Optimal Solar PV Site Identification Using AutoEncoders and Clustering

Smitesh Patil; Abdul Wahid; Karl Mason

doi:10.1007/978-3-031-73058-0_23

Optimal Solar PV Site Identification Using AutoEncoders and Clustering

Smitesh Patil
, Abdul Wahid
, Karl Mason

University of Galway

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

This study explores the integration of Autoencoders and clustering techniques within the framework of Geographical Information Systems (GIS) to identify optimal locations for Solar PV (Photovoltaic) installations. By harnessing advanced machine learning methodologies in conjunction with spatial analysis, this research aims to offer a novel approach, distinct from previous studies in this field. Through the analysis of diverse environmental, climatic, and topographical factors, the proposed autoencoder and clustering-based methods provide a holistic solution for identifying areas with peak solar energy potential. The results outline vast swaths of land in different regions in India that can be considered for surveying in preparation for solar PV plant setup. Particularly, results identified large swaths of suitable lands in the states of Rajasthan, Gujarat, and Maharashtra for Solar PV plant setup. These outcomes not only underscore the efficacy and robustness of the suggested approach but also highlight its prospective applications in the broader scope of renewable energy planning.

Original language	English
Title of host publication	Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins
Subtitle of host publication	The PAAMS Collection - International Workshops of PAAMS 2024, Proceedings
Editors	Alfonso González-Briones, Vicente Julian Inglada, Alia El Bolock, Cedric Marco-Detchart, Jaume Jordan, Karl Mason, Fernando Lopes, Nada Sharaf
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	281-292
Number of pages	12
ISBN (Print)	9783031730573
DOIs	https://doi.org/10.1007/978-3-031-73058-0_23
Publication status	Published - 2025
Event	International Workshops on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2024 - Salamanca, Spain Duration: 26 Jun 2024 → 28 Jun 2024

Publication series

Name	Communications in Computer and Information Science
Volume	2149 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	International Workshops on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2024
Country/Territory	Spain
City	Salamanca
Period	26/06/24 → 28/06/24

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy
SDG 17 Partnerships for the Goals

Keywords

Analytical-Hierarchical Process
Geospatial Information
Renewable Energy
Self-supervised Learning
Site Selection
Spatial Analysis
Sustainability
Unsupervised Learning

Access to Document

10.1007/978-3-031-73058-0_23

Cite this

Patil, S., Wahid, A., & Mason, K. (2025). Optimal Solar PV Site Identification Using AutoEncoders and Clustering. In A. González-Briones, V. Julian Inglada, A. El Bolock, C. Marco-Detchart, J. Jordan, K. Mason, F. Lopes, & N. Sharaf (Eds.), Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection - International Workshops of PAAMS 2024, Proceedings (pp. 281-292). (Communications in Computer and Information Science; Vol. 2149 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-73058-0_23

Patil, Smitesh ; Wahid, Abdul ; Mason, Karl. / Optimal Solar PV Site Identification Using AutoEncoders and Clustering. Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection - International Workshops of PAAMS 2024, Proceedings. editor / Alfonso González-Briones ; Vicente Julian Inglada ; Alia El Bolock ; Cedric Marco-Detchart ; Jaume Jordan ; Karl Mason ; Fernando Lopes ; Nada Sharaf. Springer Science and Business Media Deutschland GmbH, 2025. pp. 281-292 (Communications in Computer and Information Science).

@inproceedings{5910c3ce1d824c1b96e87ab389cf4561,

title = "Optimal Solar PV Site Identification Using AutoEncoders and Clustering",

abstract = "This study explores the integration of Autoencoders and clustering techniques within the framework of Geographical Information Systems (GIS) to identify optimal locations for Solar PV (Photovoltaic) installations. By harnessing advanced machine learning methodologies in conjunction with spatial analysis, this research aims to offer a novel approach, distinct from previous studies in this field. Through the analysis of diverse environmental, climatic, and topographical factors, the proposed autoencoder and clustering-based methods provide a holistic solution for identifying areas with peak solar energy potential. The results outline vast swaths of land in different regions in India that can be considered for surveying in preparation for solar PV plant setup. Particularly, results identified large swaths of suitable lands in the states of Rajasthan, Gujarat, and Maharashtra for Solar PV plant setup. These outcomes not only underscore the efficacy and robustness of the suggested approach but also highlight its prospective applications in the broader scope of renewable energy planning.",

keywords = "Analytical-Hierarchical Process, Geospatial Information, Renewable Energy, Self-supervised Learning, Site Selection, Spatial Analysis, Sustainability, Unsupervised Learning",

author = "Smitesh Patil and Abdul Wahid and Karl Mason",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; International Workshops on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2024 ; Conference date: 26-06-2024 Through 28-06-2024",

year = "2025",

doi = "10.1007/978-3-031-73058-0\_23",

language = "English",

isbn = "9783031730573",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "281--292",

editor = "Alfonso Gonz{\'a}lez-Briones and \{Julian Inglada\}, Vicente and \{El Bolock\}, Alia and Cedric Marco-Detchart and Jaume Jordan and Karl Mason and Fernando Lopes and Nada Sharaf",

booktitle = "Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins",

}

Patil, S, Wahid, A & Mason, K 2025, Optimal Solar PV Site Identification Using AutoEncoders and Clustering. in A González-Briones, V Julian Inglada, A El Bolock, C Marco-Detchart, J Jordan, K Mason, F Lopes & N Sharaf (eds), Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection - International Workshops of PAAMS 2024, Proceedings. Communications in Computer and Information Science, vol. 2149 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 281-292, International Workshops on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2024, Salamanca, Spain, 26/06/24. https://doi.org/10.1007/978-3-031-73058-0_23

Optimal Solar PV Site Identification Using AutoEncoders and Clustering. / Patil, Smitesh; Wahid, Abdul ; Mason, Karl.
Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection - International Workshops of PAAMS 2024, Proceedings. ed. / Alfonso González-Briones; Vicente Julian Inglada; Alia El Bolock; Cedric Marco-Detchart; Jaume Jordan; Karl Mason; Fernando Lopes; Nada Sharaf. Springer Science and Business Media Deutschland GmbH, 2025. p. 281-292 (Communications in Computer and Information Science; Vol. 2149 CCIS).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - Optimal Solar PV Site Identification Using AutoEncoders and Clustering

AU - Patil, Smitesh

AU - Wahid, Abdul

AU - Mason, Karl

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - This study explores the integration of Autoencoders and clustering techniques within the framework of Geographical Information Systems (GIS) to identify optimal locations for Solar PV (Photovoltaic) installations. By harnessing advanced machine learning methodologies in conjunction with spatial analysis, this research aims to offer a novel approach, distinct from previous studies in this field. Through the analysis of diverse environmental, climatic, and topographical factors, the proposed autoencoder and clustering-based methods provide a holistic solution for identifying areas with peak solar energy potential. The results outline vast swaths of land in different regions in India that can be considered for surveying in preparation for solar PV plant setup. Particularly, results identified large swaths of suitable lands in the states of Rajasthan, Gujarat, and Maharashtra for Solar PV plant setup. These outcomes not only underscore the efficacy and robustness of the suggested approach but also highlight its prospective applications in the broader scope of renewable energy planning.

AB - This study explores the integration of Autoencoders and clustering techniques within the framework of Geographical Information Systems (GIS) to identify optimal locations for Solar PV (Photovoltaic) installations. By harnessing advanced machine learning methodologies in conjunction with spatial analysis, this research aims to offer a novel approach, distinct from previous studies in this field. Through the analysis of diverse environmental, climatic, and topographical factors, the proposed autoencoder and clustering-based methods provide a holistic solution for identifying areas with peak solar energy potential. The results outline vast swaths of land in different regions in India that can be considered for surveying in preparation for solar PV plant setup. Particularly, results identified large swaths of suitable lands in the states of Rajasthan, Gujarat, and Maharashtra for Solar PV plant setup. These outcomes not only underscore the efficacy and robustness of the suggested approach but also highlight its prospective applications in the broader scope of renewable energy planning.

KW - Analytical-Hierarchical Process

KW - Geospatial Information

KW - Renewable Energy

KW - Self-supervised Learning

KW - Site Selection

KW - Spatial Analysis

KW - Sustainability

KW - Unsupervised Learning

UR - https://www.scopus.com/pages/publications/85216127257

U2 - 10.1007/978-3-031-73058-0_23

DO - 10.1007/978-3-031-73058-0_23

M3 - Conference Publication

AN - SCOPUS:85216127257

SN - 9783031730573

T3 - Communications in Computer and Information Science

SP - 281

EP - 292

BT - Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins

A2 - González-Briones, Alfonso

A2 - Julian Inglada, Vicente

A2 - El Bolock, Alia

A2 - Marco-Detchart, Cedric

A2 - Jordan, Jaume

A2 - Mason, Karl

A2 - Lopes, Fernando

A2 - Sharaf, Nada

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Workshops on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2024

Y2 - 26 June 2024 through 28 June 2024

ER -

Patil S, Wahid A , Mason K. Optimal Solar PV Site Identification Using AutoEncoders and Clustering. In González-Briones A, Julian Inglada V, El Bolock A, Marco-Detchart C, Jordan J, Mason K, Lopes F, Sharaf N, editors, Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection - International Workshops of PAAMS 2024, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 281-292. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-73058-0_23