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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Advances in network programmability enable operators to 'slice' the physicalinfrastructure into independent logical networks. By this approach, eachnetwork slice aims to accommodate the demands of increasingly diverse services.However, precise allocation of resources to slices across future 5Gmillimetre-wave backhaul networks, to optimise the total network utility, ischallenging. This is because the performance of different services oftendepends on conflicting requirements, including bandwidth, sensitivity to delay,or the monetary value of the traffic incurred. In this paper, we put forward ageneral rate utility framework for slicing mm-wave backhaul links, encompassingall known types of service utilities, i.e. logarithmic, sigmoid, polynomial,and linear. We then introduce DELMU, a deep learning solution that tackles thecomplexity of optimising non-convex objective functions built upon arbitrarycombinations of such utilities. Specifically, by employing a stack ofconvolutional blocks, DELMU can learn correlations between traffic demands andachievable optimal rate assignments. We further regulate the inferences made bythe neural network through a simple 'sanity check' routine, which guaranteesboth flow rate admissibility within the network's capacity region and minimumservice levels. The proposed method can be trained within minutes, followingwhich it computes rate allocations that match those obtained withstate-of-the-art global optimisation algorithms, yet orders of magnitudefaster. This confirms the applicability of DELMU to highly dynamic trafficregimes and we demonstrate up to 62% network utility gains over a baselinegreedy approach.

DELMU: A Deep Learning Approach to Maximising the Utility of Virtualised Millimetre-Wave Backhauls