A near optimal call admission control with genetic algorithm for multimedia services in wireless/mobile networks

In this paper, we treat a cell as a M/M/C/C queuing system with nt class users. Semi-Markov Decision Process (SMDP) can be used to provide an optimal Call Admission Control (CAC). The optimization is in thesense of optimizing the channel utilization for service providers and satisfying the Quality of Sen ice (QoS) requirements for sen ice users, which are the upper bounds of handoff blocking probabilities. However, such method fails when the state space and the action space are too large. We apply genetic algorithm approach to address such problems where the SMDP approach fails. We code the call admission control decisions as binary strings, where the value of "1" in the position i of the string stands for the decision of accepting a call ia class-i; whereas, the value of "0" in the position i of the string stands for the decision of rejecting a call in class-i. The resulting binary strings from the genetic algorithm are the near optimal CAC decisions. Simulation results from the genetic algorithm are compared with the optimal solution obtained from linear programming for SMDP. The results reveal that the genetic algorithm approximates the optimal solution very well.