Self-Supervised Representation Learning for UK Power Grid Frequency Disturbance Detection Using TC-TSS Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.3390/en18215611

This study presents a self-supervised learning framework for detecting frequency disturbances in power systems using high-resolution time series data. Employing data from the UK National Grid, we apply the Temporal Contrastive Self-Supervised Learning (TC-TSS) approach to learn task-agnostic embeddings from unlabelled 60-s rolling window segments of frequency measurements. The learned representations are then used to train four traditional classifiers, Logistic Regression (LR), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF), for binary classification of frequency stability events. The proposed method is evaluated using over 15 million data points spanning six months of system operation data. Results show that classifiers trained on TC-TSS embeddings performed better than those using raw input features, particularly in detecting rare disturbance events. ROC-AUC scores for MLP and SVM models reach as high as 0.98, indicating excellent separability in the latent space. Visualisations using UMAP and t-SNE further demonstrate the clustering quality of TC-TSS features. This study highlights the effectiveness of contrastive representation learning in the energy domain, particularly under conditions of limited labelled data, and proves its suitability for integration into real-time smart grid applications.

Related Topics

Learning Curve

Learning Theory (Education)

Experiential Learning

Group Representation

Practice (Learning Method)

Representation Theory Of The Lorentz Group

Learning Environment

Machine Learning

Deep Learning

Reinforcement Learning

Learning Standards

Proportional Representation

Concepts

No concepts available.

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.3390/en18215611
PDF: https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554
OA Status: gold
References: 31
OpenAlex ID: https://openalex.org/W4415647971

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415647971

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.3390/en18215611

Digital Object Identifier
Title: Self-Supervised Representation Learning for UK Power Grid Frequency Disturbance Detection Using TC-TSS

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-10-25

Full publication date if available
Authors: Maitreyee Dey, Soumya Prakash Rana

List of authors in order
Landing page: https://doi.org/10.3390/en18215611

Publisher landing page
PDF URL: https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex
References (count): 31

Number of works referenced by this work

Full payload

id	https://openalex.org/W4415647971
doi	https://doi.org/10.3390/en18215611
ids.doi	https://doi.org/10.3390/en18215611
ids.openalex	https://openalex.org/W4415647971
fwci
type	article
title	Self-Supervised Representation Learning for UK Power Grid Frequency Disturbance Detection Using TC-TSS
biblio.issue	21
biblio.volume	18
biblio.last_page	5611
biblio.first_page	5611
is_xpac	False
apc_list.value	2200
apc_list.currency	CHF
apc_list.value_usd	2382
apc_paid.value	2200
apc_paid.currency	CHF
apc_paid.value_usd	2382
language	en
locations[0].id	doi:10.3390/en18215611
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S198098182
locations[0].source.issn	1996-1073
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	1996-1073
locations[0].source.is_core	True
locations[0].source.is_in_doaj	True
locations[0].source.display_name	Energies
locations[0].source.host_organization	https://openalex.org/P4310310987
locations[0].source.host_organization_name	Multidisciplinary Digital Publishing Institute
locations[0].source.host_organization_lineage	https://openalex.org/P4310310987
locations[0].source.host_organization_lineage_names	Multidisciplinary Digital Publishing Institute
locations[0].license	cc-by
locations[0].pdf_url	https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Energies
locations[0].landing_page_url	https://doi.org/10.3390/en18215611
locations[1].id	pmh:oai:doaj.org/article:747dbd643bdd4eaabbaaa0a101467567
locations[1].is_oa	False
locations[1].source.id	https://openalex.org/S4306401280
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	False
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	DOAJ (DOAJ: Directory of Open Access Journals)
locations[1].source.host_organization
locations[1].source.host_organization_name
locations[1].license
locations[1].pdf_url
locations[1].version	submittedVersion
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published	False
locations[1].raw_source_name	Energies, Vol 18, Iss 21, p 5611 (2025)
locations[1].landing_page_url	https://doaj.org/article/747dbd643bdd4eaabbaaa0a101467567
indexed_in	crossref, doaj
authorships[0].author.id	https://openalex.org/A5066243328
authorships[0].author.orcid	https://orcid.org/0000-0002-6862-7032
authorships[0].author.display_name	Maitreyee Dey
authorships[0].countries	GB
authorships[0].affiliations[0].institution_ids	https://openalex.org/I126193024
authorships[0].affiliations[0].raw_affiliation_string	GENESIS Research Lab, Cyber Security Research Centre, London Metropolitan University, 166-220 Holloway Road, London N7 8DB, UK
authorships[0].institutions[0].id	https://openalex.org/I126193024
authorships[0].institutions[0].ror	https://ror.org/00ae33288
authorships[0].institutions[0].type	education
authorships[0].institutions[0].lineage	https://openalex.org/I126193024
authorships[0].institutions[0].country_code	GB
authorships[0].institutions[0].display_name	London Metropolitan University
authorships[0].author_position	first
authorships[0].raw_author_name	Maitreyee Dey
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	GENESIS Research Lab, Cyber Security Research Centre, London Metropolitan University, 166-220 Holloway Road, London N7 8DB, UK
authorships[1].author.id	https://openalex.org/A5088331544
authorships[1].author.orcid	https://orcid.org/0000-0002-8014-8122
authorships[1].author.display_name	Soumya Prakash Rana
authorships[1].countries	GB
authorships[1].affiliations[0].institution_ids	https://openalex.org/I55060895
authorships[1].affiliations[0].raw_affiliation_string	School of Engineering, University of Greenwich, Medway Campus, Central Avenue, Chatham ME4 4TB, UK
authorships[1].institutions[0].id	https://openalex.org/I55060895
authorships[1].institutions[0].ror	https://ror.org/00bmj0a71
authorships[1].institutions[0].type	education
authorships[1].institutions[0].lineage	https://openalex.org/I55060895
authorships[1].institutions[0].country_code	GB
authorships[1].institutions[0].display_name	University of Greenwich
authorships[1].author_position	last
authorships[1].raw_author_name	Soumya Prakash Rana
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	School of Engineering, University of Greenwich, Medway Campus, Central Avenue, Chatham ME4 4TB, UK
has_content.pdf	True
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-29T00:00:00
display_name	Self-Supervised Representation Learning for UK Power Grid Frequency Disturbance Detection Using TC-TSS
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	doi:10.3390/en18215611
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S198098182
best_oa_location.source.issn	1996-1073
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	1996-1073
best_oa_location.source.is_core	True
best_oa_location.source.is_in_doaj	True
best_oa_location.source.display_name	Energies
best_oa_location.source.host_organization	https://openalex.org/P4310310987
best_oa_location.source.host_organization_name	Multidisciplinary Digital Publishing Institute
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310310987
best_oa_location.source.host_organization_lineage_names	Multidisciplinary Digital Publishing Institute
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Energies
best_oa_location.landing_page_url	https://doi.org/10.3390/en18215611
primary_location.id	doi:10.3390/en18215611
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S198098182
primary_location.source.issn	1996-1073
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	1996-1073
primary_location.source.is_core	True
primary_location.source.is_in_doaj	True
primary_location.source.display_name	Energies
primary_location.source.host_organization	https://openalex.org/P4310310987
primary_location.source.host_organization_name	Multidisciplinary Digital Publishing Institute
primary_location.source.host_organization_lineage	https://openalex.org/P4310310987
primary_location.source.host_organization_lineage_names	Multidisciplinary Digital Publishing Institute
primary_location.license	cc-by
primary_location.pdf_url	https://www.mdpi.com/1996-1073/18/21/5611/pdf?version=1761380554
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Energies
primary_location.landing_page_url	https://doi.org/10.3390/en18215611
publication_date	2025-10-25
publication_year	2025
referenced_works	https://openalex.org/W2085066397, https://openalex.org/W3087125603, https://openalex.org/W3180134988, https://openalex.org/W2947917444, https://openalex.org/W3198487846, https://openalex.org/W4313039525, https://openalex.org/W4385423342, https://openalex.org/W4311724006, https://openalex.org/W4406080987, https://openalex.org/W3171543093, https://openalex.org/W4404244755, https://openalex.org/W4404643938, https://openalex.org/W4394568299, https://openalex.org/W4411885380, https://openalex.org/W4410985766, https://openalex.org/W2938533916, https://openalex.org/W3207924272, https://openalex.org/W3168984673, https://openalex.org/W3213550270, https://openalex.org/W4411725921, https://openalex.org/W4386212336, https://openalex.org/W4409990139, https://openalex.org/W4389381257, https://openalex.org/W4310211614, https://openalex.org/W4408126702, https://openalex.org/W4410788439, https://openalex.org/W3198047772, https://openalex.org/W4213304546, https://openalex.org/W3205893516, https://openalex.org/W4399926806, https://openalex.org/W4385805454
referenced_works_count	31
abstract_inverted_index.a	3
abstract_inverted_index.15	87
abstract_inverted_index.UK	23
abstract_inverted_index.as	128, 130
abstract_inverted_index.in	11, 115, 135, 161
abstract_inverted_index.is	83
abstract_inverted_index.of	45, 76, 94, 149, 157, 168
abstract_inverted_index.on	103
abstract_inverted_index.to	35, 54
abstract_inverted_index.we	26
abstract_inverted_index.MLP	123
abstract_inverted_index.SVM	125
abstract_inverted_index.The	48, 80
abstract_inverted_index.and	69, 124, 142, 172
abstract_inverted_index.are	51
abstract_inverted_index.for	7, 73, 122, 176
abstract_inverted_index.its	174
abstract_inverted_index.raw	111
abstract_inverted_index.six	92
abstract_inverted_index.the	22, 28, 136, 146, 155, 162
abstract_inverted_index.60-s	41
abstract_inverted_index.This	0, 152
abstract_inverted_index.UMAP	141
abstract_inverted_index.data	20, 89
abstract_inverted_index.four	56
abstract_inverted_index.from	21, 39
abstract_inverted_index.grid	181
abstract_inverted_index.high	129
abstract_inverted_index.into	178
abstract_inverted_index.over	86
abstract_inverted_index.rare	117
abstract_inverted_index.show	99
abstract_inverted_index.than	108
abstract_inverted_index.that	100
abstract_inverted_index.then	52
abstract_inverted_index.time	16
abstract_inverted_index.used	53
abstract_inverted_index.(LR),	61
abstract_inverted_index.(RF),	72
abstract_inverted_index.0.98,	131
abstract_inverted_index.Grid,	25
abstract_inverted_index.apply	27
abstract_inverted_index.data,	171
abstract_inverted_index.data.	18, 97
abstract_inverted_index.input	112
abstract_inverted_index.learn	36
abstract_inverted_index.power	12
abstract_inverted_index.reach	127
abstract_inverted_index.smart	180
abstract_inverted_index.study	1, 153
abstract_inverted_index.t-SNE	143
abstract_inverted_index.those	109
abstract_inverted_index.train	55
abstract_inverted_index.under	166
abstract_inverted_index.using	14, 85, 110, 140
abstract_inverted_index.(MLP),	68
abstract_inverted_index.(SVM),	65
abstract_inverted_index.Forest	71
abstract_inverted_index.Random	70
abstract_inverted_index.TC-TSS	104, 150
abstract_inverted_index.Vector	63
abstract_inverted_index.better	107
abstract_inverted_index.binary	74
abstract_inverted_index.energy	163
abstract_inverted_index.latent	137
abstract_inverted_index.method	82
abstract_inverted_index.models	126
abstract_inverted_index.months	93
abstract_inverted_index.points	90
abstract_inverted_index.proves	173
abstract_inverted_index.scores	121
abstract_inverted_index.series	17
abstract_inverted_index.space.	138
abstract_inverted_index.system	95
abstract_inverted_index.window	43
abstract_inverted_index.Machine	64
abstract_inverted_index.ROC-AUC	120
abstract_inverted_index.Results	98
abstract_inverted_index.Support	62
abstract_inverted_index.domain,	164
abstract_inverted_index.events.	79, 119
abstract_inverted_index.further	144
abstract_inverted_index.learned	49
abstract_inverted_index.limited	169
abstract_inverted_index.million	88
abstract_inverted_index.quality	148
abstract_inverted_index.rolling	42
abstract_inverted_index.systems	13
abstract_inverted_index.trained	102
abstract_inverted_index.(TC-TSS)	33
abstract_inverted_index.Learning	32
abstract_inverted_index.Logistic	59
abstract_inverted_index.National	24
abstract_inverted_index.Temporal	29
abstract_inverted_index.approach	34
abstract_inverted_index.labelled	170
abstract_inverted_index.learning	5, 160
abstract_inverted_index.presents	2
abstract_inverted_index.proposed	81
abstract_inverted_index.segments	44
abstract_inverted_index.spanning	91
abstract_inverted_index.Employing	19
abstract_inverted_index.detecting	8, 116
abstract_inverted_index.evaluated	84
abstract_inverted_index.excellent	133
abstract_inverted_index.features,	113
abstract_inverted_index.features.	151
abstract_inverted_index.framework	6
abstract_inverted_index.frequency	9, 46, 77
abstract_inverted_index.operation	96
abstract_inverted_index.performed	106
abstract_inverted_index.real-time	179
abstract_inverted_index.stability	78
abstract_inverted_index.Perceptron	67
abstract_inverted_index.Regression	60
abstract_inverted_index.clustering	147
abstract_inverted_index.conditions	167
abstract_inverted_index.embeddings	38, 105
abstract_inverted_index.highlights	154
abstract_inverted_index.indicating	132
abstract_inverted_index.unlabelled	40
abstract_inverted_index.Contrastive	30
abstract_inverted_index.Multi-Layer	66
abstract_inverted_index.classifiers	101
abstract_inverted_index.contrastive	158
abstract_inverted_index.demonstrate	145
abstract_inverted_index.disturbance	118
abstract_inverted_index.integration	177
abstract_inverted_index.suitability	175
abstract_inverted_index.traditional	57
abstract_inverted_index.classifiers,	58
abstract_inverted_index.disturbances	10
abstract_inverted_index.particularly	114, 165
abstract_inverted_index.separability	134
abstract_inverted_index.applications.	182
abstract_inverted_index.effectiveness	156
abstract_inverted_index.measurements.	47
abstract_inverted_index.task-agnostic	37
abstract_inverted_index.Visualisations	139
abstract_inverted_index.classification	75
abstract_inverted_index.representation	159
abstract_inverted_index.Self-Supervised	31
abstract_inverted_index.high-resolution	15
abstract_inverted_index.representations	50
abstract_inverted_index.self-supervised	4
cited_by_percentile_year
countries_distinct_count	1
institutions_distinct_count	2
citation_normalized_percentile