Contention avoidance scheme using machine learning inspired deflection routing approach in optical burst switched network

Optical transport has emerged as a candidate solution to cope with the rising data transmission challenges of enormously evolving data. In the bufferless environment, only the ingress node beholds the buffering to speed up the data transfer in the form of data bursts. However, such networks are prone to data contention issues that degrade the overall performance and eventually result in burst loss. The paper proposes a machine learning (ML) inspired deflection routing (DR) algorithm to overcome contention issues in optical burst switching (OBS) network. The contending burst is first evaluated and assigned the priority order as per the available bits. Based on the burst traffic analysis, support vector machine (SVM) kernels are trained to select an alternate route and redirected the bursts to a new output node. It has been observed that for 65% of cases, radial basis function (RBF) kernel demonstrated the best results among the three kernel functions. The work further shows that ML offers a wiser decision to avoid and overcome contention in the deflection of the route of the contenting bursts. Moreover, the proposed DR scheme has achieved the highest throughput and packet delivery ratio (PDR) with an average delay of 9.66 s using an OBS network deployed with 10 groups of nodes. When compared against the contention scenario and the existing work, the proposed DR outperformed the existing technique with a 4% to 11% margin.