An Effective QoS Providing Mechanism Using Prediction-Based Decentralized Routing

In this paper, we introduce an adaptive Ant-based mechanism integrated with an advanced traffic prediction approach for optimizing the performance of Prediction-based Decentralized Routing (PDR) algorithm. The PDR algorithm is based on the Ant Colony Optimization (ACO) meta-heuristics in order to compute the routes. In this approach, an ant uses a combination of the link state information and the predicted available bandwidth instead of the ant´s trip time to determine the amount of deposited pheromone. We have two contributions. The first is introducing the new enhanced Ant-based mechanism which is incorporated with a new efficient prediction approach in order to effectively outperform the previous versions of PDR and various decentralized routing algorithms. The second is presenting a comparative study between PDRv.3 and different centralized routing algorithms. We study three performance parameters: the rejection ratio of requests, the percentage of accepted BW and the effect of prediction use. In general, our new algorithm, which uses more effective predictor, reduces the rejection ratio of requests and accepts more BW when compared to the Ant Net, TB, PDRv.2, CSPF and LIOA algorithms and based on generated and real traffic.