Matches in SemOpenAlex for { <https://semopenalex.org/work/W2134568800> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2134568800 abstract "System level power management must consider the uncertainty and variability that comes from the environment, the application and the hardware. A robust power management technique must be able to learn the optimal decision from past history and improve itself as the environment changes. This paper presents a novel online power management technique based on model-free constrained reinforcement learning (RL). It learns the best power management policy that gives the minimum power consumption for a given performance constraint without any prior information of workload. Compared with existing machine learning based power management techniques, the RL based learning is capable of exploring the trade-off in the power-performance design space and converging to a better power management policy. Experimental results show that the proposed RL based power management achieves 24% and 3% reduction in power and latency respectively comparing to the existing expert based power management." @default.
- W2134568800 created "2016-06-24" @default.
- W2134568800 creator A5018468480 @default.
- W2134568800 creator A5035829494 @default.
- W2134568800 creator A5071037763 @default.
- W2134568800 date "2009-11-02" @default.
- W2134568800 modified "2023-10-18" @default.
- W2134568800 title "Adaptive power management using reinforcement learning" @default.
- W2134568800 cites W2002219388 @default.
- W2134568800 cites W2020142038 @default.
- W2134568800 cites W2024590918 @default.
- W2134568800 cites W2109095340 @default.
- W2134568800 cites W2111616126 @default.
- W2134568800 cites W2126940339 @default.
- W2134568800 cites W2136244995 @default.
- W2134568800 cites W2146510091 @default.
- W2134568800 cites W2170311029 @default.
- W2134568800 doi "https://doi.org/10.1145/1687399.1687486" @default.
- W2134568800 hasPublicationYear "2009" @default.
- W2134568800 type Work @default.
- W2134568800 sameAs 2134568800 @default.
- W2134568800 citedByCount "112" @default.
- W2134568800 countsByYear W21345688002012 @default.
- W2134568800 countsByYear W21345688002013 @default.
- W2134568800 countsByYear W21345688002014 @default.
- W2134568800 countsByYear W21345688002015 @default.
- W2134568800 countsByYear W21345688002016 @default.
- W2134568800 countsByYear W21345688002017 @default.
- W2134568800 countsByYear W21345688002018 @default.
- W2134568800 countsByYear W21345688002019 @default.
- W2134568800 countsByYear W21345688002020 @default.
- W2134568800 countsByYear W21345688002021 @default.
- W2134568800 countsByYear W21345688002022 @default.
- W2134568800 countsByYear W21345688002023 @default.
- W2134568800 crossrefType "proceedings-article" @default.
- W2134568800 hasAuthorship W2134568800A5018468480 @default.
- W2134568800 hasAuthorship W2134568800A5035829494 @default.
- W2134568800 hasAuthorship W2134568800A5071037763 @default.
- W2134568800 hasConcept C111919701 @default.
- W2134568800 hasConcept C121332964 @default.
- W2134568800 hasConcept C127413603 @default.
- W2134568800 hasConcept C154945302 @default.
- W2134568800 hasConcept C163258240 @default.
- W2134568800 hasConcept C200601418 @default.
- W2134568800 hasConcept C2778476105 @default.
- W2134568800 hasConcept C2778774385 @default.
- W2134568800 hasConcept C2984118289 @default.
- W2134568800 hasConcept C41008148 @default.
- W2134568800 hasConcept C62520636 @default.
- W2134568800 hasConcept C97541855 @default.
- W2134568800 hasConceptScore W2134568800C111919701 @default.
- W2134568800 hasConceptScore W2134568800C121332964 @default.
- W2134568800 hasConceptScore W2134568800C127413603 @default.
- W2134568800 hasConceptScore W2134568800C154945302 @default.
- W2134568800 hasConceptScore W2134568800C163258240 @default.
- W2134568800 hasConceptScore W2134568800C200601418 @default.
- W2134568800 hasConceptScore W2134568800C2778476105 @default.
- W2134568800 hasConceptScore W2134568800C2778774385 @default.
- W2134568800 hasConceptScore W2134568800C2984118289 @default.
- W2134568800 hasConceptScore W2134568800C41008148 @default.
- W2134568800 hasConceptScore W2134568800C62520636 @default.
- W2134568800 hasConceptScore W2134568800C97541855 @default.
- W2134568800 hasLocation W21345688001 @default.
- W2134568800 hasOpenAccess W2134568800 @default.
- W2134568800 hasPrimaryLocation W21345688001 @default.
- W2134568800 hasRelatedWork W2033105901 @default.
- W2134568800 hasRelatedWork W2086926890 @default.
- W2134568800 hasRelatedWork W2329086085 @default.
- W2134568800 hasRelatedWork W2360026318 @default.
- W2134568800 hasRelatedWork W2378563863 @default.
- W2134568800 hasRelatedWork W2566975275 @default.
- W2134568800 hasRelatedWork W2959276766 @default.
- W2134568800 hasRelatedWork W4206669594 @default.
- W2134568800 hasRelatedWork W4256725780 @default.
- W2134568800 hasRelatedWork W4295941380 @default.
- W2134568800 isParatext "false" @default.
- W2134568800 isRetracted "false" @default.
- W2134568800 magId "2134568800" @default.
- W2134568800 workType "article" @default.