End-to-End Delay Minimization-Based Joint Rule Caching and Flow Forwarding Algorithm for SDN

Abstract

Software-defined networking (SDN) technology is expected to offer higher flexibility and programmability and enhanced transmission performance by decoupling control plane from data plane and enabling centralized network management. In SDN, switches may cache a certain number of flow forwarding rules, so that user flows can be forwarded accordingly. In this article, stressing the limited caching space of switches and the heterogeneous transmission performance of switches and links, we jointly design rule caching and flow forwarding strategy for multiple user flows in SDN. To emphasize the importance of the end-to-end delay caused by the transmission and processing of user flows in both the data plane and control plane, we formulate the joint optimization problem as an end-to-end delay minimization problem. As the original optimization problem is a non-deterministic polynomial hard (NP-hard) problem, which cannot be solved directly, we propose a heuristic algorithm which successively solves three subproblems, i.e., flow forwarding subproblem, rule caching and candidate path selection subproblem, and resource sharing subproblem. By applying the K-shortest path algorithm, a priority-based rule caching algorithm, and Lagrangian dual method, respectively, the three subproblems are solved and the joint rule caching and flow forwarding strategy is obtained. Simulation experiments are conducted to examine the effectiveness of the proposed algorithm, and the results indicate that our proposed algorithm is capable of improving system performance by about 20% compared with the previous solutions.INDEX TERMS Software-defined networking, end-to-end delay, rule caching, flow forwarding, resource sharing.

Mobility-Aware Hybrid Flow Rule Cache Scheme in Software-Defined Access Networks

“…F. Giroire et al [9] presented an optimization scheme to minimize the energy consumption of the routers and guarantee the QoS requirements based on the centralized network view. L. Luo et al [10] formulated an optimization problem for the rule caching method to minimize the end-to-end delay and provided a heuristic algorithm to solve it. However, these works only considered the static scenarios in the core network.…”

“…It can be noticed that the controller can monitor the queuing delays according to the current state. In this paper, we assume that the controller follows the M/M/1 queuing model, as it is generally utilized for SDN controllers [10]. Then, the average response delay, except for the transmission and propagation delays, is given by 1/(C − λ) according to Little's law [32], where C is the processing capacity of the controller and λ is the packet-in message arrival rates.…”

“…Equations ( 9) and (10) denote that the controller proactively caches the rule by comparing its delay performance with the flow's delay constraint.…”

“…Considering the rule placement problem with the capacity constraint of the forwarding node, conventional studies have provided rule compression [7], distribution [8], and energyaware rule caching [9]. However, these studies focused on the static scenarios without considerations of the mobile environment [10].…”