Community Detection and Attention-Weighted Federated Learning Based Proactive Edge Caching for D2D-Assisted Wireless Networks

Li, Dongyang; Zhang, Haixia; Li, Tiantian; Ding, Hui; Yuan, Dongfeng

doi:10.1109/twc.2023.3249756

Cited by 8 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [15], [16], the authors design joint caching and resource allocation strategies to minimize energy consumption. The authors in [17] study proactive edge caching problem for device-to-device (D2D)-assisted wireless networks and present a bidirectional LSTM (BiLSTM)-based content popularity prediction algorithm.…”

Section: A Literature Reviewmentioning

confidence: 99%

“…In (17), D q j denotes the queuing delay of UEs at UAV j . In this work, we assume that the number of content requests arriving at the UAVs follows the Poisson distribution and the request processing time of the UAVs follows exponential distribution, then we model the content request processing at the UAVs as the M/M/1 queuing model [39].…”

Section: A Objective Function Formulationmentioning

confidence: 99%

See 1 more Smart Citation

Content Fetching Delay Optimization-Based Caching and Resource Allocation for UAV-Enabled Networks

Bayessa,

Chai,

Liang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In this work, we investigate content caching problem in unmanned aerial vehicle (UAV)enabled networks where UAVs are allowed to store user requested content so as to enhance the content transmission performance of users. To predict user content request, we propose a bidirectional long shortterm memory-based algorithm. Then, the content transmission delay of users is examined and the UAV deployment, content caching and resource allocation problem is formulated as an overall content fetching delay minimization problem. As the formulated problem is difficult to solve, we transform it into two subproblems which are solved iteratively. To tackle the UAV deployment and content caching subproblem, we first design a modified K-means-based clustering scheme and then propose a UAV deployment strategy by using quadratic transformation. To solve subcarrier and power allocation subproblem, we apply Lagrangian dual method to determine power allocation strategy and propose a Kuhn-Munkres algorithm-based subcarrier allocation strategy. Simulation results show that our approach achieves approximately 11.1% lower overall content fetching delay compared to the existing algorithm.INDEX TERMS Unmanned aerial vehicles, user clustering, UAV deployment, content caching, resource allocation.

show abstract

Section: A Literature Reviewmentioning

confidence: 99%

Section: A Objective Function Formulationmentioning

confidence: 99%

Content Fetching Delay Optimization-Based Caching and Resource Allocation for UAV-Enabled Networks

Bayessa,

Chai,

Liang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…And when popular services are repeatedly requested in a short period of time, 6G cloud server backhaul is facing tremendous pressure [4][5][6]. In order to fulfill the application requirements and reduce the pressure on the cloud server, the edge caching technology allows for service content caching on edge servers, enabling users to retrieve content from these edge servers to meet their repetitive requests, so as to cope with the swift expansion of 6G wireless service load and significantly reduce the transmission load of 6G cloud server [7][8][9]. Therefore, the research of edge caching technology is of paramount importance for 6G.…”

Section: Introductionmentioning

confidence: 99%

Epidemic dynamics edge caching strategy for 6G networks

Wang,

Zhang,

Zhang

2024

Front. Phys.

View full text Add to dashboard Cite

By caching popular content on edge servers closer to users to respond to users’ content requests in 6G networks, the transmission load of backhaul links can be reduced. However, the time-varying characteristics of content prevalence leads to the issue that the cache content may not match the user’s needs, resulting in a decrease in cache success ratio. To solve these issues, we proposed a cache distribution strategy based on epidemic dynamics (CDSED) for 6G edge network. First, a 6G edge caching content model (6G ECCM) is constructed to establish the process of cache content propagation among users as an infectious disease propagation process, analyze the distribution of users’ interest in cache content and obtain the cache content state probability prediction equation, and use the cache content state probability prediction equation to predict the cache content prevalence. Second, based on the predicted prevalence results, a prevalence predictive genetic-annealing cache content algorithm (PGAC) is proposed with the optimization objective of maximizing the cache success ratio. The algorithm designs the selection function of the traditional genetic algorithm as a simulated annealing selection function based on the cache content success ratio, which avoids the defect of the genetic algorithm that converges to the locally optimum cache strategy too early and enhances the cache success ratio. Finally, the optimum cache content decision is solved by iterative alternation. Simulation results demonstrate that CDSED strategy can enhance cache success ratio than the LRU strategy, the LFU strategy, and the MPC strategy.

show abstract

Improving cache-enabled D2D communications using actor–critic networks over licensed and unlicensed spectrum

Sheraz,

Chuah,

Sultan

et al. 2024

Journal of King Saud University - Computer and Information Scie

View full text Add to dashboard Cite

Community Detection and Attention-Weighted Federated Learning Based Proactive Edge Caching for D2D-Assisted Wireless Networks

Cited by 8 publications

References 43 publications

Content Fetching Delay Optimization-Based Caching and Resource Allocation for UAV-Enabled Networks

Content Fetching Delay Optimization-Based Caching and Resource Allocation for UAV-Enabled Networks

Epidemic dynamics edge caching strategy for 6G networks

Improving cache-enabled D2D communications using actor–critic networks over licensed and unlicensed spectrum

Contact Info

Product

Resources

About