! Energy!Efficient!Content! Distribu2on!in!an!ISP!network ! - PowerPoint PPT Presentation

! Energy!Efficient!Content! Distribu2on!in!an!ISP!network ! Jean:Claude!BERMOND! ! Sophia!An*polis,!France!

Energy!Efficient!Content!Distribu*on! • Work!presented!at!Globecom!2013! Giroire,!Modrzejewski,! Coa*,!Sophia!An*polis,!France! Tahiri! Chiaraviglio! CNIT!and!University!la!Sapienza,!Rome,!Italy.!! Le!Rouzic! Orange/France!Telecom,!Lannion,!France! BoneSo! Politecnico!di!Torino,!Italy! Musumeci! CNIT!and!Politecnico!di!Milano,!Italy! Gonzalez,!Guerrero! Universidad!Carlos!III,!Madrid,!Spain! 2!

Context! Huge!increase!in!Traffic! Global Consumer Tra ffi c [PB/day] 3000 Video streaming 2500 File sharing Other 2000 1500 1000 500 0 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 Year Year%to%year)peak)increases)around)40%) 3! !

Context! Limited!financial!resources!to!accomodate! growth! 1200 1000 Price [ $ / Mb ] 800 600 400 200 0 1998 2000 2002 2004 2006 2008 2010 2012 Year Year%to%year)price)falls)around)35%) ! 4!

Context! Environmental!pressure! 2)to)10%)of)global)energy)consump>on) ! 5!

Context! Crucial!trend:!Traffic!is!video.!! Global Consumer Tra ffi c [PB/day] 3000 Video streaming 2500 File sharing Other 2000 1500 1000 500 0 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 Year Video)streaming)already)over)50%) [CISCO)Forecast])86%)by)2016) 6! !

Context! Different!models!to!distribute!(redondant)!content! 7!

Problem! Internet Peering Link Core • We!consider!a! network!operator .!! Network Content Metro Network Access • The!network!operator!distributes! Network – Traffic!of!content!providers!! DSLAM – Its!own!traffic!(money!is!in!the!content,!! Users less!in!the!transport)! ! • 70%!of!traffic!comes!from!the! peering!link! 8!

Problem! Internet Peering Link Core • Problem:! How!to! distribute!this! Network Content content! in!order!to!be! energy! Metro Network efficient ?!! Access Network DSLAM • Ques2ons:!! Users – Where!to !place!caching!facili2es ?! – Where!to! place!storage!facili2es! for! the!operator’s!own!content?! 9!

Contribu*ons!and!Related!Work! • Lots!of!work!on!distribu*ng!content!and!caching,!e.g.!:!! [1]!V.!Jacobson,!D.!K.!SmeSers,!J.!D.!Thornton,!M.!F.!Plass,!N.!H.!Briggs!and!R.!L.! Branard.!Networking!named!content.!ACM!CoNEXT!2009.! [2]!D.!Perino,!M.!Varvello.!A!reality!check!for!content!centric!networking.!ACM! SIGCOMM!2011.! [3]I.!Baev,!R.!Rajaraman!and!C.!Swamy.!Approxima*on!algorithms!for!data! placement!problems.!SIAM!Journal!on!Compu*ng,!2008.! • Here,!! – Different!ques*on:!How!much!can!we!save!energy!in!an! op*mal!content!distribu*on!when!controling!both! transport!and!storage?!! – Realis*c!scenario,!provided!by!Orange/France!Telecom! – Efficient!analy*cal!model!for!op*mal!dimensioning! 10!

Our!Model! Diffusion)of)content)is)done)via)a)logical)tree) 11!

Our!Model! A)video)is)sent)to)one)user) 12!

Our!Model! A)video)is)sent)to)several)users:)not)efficient)use)of)energy) 13!

Our!Model! Placement)of)storage)facili>es) 14!

Our!Model! Placement)of)storage)facili>es:)energy)is)saved) 15!

Our!Model! Not)worth)for)non)popular)videos) 16!

Modeling!Popularity! 17!

Modeling!Popularity! 18!

Modeling!Popularity! 19!

Modeling!Popularity! 20!

Modeling!Popularity! 21!

Modeling!Popularity! 22!

Power!Models! 23!

Power!Models! 24!

Efficient!Analy*cal!Model! • We!assume:! – Network!represented!by!a!leveljregular!tree! – Homogeneous!user!popula*on! – Linear!power!model,!known!devices!for!levels! – Zipfian!popularity!model! 25!

Efficient!Analy*cal!Model! • For!one!class!of!videos:!find!the!best!level!to!cache!it! • For!efficiency:!Compute!the!interval!of!popularity!of! videos!cached!at!each!level.!! 26!

Results! 27!

Results!j!Sen*vity! Small!changes!in!β!–!huge!changes!in!results! ! 28!

Results!j!Sen*vity! Changes!in!total!throughput,!small!changes!in!results!! ! 29!

Takejaways! • Around!10%!savings! • Importance!of!model!parameters:!! – Knowing!popularity!distribu*on!is!crucial! – Op*mizing!cost!of!storage!more!important!! than!I/O!! • Op*mal!is!feasible:!! – No!changes!in!core!networks! – DSLAM!augmented!by!a!small!flash!module! routers!by!single!servers! 30!

Future!Work! • Study!other!architectures:!!! – with!mul*ple!peering!points,!! – other!tree!degree!distribu*ons.!! – with!Operator’s!datacenter.!! • Here:!op*mal!gain.!Test!caching!on!real!traffic! traces.!! • Economic!studies:!Content!providers!are! reluctant!to!allow!caching!of!their!content! (contract,!incen*ve…)! 31!

Future!Work! • Study!other!architectures:!!! – with!mul*ple!peering!points,!! – other!tree!degree!distribu*ons.!! – with!Operator’s!datacenter.!! • Here:!op*mal!gain.!Test!caching!on!real!traffic! traces.!! • Economic!studies:!Content!providers!are! reluctant!to!allow!caching!of!their!content! (contract,!incen*ve…)! THANKS!!!!! 32!