IEEETOB

Enda Fallon, Liam Murphy, Member, IEEE, John Murphy, Senior Member, IEEE, Gabriel Miro-Muntean Member, IEEE

Media Independent Handover (MIH) is a recent standard which supports the communication of network critical events to upper layer mobility protocols. One of the key features of MIH is an event service, which supports predictive network degradation events that are triggered based on link layer metrics. As a framework, MIH does not provide specifics on how events should be triggered. Typically events are triggered when performance characteristics such as RSS and link loss rate exceed a predefined threshold. In this paper we suggest that for public service vehicles such as busses, the constrained nature of movement enables network performance prediction. We propose to capture this performance predictability through a Fixed Route Adapted, Media-streaming Enhanced (FRAME) handover algorithm. FRAME uses a directed feed forward neural network to trigger MIH link events. FRAME provides a pluggable learning mechanism which allows for the extensible definition of alternative learning metrics. FRAME is evaluated using a commercial metropolitan heterogeneous network. Results show that FRAME has significant performance improvements over existing MIH link triggering mechanisms.