Minority Games With Applications to Distributed Decision Making and Control in Wireless Networks

TL;DR

This paper explores the use of minority games as a distributed decision-making framework for resource allocation in 5G dense small cell networks, aiming to enable autonomous and scalable network management.

Contribution

It provides a theoretical foundation for MGs, reviews their applications in communication networks, and demonstrates their use in offloading decisions in small cell networks.

Findings

MGs can effectively model distributed resource allocation.

Application of MGs improves decision-making in SCNs.

Theoretical analysis supports MG's equilibrium properties.

Abstract

Fifth generation (5G) dense small cell networks (SCNs) are expected to meet the thousand-fold mobile traffic challenge within the next few years. When developing solution schemes for resource allocation problems in such networks, conventional centralized control is no longer viable due to excessive computational complexity and large signaling overhead caused by the large number of users and network nodes in such a network. Instead, distributed resource allocation (or decision making) methods with low complexity would be desirable to make the network self-organizing and autonomous. Minority game (MG) has recently gained attention of the research community as a tool to model and solve distributed resource allocation problems. The main objective of this article is to study the applicability of the MG to solve the distributed decision making problems in future wireless networks. We present the fundamental theoretical aspects of basic MG, some variants of MG, and the notion of equilibrium. We also study the current state-of-the-art on the applications of MGs in communication networks. Furthermore, we describe an example application of MG to SCNs, where the problem of computation offloading by users in an SCN is modeled and analyzed using MG.