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 distributed software-defined networks (SDN), multiple physical SDNcontrollers, each managing a network domain, are implemented to balancecentralized control, scalability and reliability requirements. In suchnetworking paradigm, controllers synchronize with each other to maintain alogically centralized network view. Despite various proposals of distributedSDN controller architectures, most existing works only assume that suchlogically centralized network view can be achieved with some synchronizationdesigns, but the question of how exactly controllers should synchronize witheach other to maximize the benefits of synchronization under the eventualconsistency assumptions is largely overlooked. To this end, we formulate thecontroller synchronization problem as a Markov Decision Process (MDP) and applyreinforcement learning techniques combined with deep neural network to train asmart controller synchronization policy, which we call the Deep-Q (DQ)Scheduler. Evaluation results show that DQ Scheduler outperforms theantientropy algorithm implemented in the ONOS controller by up to 95.2% forinter-domain routing tasks.

DQ Scheduler: Deep Reinforcement Learning Based Controller Synchronization in Distributed SDN