dc.contributor.author | Wang, J | |
dc.contributor.author | Hu, J | |
dc.contributor.author | Min, G | |
dc.contributor.author | Zomaya, AY | |
dc.contributor.author | Georgalas, N | |
dc.date.accessioned | 2020-08-05T15:10:50Z | |
dc.date.issued | 2020-08-06 | |
dc.description.abstract | Multi-access edge computing (MEC) aims to extend cloud service to the network edge to reduce network traffic and service
latency. A fundamental problem in MEC is how to efficiently offload heterogeneous tasks of mobile applications from user equipment
(UE) to MEC hosts. Recently, many deep reinforcement learning (DRL) based methods have been proposed to learn offloading policies
through interacting with the MEC environment that consists of UE, wireless channels, and MEC hosts. However, these methods have
weak adaptability to new environments because they have low sample efficiency and need full retraining to learn updated policies for
new environments. To overcome this weakness, we propose a task offloading method based on meta reinforcement learning, which
can adapt fast to new environments with a small number of gradient updates and samples. We model mobile applications as Directed
Acyclic Graphs (DAGs) and the offloading policy by a custom sequence-to-sequence (seq2seq) neural network. To efficiently train the
seq2seq network, we propose a method that synergizes the first order approximation and clipped surrogate objective. The experimental
results demonstrate that this new offloading method can reduce the latency by up to 25% compared to three baselines while being able
to adapt fast to new environments. | en_GB |
dc.identifier.citation | Vol. 32 (1), pp. 242 - 253 | en_GB |
dc.identifier.doi | 10.1109/TPDS.2020.3014896 | |
dc.identifier.uri | http://hdl.handle.net/10871/122338 | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_GB |
dc.rights | © 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. | |
dc.subject | Multi-access edge computing | en_GB |
dc.subject | task offloading | en_GB |
dc.subject | meta reinforcement learning | en_GB |
dc.subject | deep learning | en_GB |
dc.title | Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2020-08-05T15:10:50Z | |
dc.identifier.issn | 1045-9219 | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record | en_GB |
dc.identifier.journal | IEEE Transactions on Parallel and Distributed Systems | en_GB |
dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | en_GB |
dcterms.dateAccepted | 2020-07-30 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2020-07-30 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2020-08-05T12:54:23Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2020-08-27T15:43:29Z | |
refterms.panel | B | en_GB |