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

We present an overview of scalable load balancing algorithms which providefavorable delay performance in large-scale systems, and yet only requireminimal implementation overhead. Aimed at a broad audience, the paper startswith an introduction to the basic load balancing scenario, consisting of asingle dispatcher where tasks arrive that must immediately be forwarded to oneof $N$ single-server queues.  A popular class of load balancing algorithms are so-called power-of-$d$ orJSQ($d$) policies, where an incoming task is assigned to a server with theshortest queue among $d$ servers selected uniformly at random. This classincludes the Join-the-Shortest-Queue (JSQ) policy as a special case ($d = N$),which has strong stochastic optimality properties and yields a mean waitingtime that vanishes as $N$ grows large for any fixed subcritical load. However,a nominal implementation of the JSQ policy involves a prohibitive communicationburden in large-scale deployments. In contrast, a random assignment policy ($d= 1$) does not entail any communication overhead, but the mean waiting timeremains constant as $N$ grows large for any fixed positive load.  In order to examine the fundamental trade-off between performance andimplementation overhead, we consider an asymptotic regime where $d(N)$ dependson $N$. We investigate what growth rate of $d(N)$ is required to match theperformance of the JSQ policy on fluid and diffusion scale. The resultsdemonstrate that the asymptotics for the JSQ($d(N)$) policy are insensitive tothe exact growth rate of $d(N)$, as long as the latter is sufficiently fast,implying that the optimality of the JSQ policy can asymptotically be preservedwhile dramatically reducing the communication overhead. We additionally showhow the communication overhead can be reduced yet further by the so-calledJoin-the-Idle-Queue scheme, leveraging memory at the dispatcher.

Scalable Load Balancing in Networked Systems: Universality Properties and Stochastic Coupling Methods