SAFAR: Simulated Annealing-Based Flow Allocation Rules for Industrial Networks

In this article, we address the problem of optimal flow allocation in the context of industrial networks. The problem is known to be computationally hard, which makes it difficult to solve for large networks. Moreover, industrial networks, such as power grids, often have unique characteristics, for example, integral flows and delay-symmetric path requirements, which further constrain the problem. To address these challenges, we propose the Simulated Annealing-based Flow Allocation Rules (SAFAR) scheme. At a high level, SAFAR identifies the near-optimal paths satisfying the bandwidth demands of a subset of flows by iteratively considering several configurations. The optimality criteria herein corresponds to maximizing the number of flows for which bandwidth paths are obtained, as well as improving the relative fairness in link utilization arising out of the process. Subsequently, SAFAR assigns a fraction of bandwidth (slice) to the remaining flows. Finally, SAFAR generates appropriate forwarding rules for the switches. Results of performance evaluation using real-life and synthetically-generated networks reveal that SAFAR can allocate up to 99% flows, which is an improvement of up to 9.6% over a contemporary greedy scheme. Moreover, SAFAR can improve the flow allocation fairness relatively by up to 37%. Finally, we also use a network of Open vSwitch switches to verify the end-to-end functionality of SAFAR.