{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/125536"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/125536","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Cloud systems management with efficient and robust online learning","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","abstract_has_math":false,"creators":["Qiu, Haoran"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Iyer, Ravishankar K","Başar, Tamer","Nahrstedt, Klara","Gupta, Indranil","Mutlu, Onur"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-08","date_published":"2024-08","updated_at":"2026-07-22T22:25:02Z","subjects":["Serverless Computing","Cloud Computing","Distributed Systems","Machine Learning Systems","Resource Management","Quality-of-service","Reliability","Microservices"],"languages":["en","eng"],"rights":["Copyright 2024 Haoran Qiu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/125536","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Iyer, Ravishankar K","Başar, Tamer","Nahrstedt, Klara","Gupta, Indranil","Mutlu, Onur"]},{"key":"dc:creator","label":"Author","values":["Qiu, Haoran"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-08","2024-06-25"]},{"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 at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Serverless Computing","Cloud Computing","Distributed Systems","Machine Learning Systems","Resource Management","Quality-of-service","Reliability","Microservices"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Haoran Qiu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/125536"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","The student, Haoran Qiu, accepted the attached license on 2024-06-24 at 19:04.","The student, Haoran Qiu, submitted this Dissertation for approval on 2024-06-24 at 19:17.","This Dissertation was approved for publication on 2024-06-25 at 13:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20869 on 2025-02-04 at 21:03:55","Large-scale cloud computing systems rely heavily on decision-making algorithms for critical system management tasks such as resource allocation, job scheduling, and power management. Manually crafted heuristics for these algorithms become increasingly untenable given the complexity and heterogeneity of modern cloud environments because the intricate interactions across diverse workloads, hardware platforms, and operating conditions make it exceedingly difficult to devise fixed heuristics that work well across all scenarios. Although machine learning techniques have been proposed to automatically learn optimized system management policies, existing approaches face practical limitations and lack the robustness necessary for production-grade cloud systems. This dissertation pioneers a novel abstraction-driven paradigm of efficient and robust online learning to fundamentally transform cloud systems management at scale. We develop a general framework that leverages deep reinforcement learning with system domain knowledge at its core to discover optimized management policies by continuously exploring and refining them through in situ interactions with cloud environments. To practically and robustly apply learning in cloud systems at scale, we further design two key abstractions: (1) A virtual agent abstraction that coordinates the distributed learned policies to resolve multi-agent interferences and stably converge on system-wide objectives, and (2) A meta learner abstraction that extracts generalizable policy embeddings that can rapidly adapt across the breadth of heterogeneous cloud applications and platforms. This abstraction-driven approach provides practical and extensible support for a wide range of online learning algorithms and diverse systems management tasks. Instantiated in systems like FIRM (for microservices), SIMPPO (for serverless computing), and μ-Serve (for deep learning model serving), our innovative framework delivers order-of-magnitude improvements in resource efficiency, performance isolation, power optimization, and generalization compared to traditional heuristic-driven approaches. More profoundly, it establishes the foundations for practical and robust autonomous cloud systems management. Our contributions span the full stack, from mathematical models and optimizations to system design, implementation, and deployment."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Cloud systems management with efficient and robust online learning"]}]}],"canonical_facts":{"dc:contributor":["Iyer, Ravishankar K","Başar, Tamer","Nahrstedt, Klara","Gupta, Indranil","Mutlu, Onur"],"dc:creator":["Qiu, Haoran"],"dc:date":["2024-08","2024-06-25"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","The student, Haoran Qiu, accepted the attached license on 2024-06-24 at 19:04.","The student, Haoran Qiu, submitted this Dissertation for approval on 2024-06-24 at 19:17.","This Dissertation was approved for publication on 2024-06-25 at 13:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20869 on 2025-02-04 at 21:03:55","Large-scale cloud computing systems rely heavily on decision-making algorithms for critical system management tasks such as resource allocation, job scheduling, and power management. Manually crafted heuristics for these algorithms become increasingly untenable given the complexity and heterogeneity of modern cloud environments because the intricate interactions across diverse workloads, hardware platforms, and operating conditions make it exceedingly difficult to devise fixed heuristics that work well across all scenarios. Although machine learning techniques have been proposed to automatically learn optimized system management policies, existing approaches face practical limitations and lack the robustness necessary for production-grade cloud systems. This dissertation pioneers a novel abstraction-driven paradigm of efficient and robust online learning to fundamentally transform cloud systems management at scale. We develop a general framework that leverages deep reinforcement learning with system domain knowledge at its core to discover optimized management policies by continuously exploring and refining them through in situ interactions with cloud environments. To practically and robustly apply learning in cloud systems at scale, we further design two key abstractions: (1) A virtual agent abstraction that coordinates the distributed learned policies to resolve multi-agent interferences and stably converge on system-wide objectives, and (2) A meta learner abstraction that extracts generalizable policy embeddings that can rapidly adapt across the breadth of heterogeneous cloud applications and platforms. This abstraction-driven approach provides practical and extensible support for a wide range of online learning algorithms and diverse systems management tasks. Instantiated in systems like FIRM (for microservices), SIMPPO (for serverless computing), and μ-Serve (for deep learning model serving), our innovative framework delivers order-of-magnitude improvements in resource efficiency, performance isolation, power optimization, and generalization compared to traditional heuristic-driven approaches. More profoundly, it establishes the foundations for practical and robust autonomous cloud systems management. Our contributions span the full stack, from mathematical models and optimizations to system design, implementation, and deployment."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/125536"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Haoran Qiu"],"dc:subject":["Serverless Computing","Cloud Computing","Distributed Systems","Machine Learning Systems","Resource Management","Quality-of-service","Reliability","Microservices"],"dc:title":["Cloud systems management with efficient and robust online learning"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:02Z"}