On Optimal and Fair Service Allocation in Mobile Cloud Computing

2,375 views

Published on

Published in: Technology
2 Comments
1 Like
Statistics
Notes
No Downloads
Views
Total views
2,375
On SlideShare
0
From Embeds
0
Number of Embeds
504
Actions
Shares
0
Downloads
20
Comments
2
Likes
1
Embeds 0
No embeds

No notes for slide

On Optimal and Fair Service Allocation in Mobile Cloud Computing

  1. 1. On Optimal and Fair ServiceAllocation in Mobile CloudComputing(short version)Reza RahimiSCHOOL OF INFORMATION AND COMPUTER SCIENCE,University of California,Irvine, CA.
  2. 2. Prologue2MapCloud:Optimal Service Allocation forMobile UsersMobile UsersCriteria: Lowprice, Low delay,proximityMobile UserBehavior: Mobilitypatterns, …XaaS:Computation,Storage,Bandwidth,…
  3. 3. MapCloud Features• It uses 2-Tiere Cloud architecture as an efficientplatform for mobile cloud computing.• Proposing Location-Time Workflow as an efficientFramework for modeling mobile applications andtheir QoS (power consumption, delay and price )based on cloud.• Proposing an efficient service allocation algorithmcalled MuSIC for different classes of mobileapplication like single user application or group-based and collaborative application.• Finally, it provides an Abstraction and Genericframework for efficient service allocation inmobile cloud computing!3
  4. 4. Location-Time Workflow4t1 t2 t4t3 tNl2l1l3lnW1Wk+1WkWj+1WjLocation-Time Workflow
  5. 5. 5Tier 2: Local Cloud(+) Low Delay, Low Power,Almost Free(-) Not Scalable and ElasticTier 1: Public Cloud(+) Scalable and Elastic(-) Price, DelayWi-Fi AccessPoint3G AccessPointRTT:~290msRTT:~80ms2-Tier Cloud Architecture
  6. 6. MobileUserLogger DBand QoSAnalyzerLocation-TimeAnalyticsQoS-AwareServiceScheduler2-Tier QoS-AwareCloud Registry2-Tier CloudServicePoolMapCloud Sequence DiagramExtract user webserviceusage pattern andsave itAs location-Timeworkflow .RecommendedWeb Serviceswith their URLs.User Web ServiceUsage Log withExperienced QoS .Run MuSIC or UseMuSIC Result onprevious collecteddata from mobileusers to find bestservice allocation.It analyzes userexperiencedQoS and updatescloud registry, Notnecessarily in thistime period, couldbe runindependently!User Logslike:Web ServiceUsage,ExperiencedQoS like:delay, powerconsumption6
  7. 7. MapCloud Prototype Snapshots7
  8. 8. 8
  9. 9. 9
  10. 10. 10
  11. 11. 11
  12. 12. References1. M. Reza. Rahimi, Nalini Venkatasubramanian, Athanasios Vasilakos, "MuSIC: OnMobility-Aware Optimal Service Allocation in Mobile Cloud Computing", In theIEEE 6th International Conference on Cloud Computing, (Cloud 2013), July 2013, SiliconValley, CA, USA.2. M. Reza. Rahimi, Nalini Venkatasubramanian, Sharad Mehrotra and AthanasiosVasilakos, "MAPCloud: Mobile Applications on an Elastic and Scalable 2-TierCloud Architecture", In the 5th IEEE/ACM International Conference on Utility andCloud Computing (UCC 2012), Nov 2012, USA.3. M. Reza. Rahimi, Nalini Venkatasubramania "Exploiting an Elastic 2-Tiered CloudArchitecture for Rich Mobile Applications", poster in the IEEE/ACM 13thInternational Symposium on a World of Wireless, Mobile and Multimedia Networks(WoWMoM 2012), June 2012, USA.4. M. Reza. Rahimi, Nalini Venkatasubramania "Cloud Based Framework for RichContent Mobile Applications", poster in the IEEE/ACM 11th InternationalSymposium on Cluster, Cloud and Grid Computing (CCGRID2011), Newport Beach,May 2011, USA.5. Shivajit Mohapatra, M. Reza. Rahimi, Nalini Venkatasubranian "Power-AwareMiddleware for Mobile Applications", Chapter 10 of the Handbook of Energy-Awareand Green Computing, ISBN: 978-1-4398-5040-4, Chapman & Hall/CRC, 2011.12

×