VoIP-HDK – A novel channel allocation technique for QoS aware VoIP communication over heterogeneous networks

Abstract

Abstract Channel allocation for VoIP (Voice over IP) is a critical problem in modern-day heterogeneous networks having diverse application requirements. Conventional stochastic and machine-learning based models that predict channel suitability for VoIP underperform under dynamic conditions. In contrast, this paper deploys VoIP-HDK2 – a novel technique that uses an efficient combination of K-Nearest Neighbors algorithm, 2-order Hidden Markov Model, Damerau-Levenshtein distance based model and K-Means Clustering technique to accurately predict and allocate channels with sufficient QoS (Quality of Service) guarantees to VoIP calls. The primary contribution of this paper lays both in the formulation of the proposed methodology involving tailor-made algorithms as well as complete test-bed based dataset creation, execution of VoIP-HDK2 and validation of its performance in terms of maintaining high quality VoIP calls. Comparative performance evaluation records significant reduction in call drops and packet-loss and enhancement in call quality and throughput for VoIP-HDK2 with respect to existing works in literature.