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

Recent years have seen a great increase in the capacity and parallelprocessing power of data centers and cloud services. To fully utilize the saiddistributed systems, optimal load balancing for parallel queuing architecturesmust be realized. Existing state-of-the-art solutions fail to consider theeffect of communication delays on the behaviour of very large systems with manyclients. In this work, we consider a multi-agent load balancing system, withdelayed information, consisting of many clients (load balancers) and manyparallel queues. In order to obtain a tractable solution, we model this systemas a mean-field control problem with enlarged state-action space in discretetime through exact discretization. Subsequently, we apply policy gradientreinforcement learning algorithms to find an optimal load balancing solution.Here, the discrete-time system model incorporates a synchronization delay underwhich the queue state information is synchronously broadcasted and updated atall clients. We then provide theoretical performance guarantees for ourmethodology in large systems. Finally, using experiments, we prove that ourapproach is not only scalable but also shows good performance when compared tothe state-of-the-art power-of-d variant of the Join-the-Shortest-Queue (JSQ)and other policies in the presence of synchronization delays.

Learning Mean-Field Control for Delayed Information Load Balancing in Large Queuing Systems