A joint optimization scheme of content caching and resource allocation for internet of vehicles in mobile edge computing

Zhang, Mu; Wang, Song; Gao, Qing

doi:10.1186/s13677-020-00182-x

Cited by 20 publications

(7 citation statements)

References 22 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing literature on RA can mainly be categorized into two approaches: 1) centralized and 2) decentralized schemes. To obtain general network information, centralized algorithms would experience a large transmission overhead such that each vehicle would have to transmit interference information and the local channel state to the central controller [14]- [16]. However, it is challenging for these centralized schemes to satisfy various QoS constraints precisely with ultralow end-to-end delay and high reliability.…”

Section: Related Workmentioning

confidence: 99%

Decentralized Resource Allocation-Based Multiagent Deep Learning in Vehicular Network

Mafuta

Maharaj

Alfa

2023

IEEE Systems Journal

View full text Add to dashboard Cite

Resource allocation (RA) has a significant impact on vehicular network performance. With high mobility, RA is more challenging, as the number of vehicles in close proximity changes dynamically in the nonstationary environment. In this article, we propose a multiagent double deep Q-networks scheme to stabilize the system and maximize the sum-capacity of the vehicle-toinfrastructure (V2I) links, while satisfying the reliability and delay constraints for vehicle-to-vehicle (V2V) links. To avoid interference caused by unstable V2V links, a transmission mode selection is considered in the scheme design. In addition, we introduce a binarized weight algorithm to accelerate the deep neural network learning process and, therefore, improve the computational complexity of our scheme. Through extensive simulations and complexity analysis, we demonstrate that the proposed scheme yields excellent performance in terms of the sum-rate and probability rate of V2I and V2V communication modes. We also compare the proposed scheme with binarized weights with other algorithms in terms of accuracy evaluation.

show abstract

Section: Related Workmentioning

confidence: 99%

Decentralized Resource Allocation-Based Multiagent Deep Learning in Vehicular Network

Mafuta

Maharaj

Alfa

2023

IEEE Systems Journal

View full text Add to dashboard Cite

show abstract

“…Moreover, the gains are amplified by the reduction in server load and cache redundancy is achieved. Some research works address the mobility-aware proactive caching in IoV, [16][17][18][19][20]. In the paper [16], authors consider vehicular caching where vehicles are also caching devices and propose a vehicular caching scheme in content-centric networks, developing an optimization model which minimizes the network's energy consumption.…”

Section: Related Workmentioning

confidence: 99%

“…The work in [ 20 ] formulates a joint optimization scheme for content caching and resource allocation for high-speed IoV and mobile edge computing. It considers the bandwidth of vehicle to infrastructure (V2I) and V2V links and the cache storage limit of edge storage and proposes a strategy to minimize the weighted average delay.…”

Section: Background and Related Workmentioning

confidence: 99%

Mobility-Aware Proactive Edge Caching Optimization Scheme in Information-Centric IoV Networks

Musa

Zennaro

Libsie

et al. 2022

Sensors

View full text Add to dashboard Cite

Edge caching is a promising approach to alleviate the burden on the backhaul of network links. It has a significant role in the Internet of Vehicle (IoV) networks performance by providing cached data at the edge and reduce the burden of the core network caused by the number of participating vehicles and data volume. However, due to the limited computing and storage capabilities of edge devices, it is hard to guarantee that all contents are cached and every requirement of the device are satisfied for all users. In this paper, we design an Information-Centric Network (ICN) with mobility-aware proactive caching scheme to provide delay-sensitive services on IoV networks. The real-time status and interaction of vehicles with other vehicles and Roadside Units (RSU) is modeled using a Markov process. Mobility aware proactive edge caching decision that maximize network performance while minimizing transmission delay is applied. Our numerical simulation results show that the proposed scheme outperforms related caching schemes in terms of latency by 20–25% in terms of latency and by 15–23% in cache hits.

show abstract

“…In ref. [ 25 ], the authors present a machine learning-based content pre-caching scheme for V2V and V2I communication. The situation is limited to cache enhancement and cache control which shows that cache content is one of the techniques which places the content toward cache enhancement.…”

Section: Literature Reviewmentioning

confidence: 99%

Towards Intelligent Zone-Based Content Pre-Caching Approach in VANET for Congestion Control

Nazar

Saeed²,

Ali³

et al. 2022

Sensors

View full text Add to dashboard Cite

In vehicular ad hoc networks (VANETs), content pre-caching is a significant technology that improves network performance and lowers network response delay. VANET faces network congestion when multiple requests for the same content are generated. Location-based dependency requirements make the system more congested. Content pre-caching is an existing challenge in VANET; pre-caching involves the content’s early delivery to the requested vehicles to avoid network delays and control network congestion. Early content prediction saves vehicles from accidents and road disasters in urban environments. Periodic data dissemination without considering the state of the road and surrounding vehicles are considered in this research. The content available at a specified time poses considerable challenges in VANET for content delivery. To address these challenges, we propose a machine learning-based, zonal/context-aware-equipped content pre-caching strategy in this research. The proposed model improves content placement and content management in the pre-caching mode for VANET. Content caching is achieved through machine learning, which significantly improves content prediction by pre-caching the content early to the desired vehicles that are part of the zone. In this paper, three algorithms are presented, the first is zone selection using the customized algorithm, the second is the content dissemination algorithm, and the third is the content pre-caching decision algorithm using supervised machine learning that improves the early content prediction accuracy by 99.6%. The cache hit ratio for the proposed technique improves by 13% from the previous techniques. The prediction accuracy of the proposed technique is compared with CCMP, MLCP, and PCZS+PCNS on the number of vehicles from 10 to 150, with an improved average of 16%. Finally, the average delay reduces over time compared with the state-of-the-art techniques of RPSS, MLCP, CCMP, and PCZS+PCNS. Finally, the average delay shows that the proposed method effectively reduces the delay when the number of nodes increases. The proposed solution improves the content delivery request while comparing it with existing techniques. The results show improved pre-caching in VANET to avoid network congestion.

show abstract

A joint optimization scheme of content caching and resource allocation for internet of vehicles in mobile edge computing

Cited by 20 publications

References 22 publications

Decentralized Resource Allocation-Based Multiagent Deep Learning in Vehicular Network

Decentralized Resource Allocation-Based Multiagent Deep Learning in Vehicular Network

Mobility-Aware Proactive Edge Caching Optimization Scheme in Information-Centric IoV Networks

Towards Intelligent Zone-Based Content Pre-Caching Approach in VANET for Congestion Control

Contact Info

Product

Resources

About