Presentation on theme: "Distribute what you can, centralize what you must!"— Presentation transcript:
1Distribute what you can, centralize what you must! Narseo Vallina-RodriguezSupervisor: Jon CrowcroftQualcomm – Cambridge 22nd May 2013Apologize Jon; 2 day project meeting in LondonIdea: current centralised model: cloud-phone does not really work
2Motivation The web is becoming mobile Apps rely on multiple online/cloud services (mobile mashup):CDNs (Akamai)Cloud services (Amazon WS)Authentication APIs (Oauth)Assisting sensors (A-GPS)Advertisement (AdMob, Burstly, Millennial Media, …)Push notifications (Google’s GCM)NAT punching for P2P (Skype)
3Research questionHow do mobile apps’ cloud dependency impact on cellular network and battery life of mobile handsets?
4outcomeWhen Assistance becomes Dependence: characterizing the costs and inefficiencies of A-GPS. Vallina-Rodriguez, Finamore, Grunenberger, Papagiannaki and Crowcroft. ACM SIGMOBILE MC2R (under review)Breaking for Commercials: Characterizing Mobile Advertising. Vallina-Rodriguez, Finamore, Shah, Grunenberger, Haddadi, Papagiannaki and Crowcroft. In ACM Internet Measurement Conference 2012(IMC'12)Energy Management Techniques in Modern Mobile Devices. Vallina-Rodriguez and Crowcroft. In IEEE Communications Tutorials and Surveys, 2012.When David can help Goliath: the case for cellular augmentation of wired networks. Vallina-Rodriguez, Erramilli, Grunenberger, Gyarmati, Laoutaris, Stanojevic, Papagiannaki, In ACM HotNets'12Signposts: End-to-End Networking in a World of Middleboxes. Aucinas, Chaudhry, Crowcroft, Probst Eide, Hand, Madhavapeddy, Moore, Mortier, Rotsos and Vallina-Rodriguez. In ACM SIGCOMM DEMO
5Take away: moving to the edge! Mobile applications may abuse cellular networks: they cause network (signaling/channels/operational) and energy costs!Fetching content in a centralized fashion is not the only wayApps and OS must exploit locality and neighboring devices when possible!
7Flashlinq/LTE-direct P2P wireless technologyPerfect candidate for transparent communication in the edge!Peer discovery (energy efficient)Expression-based discovery (service)Always-on background service with low duty-cycleSimilar to powering up a paging channel every X secondsCurrent prototype performance:Low-latency (<10 ms)Good throughput (~ 20 Mbps)Discovery (1~2 seconds)
10Use case 1: Localized data A large fraction of mobile data is localWeatherNotificationsAdsApps use cellular networks and push notifications to fetch this contentHigh latencyNo delivery guarantees[Cellular data network infrastructure characterization and implication on mobile content placement, Xu et al. SIGMETRICS’2011]
11Use case 1: Airport notifications SERVER (UK)NODE BGoogleGCM (Ir)RNCSGSNGGSNINTERNET
12Use case 1: Airport notifications Traffic Pattern Heathrow App For Android (Flight Update)Energy Signaling Spectrum (HSPA)TCP/IP Push notification model is broken for local data:Frequent RNC promotions (some caused by TCP Heartbeats)Waste of energy, middleboxes/proxies memory and radio channels (+200K users/day, a lot of signaling traffic!)
13Use case 1: Airport notifications PubSub model Low latencyNo net overheadEnergy efficientNo Middleboxes!SERVER (UK)FlashlinqNODE BGoogleGCM (Ir)RNCSGSNGGSNINTERNET
15Use case 2: Collaborative A-GPS Assisting data (time, ephemeris, almanac, coarse location) downloaded from network:Reduces TTFF (usability)Temporal validity up to 2 weeks for ephemerisProblem: use of cellular network may impair performance and increase energy costs!
16Use case 2: Collaborative A-GPS 2x current!Control-plane latency
17Use case 2: Collaborative A-GPS Collaboration between devices in a P2P fashion:Context-awareness (sense environment so do not turn on AGPS indoors!)Share/pre-fetch assisting data (reduces latency to fetch data)Prototype for Nexus One:Pre-fetch and cache of assisting dataDevices can detect if they’re indoors in less than 10 secondsBlackbox. Hard to inject assisting data on chipsets (A-GPS is controlled by binary/proprietary files/drivers )
183. Wired-wireless integration Thinking beyond app-level use cases,Flashlinq is a perfect candidate for wired-wireless integration.
19Use case 3: Wired-wireless integration 3G offloading to WiFi and femtocells:Reduce network trafficNo real benefit for users (unless volume cap in data-plan)Wired network can be constrained!Can cellular networks augment wired networks?Wired nets deployment is $$$Cellular nets have good coverage
20Use case 3: Wired-wireless integration Cellular network can provide more capacity than wired ones (DSL)Spare capacity on cellular networkPowerboost for video- streaming appsUse-and-releaseDoes NOT work everywhere anytime!4.7 MbpsDSLAMDSL in rural/suburbs: far from DSLAMSpare capacity for small periods of time (HSPA)Powerboost (use and release)A2 Km2.8 MbpsGoogle Maps
21Use case 3: Wired-wireless integration 2x downlink/5x uplink for most locations with 1 mobile deviceSimulation: 50% of the videos have a speed up factor of 10x2x downlink5x uplinkSome locations are congestedNevertheless, worst case shows that 50% apps can reduce by 10x the buffering time
22Conclusions Current cloud-mobile model is not efficient Hyper-centralized: push notificationsLack of connectivity between handsets: missing opportunitiesCellular and wired networks are fully decoupledFlashlinq/LTE-direct can bring a new mobile paradigm!Energy and network efficientDistributedFlexible
23Flashlinq limitations and extensions Transparent security/authentication mechanismsLessons to be learnt from the past: Bluetooth and WiFi-direct failed!Source of DoS/Privacy/Energy attacksGlobal Signpost-ish naming (OpenSource, DNSSEC based)Low-level radio details must be exposed to OS!Too much layering hides inefficiencies: e.g. A-GPS and 3GCross-layer optimizations are key (e.g. iPhone vs. Android)Incentives for operators?Reduce operational costs: better use of limited capacityLicensed frequency.. But there are few missing bits from my perspective as a developer that are being missing