Back to search

University of Glasgow

Changepoint detection for net electricity demand modelling in Great Britain

Abstract

dc:description.abstract

This thesis investigates a changepoint detection methodology applied to net electricity demand modelling in Great Britain. With the increasing integration of renewable energy sources and the growing complexity of electricity demand patterns, accurately identifying abrupt changes, or “changepoints,” in demand data has become essential for reliable grid management. Initial analyses of national electricity demand data were conducted to explore the underlying features and factors influencing consumption patterns. By integrating Generalised Additive Models (GAMs) within a changepoint detection framework, this research introduces a flexible approach capable of capturing non-linear trends and seasonal variations without requiring extensive manual adjustments, allowing the model to adapt to diverse fluctuations in demand. Traditional changepoint algorithms were evaluated, but the unique complexities of electricity demand data led to the development of a novel changepoint detection algorithm tailored to these demands. Simulation studies tested the proposed methodology under various mean shifts and noise levels, offering insights into how these parameters impact changepoint detection accuracy. The novel algorithm was subsequently applied to regional Grid Supply Point (GSP) electricity demand data, demonstrating how different demand patterns across geographic areas influence changepoint locations. The findings underscore both the strengths and limitations of integrating model-based cost functions and GAMs within changepoint detection, particularly in managing daily and seasonal cycles, addressing computational constraints, and scaling across large datasets. This approach enhances the accuracy and flexibility of electricity demand modelling by effectively identifying abrupt changes, enabling a more robust response to demand variability.

Degree

thesis:*
Level dc:type.qualificationlevel
MPhil(R)
Grantor dc:publisher.institution
University of Glasgow
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Boonsuriyatham, Panthakan

Subjects

dc:subject × 1

Rights

Language dc:language
en

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
University of Glasgow
Base URL
theses.gla.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Boonsuriyatham, Panthakan. Changepoint detection for net electricity demand modelling in Great Britain. MPhil(R) thesis, University of Glasgow, 2025. https://doi.org/10.5525/gla.thesis.85614