Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920933065> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2920933065 endingPage "1336" @default.
- W2920933065 startingPage "1325" @default.
- W2920933065 abstract "In this paper, we aim to study networking problems from a whole new perspective by leveraging emerging deep learning, to develop an experience-driven approach, which enables a network or a protocol to learn the best way to control itself from its own experience (e.g., runtime statistics data), just as a human learns a skill. We present design, implementation and evaluation of a deep reinforcement learning (DRL)-based control framework, DRL-CC (DRL for Congestion Control), which realizes our experience-driven design philosophy on multi-path TCP (MPTCP) congestion control. DRL-CC utilizes a single (instead of multiple independent) agent to dynamically and jointly perform congestion control for all active MPTCP flows on an end host with the objective of maximizing the overall utility. The novelty of our design is to utilize a flexible recurrent neural network, LSTM, under a DRL framework for learning a representation for all active flows and dealing with their dynamics. Moreover, we, for the first time, integrate the above LSTM-based representation network into an actor-critic framework for continuous (congestion) control, which leverages the emerging deterministic policy gradient to train critic, actor, and LSTM networks in an end-to-end manner. We implemented DRL-CC based on the MPTCP implementation in the Linux kernel. The experimental results show that 1) DRL-CC consistently and significantly outperforms a few well-known MPTCP congestion control algorithms in terms of goodput without sacrificing fairness, 2) it is flexible and robust to highly-dynamic network environments with time-varying flows, and 3) it is friendly to regular TCP." @default.
- W2920933065 created "2019-03-22" @default.
- W2920933065 creator A5025596795 @default.
- W2920933065 creator A5026230689 @default.
- W2920933065 creator A5031741238 @default.
- W2920933065 creator A5039176528 @default.
- W2920933065 creator A5047324704 @default.
- W2920933065 date "2019-06-01" @default.
- W2920933065 modified "2023-10-10" @default.
- W2920933065 title "Experience-Driven Congestion Control: When Multi-Path TCP Meets Deep Reinforcement Learning" @default.
- W2920933065 cites W1576831194 @default.
- W2920933065 cites W1988975763 @default.
- W2920933065 cites W2007309295 @default.
- W2920933065 cites W2037710455 @default.
- W2920933065 cites W2050600889 @default.
- W2920933065 cites W2064675550 @default.
- W2920933065 cites W2080835330 @default.
- W2920933065 cites W2101182788 @default.
- W2920933065 cites W2132404093 @default.
- W2920933065 cites W2137775453 @default.
- W2920933065 cites W2145339207 @default.
- W2920933065 cites W2151469723 @default.
- W2920933065 cites W2162986857 @default.
- W2920933065 cites W2283584307 @default.
- W2920933065 cites W2461171666 @default.
- W2920933065 cites W2480649850 @default.
- W2920933065 cites W2763218808 @default.
- W2920933065 cites W2963549123 @default.
- W2920933065 cites W3161213569 @default.
- W2920933065 cites W4233762780 @default.
- W2920933065 cites W4292544546 @default.
- W2920933065 doi "https://doi.org/10.1109/jsac.2019.2904358" @default.
- W2920933065 hasPublicationYear "2019" @default.
- W2920933065 type Work @default.
- W2920933065 sameAs 2920933065 @default.
- W2920933065 citedByCount "115" @default.
- W2920933065 countsByYear W29209330652019 @default.
- W2920933065 countsByYear W29209330652020 @default.
- W2920933065 countsByYear W29209330652021 @default.
- W2920933065 countsByYear W29209330652022 @default.
- W2920933065 countsByYear W29209330652023 @default.
- W2920933065 crossrefType "journal-article" @default.
- W2920933065 hasAuthorship W2920933065A5025596795 @default.
- W2920933065 hasAuthorship W2920933065A5026230689 @default.
- W2920933065 hasAuthorship W2920933065A5031741238 @default.
- W2920933065 hasAuthorship W2920933065A5039176528 @default.
- W2920933065 hasAuthorship W2920933065A5047324704 @default.
- W2920933065 hasBestOaLocation W29209330651 @default.
- W2920933065 hasConcept C111919701 @default.
- W2920933065 hasConcept C120314980 @default.
- W2920933065 hasConcept C154945302 @default.
- W2920933065 hasConcept C157764524 @default.
- W2920933065 hasConcept C158379750 @default.
- W2920933065 hasConcept C195563490 @default.
- W2920933065 hasConcept C31258907 @default.
- W2920933065 hasConcept C41008148 @default.
- W2920933065 hasConcept C555944384 @default.
- W2920933065 hasConcept C94022561 @default.
- W2920933065 hasConcept C97541855 @default.
- W2920933065 hasConceptScore W2920933065C111919701 @default.
- W2920933065 hasConceptScore W2920933065C120314980 @default.
- W2920933065 hasConceptScore W2920933065C154945302 @default.
- W2920933065 hasConceptScore W2920933065C157764524 @default.
- W2920933065 hasConceptScore W2920933065C158379750 @default.
- W2920933065 hasConceptScore W2920933065C195563490 @default.
- W2920933065 hasConceptScore W2920933065C31258907 @default.
- W2920933065 hasConceptScore W2920933065C41008148 @default.
- W2920933065 hasConceptScore W2920933065C555944384 @default.
- W2920933065 hasConceptScore W2920933065C94022561 @default.
- W2920933065 hasConceptScore W2920933065C97541855 @default.
- W2920933065 hasFunder F4320306076 @default.
- W2920933065 hasIssue "6" @default.
- W2920933065 hasLocation W29209330651 @default.
- W2920933065 hasOpenAccess W2920933065 @default.
- W2920933065 hasPrimaryLocation W29209330651 @default.
- W2920933065 hasRelatedWork W1481339676 @default.
- W2920933065 hasRelatedWork W1499416298 @default.
- W2920933065 hasRelatedWork W1594135139 @default.
- W2920933065 hasRelatedWork W2022936788 @default.
- W2920933065 hasRelatedWork W2058869056 @default.
- W2920933065 hasRelatedWork W2065144932 @default.
- W2920933065 hasRelatedWork W2068902604 @default.
- W2920933065 hasRelatedWork W2125636680 @default.
- W2920933065 hasRelatedWork W2139105472 @default.
- W2920933065 hasRelatedWork W2787285875 @default.
- W2920933065 hasVolume "37" @default.
- W2920933065 isParatext "false" @default.
- W2920933065 isRetracted "false" @default.
- W2920933065 magId "2920933065" @default.
- W2920933065 workType "article" @default.