Reinforcement Learning With Network-Assisted Feedback for Heterogeneous RAT Selection
- 27 June 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 16 (9) , 6062-6076
Abstract
Future wireless networks (e.g., 5G) will consist of multiple radio access technologies (RATs). In these networks, deciding which RAT users should connect to is not a trivial problem. Current fully distributed algorithms although guaranteeing convergence to equilibrium states, are often slow, require high exploration times and may converge to undesirable equilibria. To overcome these limitations, this paper develops a network feedback framework that uses limited network-assisted information to improve efficiency of distributed algorithms for RAT selection problem. We prove theoretically that a fully distributed algorithm developed within this framework is guaranteed to converge to a set of correlated equilibria. Our framework guarantees convergence in self-play even when only a single user applies the algorithm. Simulation results demonstrate that our solution: 1) is highly efficient with fast convergence time and low signaling overheads while achieving competitive, if not better, performance both in fairness and utility, as well as achieving lower per-user switchings than state-of-the-art algorithms; and 2) can flexibly support a wide range of network-assisted feedback. The simulations demonstrate the effectiveness of our solution in a heterogeneous environment, where users may potentially apply a number of different RAT selection procedures.Keywords
Funding Information
- Australian Research Council Linkage (LP140100489)
This publication has 28 references indexed in Scilit:
- Performance of adaptive RAT selection algorithms in 5G heterogeneous wireless networks2016
- HetNets Selection by Clients: Convergence, Efficiency, and PracticalityIEEE/ACM Transactions on Networking, 2016
- A Network-Assisted Approach for RAT Selection in Heterogeneous Cellular NetworksIEEE Journal on Selected Areas in Communications, 2015
- Exploiting User Demand Diversity in Heterogeneous Wireless NetworksIEEE Transactions on Wireless Communications, 2015
- Intelligent access network selection in converged multi-radio heterogeneous networksIEEE Wireless Communications, 2014
- Learning efficient correlated equilibria2014
- Fully Distributed Learning for Global Optima2012
- A Distributed Access Point Selection Algorithm Based on No-Regret Learning for Wireless Access Networks2010
- Dynamics of Network Selection in Heterogeneous Wireless Networks: An Evolutionary Game ApproachIEEE Transactions on Vehicular Technology, 2008
- A Reinforcement Procedure Leading to Correlated Equilibrium2001