In-network cache deployment is recognized as an effective technique for reducing content access delay. Caches serve content from multiple content providers, and wish to provide them differentiated services due to monetary incentives and legal obligations. Partitioning is a common approach in providing differentiated storage services. In this paper, we propose a utility-driven cache partitioning approach to cache resource allocation among multiple content providers, where we associate with each content provider a utility that is a function of the hit rate to its content. A cache is partitioned into slices with each partition being dedicated to a particular content provider. We formulate an optimization problem where the objective is to maximize the sum of weighted utilities over all content providers through proper cache partitioning, and mathematically show its convexity. We also give a formal proof that partitioning the cache yields better performance compared to sharing it. We validate the effectiveness of cache partitioning through numerical evaluations, and investigate the impact of various factors (e.g., content popularity, request rate) on the hit rates observed by contending content providers.
|Original language||English (US)|
|Title of host publication||ACM-ICN 2016 - Proceedings of the 2016 3rd ACM Conference on Information-Centric Networking|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||6|
|State||Published - Sep 26 2016|
|Event||3rd ACM International Conference on Information-Centric Networking, ACM-ICN 2016 - Kyoto, Japan|
Duration: Sep 26 2016 → Sep 28 2016
|Name||ACM-ICN 2016 - Proceedings of the 2016 3rd ACM Conference on Information-Centric Networking|
|Other||3rd ACM International Conference on Information-Centric Networking, ACM-ICN 2016|
|Period||9/26/16 → 9/28/16|
Bibliographical noteFunding Information:
This work was conducted under NSFC grant 61502393, NSF grants CNS-1413998, CRI-1305237 and CNS-1411636.
© 2016 ACM.
- Cache partitioning
- Information-centric networking
- Resource allocation