Joint Optimization of Rule Placement and Traffic Engineering for QoS Provisioning in Software Defined Network

Abstract

Software-Defined Network (SDN) is a promising network paradigm that separates the control plane and data plane in the network. It has shown great advantages in simplifying network management such that new functions can be easily supported without physical access to the network switches. However, Ternary Content Addressable Memory (TCAM), as a critical hardware storing rules for high-speed packet processing in SDN-enabled devices, can be supplied to each device with very limited quantity because it is expensive and energy-consuming. To efficiently use TCAM resources, we propose a rule multiplexing scheme, in which the same set of rules deployed on each node apply to the whole flow of a session going through but towards different paths. Based on this scheme, we study the rule placement problem with the objective of minimizing rule space occupation for multiple unicast sessions under QoS constraints. We formulate the optimization problem jointly considering routing engineering and rule placement under both existing and our rule multiplexing schemes. Via an extensive review of the state-of-the-art work, to the best of our knowledge, we are the first to study the non-routing-rule placement problem. Finally, extensive simulations are conducted to show that our proposals significantly outperform existing solutions.

A Software-Defined Networking Framework to Provide Dynamic QoS Management in IEEE 802.11 Networks

“…Regarding QoS management in SDN networks, the rule placement and caching in SDN switches have been studied in [13,14]. Given a set of sessions with certain QoS requirements, instead of installing all the forwarding rules and QoS requirement rules in every switch, the authors of [13] divide a session into several independent sub-sessions with different subsets of QoS requirement rules, which are scattered across multiple switches, to reduce the TCAM usage.…”

“…Given a set of sessions with certain QoS requirements, instead of installing all the forwarding rules and QoS requirement rules in every switch, the authors of [13] divide a session into several independent sub-sessions with different subsets of QoS requirement rules, which are scattered across multiple switches, to reduce the TCAM usage. In [14], the authors studied the rule caching problem in SDN in order to minimize the amount of TCAM and remote controller processing cost.…”

Hybrid routing by joint optimization of per-flow routing and tag-based routing in software-defined networks

“…Under this circumstance, the bottleneck of the datacenter networks usually is the core switches, which encounter a massive number of flows [9] . Due to the development of Open vSwitch and Overlay technologies, the resource shortages of edge switches have been eased [10] , which means the switches 5 , and v 6 are highly likely to encounter resource shortages and deployment delay problems in Fig. 1.…”

“…However, due to the high price and energy consumption of Ternary Content Addressable Memory (TCAM) units, an SDN switch usually contains only a few thousand flow rules [4] . Recent testing results show a 3.3 ms delay when inserting a single flow rule into a flow table on a commodity switch [5] . Deployment delays are critical for many applications, e.g., the authors of Ref.…”

A consistent QoS routing strategy for video streaming services in SDN networks

“…The authors considered the calculation of optimal paths per domain (ie, local minimum) and the sharing of this knowledge between distributed SDN controllers. In Huang et al, given the high cost and energy consumption of the ternary content‐addressable memories (TCAMs) that are used in SDN‐enabled switches to store flow forwarding rules, the authors proposed an efficient use of such memories. For this purpose, a study based jointly on traffic engineering and rule placement is conducted.…”