ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge Article Swipe

PDF

Daghash K. Alqahtani , Maria A. Rodriguez , Muhammad Aamir Cheema , Hamid Rezatofighi , Adel N. Toosi ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.06011

Edge computing enables data processing closer to the source, significantly reducing latency, an essential requirement for real-time vision-based analytics such as object detection in surveillance and smart city environments. However, these tasks place substantial demands on resource-constrained edge devices, making the joint optimization of energy consumption and detection accuracy critical. To address this challenge, we propose ECORE, a framework that integrates multiple dynamic routing strategies, including a novel estimation-based techniques and an innovative greedy selection algorithm, to direct image processing requests to the most suitable edge device-model pair. ECORE dynamically balances energy efficiency and detection performance based on object characteristics. We evaluate our framework through extensive experiments on real-world datasets, comparing against widely used baseline techniques. The evaluation leverages established object detection models (YOLO, SSD, EfficientDet) and diverse edge platforms, including Jetson Orin Nano, Raspberry Pi 4 and 5, and TPU accelerators. Results demonstrate that our proposed context-aware routing strategies can reduce energy consumption and latency by 35% and 49%, respectively, while incurring only a 2% loss in detection accuracy compared to accuracy-centric methods.

Related Topics

Truth And Reconciliation Commission Of Canada

2025 Nba Draft

28 Years Later

Reich Ministry Of Public Enlightenment And Propaganda

Mahmood Mamdani

Rick Hurst

Degenerate Art Exhibition

Mutual Aid

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2507.06011
PDF: https://arxiv.org/pdf/2507.06011
OA Status: green
OpenAlex ID: https://openalex.org/W4416062053

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416062053

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2507.06011

Digital Object Identifier
Title: ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-08

Full publication date if available
Authors: Daghash K. Alqahtani, Maria A. Rodriguez, Muhammad Aamir Cheema, Hamid Rezatofighi, Adel N. Toosi

List of authors in order
Landing page: https://arxiv.org/abs/2507.06011

Publisher landing page
PDF URL: https://arxiv.org/pdf/2507.06011

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2507.06011

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416062053
doi	https://doi.org/10.48550/arxiv.2507.06011
ids.doi	https://doi.org/10.48550/arxiv.2507.06011
ids.openalex	https://openalex.org/W4416062053
fwci
type	preprint
title	ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2507.06011
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2507.06011
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2507.06011
locations[1].id	doi:10.48550/arxiv.2507.06011
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2507.06011
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5098960058
authorships[0].author.orcid	https://orcid.org/0009-0001-5309-6996
authorships[0].author.display_name	Daghash K. Alqahtani
authorships[0].author_position	first
authorships[0].raw_author_name	Alqahtani, Daghash K.
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5032796449
authorships[1].author.orcid	https://orcid.org/0000-0002-2831-8526
authorships[1].author.display_name	Maria A. Rodriguez
authorships[1].author_position	middle
authorships[1].raw_author_name	Rodriguez, Maria A.
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5047549903
authorships[2].author.orcid	https://orcid.org/0000-0003-2139-9121
authorships[2].author.display_name	Muhammad Aamir Cheema
authorships[2].author_position	middle
authorships[2].raw_author_name	Cheema, Muhammad Aamir
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5099282607
authorships[3].author.orcid
authorships[3].author.display_name	Hamid Rezatofighi
authorships[3].author_position	middle
authorships[3].raw_author_name	Rezatofighi, Hamid
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5083902835
authorships[4].author.orcid	https://orcid.org/0000-0001-5655-5337
authorships[4].author.display_name	Adel N. Toosi
authorships[4].author_position	last
authorships[4].raw_author_name	Toosi, Adel N.
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2507.06011
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T10:25:07.004793
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2507.06011
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2507.06011
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2507.06011
primary_location.id	pmh:oai:arXiv.org:2507.06011
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2507.06011
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2507.06011
publication_date	2025-07-08
publication_year	2025
referenced_works_count	0
abstract_inverted_index.4	136
abstract_inverted_index.a	57, 66, 164
abstract_inverted_index.2%	165
abstract_inverted_index.5,	138
abstract_inverted_index.Pi	135
abstract_inverted_index.To	50
abstract_inverted_index.We	100
abstract_inverted_index.an	12, 71
abstract_inverted_index.as	20
abstract_inverted_index.by	156
abstract_inverted_index.in	23, 167
abstract_inverted_index.of	43
abstract_inverted_index.on	35, 97, 107
abstract_inverted_index.to	6, 76, 81, 171
abstract_inverted_index.we	54
abstract_inverted_index.35%	157
abstract_inverted_index.TPU	140
abstract_inverted_index.The	116
abstract_inverted_index.and	25, 46, 70, 93, 126, 137, 139, 154, 158
abstract_inverted_index.can	150
abstract_inverted_index.for	15
abstract_inverted_index.our	102, 145
abstract_inverted_index.the	7, 40, 82
abstract_inverted_index.49%,	159
abstract_inverted_index.Edge	0
abstract_inverted_index.Orin	132
abstract_inverted_index.SSD,	124
abstract_inverted_index.city	27
abstract_inverted_index.data	3
abstract_inverted_index.edge	37, 85, 128
abstract_inverted_index.loss	166
abstract_inverted_index.most	83
abstract_inverted_index.only	163
abstract_inverted_index.such	19
abstract_inverted_index.that	59, 144
abstract_inverted_index.this	52
abstract_inverted_index.used	113
abstract_inverted_index.ECORE	88
abstract_inverted_index.Nano,	133
abstract_inverted_index.based	96
abstract_inverted_index.image	78
abstract_inverted_index.joint	41
abstract_inverted_index.novel	67
abstract_inverted_index.pair.	87
abstract_inverted_index.place	32
abstract_inverted_index.smart	26
abstract_inverted_index.tasks	31
abstract_inverted_index.these	30
abstract_inverted_index.while	161
abstract_inverted_index.(YOLO,	123
abstract_inverted_index.ECORE,	56
abstract_inverted_index.Jetson	131
abstract_inverted_index.closer	5
abstract_inverted_index.direct	77
abstract_inverted_index.energy	44, 91, 152
abstract_inverted_index.greedy	73
abstract_inverted_index.making	39
abstract_inverted_index.models	122
abstract_inverted_index.object	21, 98, 120
abstract_inverted_index.reduce	151
abstract_inverted_index.widely	112
abstract_inverted_index.Results	142
abstract_inverted_index.address	51
abstract_inverted_index.against	111
abstract_inverted_index.demands	34
abstract_inverted_index.diverse	127
abstract_inverted_index.dynamic	62
abstract_inverted_index.enables	2
abstract_inverted_index.latency	155
abstract_inverted_index.propose	55
abstract_inverted_index.routing	63, 148
abstract_inverted_index.source,	8
abstract_inverted_index.through	104
abstract_inverted_index.However,	29
abstract_inverted_index.accuracy	48, 169
abstract_inverted_index.balances	90
abstract_inverted_index.baseline	114
abstract_inverted_index.compared	170
abstract_inverted_index.devices,	38
abstract_inverted_index.evaluate	101
abstract_inverted_index.latency,	11
abstract_inverted_index.methods.	173
abstract_inverted_index.multiple	61
abstract_inverted_index.proposed	146
abstract_inverted_index.reducing	10
abstract_inverted_index.requests	80
abstract_inverted_index.suitable	84
abstract_inverted_index.Raspberry	134
abstract_inverted_index.analytics	18
abstract_inverted_index.comparing	110
abstract_inverted_index.computing	1
abstract_inverted_index.critical.	49
abstract_inverted_index.datasets,	109
abstract_inverted_index.detection	22, 47, 94, 121, 168
abstract_inverted_index.essential	13
abstract_inverted_index.extensive	105
abstract_inverted_index.framework	58, 103
abstract_inverted_index.including	65, 130
abstract_inverted_index.incurring	162
abstract_inverted_index.leverages	118
abstract_inverted_index.real-time	16
abstract_inverted_index.selection	74
abstract_inverted_index.algorithm,	75
abstract_inverted_index.challenge,	53
abstract_inverted_index.efficiency	92
abstract_inverted_index.evaluation	117
abstract_inverted_index.innovative	72
abstract_inverted_index.integrates	60
abstract_inverted_index.platforms,	129
abstract_inverted_index.processing	4, 79
abstract_inverted_index.real-world	108
abstract_inverted_index.strategies	149
abstract_inverted_index.techniques	69
abstract_inverted_index.consumption	45, 153
abstract_inverted_index.demonstrate	143
abstract_inverted_index.dynamically	89
abstract_inverted_index.established	119
abstract_inverted_index.experiments	106
abstract_inverted_index.performance	95
abstract_inverted_index.requirement	14
abstract_inverted_index.strategies,	64
abstract_inverted_index.substantial	33
abstract_inverted_index.techniques.	115
abstract_inverted_index.device-model	86
abstract_inverted_index.optimization	42
abstract_inverted_index.surveillance	24
abstract_inverted_index.vision-based	17
abstract_inverted_index.EfficientDet)	125
abstract_inverted_index.accelerators.	141
abstract_inverted_index.context-aware	147
abstract_inverted_index.environments.	28
abstract_inverted_index.respectively,	160
abstract_inverted_index.significantly	9
abstract_inverted_index.accuracy-centric	172
abstract_inverted_index.characteristics.	99
abstract_inverted_index.estimation-based	68
abstract_inverted_index.resource-constrained	36
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile