Flexpop: A popularity-based caching strategy for multimedia applications in information-centric networking
Information-Centric Networking (ICN) is the dominant architecture for the future Internet. In ICN, the content items are stored temporarily in network nodes such as routers. When the memory of routers becomes full and there is no room for a new arriving content, the stored contents are evicted to...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | eng eng |
| Published: |
2016
|
| Subjects: | |
| Online Access: | https://etd.uum.edu.my/6014/1/s900424_01.pdf https://etd.uum.edu.my/6014/2/s900424_02.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Information-Centric Networking (ICN) is the dominant architecture for the future Internet.
In ICN, the content items are stored temporarily in network nodes such as routers. When the memory of routers becomes full and there is no room for a new
arriving content, the stored contents are evicted to cope with the limited cache size of the routers. Therefore, it is crucial to develop an effective caching strategy for keeping popular contents for a longer period of time. This study proposes a new caching strategy, named Flexible Popularity-based Caching (FlexPop) for storing popular contents.
The FlexPop comprises two mechanisms, i.e., Content Placement Mechanism (CPM), which is responsible for content caching, and Content Eviction Mechanism
(CEM) that deals with content eviction when the router cache is full and there is no space for the new incoming content. Both mechanisms are validated using Fuzzy Set Theory, following the Design Research Methodology (DRM) to manifest that the research is rigorous and repeatable under comparable conditions. The performance of FlexPop is evaluated through simulations and the results are compared with those of the Leave Copy Everywhere (LCE), ProbCache, and Most Popular Content (MPC) strategies. The results show that the FlexPop strategy outperforms LCE, ProbCache,
and MPC with respect to cache hit rate, redundancy, content retrieval delay, memory utilization, and stretch ratio, which are regarded as extremely important metrics (in various studies) for the evaluation of ICN caching. The outcomes exhibited in this study are noteworthy in terms of making FlexPop acceptable to users as they can verify
the performance of ICN before selecting the right caching strategy. Thus FlexPop has potential in the use of ICN for the future Internet such as in deployment of the IoT technology. |
|---|