Green Days @ Toulouse Segment Routing based Traffjc Engineering - - PowerPoint PPT Presentation

▶
green days toulouse segment routing based traffjc
SMART_READER_LITE
LIVE PREVIEW

Green Days @ Toulouse Segment Routing based Traffjc Engineering - - PowerPoint PPT Presentation

Aug 23, 2022 331 likes •585 views

Green Days @ Toulouse Segment Routing based Traffjc Engineering for Energy Effjcient Backbone Networks Radu Crpa, Olivier Glck, Laurent Lefvre radu.carpa@ens-lyon.fr 16 / 03 / 2015 INRIA AVALON / LIP Ecole Normale CHIST -ERA STAR

slide-1
SLIDE 1

Segment Routing based Traffjc Engineering for Energy Effjcient Backbone Networks

Radu Cârpa, Olivier Glück, Laurent Lefèvre

radu.carpa@ens-lyon.fr

INRIA AVALON / LIP

Ecole Normale Supérieure de Lyon

16 / 03 / 2015

CHIST

  • ERA STAR

Green Days @ Toulouse

slide-2
SLIDE 2

Outline

  • Context: energy effjciency and backbone networks
  • Switching OFF/ON for energy effjciency
  • Why?
  • What?
  • How?
  • Simulation
  • Results
  • Future work
  • 2
slide-3
SLIDE 3

Ice melting: 500Gtons/year in 2011-2014 x2/x3 increase compared to averages in 2003 - 2009

  • cean rising > 1 m (2100)

T emperature increasing (2°C – 2100) -> 4°C (50% chance – 2100) No more oil in 50 years … more coal usage…

IT -> electricity -> CO2 -> impact IT -> electricity -> $

Some messages from our planet

  • 3
slide-4
SLIDE 4
  • 4

Backbone networks

slide-5
SLIDE 5

Backbone networks

  • High speed core networks
  • Relatively small number of nodes
  • High speed ports
  • The network must not be disconnected

Nantes2014_Laurent_Lefevre.ppt

  • Based on optical fjbers
  • High energy consumption
  • Overprovisioning
  • 5
slide-6
SLIDE 6

Energy proportionality

Servers Idle power consumption Non-linear increase of energy effjciency Network Even less proportional Energy consumption almost constant

*Luiz André Barroso and Urs Hölzle, « The case for Energy-Proportional Computing », IEEE Computer, 2007 Mohammed El Mehdi Diouri. Efjcacite energetique dans le calcul tres haute performance : application a la tolerance aux pannes et a la difusion de donnees. Ecole normale superieure de lyon - ENS LYON, 2013.

  • 6
slide-7
SLIDE 7
  • 7

*Sushant Jain, Alok Kumar et al. «B4: experience with a globally-deployed software defjned wan». SIGCOMM

  • Comput. Commun. Rev. 43, 4 (August 2013), 3-14.

Google's way: increase the utilization! Increasing the energy effjciency

slide-8
SLIDE 8

Our way: increase the utilization ...

  • 8

… of some links Completely unload other links and switch them ofg

  • lesser trafjc in the network = more savings possible

Increasing the energy effjciency

slide-9
SLIDE 9

Overprovisioning

Distribution of link utilization in the Geant network

  • 9
slide-10
SLIDE 10

During the ofg-peak hours, choose the best links to be switched of

  • May be easy (ineffjcient), up to NP-hard
  • Using link utilization (actual solution), or fmow matrices:
  • In most cases are diffjcult to obtain
  • Can be estimated, but error-prone and expensive

During the rush periods, fjnd the links to be switched on

  • Can be even more complex

On-demand ON/OFF

  • 10
slide-11
SLIDE 11

in a multi-layered network

*Van Heddeghem, Ward, Filip Idzikowski et al.. 2012. “Power Consumption Modeling in Optical Multilayer Networks.” Photonic Network Communications 24 (2): 86–102

IP Layer Optical Layer

Choosing what to switch of/on

  • 11
slide-12
SLIDE 12

On optical layer

  • Switching ofg optical fjbers
  • Allows to switch ofg amplifjers
  • 17 -> 1870 W
  • Need to reconfjgure optical paths
  • Amplifjers switch ON is long

On IP layer

  • Switching ofg IP links
  • Allows to switch ofg router ports
  • 2 -> 5588 W
  • Need to re-route in IP layer
  • Ports switch ON is faster than

amplifjers switch ON

Choosing what to switch of/on

  • 12
slide-13
SLIDE 13
  • 13

Usualy used In optical transport networks : GMPLS distributed management. Industry moving towards centralized network management: SDN

Good news for energy effjciency ! SDN controller can coordinate the switch-ofg/on optimaly Use trafjc matrices for optimal rerouting Without disconnecting the network Fast reaction to increase in network loadis slow adopting

new technologies

Coordinating the switch of/on process

slide-14
SLIDE 14
  • 14

Current IETF draft (last update on march 3, 2015) Source routing protocol designed for trafjc engineering Robust and scalable

Rerouting: SPRING/Segment Routing

Source Packet Routing In NetworkinG

slide-15
SLIDE 15
  • 15

Example

slide-16
SLIDE 16
  • 16

Example

slide-17
SLIDE 17
  • 17

Example

slide-18
SLIDE 18
  • 18

Example

slide-19
SLIDE 19
  • 19

Example

slide-20
SLIDE 20
  • 20

Example

slide-21
SLIDE 21

Simulation

  • 21

in the OMNeT++ simulator Implementation of SPRING Full emulation of a network Including management protocols

slide-22
SLIDE 22

Simulation results on backbone topologies

Night traffjc 20% delay increase Impact of US nodes : switiching ofg links impose routing in Europe

  • 22
slide-23
SLIDE 23

Conclusion

  • 23

Solution fully implemented in OMNeT++ Proving SPRING may be the right choice for energy effjcient traffjc engineering Reducing the energy consumed in ports by almost 50%: Géant: 204 kWh/day Germany50: 522 kWh/day

slide-24
SLIDE 24

NetFPGA test-bed

Implementing and testing the proposed solution on a network

  • f NetFPGA devices

OMNeT++ : we'll try to push our changes upstream

Opaque LSA option for OSPF SPRING

Next Steps

  • 24
slide-25
SLIDE 25

Thank You

radu.carpa@ens-lyon.fr