Caching With Finite Buffer and Request Delay Information: A Markov Decision Process Approach

Hui, Haiming; Chen, Wei; Wang, Li

doi:10.1109/twc.2020.2989513

Cited by 11 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A memory-efficient eviction policy for edge caching is presented in [21] to increase the storage efficiency at BSs. In addition, when the cache memory is full, less popular files can be replaced newly pushed ones [23,24]. Moreover, when a user is experiencing a poor channel condition or the spectrum is crowded, content placement, and memory update are ineffective in terms of transmission costs.…”

Section: Memory Cost To Be Paid For Cachingmentioning

confidence: 99%

See 1 more Smart Citation

Wireless Caching: Making Radio Access Networks More than Bit-Pipelines

Chen

Poor

2021

Network

Self Cite

View full text Add to dashboard Cite

Caching has attracted much attention recently because it holds the promise of scaling the service capability of radio access networks (RANs). We envision that caching will ultimately make next-generation RANs more than bit-pipelines and emerge as a multi-disciplinary area via the union with communications, pricing, recommendation, compression, and computation units. By summarizing cutting-edge caching policies, we trace a common root of their gains to the prolonged transmission time, which is then traded for higher spectral or energy efficiency. To realize caching, the physical layer and higher layers have to function together, with the aid of prediction and memory units, which substantially broadens the concept of cross-layer design to a multi-unit collaboration methodology. We revisit caching from a generalized cross-layer perspective, with a focus on its emerging opportunities, challenges, and theoretical performance limits. To motivate the application and evolution of caching, we conceive a hierarchical pricing infrastructure that provides incentives to network operators and users. To make RANs even more proactive, we design caching and recommendation jointly, showing a user what it might be interested in and what has been done for it. Furthermore, the user-specific demand prediction motivates edge compression and proactive MEC as new applications. The beyond-bit-pipeline RAN is a paradigm shift that brings with it many cross-disciplinary research opportunities.

show abstract

Section: Memory Cost To Be Paid For Cachingmentioning

confidence: 99%

“…Second, the hit ratio can be increased by dropping less popular items when the memory is full. This makes the eviction policy more complicated [24]. Finally, the joint scheduling of memories and wireless links generalizes the concept of cross-layer design by involving both the communication and memory units.…”

Section: Memory Costsmentioning

confidence: 99%