A Genetic Algorithm-based Framework for Soft Handoff Optimization in Wireless Networks

Abstract

In this paper, a genetic algorithm (GA)-based approach is used to evaluate the probability of successful handoff in heterogeneous wireless networks (HWNs) so as to increase capacity and network performance. The traditional handoff schemes are prone to ping pong and corner effects and developing an optimized handoff scheme for seamless, faster, and less power consuming handoff decision is challenging. The GA scheme can effectively optimize soft handoff decision by selecting the best fit network for the mobile terminal (MT) considering quality of service (QoS) requirements, network parameters and user’s preference in terms of cost of different attachment points for the MT. The robustness and ability to determine global optima for any function using crossover and mutation operations makes GA a promising solution. The developed optimization framework was simulated in Matrix Laboratory (MATLAB) software using MATLAB’s optima tool and results show that an optimal MT attachment point is the one with the highest handoff success probability value which determines direction for successful handoff in HWN environment. The system maintained a 90%  with 4 channels and more while a 75% was obtained even at high traffic intensity.