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

The evaluation of the impact of using Machine Learning in the management ofsoftwarized networks is considered in multiple research works. Beyond that, wepropose to evaluate the robustness of online learning for optimal network sliceplacement. A major assumption to this study is to consider that slice requestarrivals are non-stationary. In this context, we simulate unpredictable networkload variations and compare two Deep Reinforcement Learning (DRL) algorithms: apure DRL-based algorithm and a heuristically controlled DRL as a hybridDRL-heuristic algorithm, to assess the impact of these unpredictable changes oftraffic load on the algorithms performance. We conduct extensive simulations ofa large-scale operator infrastructure. The evaluation results show that theproposed hybrid DRL-heuristic approach is more robust and reliable in case ofunpredictable network load changes than pure DRL as it reduces the performancedegradation. These results are follow-ups for a series of recent research wehave performed showing that the proposed hybrid DRL-heuristic approach isefficient and more adapted to real network scenarios than pure DRL.

On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement