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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we examine cloud-edge-terminal IoT networks, where edgesundertake a range of typical dynamic scheduling tasks. In these IoT networks, acentral policy for each task can be constructed at a cloud server. The centralpolicy can be then used by the edges conducting the task, thereby mitigatingthe need for them to learn their own policy from scratch. Furthermore, thiscentral policy can be collaboratively learned at the cloud server byaggregating local experiences from the edges, thanks to the hierarchicalarchitecture of the IoT networks. To this end, we propose a novel collaborativepolicy learning framework for dynamic scheduling tasks using federatedreinforcement learning. For effective learning, our framework adaptivelyselects the tasks for collaborative learning in each round, taking into accountthe need for fairness among tasks. In addition, as a key enabler of theframework, we propose an edge-agnostic policy structure that enables theaggregation of local policies from different edges. We then provide theconvergence analysis of the framework. Through simulations, we demonstrate thatour proposed framework significantly outperforms the approaches withoutcollaborative policy learning. Notably, it accelerates the learning speed ofthe policies and allows newly arrived edges to adapt to their tasks moreeasily.

Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learning