An Optimization-based Approach for Flow Table Capacity Bottleneck Mitigation in Software-Defined Networks

TL;DR

This paper presents an optimization-based algorithm for flow delegation in SDN to mitigate flow table capacity bottlenecks, incorporating future network knowledge and multiple optimization criteria, outperforming previous greedy methods.

Contribution

It introduces a novel delegation template and multi-objective optimization approach, enabling efficient flow rule relocation considering future network states.

Findings

Significantly better performance than greedy algorithms

Capable of handling networks with hundreds of switches

Effectively incorporates future network information

Abstract

Flow delegation is a flexible technique to mitigate flow table capacity bottlenecks in Software-defined Networks (SDN). Such bottlenecks occur when SDN switches provide insufficient flow table capacity which leads to performance degradation and network failures. Flow delegation addresses this problem by automatically relocating flow rules from a bottlenecked switch to neighboring switches with spare capacity. This paper introduces a new algorithm to efficiently perform flow delegation based on a novel delegation template abstraction and multi-period multi-objective optimization. Different from existing work, our approach can include estimated knowledge about future network situations and deal with different optimization criteria such as link and control overhead. We discuss the problem decomposition for the new algorithm and introduce an efficient two-step heuristic. Results show, that our approach performs significantly better than the simple greedy algorithm used in earlier work and is capable of handling flow delegation for networks with hundreds of switches.