An energy-efficient load distribution framework for SDN controllers

Priyadarsini, Madhukrishna; Kumar, Shailesh; Bera, Padmalochan; Rahman, Mohammad Ashiqur

doi:10.1007/s00607-019-00751-2

Cited by 18 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works have used network programmability to enhance energy efficiency [9][10][11][12][13][14]. Most works use already known or new routing algorithms that optimize for energyconsumption by turning off links or entire switches [9,[13][14][15].…”

Section: Sdn On Data Center Network (Dcn)mentioning

confidence: 99%

“…Most works use already known or new routing algorithms that optimize for energyconsumption by turning off links or entire switches [9,[13][14][15]. Another common strategy is to distribute the load of switches among many controllers [10,12]. Ruiz-Rivera et al [11] defined the best controller location to minimize energy consumption, while Son et al [16] used the northbound interface to migrate applications and virtual machines to better meet Service Level Agreements (SLA) while minimizes link usage.…”

Section: Sdn On Data Center Network (Dcn)mentioning

confidence: 99%

“…A more comprehensive approach to energy consumption on SDN, which accounts also for the control-plane consumption, was developed by Priyadarsini et al [10] using a load balancing between many controllers to lower the demand on links by coalescing traffic turning off switches and controllers reducing energy on all planes. The algorithm is executed before the network is operational; it selects the most energy-efficient among various known routing algorithms and picks the most energy-efficient for that particular topology.…”

Section: Related Workmentioning

confidence: 99%

“…Energy consumption on SDN can be divided into three parts: the controllers, the switches and the links on a network. The work of Priyadarsini et al [10] shows how each part interacts and models this consumption based on packet flows on the network. The comprehensive network energy model:…”

Section: Energy Consumption On Sdnmentioning

confidence: 99%

See 3 more Smart Citations

Improving Energy Efficiency on SDN Control-Plane Using Multi-Core Controllers

2021

View full text Add to dashboard Cite

Software-defined networks have become more common in data centers. The programmability of these networks is a great feature that allows innovation to be deployed fast, following the increasing number of new applications. This growth comes with a cost of more processing power and energy consumption. Many researchers have tackled this issue using existing routing techniques to dynamically adjust the network forwarding plane to save energy. On the control-plane, researchers have found algorithms for positioning the controller in a way to reduce the number of used links, thus reducing energy. These strategies reduce energy consumption at the expense of processing power of the controllers. This paper proposes a novel approach to energy efficiency focused on the network’s control-plane, which is complementary to the many already existing data-plane solutions. It takes advantage of the parallel processing capabilities of modern off-the-shelf multicore processors to split the many tasks of the controller among the cores. By dividing the tasks among homogeneous cores, one can lower the frequency of operations, lowering the overall energy consumption while keeping the same quality of service level. We show that a multicore controller can use an off-the-shelf multicore processor to save energy while keeping the level of service. We performed experiments based on standard network measures, namely latency and throughput, and standard energy efficiency metrics for data centers such as the Communication Network Energy Efficiency (CNEE) metric. Higher energy efficiency is achieved by a parallel implementation of the controller and lowering each core’s frequency of operation. In our experiments, we achieved a drop of 28% on processor energy use for a constant throughput scenario when comparing with the single-core approach.

show abstract