Autonomous Resource Slicing for Virtualized Vehicular Networks With D2D Communications Based on Deep Reinforcement Learning

Boateng, Gordon Owusu; Ayepah-Mensah, Daniel; Liu, Guisong; Jiang, Wei

doi:10.1109/jsyst.2020.2982857

Cited by 53 publications

(17 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sun et al [68] proposed a novel slicing framework and optimization solution based on dynamic reinforcement learning for efficient resource allocation in virtual networks with D2D-based V2V communication. The goal is to balance resource utilization and QOS satisfaction across multiple slices.…”

Section: Deep Reinforcement Learning Algorithm Based On Value Functionmentioning

confidence: 99%

Deep Learning for Video Application in Cooperative Vehicle-Infrastructure System: A Comprehensive Survey

Dai

2022

Applied Sciences

View full text Add to dashboard Cite

Video application is a research hotspot in cooperative vehicle-infrastructure systems (CVIS) which is greatly related to traffic safety and the quality of user experience. Dealing with large datasets of feedback from complex environments is a challenge when using traditional video application approaches. However, the in-depth structure of deep learning has the ability to deal with high-dimensional data sets, which shows better performance in video application problems. Therefore, the research value and significance of video applications over CVIS can be better reflected through deep learning. Firstly, the research status of traditional video application methods and deep learning methods over CVIS were introduced; the existing video application methods based on deep learning were classified according to generative and discriminative deep architecture. Then, we summarized the main methods of deep learning and deep reinforcement learning algorithms for video applications over CVIS, and made a comparative study of their performances. Finally, the challenges and development trends of deep learning in the field were explored and discussed.

show abstract

Section: Deep Reinforcement Learning Algorithm Based On Value Functionmentioning

confidence: 99%

Deep Learning for Video Application in Cooperative Vehicle-Infrastructure System: A Comprehensive Survey

Dai

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The research work on using D2D with network slicing concept in 5G cellular networks has not been explicitly explored to date. Previously, work has been done using SDN and virtualized networks which is still in its infancy [143]. For virtualized networks, the SDN controller or slice controller is responsible to direct the D2D connection for a successful session.…”

Section: F Research Work In D2d With Nsmentioning

confidence: 99%

“…Further, [139] proved better capacity and optimizing the sum rate when D2D users are related to multiple operators. [143] studies the effect of resource aggregation in a virtualized common pool for D2D receivers and transmitters so that efficient resources can be allocated for available for D2D systems. Table.…”

Section: F Research Work In D2d With Nsmentioning

confidence: 99%

Integration of D2D, Network Slicing, and MEC in 5G Cellular Networks: Survey and Challenges

et al. 2021

View full text Add to dashboard Cite

With the tremendous demand for connectivity anywhere and anytime, existing network architectures should be modified. To cope with the challenges that arise due to the increasing flood of devices/users and a diverse range of application requirements, new technologies and concepts must be integrated to enable their benefits. Service providers and business companies are looking for new areas of research to enhance overall system performance. This paper gives a detailed survey about the recent 5G technologies, the solutions they provide, and the effect caused by their addition to current cellular networks. It is based on the three most important 5G concepts: Device to Device (D2D), Network Slicing (NS), and Mobile Edge Computing (MEC). This study proposes to design the future 5G networks by the integration of all three technologies. It is believed that spectrum efficiency, energy efficiency, and overall throughput will be greatly improved by using D2D. The system delay and computational load will be reduced as tasks will be handled by edge routers located at the base stations. Thus offloading the core network and the system capital expenses and operational expenses will be reduced significantly by slicing the network.

show abstract

“…This approach does not follow the ITU use cases for 5G. Sun et al [24] propose an RA algorithm for vehicular networks based on DRL to provide QoS inefficiently in which the DRL-agent adjusts the [3] RL (Q-Learning) Provider profit [6] Queuing theory Utility rate, admission rate, request waiting time [7] Big Data Analytics Provider profit [8] Heuristic algorithm QoE, resource utilization [9] Heuristic algorithm System resource utilization [10] Heuristic algorithm Provider revenue [11] Knapsack problem Monetization ratio [12] RL (Q-Learning) Provider revenue [13] DRL (DQN) Provider revenue [15] Heuristic algorithm Acceptance ratio and Execution time [16] Heuristic algorithm Acceptance ratio, provider revenue [17] Queuing Theory Running time [18] Complex Network Theory Resource efficiency, acceptance ratio, execution time [19] Integer Programming CPU Utilization [20] Alternating Direction Method of Multipliers Latency [21] Artificial Neural Networks Latency [22] DRL (DQN) Spectrum efficiency and QoE [23] DRL (DQN) Resource Utilization [24] DRL (DQN) Resource Utilization and Satisfaction ratio [25] DRL (DDPG) Provider revenue SARA/DSARA Q-learning and DQN Provider profit, resource utilization, acceptance ratio allocated resources for a slice as a function of the demand. Zhang et al [25] perform slicing in data center networks by using a DRL-agent.…”

Section: B Resource Allocation In 5g Network Slicingmentioning

confidence: 99%

Admission Control for 5G Network Slicing based on (Deep) Reinforcement Learning

Jácome¹,

Rendón²,

Fonseca³

2021

Preprint

View full text Add to dashboard Cite

Network Slicing is a promising technology for providing customized logical and virtualized networks for the industry’s vertical segments.This paper proposes SARA and DSARA for the performance of admission control and resource allocation for network slice requests of eMBB, URLLC, and MIoT type in the 5G core network. SARA introduced a Q-learning based algorithm and DSARA a DQN-based algorithm to select the most profitable requests from a set that arrived in given time windows. These algorithms are model-free, meaning they do not make assumptions about the substrate network as do optimization based approaches.

show abstract

Autonomous Resource Slicing for Virtualized Vehicular Networks With D2D Communications Based on Deep Reinforcement Learning

Cited by 53 publications

References 33 publications

Deep Learning for Video Application in Cooperative Vehicle-Infrastructure System: A Comprehensive Survey

Deep Learning for Video Application in Cooperative Vehicle-Infrastructure System: A Comprehensive Survey

Integration of D2D, Network Slicing, and MEC in 5G Cellular Networks: Survey and Challenges

Admission Control for 5G Network Slicing based on (Deep) Reinforcement Learning

Contact Info

Product

Resources

About