{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/132532"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/132532","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Acies-OS: a twin-assisted systems architecture for edge intelligence","abstract":"The rapid proliferation of Artificial Intelligence (AI) within the Internet of Things (IoT) and Cyber-Physical Systems (CPS) has created new opportunities for intelligent sensing, perception, and control at the network edge. However, deploying deep learning-based intelligence on embedded platforms introduces fundamental challenges, including limited computational resources, thermal constraints, and unreliable network connectivity. Addressing these challenges requires system-level innovation that spans from performance modeling and resource optimization to workflow orchestration and adaptive learning. This dissertation introduces Acies-OS, a twin-assisted, content-centric middleware framework designed to enhance the efficiency and robustness of distributed edge intelligence systems. Acies-OS unifies data, computation, and control under a structured namespace abstraction, allowing distributed nodes to coordinate seamlessly through declarative data and control interfaces. Its design combines efficient latency and thermal modeling for performance optimization, a digital twin mechanism for cross-layer monitoring and failover recovery, and an extensible control plane for implementing runtime optimization services such as model selection and workflow reconfiguration. Together, these mechanisms enable dynamic, data-driven management of complex sensing-to-decision workflows in resource-constrained environments. The dissertation further introduces an unsupervised collaborative adaptation framework that enables in-situ model refinement at runtime without labeled data. By leveraging spatial and temporal correlations across distributed sensors, this approach improves model robustness against domain shifts encountered in real deployments. The system is implemented and evaluated using a multi-modal, multi-node vehicle classification testbed that has supported numerous research efforts and produced the largest publicly available dataset of its kind. Finally, the dissertation outlines a design for extending Acies-OS toward agentic edge intelligence, integrating large language model (LLM)-based agents with cyber-physical systems through standardized control interfaces. Overall, this work presents an integrated architecture that advances the efficiency, adaptability, and resilience of edge AI systems. By connecting AI optimization, system middleware, and digital twinning within a unified framework, Acies-OS offers a practical step toward enabling intelligent and self-managing IoT and CPS deployments.","abstract_html":"The rapid proliferation of Artificial Intelligence (AI) within the Internet of Things (IoT) and Cyber-Physical Systems (CPS) has created new opportunities for intelligent sensing, perception, and control at the network edge. However, deploying deep learning-based intelligence on embedded platforms introduces fundamental challenges, including limited computational resources, thermal constraints, and unreliable network connectivity. Addressing these challenges requires system-level innovation that spans from performance modeling and resource optimization to workflow orchestration and adaptive learning. This dissertation introduces Acies-OS, a twin-assisted, content-centric middleware framework designed to enhance the efficiency and robustness of distributed edge intelligence systems. Acies-OS unifies data, computation, and control under a structured namespace abstraction, allowing distributed nodes to coordinate seamlessly through declarative data and control interfaces. Its design combines efficient latency and thermal modeling for performance optimization, a digital twin mechanism for cross-layer monitoring and failover recovery, and an extensible control plane for implementing runtime optimization services such as model selection and workflow reconfiguration. Together, these mechanisms enable dynamic, data-driven management of complex sensing-to-decision workflows in resource-constrained environments. The dissertation further introduces an unsupervised collaborative adaptation framework that enables in-situ model refinement at runtime without labeled data. By leveraging spatial and temporal correlations across distributed sensors, this approach improves model robustness against domain shifts encountered in real deployments. The system is implemented and evaluated using a multi-modal, multi-node vehicle classification testbed that has supported numerous research efforts and produced the largest publicly available dataset of its kind. Finally, the dissertation outlines a design for extending Acies-OS toward agentic edge intelligence, integrating large language model (LLM)-based agents with cyber-physical systems through standardized control interfaces. Overall, this work presents an integrated architecture that advances the efficiency, adaptability, and resilience of edge AI systems. By connecting AI optimization, system middleware, and digital twinning within a unified framework, Acies-OS offers a practical step toward enabling intelligent and self-managing IoT and CPS deployments.","abstract_has_math":false,"creators":["Li, Jinyang"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Abdelzaher, Tarek","Nahrstedt, Klara","Caesar, Matthew","Shenoy, Prashant"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-22T22:25:07Z","subjects":["Edge AI","Digital Twin","Cyber-Physical System","Internet of Things"],"languages":["en"],"rights":["Copyright 2025 Jinyang Li"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/132532","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Abdelzaher, Tarek","Nahrstedt, Klara","Caesar, Matthew","Shenoy, Prashant"]},{"key":"dc:creator","label":"Author","values":["Li, Jinyang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12","2025-11-26"]},{"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":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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 AI","Digital Twin","Cyber-Physical System","Internet of Things"]}]},{"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 Jinyang Li"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/132532"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The rapid proliferation of Artificial Intelligence (AI) within the Internet of Things (IoT) and Cyber-Physical Systems (CPS) has created new opportunities for intelligent sensing, perception, and control at the network edge. However, deploying deep learning-based intelligence on embedded platforms introduces fundamental challenges, including limited computational resources, thermal constraints, and unreliable network connectivity. Addressing these challenges requires system-level innovation that spans from performance modeling and resource optimization to workflow orchestration and adaptive learning. This dissertation introduces Acies-OS, a twin-assisted, content-centric middleware framework designed to enhance the efficiency and robustness of distributed edge intelligence systems. Acies-OS unifies data, computation, and control under a structured namespace abstraction, allowing distributed nodes to coordinate seamlessly through declarative data and control interfaces. Its design combines efficient latency and thermal modeling for performance optimization, a digital twin mechanism for cross-layer monitoring and failover recovery, and an extensible control plane for implementing runtime optimization services such as model selection and workflow reconfiguration. Together, these mechanisms enable dynamic, data-driven management of complex sensing-to-decision workflows in resource-constrained environments. The dissertation further introduces an unsupervised collaborative adaptation framework that enables in-situ model refinement at runtime without labeled data. By leveraging spatial and temporal correlations across distributed sensors, this approach improves model robustness against domain shifts encountered in real deployments. The system is implemented and evaluated using a multi-modal, multi-node vehicle classification testbed that has supported numerous research efforts and produced the largest publicly available dataset of its kind. Finally, the dissertation outlines a design for extending Acies-OS toward agentic edge intelligence, integrating large language model (LLM)-based agents with cyber-physical systems through standardized control interfaces. Overall, this work presents an integrated architecture that advances the efficiency, adaptability, and resilience of edge AI systems. By connecting AI optimization, system middleware, and digital twinning within a unified framework, Acies-OS offers a practical step toward enabling intelligent and self-managing IoT and CPS deployments.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms","The student, Jinyang Li, accepted the attached license on 2025-11-25 at 16:20.","The student, Jinyang Li, submitted this Dissertation for approval on 2025-11-25 at 16:28.","This Dissertation was approved for publication on 2025-11-26 at 10:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22955 on 2026-02-19 at 18:25:22"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Acies-OS: a twin-assisted systems architecture for edge intelligence"]}]}],"canonical_facts":{"dc:contributor":["Abdelzaher, Tarek","Nahrstedt, Klara","Caesar, Matthew","Shenoy, Prashant"],"dc:creator":["Li, Jinyang"],"dc:date":["2025-12","2025-11-26"],"dc:description":["The rapid proliferation of Artificial Intelligence (AI) within the Internet of Things (IoT) and Cyber-Physical Systems (CPS) has created new opportunities for intelligent sensing, perception, and control at the network edge. However, deploying deep learning-based intelligence on embedded platforms introduces fundamental challenges, including limited computational resources, thermal constraints, and unreliable network connectivity. Addressing these challenges requires system-level innovation that spans from performance modeling and resource optimization to workflow orchestration and adaptive learning. This dissertation introduces Acies-OS, a twin-assisted, content-centric middleware framework designed to enhance the efficiency and robustness of distributed edge intelligence systems. Acies-OS unifies data, computation, and control under a structured namespace abstraction, allowing distributed nodes to coordinate seamlessly through declarative data and control interfaces. Its design combines efficient latency and thermal modeling for performance optimization, a digital twin mechanism for cross-layer monitoring and failover recovery, and an extensible control plane for implementing runtime optimization services such as model selection and workflow reconfiguration. Together, these mechanisms enable dynamic, data-driven management of complex sensing-to-decision workflows in resource-constrained environments. The dissertation further introduces an unsupervised collaborative adaptation framework that enables in-situ model refinement at runtime without labeled data. By leveraging spatial and temporal correlations across distributed sensors, this approach improves model robustness against domain shifts encountered in real deployments. The system is implemented and evaluated using a multi-modal, multi-node vehicle classification testbed that has supported numerous research efforts and produced the largest publicly available dataset of its kind. Finally, the dissertation outlines a design for extending Acies-OS toward agentic edge intelligence, integrating large language model (LLM)-based agents with cyber-physical systems through standardized control interfaces. Overall, this work presents an integrated architecture that advances the efficiency, adaptability, and resilience of edge AI systems. By connecting AI optimization, system middleware, and digital twinning within a unified framework, Acies-OS offers a practical step toward enabling intelligent and self-managing IoT and CPS deployments.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2026-02-19 without embargo terms","The student, Jinyang Li, accepted the attached license on 2025-11-25 at 16:20.","The student, Jinyang Li, submitted this Dissertation for approval on 2025-11-25 at 16:28.","This Dissertation was approved for publication on 2025-11-26 at 10:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22955 on 2026-02-19 at 18:25:22"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/132532"],"dc:language":["en"],"dc:rights":["Copyright 2025 Jinyang Li"],"dc:subject":["Edge AI","Digital Twin","Cyber-Physical System","Internet of Things"],"dc:title":["Acies-OS: a twin-assisted systems architecture for edge intelligence"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:07Z"}