FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225549801> ?p ?o ?g. }

• W4225549801 endingPage "1309" @default.
• W4225549801 startingPage "1296" @default.
• W4225549801 abstract "To reduce the skyrocketing energy consumption of data centers, the prevailing approaches adopt the time-driven manner to control IT and cooling subsystems. These methods suffer from highly dynamic system states, complex action spaces and the risk of instability caused by frequent and unnecessary control operations. To tackle these problems, we propose a novel event-driven control paradigm and an optimization algorithm, under the deep reinforcement learning (DRL) framework. The principle is to make decisions based on certain critical events (e.g., overheating), rather than fixed periodic control. Specifically, we design an event-driven optimization framework to trigger control operations. Then, we present several models to describe IT and cooling subsystems, and mathematically define events to capture four types of prior factors that impact system performance. Furthermore, we develop an event-driven DRL (E-DRL) optimization algorithm to dispatch jobs and regulate cooling facilities for energy efficiency. Using two different types of real workload traces, we conduct extensive experiments to demonstrate that: 1) E-DRL reduces the number of regulating decisions by 70% <inline-formula><tex-math notation=LaTeX>$sim$</tex-math></inline-formula> 95% while achieving a comparable or even better energy efficiency in comparison with the state-of-the-art algorithm; and 2) E-DRL can adapt the control frequency to the changing operational conditions and diverse workloads." @default.
• W4225549801 created "2022-05-05" @default.
• W4225549801 creator A5016656803 @default.
• W4225549801 creator A5020194895 @default.
• W4225549801 creator A5041572550 @default.
• W4225549801 creator A5067563426 @default.
• W4225549801 date "2023-03-01" @default.
• W4225549801 modified "2023-10-14" @default.
• W4225549801 title "Optimizing Data Center Energy Efficiency via Event-Driven Deep Reinforcement Learning" @default.
• W4225549801 cites W1667199472 @default.
• W4225549801 cites W1965522053 @default.
• W4225549801 cites W1978631822 @default.
• W4225549801 cites W2053211348 @default.
• W4225549801 cites W2055043902 @default.
• W4225549801 cites W2093311403 @default.
• W4225549801 cites W2145339207 @default.
• W4225549801 cites W2245628559 @default.
• W4225549801 cites W2257979135 @default.
• W4225549801 cites W2275624464 @default.
• W4225549801 cites W2327388626 @default.
• W4225549801 cites W2555390784 @default.
• W4225549801 cites W2587207633 @default.
• W4225549801 cites W2610077734 @default.
• W4225549801 cites W2774852867 @default.
• W4225549801 cites W2777549886 @default.
• W4225549801 cites W2781724993 @default.
• W4225549801 cites W2790037750 @default.
• W4225549801 cites W2795344589 @default.
• W4225549801 cites W2802106953 @default.
• W4225549801 cites W2884168111 @default.
• W4225549801 cites W2888655287 @default.
• W4225549801 cites W2889856497 @default.
• W4225549801 cites W2964229770 @default.
• W4225549801 cites W2965676832 @default.
• W4225549801 cites W2971974314 @default.
• W4225549801 cites W2982619481 @default.
• W4225549801 cites W2982625995 @default.
• W4225549801 cites W2983710998 @default.
• W4225549801 cites W2987965537 @default.
• W4225549801 doi "https://doi.org/10.1109/tsc.2022.3157145" @default.
• W4225549801 hasPublicationYear "2023" @default.
• W4225549801 type Work @default.
• W4225549801 citedByCount "6" @default.
• W4225549801 countsByYear W42255498012022 @default.
• W4225549801 crossrefType "journal-article" @default.
• W4225549801 hasAuthorship W4225549801A5016656803 @default.
• W4225549801 hasAuthorship W4225549801A5020194895 @default.
• W4225549801 hasAuthorship W4225549801A5041572550 @default.
• W4225549801 hasAuthorship W4225549801A5067563426 @default.
• W4225549801 hasConcept C111919701 @default.
• W4225549801 hasConcept C119599485 @default.
• W4225549801 hasConcept C120314980 @default.
• W4225549801 hasConcept C121332964 @default.
• W4225549801 hasConcept C126255220 @default.
• W4225549801 hasConcept C127413603 @default.
• W4225549801 hasConcept C153740404 @default.
• W4225549801 hasConcept C154945302 @default.
• W4225549801 hasConcept C2742236 @default.
• W4225549801 hasConcept C2775924081 @default.
• W4225549801 hasConcept C2778476105 @default.
• W4225549801 hasConcept C2779662365 @default.
• W4225549801 hasConcept C2780165032 @default.
• W4225549801 hasConcept C33923547 @default.
• W4225549801 hasConcept C41008148 @default.
• W4225549801 hasConcept C45357846 @default.
• W4225549801 hasConcept C62520636 @default.
• W4225549801 hasConcept C79403827 @default.
• W4225549801 hasConcept C94375191 @default.
• W4225549801 hasConcept C97541855 @default.
• W4225549801 hasConceptScore W4225549801C111919701 @default.
• W4225549801 hasConceptScore W4225549801C119599485 @default.
• W4225549801 hasConceptScore W4225549801C120314980 @default.
• W4225549801 hasConceptScore W4225549801C121332964 @default.
• W4225549801 hasConceptScore W4225549801C126255220 @default.
• W4225549801 hasConceptScore W4225549801C127413603 @default.
• W4225549801 hasConceptScore W4225549801C153740404 @default.
• W4225549801 hasConceptScore W4225549801C154945302 @default.
• W4225549801 hasConceptScore W4225549801C2742236 @default.
• W4225549801 hasConceptScore W4225549801C2775924081 @default.
• W4225549801 hasConceptScore W4225549801C2778476105 @default.
• W4225549801 hasConceptScore W4225549801C2779662365 @default.
• W4225549801 hasConceptScore W4225549801C2780165032 @default.
• W4225549801 hasConceptScore W4225549801C33923547 @default.
• W4225549801 hasConceptScore W4225549801C41008148 @default.
• W4225549801 hasConceptScore W4225549801C45357846 @default.
• W4225549801 hasConceptScore W4225549801C62520636 @default.
• W4225549801 hasConceptScore W4225549801C79403827 @default.
• W4225549801 hasConceptScore W4225549801C94375191 @default.
• W4225549801 hasConceptScore W4225549801C97541855 @default.
• W4225549801 hasFunder F4320320671 @default.
• W4225549801 hasFunder F4320320709 @default.
• W4225549801 hasFunder F4320321001 @default.
• W4225549801 hasIssue "2" @default.
• W4225549801 hasLocation W42255498011 @default.
• W4225549801 hasOpenAccess W4225549801 @default.
• W4225549801 hasPrimaryLocation W42255498011 @default.
• W4225549801 hasRelatedWork W1697832939 @default.
• W4225549801 hasRelatedWork W175105024 @default.

• next