A new clustered load balancing approach for distributed systems

Chatterjee, Moumita; Setua, S. K.

doi:10.1109/c3it.2015.7060188

Cited by 6 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particularly, Hong et al [10] highlighted some problems regarding the use of non-cooperative game theoretical approaches to solve resource allocation problems in wireless networks. Moreover, cluster based load balancing approach for a computer network was proposed in [11], since fully centralized (or fully decentralized) networks may not perform well in terms of scalability (or with lack of information in each server).…”

Section: Introductionmentioning

confidence: 99%

Joint optimization of power consumption and load balancing in wireless dynamic network architecture

Sugathapala

Glisic

Juntti

et al. 2017

2017 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

The concept of the wireless dynamic network architecture (DNA) stands for a system design, which allows terminals to convert into temporary access points (APs) when necessary. In this paper, we propose a framework to solve the problem of load balancing in DNA. Particularly, the user association in DNAs is optimized to minimize the number of active APs and the network cost in terms of tradeoff between power and load, while ensuring users' quality of service (QoS). In general, such a problem is a non-convex mixed integer nonlinear program in the sense that its continuous relaxation is a non-convex problem. To solve this optimization, we use the standard continuous relaxation method and approximate the relaxed problem by a series of second order cone programs with the aid of successive convex approximation (SCA) framework. Numerical results show that the proposed algorithm converges within a few iterations and jointly minimizes the network cost and the number of APs in the network.

show abstract

Section: Introductionmentioning

confidence: 99%