A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach

Maintaining a balance between electricity generation and consumption is vital for ensuring grid stability and preventing disruptions. Spatial load forecasting (SLF) predicts geographical electricity demand, thereby aiding in power system planning. However, conventional methods like multiple linear r...

Full description

Saved in:
Bibliographic Details
Main Authors: Terence Kibula Lukong, Derick Nganyu Tanyu, Yannick Nkongtchou, Thomas Tamo Tatietse, Detlef Schulz
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/10/2484
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126148031217664
author Terence Kibula Lukong
Derick Nganyu Tanyu
Yannick Nkongtchou
Thomas Tamo Tatietse
Detlef Schulz
author_facet Terence Kibula Lukong
Derick Nganyu Tanyu
Yannick Nkongtchou
Thomas Tamo Tatietse
Detlef Schulz
author_sort Terence Kibula Lukong
collection DOAJ
description Maintaining a balance between electricity generation and consumption is vital for ensuring grid stability and preventing disruptions. Spatial load forecasting (SLF) predicts geographical electricity demand, thereby aiding in power system planning. However, conventional methods like multiple linear regression and autoregressive integrated moving average struggle to capture the complex spatiotemporal patterns in historical data. Advanced methods like spatiotemporal graph transformers, graph convolutional networks, and improved scale-limited dynamic time warping better capture these dependencies, thereby enhancing prediction accuracy. Despite the advancements, challenges persist, particularly in developing economies with limited reliable data. This paper presents a novel SLF approach that divides the grid into predefined clusters based on regional characteristics and economic activity. For each cluster, a customized long short-term memory (LSTM) model captures unique spatiotemporal dependencies for more accurate predictions. The proposed method was tested across five load clusters using real-world data from Cameroon’s National Electricity Transmission Company and Energy Utilities. The results, compared against a linear regression model, demonstrated the superior performance of the LSTM approach across metrics like the mean absolute percentage error, root-mean-square error, mean absolute error, and <i>R</i><sup>2</sup> score. This approach highlights the potential for enhanced, localized load forecasting in regions with data constraints.
format Article
id doaj-art-98fd793dbef34f46837cf6823e8bc682
institution OA Journals
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-98fd793dbef34f46837cf6823e8bc6822025-08-20T02:33:59ZengMDPI AGEnergies1996-10732025-05-011810248410.3390/en18102484A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning ApproachTerence Kibula Lukong0Derick Nganyu Tanyu1Yannick Nkongtchou2Thomas Tamo Tatietse3Detlef Schulz4Doctoral School, National Advanced School of Engineering, University of Yaoundé I, Yaounde 8390, CameroonCentre for Industrial Mathematics (ZeTeM), University of Bremen, 28359 Bremen, GermanyDoctoral School, National Advanced School of Engineering, University of Yaoundé I, Yaounde 8390, CameroonDoctoral School, National Advanced School of Engineering, University of Yaoundé I, Yaounde 8390, CameroonDepartment of Electrical Power Systems, Helmut Schmidt University, 22043 Hamburg, GermanyMaintaining a balance between electricity generation and consumption is vital for ensuring grid stability and preventing disruptions. Spatial load forecasting (SLF) predicts geographical electricity demand, thereby aiding in power system planning. However, conventional methods like multiple linear regression and autoregressive integrated moving average struggle to capture the complex spatiotemporal patterns in historical data. Advanced methods like spatiotemporal graph transformers, graph convolutional networks, and improved scale-limited dynamic time warping better capture these dependencies, thereby enhancing prediction accuracy. Despite the advancements, challenges persist, particularly in developing economies with limited reliable data. This paper presents a novel SLF approach that divides the grid into predefined clusters based on regional characteristics and economic activity. For each cluster, a customized long short-term memory (LSTM) model captures unique spatiotemporal dependencies for more accurate predictions. The proposed method was tested across five load clusters using real-world data from Cameroon’s National Electricity Transmission Company and Energy Utilities. The results, compared against a linear regression model, demonstrated the superior performance of the LSTM approach across metrics like the mean absolute percentage error, root-mean-square error, mean absolute error, and <i>R</i><sup>2</sup> score. This approach highlights the potential for enhanced, localized load forecasting in regions with data constraints.https://www.mdpi.com/1996-1073/18/10/2484spatial load forecastingnetwork planningLSTM model
spellingShingle Terence Kibula Lukong
Derick Nganyu Tanyu
Yannick Nkongtchou
Thomas Tamo Tatietse
Detlef Schulz
A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach
Energies
spatial load forecasting
network planning
LSTM model
title A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach
title_full A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach
title_fullStr A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach
title_full_unstemmed A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach
title_short A Spatial Long-Term Load Forecast Using a Multiple Delineated Machine Learning Approach
title_sort spatial long term load forecast using a multiple delineated machine learning approach
topic spatial load forecasting
network planning
LSTM model
url https://www.mdpi.com/1996-1073/18/10/2484
work_keys_str_mv AT terencekibulalukong aspatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT dericknganyutanyu aspatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT yannicknkongtchou aspatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT thomastamotatietse aspatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT detlefschulz aspatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT terencekibulalukong spatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT dericknganyutanyu spatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT yannicknkongtchou spatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT thomastamotatietse spatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach
AT detlefschulz spatiallongtermloadforecastusingamultipledelineatedmachinelearningapproach