Smart caching in wireless small cell networks via contextual multi-armed bandits

Müller, Sabrina; Atan, Onur; Schaar, Mihaela van der; Klein, Anja

doi:10.1109/icc.2016.7511570

Cited by 45 publications

(33 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…preferences on their context and supports service differentiation. Compared to our previous work [1], we now take into account context information at a single user level, instead of averaging context information over the currently connected users. This enables more fine-grained learning.…”

Section: Related Workmentioning

confidence: 99%

Context-Aware Proactive Content Caching With Service Differentiation in Wireless Networks

Müller¹,

Atan²,

Schaar³

et al. 2017

IEEE Trans. Wireless Commun.

Self Cite

251

199

View full text Add to dashboard Cite

Content caching in small base stations or wireless infostations is considered to be a suitable approach to improve the efficiency in wireless content delivery. Placing the optimal content into local caches is crucial due to storage limitations, but it requires knowledge about the content popularity distribution, which is often not available in advance. Moreover, local content popularity is subject to fluctuations since mobile users with different interests connect to the caching entity over time. Which content a user prefers may depend on the user's context. In this paper, we propose a novel algorithm for contextaware proactive caching. The algorithm learns context-specific content popularity online by regularly observing context information of connected users, updating the cache content and observing cache hits subsequently. We derive a sublinear regret bound, which characterizes the learning speed and proves that our algorithm converges to the optimal cache content placement strategy in terms of maximizing the number of cache hits. Furthermore, our algorithm supports service differentiation by allowing operators of caching entities to prioritize customer groups. Our numerical results confirm that our algorithm outperforms state-of-the-art algorithms in a real world data set, with an increase in the number of cache hits of at least 14%.

show abstract

Section: Related Workmentioning

confidence: 99%

Context-Aware Proactive Content Caching With Service Differentiation in Wireless Networks

Müller¹,

Atan²,

Schaar³

et al. 2017

IEEE Trans. Wireless Commun.

Self Cite

251

199

View full text Add to dashboard Cite

show abstract

“…Besides, because of different users contributes content popularity, a contextual MAB algorithm [2] is used to learn the content's popularity with considering different users' information. It is an extended work of [11] which aggregated context information, such as user density and request file time. However, above methods all designed for the central environment where server gather all data, which may raise user privacy fears.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning Based Proactive Content Caching in Edge Computing

Min

et al. 2018

2018 IEEE Global Communications Conference (GLOBECOM)

120

View full text Add to dashboard Cite

Content caching is a promising approach in edge computing to cope with the explosive growth of mobile data on 5G networks, where contents are typically placed on local caches for fast and repetitive data access. Due to the capacity limit of caches, it is essential to predict the popularity of files and cache those popular ones. However, the fluctuated popularity of files makes the prediction a highly challenging task. To tackle this challenge, many recent works propose learning based approaches which gather the users' data centrally for training, but they bring a significant issue: users may not trust the central server and thus hesitate to upload their private data. In order to address this issue, we propose a Federated learning based Proactive Content Caching (FPCC) scheme, which does not require to gather users' data centrally for training. The FPCC is based on a hierarchical architecture in which the server aggregates the users' updates using federated averaging, and each user performs training on its local data using hybrid filtering on stacked autoencoders. The experimental results demonstrate that, without gathering user's private data, our scheme still outperforms other learning-based caching algorithms such as m--greedy and Thompson sampling in terms of cache efficiency.

show abstract

“…Such networks offer an important applications area for local content caching by using the SBSs as cache storage units at the edge of the network. In other works, 48,[145][146][147][148][149][150][151][152][153] small cell network proactive caching has been studied. A distributed cache placement problem is recently studied in the work of Shanmugam et al 153 with an aim to reduce the delay in delivering the files to the end user; whereas, in the work of Blasco and Gunduz, 146 a single SBS cache content placement problem was addressed from a reinforcement learning perspective.…”

Section: Impact On System Performancementioning

confidence: 99%

The role of caching in next generation cellular networks: A survey and research outlook

Kabir

Rehman

Gilani

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Mobile applications and social networks tend to enhance the needs for high‐quality content access. To address the expeditious growing demand for data services in 5G cellular networks, it is important to develop distribution techniques and an efficient content caching, aiming to significantly reduce redundant data transmission and, thus, improve the efficiency of the networks. In modern communication systems, caching has emerged as a vital tool for reducing peak data rates. It is anticipated that energy harvesting and self‐powered small base stations are the fundamental part of next‐generation cellular networks. However, uncertainties in energy are the main reason to adopt energy efficient power control schemes to reduce SBS energy consumption and ensure the quality of services for users. Using the edge cooperative caching such as energy efficient design can also be achievable, which reduces the usage of the capacity limited SBSs backhaul and the energy consumption. To support the huge power demand of cellular network, renewable energy harvesting technologies can be leveraged. In addition to this, power supply to the infrastructures is the main challenge to the mobile network operators (MNOs) especially in terms of economic optimum, sustainability, and green energy in developing countries for the growth of cellular networks. Renewable energy–based solutions for MNOs not only reduce the overall carbon dioxide emissions but also provide numerous profits.

show abstract

Smart caching in wireless small cell networks via contextual multi-armed bandits

Cited by 45 publications

References 12 publications

Context-Aware Proactive Content Caching With Service Differentiation in Wireless Networks

Context-Aware Proactive Content Caching With Service Differentiation in Wireless Networks

Federated Learning Based Proactive Content Caching in Edge Computing

The role of caching in next generation cellular networks: A survey and research outlook

Contact Info

Product

Resources

About