Average-Bandwidth Delay Q-Routing Adaptive Algorithm

In the last decade, due to emerging real-time and multimedia applications, there has been much interest for developing mechanisms to take into account the quality of service required by these applications. One of these mechanisms consists to integrate simultaneously many criteria of quality of service (QoS) in routing decision. Efficient routing of information packets in dynamically changing communication network requires that as the load levels, traffic patterns and topology of the network change, the routing policy also adapts. We propose in this paper an approach used an adaptive algorithm for packet routing using reinforcement learning called AV-BW Delay Q- Routing. This approach is based on earlier developed K-Optimal path Q-Routing Algorithm (KOQRA) which optimizes simultaneously two additive QoS criteria: cumulative cost path and end-to-end delay. The approach developed here adds a third criterion to KOQRA regarding residual bandwidth. This proposed technique uses an inductive approach based on trial/error paradigm combined with swarm adaptive approaches. The whole algorithm uses a model combining both a stochastic planned pre-navigation for the exploration phase and a deterministic approach for the backward phase. Numerical results obtained with OPNET simulator for different levels of traffic´s load show that AV-BW Delay Q-Routing improves clearly performances of our earlier KOQRA.