English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With the continuous growth of mobile data and the unprecedented demand forcomputing power, resource-constrained edge devices cannot effectively meet therequirements of Internet of Things (IoT) applications and Deep Neural Network(DNN) computing. As a distributed computing paradigm, edge offloading thatmigrates complex tasks from IoT devices to edge-cloud servers can break throughthe resource limitation of IoT devices, reduce the computing burden and improvethe efficiency of task processing. However, the problem of optimal offloadingdecision-making is NP-hard, traditional optimization methods are difficult toachieve results efficiently. Besides, there are still some shortcomings inexisting deep learning methods, e.g., the slow learning speed and the failureof the original network parameters when the environment changes. To tacklethese challenges, we propose a Deep Meta Reinforcement Learning-basedoffloading (DMRO) algorithm, which combines multiple parallel DNNs withQ-learning to make fine-grained offloading decisions. By aggregating theperceptive ability of deep learning, the decision-making ability ofreinforcement learning, and the rapid environment learning ability ofmeta-learning, it is possible to quickly and flexibly obtain the optimaloffloading strategy from the IoT environment. Simulation results demonstratethat the proposed algorithm achieves obvious improvement over the DeepQ-Learning algorithm and has strong portability in making real-time offloadingdecisions even in time-varying IoT environments.

DMRO:A Deep Meta Reinforcement Learning-based Task Offloading Framework for Edge-Cloud Computing