{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/132704"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/132704","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Dora: QoE-aware hybrid parallelism for distributed edge AI","abstract":"With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first-class objective, as these models operate in resource-constrained settings and directly interact with users. Yet, modern AI models routinely exceed the resource capacity of individual devices, necessitating distributed execution across heterogeneous devices over variable and contention-prone networks. Existing planners for hybrid (e.g., data and pipeline) parallelism largely optimize for throughput or device utilization, overlooking QoE, leading to severe resource inefficiency (e.g., unnecessary energy drain), or QoE violations under runtime dynamics. We present Dora, a framework for QoE-aware hybrid parallelism in distributed edge AI training and inference. Dora jointly optimizes heterogeneous computation, contention prone networks, and multi-dimensional QoE objectives via three key mechanisms: (i) a heterogeneity-aware model partitioner that determines and assigns model partitions across devices, forming a compact set of QoE-compliant plans; (ii) a contention-aware network scheduler further refines these candidate plans by maximizing compute–communication overlap; and (iii) a runtime adapter that adaptively composes multiple plans to maximize global efficiency while respecting overall QoEs. Across representative edge deployments—including smart homes, traffic analytics, and small edge clusters—Dora achieves 1.1–6.3× faster execution and, alternatively, reduces energy consumption by 21–82%, all while maintaining QoE under runtime dynamics.","abstract_html":"With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first-class objective, as these models operate in resource-constrained settings and directly interact with users. Yet, modern AI models routinely exceed the resource capacity of individual devices, necessitating distributed execution across heterogeneous devices over variable and contention-prone networks. Existing planners for hybrid (e.g., data and pipeline) parallelism largely optimize for throughput or device utilization, overlooking QoE, leading to severe resource inefficiency (e.g., unnecessary energy drain), or QoE violations under runtime dynamics. We present Dora, a framework for QoE-aware hybrid parallelism in distributed edge AI training and inference. Dora jointly optimizes heterogeneous computation, contention prone networks, and multi-dimensional QoE objectives via three key mechanisms: (i) a heterogeneity-aware model partitioner that determines and assigns model partitions across devices, forming a compact set of QoE-compliant plans; (ii) a contention-aware network scheduler further refines these candidate plans by maximizing compute–communication overlap; and (iii) a runtime adapter that adaptively composes multiple plans to maximize global efficiency while respecting overall QoEs. Across representative edge deployments—including smart homes, traffic analytics, and small edge clusters—Dora achieves 1.1–6.3× faster execution and, alternatively, reduces energy consumption by 21–82%, all while maintaining QoE under runtime dynamics.","abstract_has_math":false,"creators":["Jin, Jianli"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Lai, Fan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-22T22:25:07Z","subjects":["Edge Computing","Distributed Training","System for Artificial Intelligence"],"languages":["en"],"rights":["Copyright 2025 Jianli Jin"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/132704","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lai, Fan"]},{"key":"dc:creator","label":"Author","values":["Jin, Jianli"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12","2025-12-10"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Edge Computing","Distributed Training","System for Artificial Intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Jianli Jin"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/132704"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first-class objective, as these models operate in resource-constrained settings and directly interact with users. Yet, modern AI models routinely exceed the resource capacity of individual devices, necessitating distributed execution across heterogeneous devices over variable and contention-prone networks. Existing planners for hybrid (e.g., data and pipeline) parallelism largely optimize for throughput or device utilization, overlooking QoE, leading to severe resource inefficiency (e.g., unnecessary energy drain), or QoE violations under runtime dynamics. We present Dora, a framework for QoE-aware hybrid parallelism in distributed edge AI training and inference. Dora jointly optimizes heterogeneous computation, contention prone networks, and multi-dimensional QoE objectives via three key mechanisms: (i) a heterogeneity-aware model partitioner that determines and assigns model partitions across devices, forming a compact set of QoE-compliant plans; (ii) a contention-aware network scheduler further refines these candidate plans by maximizing compute–communication overlap; and (iii) a runtime adapter that adaptively composes multiple plans to maximize global efficiency while respecting overall QoEs. Across representative edge deployments—including smart homes, traffic analytics, and small edge clusters—Dora achieves 1.1–6.3× faster execution and, alternatively, reduces energy consumption by 21–82%, all while maintaining QoE under runtime dynamics.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-12-01","The student, Jianli Jin, accepted the attached license on 2025-12-10 at 09:25.","The student, Jianli Jin, submitted this Thesis for approval on 2025-12-10 at 09:32.","This Thesis was approved for publication on 2025-12-10 at 10:33.","DSpace SAF Submission Ingestion Package generated from Vireo submission #23118 on 2026-02-19 at 18:46:54"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Dora: QoE-aware hybrid parallelism for distributed edge AI"]}]}],"canonical_facts":{"dc:contributor":["Lai, Fan"],"dc:creator":["Jin, Jianli"],"dc:date":["2025-12","2025-12-10"],"dc:description":["With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first-class objective, as these models operate in resource-constrained settings and directly interact with users. Yet, modern AI models routinely exceed the resource capacity of individual devices, necessitating distributed execution across heterogeneous devices over variable and contention-prone networks. Existing planners for hybrid (e.g., data and pipeline) parallelism largely optimize for throughput or device utilization, overlooking QoE, leading to severe resource inefficiency (e.g., unnecessary energy drain), or QoE violations under runtime dynamics. We present Dora, a framework for QoE-aware hybrid parallelism in distributed edge AI training and inference. Dora jointly optimizes heterogeneous computation, contention prone networks, and multi-dimensional QoE objectives via three key mechanisms: (i) a heterogeneity-aware model partitioner that determines and assigns model partitions across devices, forming a compact set of QoE-compliant plans; (ii) a contention-aware network scheduler further refines these candidate plans by maximizing compute–communication overlap; and (iii) a runtime adapter that adaptively composes multiple plans to maximize global efficiency while respecting overall QoEs. Across representative edge deployments—including smart homes, traffic analytics, and small edge clusters—Dora achieves 1.1–6.3× faster execution and, alternatively, reduces energy consumption by 21–82%, all while maintaining QoE under runtime dynamics.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-12-01","The student, Jianli Jin, accepted the attached license on 2025-12-10 at 09:25.","The student, Jianli Jin, submitted this Thesis for approval on 2025-12-10 at 09:32.","This Thesis was approved for publication on 2025-12-10 at 10:33.","DSpace SAF Submission Ingestion Package generated from Vireo submission #23118 on 2026-02-19 at 18:46:54"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/132704"],"dc:language":["en"],"dc:rights":["Copyright 2025 Jianli Jin"],"dc:subject":["Edge Computing","Distributed Training","System for Artificial Intelligence"],"dc:title":["Dora: QoE-aware hybrid parallelism for distributed edge AI"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:07Z"}