station, which improves performance
over a single site-specific model. The proposed model achieved 19.74% and 59% less normalized
root mean square error (NRMSE) and mean rank compared to the benchmarks, respectively, and was
validated for nine solar stations across two regions and three climatic zones of India.
Keywords: clearness index forecasting; cloud cover; clustering; DTW
1. Introduction
Solar power is one of the viable alternatives to fossil-fuel-generated power, which
causes serious environmental damage [
1
]. In terms of total energy consumption, India is
ranked third after China and the United States [
2
], and has a target of producing 57% of total
electricity capacity from renewable sources by 2027 [
3
]. In this paper, we developed a novel
method for the short-term (some hours ahead) [
4
] forecasting of the clearness index (Kt)
(defined as the ratio of global horizontal irradiance (GHI) to extraterrestrial irradiance) [
5
–
8
]
while accounting for unpredictable weather conditions, focusing on variability in cloud
cover [
9
–
12
]. Cloud variability leads to highly localized solar prediction, as a single model
is unable to provide accurate forecasts under different weather conditions [13,14].
Long short-term memory (LSTM) [15] is one of the most popular deep-learning algo-
rithms, mainly used to handle sequential data, and it can preserve knowledge by passing
through the subsequent time steps of a time series [
16
]. In [
17
], the authors developed
a site-specific univariate LSTM for the hourly forecasting of photovoltaic power output.
In [
18
], the authors compared the performance of several alternative models for forecast-
ing clear-sky GHI. These included gated recurrent units (GRUs), LSTM, recurrent neural
networks (RNNs), feed-forward neural networks (FFNNs), and support vector regression
(SVR). GRU and LSTM outperformed the other models in terms of root mean square error
Energies 2022, 15, 3568. https://doi.org/10.3390/en15103568 https://www.mdpi.com/journal/energies
