Investigation of Electric Load Forecasting Methods Through Spatial Demand Forecasting and ARIMA for Isolated Islands in Indonesia

Indonesia has 17,503 islands, with most being isolated islands, causing limited access to electricity supplies. As a tangible action to address the issue, the Central Government has implemented the LTSHE program. PLN is mandated to replace the program after a maximum installation period of three years. PLN is currently developing methods that can be employed to electrify regions in isolated islands. Electrical system planning can commence with load forecasting to assist in determining the required power plant capacity. In forecasting electrical load on limited isolated islands, the use of spatial methods is proposed. The advantage of this method lies in considering the direction of spatial development patterns in a region in accordance with local regulations. The direction of the load projection results will be compared with the ARIMA method. Significant differences are evident in the presentation of load projection results, where the Spatial Demand Forecasting method uses a 90% confidence level in the form of a range. In contrast, the ARIMA method has a MAPE of 2.953% in the form of a single number. The findings from this comparative are crucial for evaluating trade-offs in electrical system planning when selecting a relevant electric load projection method for isolated islands.

Authors

Institutions

Publication Details

Journal
International Review on Modelling and Simulations (IREMOS)
Published
2025-02-28
DOI
https://doi.org/10.15866/iremos.v18i1.24767
Primary Topic
Energy Load and Power Forecasting
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Investigation of Electric Load Forecasting Methods Through Spatial Demand Forecasting and ARIMA for Isolated Islands in Indonesia

Sudarmono Sasmono, Jangkung Raharjo, Muhammad Zakiyullah Romdlony, I Gede Putu Oka Indra Wijaya
International Review on Modelling and Simulations (IREMOS)
Energy Load and Power Forecasting
article

Investigation of Electric Load Forecasting Methods Through Spatial Demand Forecasting and ARIMA for Isolated Islands in Indonesia

Sudarmono Sasmono, Jangkung Raharjo, Muhammad Zakiyullah Romdlony, I Gede Putu Oka Indra Wijaya
article en

Abstract

Indonesia has 17,503 islands, with most being isolated islands, causing limited access to electricity supplies. As a tangible action to address the issue, the Central Government has implemented the LTSHE program. PLN is mandated to replace the program after a maximum installation period of three years. PLN is currently developing methods that can be employed to electrify regions in isolated islands. Electrical system planning can commence with load forecasting to assist in determining the required power plant capacity. In forecasting electrical load on limited isolated islands, the use of spatial methods is proposed. The advantage of this method lies in considering the direction of spatial development patterns in a region in accordance with local regulations. The direction of the load projection results will be compared with the ARIMA method. Significant differences are evident in the presentation of load projection results, where the Spatial Demand Forecasting method uses a 90% confidence level in the form of a range. In contrast, the ARIMA method has a MAPE of 2.953% in the form of a single number. The findings from this comparative are crucial for evaluating trade-offs in electrical system planning when selecting a relevant electric load projection method for isolated islands.

International Review on Modelling and Simulations (IREMOS)Vol. 18(1)
Telkom University (ID)
Openalex Percentile: Top 88%
Energy Load and Power Forecasting
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.