3rd International ICST Conference on Quality of Service in Heterogeneous Wired/Wireless Networks

Research Article

An optimal bandwidth adaptation algorithm for multi-class traffic in wireless networks

  • @INPROCEEDINGS{10.1145/1185373.1185445,
        author={Ning  Lu and John  Bigham},
        title={An optimal bandwidth adaptation algorithm for multi-class traffic in wireless networks},
        proceedings={3rd International ICST Conference on Quality of Service in Heterogeneous Wired/Wireless Networks},
        publisher={ACM},
        proceedings_a={QSHINE},
        year={2006},
        month={8},
        keywords={},
        doi={10.1145/1185373.1185445}
    }
    
  • Ning Lu
    John Bigham
    Year: 2006
    An optimal bandwidth adaptation algorithm for multi-class traffic in wireless networks
    QSHINE
    ACM
    DOI: 10.1145/1185373.1185445
Ning Lu1,2,*, John Bigham2,*
  • 1: MPI-QMUL Information Systems Research Center, Macao Polytechnic Institute, Macao, China.
  • 2: Electronic Engineering Department, Queen Mary, University of London, UK
*Contact email: [email protected], [email protected]

Abstract

Bandwidth adaptation is becoming very attractive in wireless communications since it can dynamically adjust the allocated bandwidth of ongoing calls to cope with the network resource fluctuations. In this paper, we propose an optimal bandwidth adaptation algorithm for multi-class traffic QoS provisioning in wireless networks. With the proposed algorithm, each call is assigned a utility function that maps its bandwidth allocation to the user satisfaction. When the network is overloaded the allocated bandwidth of ongoing calls can be degraded to free bandwidth to accept the new and handoff calls. The bandwidth adaptation algorithm is performed to meet two objectives in the preference order: (i) all calls belonging to the same class receive fair utility (ii) the utility sum of all different classes of calls in each individual cell is maximized. Simulation results show that our proposed algorithm is effective in both attaining intra-class utility fairness and maximizing the total utility of the network while keeping the call blocking and handoff dropping probabilities low.