Capacity offloading in two-tier small cell networks over unlicensed band: A hierarchical learning framework
Authors:
- 1 October 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
In this paper, we investigate the capacity offloading over unlicensed band for two-tier dual-mode small cell networks. We formulate this problem as a Stackelberg game. Specifically, the macro base station (MBS) is modeled as leader and small base stations (SBSs) are followers. MBS adopts a traffic flow pricing mechanism and broadcasts the price information to all SBSs firstly, then each SBS allocates the traffic load in licensed and unlicensed band via appropriate power allocation in the sequel, considering the traffic flow payment charged by MBS in licensed band. Then, we propose two hierarchical learning schemes based on Q-learning algorithm. Simulation results show the effectiveness of the proposed schemes.Keywords
This publication has 12 references indexed in Scilit:
- A game-theoretic perspective on self-organizing optimization for cognitive small cellsIEEE Communications Magazine, 2015
- Small-Cell Traffic Balancing Over Licensed and Unlicensed BandsIEEE Transactions on Vehicular Technology, 2015
- Cellular architecture enhancement for supporting the european licensed shared access conceptIEEE Wireless Communications, 2014
- What Will 5G Be?IEEE Journal on Selected Areas in Communications, 2014
- When cellular meets WiFi in wireless small cell networksIEEE Communications Magazine, 2013
- Improving energy efficiency in Green femtocell networks: A hierarchical reinforcement learning framework2013
- Dynamics of Boltzmannlearning in two-player two-action gamesPhysical Review E, 2012
- Non-Cooperative Game for Capacity OffloadIEEE Transactions on Wireless Communications, 2012
- Decentralized learning of Nash equilibria in multi-person stochastic games with incomplete informationIEEE Transactions on Systems, Man, and Cybernetics, 1994
- Q-learningMachine Learning, 1992