On the steady-state of cache networks

Rosensweig, Elisha J.; Menasché, Daniel Sadoc; Kurose, Jim

doi:10.1109/infcom.2013.6566874

Cited by 76 publications

(52 citation statements)

References 32 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This abstract problem naturally captures-and is directly motivated by-several important real-life networking applications. These include content and information-centric networks (CCNs/ICNs) [22,32,33], core and edge content delivery networks (CDNs) [7,13], micro/femtocell networks [34], and peer-to-peer networks [28], to name a few. For example, in hierarchical CDNs, requests for content can be served by intermediate caches placed at the network's edge, e.g., within the same administrative domain (e.g., AS or ISP) as the originator of the request; if, however, content is not cached locally, the request can be forwarded to a core server, that acts as a cache of last resort.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Caching Networks with Optimality Guarantees

Ioannidis

Yeh

2016

Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science

190

View full text Add to dashboard Cite

We study the problem of optimal content placement over a network of caches, a problem naturally arising in several networking applications, including ICNs, CDNs, and P2P systems. Given a demand of content request rates and paths followed, we wish to determine the content placement that maximizes the expected caching gain, i.e., the reduction of routing costs due to intermediate caching. The offline version of this problem is NP-hard and, in general, the demand and topology may be a priori unknown. Hence, a distributed, adaptive, constant approximation content placement algorithm is desired. We show that path replication, a simple algorithm frequently encountered in literature, can be arbitrarily suboptimal when combined with traditional eviction policies, like LRU, LFU, or FIFO. We propose a distributed, adaptive algorithm that performs stochastic gradient ascent on a concave relaxation of the expected caching gain, and constructs a probabilistic content placement within 1−1/e factor from the optimal, in expectation. Motivated by our analysis, we also propose a novel greedy eviction policy to be used with path replication, and show through numerical evaluations that both algorithms significantly outperform path replication with traditional eviction policies over a broad array of network topologies.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Caching Networks with Optimality Guarantees

Ioannidis

Yeh

2016

Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science

190

View full text Add to dashboard Cite

show abstract

“…Several works characterize the content dynamics in a single cache or caching network by Markov chain [65,69,75,83,84].…”

Section: Modeling Behavior and Performance Analysis Of Caching Systemmentioning

confidence: 99%

“…In [83], a cache network is modeled as a discrete-time Markov chain with state space Ω 0 , in which the content inserted or evicted from one of the cache nodes would cause the state transition of the system. Supposing that the network has m cache nodes, each cache space is N and the total number of contents is n. The system state is s, s = (s [1] In [65], the work process of LRU replacement policy is modeled as a homogeneous Markov chain.…”

Section: Modeling Behavior and Performance Analysis Of Caching Systemmentioning

confidence: 99%

Information-centric mobile caching network frameworks and caching optimization: a survey

Jin

Zhao

et al. 2017

J Wireless Com Network

View full text Add to dashboard Cite

The demand for content oriented service and compute-intensive service stimulates the shift of current cellular networks to deal with the explosive growth in mobile traffic. Information centric mobile caching network architectures have emerged in Information-Centric Networking as well as mobile cellular and ad-hoc networks deployed with caches. Caching optimization based on information centric mobile caching has become the key issue, and several significant research challenges remain to be addressed before its widespread adoption. In this paper, a brief survey on Information centric mobile caching network architecture and caching optimization is presented, including cache placement in different mobile wireless network architectures, the taxonomy of cache insertion and eviction policies, the modeling behavior of caching networks as well as caching optimization based on network centric and user centric metrics, and typical applications based on mobile caching. Finally, the research directions and open challenges are investigated.

show abstract

“…In [6], [7] the authors use probabilistic caching to increase the cache hit rate and the fairness among content flows in a network of caches. The authors in [29] analyzed the impact of the initial system state on the selection of the system's steady-state. These works consider that the caches route requests irrespective of the associated traffic costs.…”

Section: Related Workmentioning

confidence: 99%