TRAWL – A Traffic Route Adapted Weighted Learning Algorithm

Abstract

Media Independent Handover (MIH) is an emerging standard which supports the communication of network-critical events to upper layer mobility protocols. One of the key features of MIH is the event service, which supports predictive network degradation events that are triggered based on link layer metrics. For set route vehicles, the constrained nature of movement enables a degree of network performance prediction. We propose to capture this performance predictability through a Traffic Route Adapted Weighted Learning (TRAWL) algorithm. TRAWL is a feed forward neural network whose output layer is configurable for both homogeneous and heterogeneous networks. TRAWL uses an unsupervised back propagation learning mechanism, which captures predictable network behavior while also considering dynamic performance characteristics. We evaluate the performance of TRAWL using a commercial metropolitan heterogeneous network. We show that TRAWL has significant performance improvements over existing MIH link triggering mechanisms.

An Analysis of the Effect of Synaptic Weight Configuration for a Neural Network Enabled Handover for Heterogeneous Networks

“…It is important to note that this method does not seek out the best quality connection in range at the time. Similarly in [13], synaptic weights are applied to a neural network that predicts wireless network performance encountered by vehicles that use set routes when travelling. Since it is a predictive method, an unpredictable phenomenon like weather is not considered.…”

Handoff Management Enhancement using Soft Computing Techniques

“…Unsupervised learning has no external training patterns. In this mode the ANN self organizes data presented to the network and detects recurrent properties [8]. Figure3 shows the supervised learning that will be used in this proposed work.…”