repository
Energy-efficient Multisite Offloading Policy using Markov Decision Process for Mobile Cloud Computing
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Sangyoon Oh | - |
| dc.contributor.author | Terefe Mati Bekuma | - |
| dc.date.accessioned | 2018-11-08T08:09:53Z | - |
| dc.date.available | 2018-11-08T08:09:53Z | - |
| dc.date.issued | 2014-08 | - |
| dc.identifier.other | 17465 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/11000 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :컴퓨터공학과,2014. 8 | - |
| dc.description.abstract | 모바일 디바이스의 제한점(배터리, 상대적으로 낮은 성능)을 극복하기 위해, 모바일 클라우드 컴퓨팅에서는 수행하여야 하는 연산을 클라우드 환경으로 옮겨 수행하는 Computational Offloading 방식을 사용함. 발표자는 현실적인 조건(복수의 Site에 Offloading을 하는 경우, 각 Network Path의 대역폭이 다르고 Dynamic하게 변하는 경우)을 고려하고 에너지 효율을 극대화한 Offloading 알고리즘을 제안함. 이 알고리즘은 Markov Decision Process을 사용하고 Delay-constrained least-cost shortest path problem으로 만들어진 모델에 기반하여 제안됨. 시뮬레이션 실험에서 기존의 Single Site Algorithm에 비해 20% 이상의 에너지가 소모되지 않고 보존됨을 확인하였음. | - |
| dc.description.tableofcontents | 1. Introduction 2. Background and related works 2.1 Computation Offloading 2.2 Related works 3. System Model and Problem Formulation 3.1 System Model 3.2 Finite-state Markov Channel Model 3.3 Problem Formulation 3.4 Markov Decision Process Formulation 4. Energy-efficient Multisite Offloading Decision 4.1 Optimality Equation and Value Iteration Algorithm 4.2 The Energy-efficient Multisite Offloading Policy Algorithm 5. Numerical Simulation and Evaluation 5.1 Simulation Setup 5.2 Simulation Results 6. Conclusion and future work | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Energy-efficient Multisite Offloading Policy using Markov Decision Process for Mobile Cloud Computing | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.department | 일반대학원 컴퓨터공학과 | - |
| dc.date.awarded | 2014. 8 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 652545 | - |
| dc.identifier.url | http://dcoll.ajou.ac.kr:9080/dcollection/jsp/common/DcLoOrgPer.jsp?sItemId=000000017465 | - |
| dc.subject.keyword | Multisite | - |
| dc.subject.keyword | computation offloading | - |
| dc.subject.keyword | markov decision process | - |
| dc.subject.keyword | mobile cloud computing | - |
| dc.description.alternativeAbstract | Mobile systems, such as smartphones, are becoming the primary platform of choice for user’s computational needs. However, mobile device still suffer with limited resources, such as battery life and process performance. To alleviate these limitations, a popular approach used in mobile cloud computing is computation offloading, where resource-intensive mobile components are offloaded to more resourceful cloud servers. Prior researches in this area have focused on form of offloading where only a single server is considered as offloading site. Since we have an environment where mobile devices access multiple cloud providers, it is possible for mobiles to save more energy by offloading energy-intensive components to multiple cloud servers. This thesis differentiates the data and computational intensive components of an application and performs a multisite offloading in a data and process-centric manners. In this thesis, we present a novel model to describe the energy consumption of a multisite application execution and use the discrete time Markov chain (DTMC) to model the fading wireless channel of mobiles. We adopt Markov decision process (MDP) framework to formulate the multisite partitioning problem as a delay-constrained least-cost shortest path problem on a state transition graph. An Energy-efficient Multisite Offloading Policy (EMOP) algorithm that built on the value iteration algorithm is proposed in this thesis to find the optimal solution to the problem. The numerical simulations result shows that our algorithm better adapt the dynamic bandwidth of the wireless network and takes into account the capability of each site to make the optimal offloading decision. A multisite offloading execution using our proposed EMOP algorithm reduces the energy consumption of mobiles by 20% when compared to a single site offloading execution. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Computer Engineering > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,625,493
- Total Download :1,804
- Today View :5,973
