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

Efficient network slicing is vital to deal with the highly variable anddynamic characteristics of network traffic generated by a varied range ofapplications. The problem is made more challenging with the advent of newtechnologies such as 5G and new architectures such as SDN and NFV. Networkslicing addresses a challenging dynamic network resource allocation problemwhere a single network infrastructure is divided into (virtual) multiple slicesto meet the demands of different users with varying requirements, the mainchallenges being --- the traffic arrival characteristics and the job resourcerequirements (e.g., compute, memory and bandwidth resources) for each slice canbe highly dynamic. Traditional model-based optimization or queueing theoreticmodeling becomes intractable with the high reliability, and stringent bandwidthand latency requirements imposed by 5G technologies. In addition theseapproaches lack adaptivity in dynamic environments. We propose a deepreinforcement learning approach to address this dynamic coupled resourceallocation problem. Model evaluation using both synthetic simulation data andreal workload driven traces demonstrates that our deep reinforcement learningsolution improves overall resource utilization, latency performance, anddemands satisfied as compared to a baseline equal-slicing strategy.

Deep Reinforcement Learning for Network Slicing with Heterogeneous Resource Requirements and Time Varying Traffic Dynamics