Socially-Aware Caching in Wireless Networks With Random D2D Communications

Doan, Khai Nguyen; Nguyen, Thang Van; Shin, Hyundong; Quek, Tony Q. S.

doi:10.1109/access.2019.2914693

Cited by 15 publications

(7 citation statements)

References 42 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the proposed work has the ability to predict the popularity of unpublished videos without historical information using supervised learning. The authors extend their work in [137] for socially-aware caching where socialawareness is measured as the frequency of D2D connections.…”

Section: State-of-the-art: Machine Learning Based Cachingmentioning

confidence: 99%

See 1 more Smart Citation

Applying Machine Learning Techniques for Caching in Edge Networks: A Comprehensive Survey

Shuja,

Bilal,

Alasmary

et al. 2020

Preprint

View full text Add to dashboard Cite

Edge networks provide access to a group of proximate users who may have similar content interests. Caching popular content at the edge networks leads to lower latencies while reducing the load on backhaul and core networks with the emergence of high-speed 5G networks. Edge networks are complex and dynamic. User mobility, preferences, and content popularity are the dominant dynamic features of the edge networks. Temporal and social features of content, such as the number of views and likes are applied to estimate the popularity of content from a global perspective. However, such estimates may not be mapped to an edge network with particular social and geographic characteristics. In edge networks, machine learning techniques can be applied to predict content popularity based on user preferences, user mobility based on user location history, cluster users based on similar content interests, and optimize cache placement and replacement strategies provided a set of constraints and predictions about the state of the network. These applications of machine learning can help identify relevant content for an edge network to lower latencies and increase cache hits. This article surveys the application of machine learning techniques for caching content in edge networks. We survey recent state-of-the-art literature and formulate a comprehensive taxonomy based on (a) machine learning technique (application and objective), (b) caching strategy (policy, location, and objective), and edge network (type and delivery strategy). We further survey supporting concepts for optimal edge caching decisions that require the application of machine learning. These supporting concepts are social-awareness, popularity prediction, and community detection in edge networks. A comparative analysis of the state-of-the-art literature is presented with respect to the parameters identified in the taxonomy. Moreover, we debate research challenges and future directions for optimal caching decisions and the application of machine learning towards caching in edge networks.

show abstract

Section: State-of-the-art: Machine Learning Based Cachingmentioning

confidence: 99%

“…Some of the researchers ignore user mobility [137] while others model it as Poisson point process (PPP) [127], [116], random walk model [161], [128], [159], or as Markov process [46]. Bastug et al [140] consider the location of Cache enabled BSs distributed as PPP.…”

Section: Techniquesmentioning

confidence: 99%

Applying Machine Learning Techniques for Caching in Edge Networks: A Comprehensive Survey

Shuja,

Bilal,

Alasmary

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…D2D communication has been employed in several studies for computation offloading to other nearby UEs (while not utilizing any MEC resources), e.g., [109]- [115]. Also, accessing caches at nearby UEs (while not utilizing MEC caches) has been considered in prior studies, e.g., [116]- [123], whereby specifically video file caching at other UEs has been considered in [124], [125].…”

Section: Device-to-device (D2d) Communicationmentioning

confidence: 99%

Device-Enhanced MEC: Multi-Access Edge Computing (MEC) Aided by End Device Computation and Caching: A Survey

et al. 2019

View full text Add to dashboard Cite

Multi-access edge computing (MEC) has recently been proposed to aid mobile end devices in providing compute-and data-intensive services with low latency. Growing service demands by the end devices may overwhelm MEC installations, while cost constraints limit the increases of the installed MEC computing and data storage capacities. At the same time, the ever increasing computation capabilities and storage capacities of mobile end devices are valuable resources that can be utilized to enhance the MEC. This article comprehensively surveys the topic area of device-enhanced MEC, i.e., mechanisms that jointly utilize the resources of the community of end devices and the installed MEC to provide services to end devices. We classify the device-enhanced MEC mechanisms into mechanisms for computation offloading and mechanisms for caching. We further subclassify the offloading and caching mechanisms according to the targeted performance goals, which include throughput maximization, latency minimization, energy conservation, utility maximization, and enhanced security. We identify the main limitations of the existing device-enhanced MEC mechanisms and outline future research directions. INDEX TERMS Caching, computation offloading, device-to-device (D2D) communication, mobile edge computing (MEC). I. INTRODUCTION A. MOTIVATION

show abstract

“…The user status mainly considers the number of active users, D2D clusters, and the D2D users. The comparison of resource reuse includes no-reuse scheme, random scheme [29], heuristic algorithm [30], and the Hungarian algorithm proposed in this paper. The key parameters of the simulation are shown in Table 3.…”

Section: Parameter Settingsmentioning

confidence: 99%

Emergency Communications Based on Throughput-Aware D2D Multicasting in 5G Public Safety Networks

Yin

Feng

et al. 2020

Sensors

View full text Add to dashboard Cite

Emergency communications need to meet the developing demand of equipment and the complex scenarios of network in public safety networks (PSNs). Heterogeneous Cloud Radio Access Network (H-CRAN), an important technology of the 5th generation wireless systems (5G), plays an important role in PSN. H-CRAN has the features of resource sharing and centralized allocation which can make up for resource shortage in emergency communications. Therefore, an emergency communications strategy based on Device-to-device (D2D) multicast is proposed to make PSN more flexible and rapid. Nearby users can communicate directly without a base station through D2D. This strategy may guarantee high speed data transmission and stable continuous real-time communications. It is divided into three steps. Firstly, according to the distance between users, the alternative cluster head is divided. Secondly, two kinds of cluster head user selection schemes are developed. One is based on terminal power and the other is based on the number of extended users. Last but not least, the Hungarian Algorithm based on throughput-aware is used to channel multiplexing. The numerical results show that the proposed scheme can effectively extend the coverage of PSN and optimize the utilization of resources.

show abstract

Socially-Aware Caching in Wireless Networks With Random D2D Communications

Cited by 15 publications

References 42 publications

Applying Machine Learning Techniques for Caching in Edge Networks: A Comprehensive Survey

Applying Machine Learning Techniques for Caching in Edge Networks: A Comprehensive Survey

Device-Enhanced MEC: Multi-Access Edge Computing (MEC) Aided by End Device Computation and Caching: A Survey

Emergency Communications Based on Throughput-Aware D2D Multicasting in 5G Public Safety Networks

Contact Info

Product

Resources

About