Reinforcement Learning-Based Handover Scheme with Neighbor Beacon Frame Transmission

Mobility support to change the connection from one access point (AP) next (i.e., handover) becomes of important issues in IEEE 802.11 wireless local area networks (WLANs). During handover, channel scanning procedure, which aims collect neighbor AP (NAP) information on all available channels, accounts for most delay time. To reduce a beacon frame transmission scheme (N-BTS) was proposed seamless handover. N-BTS can provide handover by removing procedure. However, always requires operating overhead even if there are few mobile stations (MSs) Therefore, this paper proposes reinforcement learning-based with (MAN-BTS) properly consider use N-BTS. The optimization equation is defined maximize expected reward find optimal policy and solved using Q-learning. Simulation results show that outperforms comparison schemes terms reward.