Please use this identifier to cite or link to this item:
|Title:||Scalable traffic management for mobile cloud services in 5G networks||Authors:||Liu, Lanchao
|Keywords:||Engineering::Computer science and engineering||Issue Date:||2018||Source:||Liu, L., Niyato, D., Wang, P., & Han, Z. (2018). Scalable traffic management for mobile cloud services in 5G networks. IEEE Transactions on Network and Service Management, 15(4), 1560-1570. doi:10.1109/TNSM.2018.2867019||Journal:||IEEE Transactions on Network and Service Management||Abstract:||Mobile cloud computing has been introduced to improve the performance of mobile application clients by offloading data processing and storage to cloud. By deploying the service on several cloud-enabled data centers, the service provider can optimally locate service instances on the cloud to provide qualified services at a reasonable cost. However, a centralized approach for both request allocation and response routing does not scale efficiently due to a large number of mobile clients involved in the mobile service traffic management. Moreover, the random and unpredictable wireless network performance (e.g., delay) complicates the problem further. In this paper, we present a stochastic distributed optimization framework for mobile cloud traffic management in 5G networks. The framework takes the impact of random wireless network characteristics into account. Utilizing the alternating direction method of multipliers, the optimization problem is decomposed into independent subproblems, which are solved in a parallel fashion on distributed agents and coordinated through dual variables. The convergence issue under the stochastic setting is addressed, and the numerical tests validate the effectiveness of the proposed algorithm.||URI:||https://hdl.handle.net/10356/141655||ISSN:||1932-4537||DOI:||10.1109/TNSM.2018.2867019||Rights:||© 2018 IEEE. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Mar 2, 2021
Updated on Feb 27, 2021
Updated on Mar 3, 2021
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.