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 wireless network, the optimization problems generally have complexconstraints, and are usually solved via utilizing the traditional optimizationmethods that have high computational complexity and need to be executedrepeatedly with the change of network environments. In this paper, to overcomethese shortcomings, an unsupervised deep unrolling framework based onprojection gradient descent, i.e., unrolled PGD network (UPGDNet), is designedto solve a family of constrained optimization problems. The set of constraintsis divided into two categories according to the coupling relations amongoptimization variables and the convexity of constraints. One category ofconstraints includes convex constraints with decoupling among optimizationvariables, and the other category of constraints includes non-convex or convexconstraints with coupling among optimization variables. Then, the firstcategory of constraints is directly projected onto the feasible region, whilethe second category of constraints is projected onto the feasible region usingneural network. Finally, an unrolled sum rate maximization network (USRMNet) isdesigned based on UPGDNet to solve the weighted SR maximization problem for themultiuser ultra-reliable low latency communication system. Numerical resultsshow that USRMNet has a comparable performance with low computationalcomplexity and an acceptable generalization ability in terms of the userdistribution.

An Unsupervised Deep Unrolling Framework for Constrained Optimization Problems in Wireless Networks