3d International ICST Conference on Bio-Inspired Models of Network, Information, and Computing Systems

Research Article

Constraint Optimization in Call Admission Control Domain with a NeuroEvolution Algorithm

Download531 downloads
  • @INPROCEEDINGS{10.4108/ICST.BIONETICS2008.4675,
        author={Xu Yang and John Bigham},
        title={Constraint Optimization in Call Admission Control Domain with a NeuroEvolution Algorithm},
        proceedings={3d International ICST Conference on Bio-Inspired Models of Network, Information, and Computing Systems},
        publisher={ICST},
        proceedings_a={BIONETICS},
        year={2010},
        month={5},
        keywords={Constraint Optimization Call Admission Control NeuroEvolution of Augmenting Topologies (NEAT)},
        doi={10.4108/ICST.BIONETICS2008.4675}
    }
    
  • Xu Yang
    John Bigham
    Year: 2010
    Constraint Optimization in Call Admission Control Domain with a NeuroEvolution Algorithm
    BIONETICS
    ICST
    DOI: 10.4108/ICST.BIONETICS2008.4675
Xu Yang1,*, John Bigham2,*
  • 1: MPI-QMUL Information Systems Research Centre, Macao Polytechnic Institute, Macao SAR, China.
  • 2: School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom.
*Contact email: xuy@mpi-qmul.org, john.bigham@elec.qmul.ac.uk

Abstract

The objective for Call admission control (CAC) is to accept or reject request calls so as to maximize the expected revenue over an infinite time period and maintain the predefined QoS constraints. This is a non-linear constraint optimization problem. This paper analyses the difficulties when handling QoS constraints in the CAC domain, and implements two constraint handling methods that cooperate with a NeuroEvolution algorithm called NEAT to learn CAC policies. The two methods are superiority of feasible points and static penalty functions. The simulation results are compared based on two evolution parameters: the ratio of feasible policies, and the ratio of ‘all accept’ policies. Some researchers argue that superiority of feasible points may fail when the feasible region is quite small compared with the whole search space, however the speciation and complexification features of NEAT makes it a very competitive method even in such cases.