Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793855276> ?p ?o ?g. }
- W2793855276 endingPage "134" @default.
- W2793855276 startingPage "129" @default.
- W2793855276 abstract "Cloud computing has become an attractive computing paradigm in both academia and industry. Through virtualization technology, Cloud Service Providers (CSPs) that own data centers can structure physical servers into Virtual Machines (VMs) to provide services, resources, and infrastructures to users. Profit-driven CSPs charge users for service access and VM rental, and reduce power consumption and electric bills so as to increase profit margin. The key challenge faced by CSPs is data center energy cost minimization. Prior works proposed various algorithms to reduce energy cost through Resource Provisioning (RP) and/or Task Scheduling (TS). However, they have scalability issues or do not consider TS with task dependencies, which is a crucial factor that ensures correct parallel execution of tasks. This paper presents DRL-Cloud, a novel Deep Reinforcement Learning (DRL)-based RP and TS system, to minimize energy cost for large-scale CSPs with very large number of servers that receive enormous numbers of user requests per day. A deep Q-learning-based two-stage RP-TS processor is designed to automatically generate the best long-term decisions by learning from the changing environment such as user request patterns and realistic electric price. With training techniques such as target network, experience replay, and exploration and exploitation, the proposed DRL-Cloud achieves remarkably high energy cost efficiency, low reject rate as well as low runtime with fast convergence. Compared with one of the state-of-the-art energy efficient algorithms, the proposed DRL-Cloud achieves up to 320% energy cost efficiency improvement while maintaining lower reject rate on average. For an example CSP setup with 5,000 servers and 200,000 tasks, compared to a fast round-robin baseline, the proposed DRL-Cloud achieves up to 144% runtime reduction." @default.
- W2793855276 created "2018-03-29" @default.
- W2793855276 creator A5057367919 @default.
- W2793855276 creator A5064803348 @default.
- W2793855276 creator A5065681916 @default.
- W2793855276 date "2018-01-22" @default.
- W2793855276 modified "2023-10-03" @default.
- W2793855276 title "DRL-cloud: deep reinforcement learning-based resource provisioning and task scheduling for cloud service providers" @default.
- W2793855276 cites W1262401806 @default.
- W2793855276 cites W1757796397 @default.
- W2793855276 cites W1965018830 @default.
- W2793855276 cites W1984560471 @default.
- W2793855276 cites W2017855273 @default.
- W2793855276 cites W2037200989 @default.
- W2793855276 cites W2044372531 @default.
- W2793855276 cites W2060204338 @default.
- W2793855276 cites W2068867834 @default.
- W2793855276 cites W2100830825 @default.
- W2793855276 cites W2129670787 @default.
- W2793855276 cites W2137695118 @default.
- W2793855276 cites W2145339207 @default.
- W2793855276 cites W2153947321 @default.
- W2793855276 cites W2254253446 @default.
- W2793855276 cites W2257979135 @default.
- W2793855276 cites W2320852659 @default.
- W2793855276 cites W2401433055 @default.
- W2793855276 cites W2534761338 @default.
- W2793855276 cites W2549630556 @default.
- W2793855276 cites W2551814622 @default.
- W2793855276 cites W2588861206 @default.
- W2793855276 cites W2597068831 @default.
- W2793855276 cites W2606469231 @default.
- W2793855276 cites W2610383189 @default.
- W2793855276 cites W2612565436 @default.
- W2793855276 cites W2616152995 @default.
- W2793855276 cites W2762734442 @default.
- W2793855276 cites W2918364912 @default.
- W2793855276 cites W2921710879 @default.
- W2793855276 cites W2952275172 @default.
- W2793855276 doi "https://doi.org/10.5555/3201607.3201635" @default.
- W2793855276 hasPublicationYear "2018" @default.
- W2793855276 type Work @default.
- W2793855276 sameAs 2793855276 @default.
- W2793855276 citedByCount "15" @default.
- W2793855276 countsByYear W27938552762018 @default.
- W2793855276 countsByYear W27938552762019 @default.
- W2793855276 countsByYear W27938552762020 @default.
- W2793855276 countsByYear W27938552762021 @default.
- W2793855276 crossrefType "proceedings-article" @default.
- W2793855276 hasAuthorship W2793855276A5057367919 @default.
- W2793855276 hasAuthorship W2793855276A5064803348 @default.
- W2793855276 hasAuthorship W2793855276A5065681916 @default.
- W2793855276 hasConcept C111919701 @default.
- W2793855276 hasConcept C119599485 @default.
- W2793855276 hasConcept C120314980 @default.
- W2793855276 hasConcept C127413603 @default.
- W2793855276 hasConcept C154945302 @default.
- W2793855276 hasConcept C172191483 @default.
- W2793855276 hasConcept C206729178 @default.
- W2793855276 hasConcept C21547014 @default.
- W2793855276 hasConcept C2742236 @default.
- W2793855276 hasConcept C31258907 @default.
- W2793855276 hasConcept C41008148 @default.
- W2793855276 hasConcept C48044578 @default.
- W2793855276 hasConcept C513985346 @default.
- W2793855276 hasConcept C79974875 @default.
- W2793855276 hasConcept C93996380 @default.
- W2793855276 hasConcept C97541855 @default.
- W2793855276 hasConceptScore W2793855276C111919701 @default.
- W2793855276 hasConceptScore W2793855276C119599485 @default.
- W2793855276 hasConceptScore W2793855276C120314980 @default.
- W2793855276 hasConceptScore W2793855276C127413603 @default.
- W2793855276 hasConceptScore W2793855276C154945302 @default.
- W2793855276 hasConceptScore W2793855276C172191483 @default.
- W2793855276 hasConceptScore W2793855276C206729178 @default.
- W2793855276 hasConceptScore W2793855276C21547014 @default.
- W2793855276 hasConceptScore W2793855276C2742236 @default.
- W2793855276 hasConceptScore W2793855276C31258907 @default.
- W2793855276 hasConceptScore W2793855276C41008148 @default.
- W2793855276 hasConceptScore W2793855276C48044578 @default.
- W2793855276 hasConceptScore W2793855276C513985346 @default.
- W2793855276 hasConceptScore W2793855276C79974875 @default.
- W2793855276 hasConceptScore W2793855276C93996380 @default.
- W2793855276 hasConceptScore W2793855276C97541855 @default.
- W2793855276 hasLocation W27938552761 @default.
- W2793855276 hasOpenAccess W2793855276 @default.
- W2793855276 hasPrimaryLocation W27938552761 @default.
- W2793855276 hasRelatedWork W1757796397 @default.
- W2793855276 hasRelatedWork W1977367431 @default.
- W2793855276 hasRelatedWork W2045287414 @default.
- W2793855276 hasRelatedWork W2068867834 @default.
- W2793855276 hasRelatedWork W2110374615 @default.
- W2793855276 hasRelatedWork W2121863487 @default.
- W2793855276 hasRelatedWork W2138583691 @default.
- W2793855276 hasRelatedWork W2145339207 @default.
- W2793855276 hasRelatedWork W2148459868 @default.
- W2793855276 hasRelatedWork W2150273829 @default.
- W2793855276 hasRelatedWork W2257979135 @default.