| Autor: |
Anh-Tien Tran, Nhu-Ngoc Dao, Sungrae Cho |
| Jazyk: |
angličtina |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 8, Pp 135844-135852 (2020) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2020.3011517 |
| Popis: |
With the evolution of 5G networks, mobile edge computing (MEC) is being considered as a key enabler for realizing significant improvements in heterogeneous video streaming services. This is because MEC provides storage and computation resources for adaptive bitrate (ABR)-video streaming services to transcode the original video into lower bitrate variants at the edge caching server proactively, thereby facilitating the heterogeneous demands of users. In this paper, we propose a caching and processing framework that jointly considers the popularity and retention rate of video streams to maximize their video bitrate. The problem is formulated as an integer linear program (ILP), which that is challenging because of its NP-hardness. Our algorithm is called online iterative greedy-base adaptation (OIGA); it is built based on the greedy approach with strict constraints for storage size and computing capacity of the cache server. The simulation results show that our proposed solution adapts well to the change in video popularity and retention rate for a maximal video bitrate. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
