Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320067888> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4320067888 abstract "To support different application scenarios, big data frameworks usually provide a large number of performance-related configuration parameters. Online auto-tuning these parameters based on deep reinforcement learning to achieve a better performance has shown their advantages over search-based and machine learning-based approaches. Unfortunately, the time consumption during the online tuning phase of conventional DRL-based methods is still heavy, especially for big data applications. Therefore, in this paper, we propose DeepCAT, a cost-efficient deep reinforcement learning-based approach to achieve online configuration auto-tuning for big data frameworks. To reduce the total online tuning cost: 1) DeepCAT utilizes the TD3 algorithm instead of DDPG to alleviate value overestimation; 2) DeepCAT modifies the conventional experience replay to fully utilize the rare but valuable transitions via a novel reward-driven prioritized experience replay mechanism; 3) DeepCAT designs a Twin-Q Optimizer to estimate the execution time of each action without the costly configuration evaluation and optimize the sub-optimal ones to achieve a low-cost exploration-exploitation trade off. Experimental results based on a local 3-node Spark cluster and HiBench benchmark applications show that DeepCAT is able to speed up the best execution time by a factor of 1.45 × and 1.65 × on average respectively over CDBTune and OtterTune, while consuming up to 50.08% and 53.39% less total tuning time." @default.
- W4320067888 created "2023-02-12" @default.
- W4320067888 creator A5011848072 @default.
- W4320067888 creator A5046247618 @default.
- W4320067888 creator A5070245791 @default.
- W4320067888 creator A5085849698 @default.
- W4320067888 date "2022-08-29" @default.
- W4320067888 modified "2023-10-17" @default.
- W4320067888 title "DeepCAT: A Cost-Efficient Online Configuration Auto-Tuning Approach for Big Data Frameworks" @default.
- W4320067888 cites W2155072926 @default.
- W4320067888 cites W2159434869 @default.
- W4320067888 cites W2613206411 @default.
- W4320067888 cites W2752764103 @default.
- W4320067888 cites W2792529086 @default.
- W4320067888 cites W2888705583 @default.
- W4320067888 cites W2948513753 @default.
- W4320067888 cites W2964298054 @default.
- W4320067888 cites W2970851599 @default.
- W4320067888 cites W2991377414 @default.
- W4320067888 cites W2999922247 @default.
- W4320067888 cites W3021864215 @default.
- W4320067888 cites W3044147426 @default.
- W4320067888 cites W3097528317 @default.
- W4320067888 cites W3098844916 @default.
- W4320067888 cites W3131827005 @default.
- W4320067888 cites W3163768429 @default.
- W4320067888 cites W3174969457 @default.
- W4320067888 cites W3189646782 @default.
- W4320067888 cites W4284689548 @default.
- W4320067888 cites W4289533904 @default.
- W4320067888 doi "https://doi.org/10.1145/3545008.3545018" @default.
- W4320067888 hasPublicationYear "2022" @default.
- W4320067888 type Work @default.
- W4320067888 citedByCount "0" @default.
- W4320067888 crossrefType "proceedings-article" @default.
- W4320067888 hasAuthorship W4320067888A5011848072 @default.
- W4320067888 hasAuthorship W4320067888A5046247618 @default.
- W4320067888 hasAuthorship W4320067888A5070245791 @default.
- W4320067888 hasAuthorship W4320067888A5085849698 @default.
- W4320067888 hasConcept C124101348 @default.
- W4320067888 hasConcept C13280743 @default.
- W4320067888 hasConcept C154945302 @default.
- W4320067888 hasConcept C185798385 @default.
- W4320067888 hasConcept C199360897 @default.
- W4320067888 hasConcept C205649164 @default.
- W4320067888 hasConcept C2781215313 @default.
- W4320067888 hasConcept C41008148 @default.
- W4320067888 hasConcept C75684735 @default.
- W4320067888 hasConcept C97541855 @default.
- W4320067888 hasConceptScore W4320067888C124101348 @default.
- W4320067888 hasConceptScore W4320067888C13280743 @default.
- W4320067888 hasConceptScore W4320067888C154945302 @default.
- W4320067888 hasConceptScore W4320067888C185798385 @default.
- W4320067888 hasConceptScore W4320067888C199360897 @default.
- W4320067888 hasConceptScore W4320067888C205649164 @default.
- W4320067888 hasConceptScore W4320067888C2781215313 @default.
- W4320067888 hasConceptScore W4320067888C41008148 @default.
- W4320067888 hasConceptScore W4320067888C75684735 @default.
- W4320067888 hasConceptScore W4320067888C97541855 @default.
- W4320067888 hasFunder F4320321001 @default.
- W4320067888 hasLocation W43200678881 @default.
- W4320067888 hasOpenAccess W4320067888 @default.
- W4320067888 hasPrimaryLocation W43200678881 @default.
- W4320067888 hasRelatedWork W2586475558 @default.
- W4320067888 hasRelatedWork W2766461310 @default.
- W4320067888 hasRelatedWork W2980795771 @default.
- W4320067888 hasRelatedWork W3006311829 @default.
- W4320067888 hasRelatedWork W3012903882 @default.
- W4320067888 hasRelatedWork W3017846737 @default.
- W4320067888 hasRelatedWork W3154228395 @default.
- W4320067888 hasRelatedWork W3202731209 @default.
- W4320067888 hasRelatedWork W4247566972 @default.
- W4320067888 hasRelatedWork W4296474751 @default.
- W4320067888 isParatext "false" @default.
- W4320067888 isRetracted "false" @default.
- W4320067888 workType "article" @default.