ANN–GA based adaptive predictive energy management for renewable energy optimization in solar-diesel hybrid systems

The intermittent nature of solar energy continues to constrain the effective utilization of photovoltaic (PV) systems in solar-diesel hybrid energy systems, particularly in tropical semi-arid regions where solar irradiance fluctuates considerably throughout the day. This study proposes a predictive energy management framework that integrates artificial neural network (ANN)-based irradiance forecasting with genetic algorithm (GA)-based optimization to support adaptive selection of energy sources between PV systems and diesel generators. Environmental data, including air temperature, relative humidity, and solar irradiance, were collected at the Badan Perakitan dan Modernisasi Pertanian (BRMP, Agricultural Assembly and Modernization Agency) experimental field in Naibonat, Kupang Regency, Indonesia. A multilayer perceptron ANN was developed to forecast short-term solar irradiance, and its predicted output was subsequently adopted as the fitness function for the GA to identify the optimal operating condition using an irradiance threshold of 300 W m−2. The ANN produced reliable short-term irradiance predictions, while the GA converged to a stable solution within approximately 15 generations, demonstrating the feasibility of the proposed predictive energy management framework. The developed approach achieved a renewable energy utilization rate of 75.0%, reduced diesel fuel consumption by 52.8% compared with the conventional threshold-based strategy, and lowered carbon dioxide emissions by approximately 53%. These findings demonstrate that the proposed framework transforms irradiance forecasting into adaptive operational decision-making, allowing energy source selection to anticipate future solar energy availability instead of relying solely on instantaneous irradiance measurements. Accordingly, the proposed framework offers a practical and scalable strategy for enhancing renewable energy utilization and reducing diesel dependency, and improving the sustainability of solar-diesel hybrid energy systems operating under highly variable tropical environmental conditions.

Authors

Institutions

Publication Details

Journal
Clean Energy Science and Technology
Published
2026-11-12
DOI
https://doi.org/10.18686/cest939
Primary Topic
Hybrid Renewable Energy Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

ANN–GA based adaptive predictive energy management for renewable energy optimization in solar-diesel hybrid systems

David Suban Koten, Folkes Eduward Laumal, Sam Herodian, Erniati et al.
Clean Energy Science and Technology
Hybrid Renewable Energy Systems
article

ANN–GA based adaptive predictive energy management for renewable energy optimization in solar-diesel hybrid systems

David Suban Koten, Folkes Eduward Laumal, Sam Herodian, Erniati, Sulaiman Abdullah
article en

Abstract

The intermittent nature of solar energy continues to constrain the effective utilization of photovoltaic (PV) systems in solar-diesel hybrid energy systems, particularly in tropical semi-arid regions where solar irradiance fluctuates considerably throughout the day. This study proposes a predictive energy management framework that integrates artificial neural network (ANN)-based irradiance forecasting with genetic algorithm (GA)-based optimization to support adaptive selection of energy sources between PV systems and diesel generators. Environmental data, including air temperature, relative humidity, and solar irradiance, were collected at the Badan Perakitan dan Modernisasi Pertanian (BRMP, Agricultural Assembly and Modernization Agency) experimental field in Naibonat, Kupang Regency, Indonesia. A multilayer perceptron ANN was developed to forecast short-term solar irradiance, and its predicted output was subsequently adopted as the fitness function for the GA to identify the optimal operating condition using an irradiance threshold of 300 W m−2. The ANN produced reliable short-term irradiance predictions, while the GA converged to a stable solution within approximately 15 generations, demonstrating the feasibility of the proposed predictive energy management framework. The developed approach achieved a renewable energy utilization rate of 75.0%, reduced diesel fuel consumption by 52.8% compared with the conventional threshold-based strategy, and lowered carbon dioxide emissions by approximately 53%. These findings demonstrate that the proposed framework transforms irradiance forecasting into adaptive operational decision-making, allowing energy source selection to anticipate future solar energy availability instead of relying solely on instantaneous irradiance measurements. Accordingly, the proposed framework offers a practical and scalable strategy for enhancing renewable energy utilization and reducing diesel dependency, and improving the sustainability of solar-diesel hybrid energy systems operating under highly variable tropical environmental conditions.

Clean Energy Science and Technology
IPB University (ID), Politeknik Negeri Kupang (ID)
Affordable and clean energy, Industry, innovation and infrastructure, Climate action
Hybrid Renewable Energy Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon