Joint spectrum allocation and power control in vehicular communications based on dueling double DQN

Ren, Jie; Chai, Zhengyi; Chen, Zhipeng

doi:10.1016/j.vehcom.2022.100543

Cited by 7 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ren et al, 94 the authors propose a distributed V2V spectrum allocation and power control scheme based on the DRL framework for RA in vehicular communications. The proposed algorithm uses DDQN with dueling architecture to find optimal RA while meeting strict latency constraints on the V2V link, improving the network capacity of the V2I link.…”

Section: Drl‐based Sac In C‐ranmentioning

confidence: 99%

Slice admission control in 5G cloud radio access network using deep reinforcement learning: A survey

Khani,

Jamali,

Sohrabi

et al. 2024

Int J Communication

View full text Add to dashboard Cite

SummaryThe emergence of 5G networks has increased the demand for network resources, making efficient resource management crucial. Slice admission control (SAC) is a process that governs the creation and allocation of virtualized network environments, known as “network slices,” which can be tailored to meet specific user requirements. However, traditional SAC methods face dynamic and heterogeneous challenges in wireless networks, especially in cloud radio access networks (C‐RANs). To address this issue, machine learning (ML) techniques, particularly deep reinforcement learning (DRL), have been proposed as powerful tools for optimizing SAC. DRL‐based approaches enable SAC systems to learn from previous interactions with the network environment and dynamically adapt to changing network conditions. This review article comprehensively explains the current state‐of‐the‐art DRL‐based SAC, focusing on C‐RANs. The article identifies key challenges and future research directions and highlights the potential benefits of using DRL for SAC, including improved network performance and efficiency. However, deploying these systems in real‐world scenarios presents several challenges and trade‐offs that need to be carefully considered. Further research and development are required to address these challenges and ensure the successful deployment of DRL‐based SAC systems in wireless networks.

show abstract

Section: Drl‐based Sac In C‐ranmentioning

confidence: 99%

Slice admission control in 5G cloud radio access network using deep reinforcement learning: A survey

Khani,

Jamali,

Sohrabi

et al. 2024

Int J Communication

View full text Add to dashboard Cite

show abstract

“…(2023b) forwarded a dueling DQN framework with prioritized experience replay (PER) function to plan the optimal trajectory for UAVs. Ren et al. (2022) designed dueling DQN and double DQN framework for spectrum access and power control respectively to improve the capacity of V2I links while satisfying the V2V link delay constraints in vehicular networks.…”

Section: Introductionmentioning

confidence: 99%

“…Zhao et al (2023b) forwarded a dueling DQN framework with prioritized experience replay (PER) function to plan the optimal trajectory for UAVs. Ren et al (2022) designed dueling DQN and double DQN framework for spectrum access and power control respectively to improve the capacity of V2I links while satisfying the V2V link delay constraints in vehicular networks. Li et al (2022) constructed a dueling double deep Q-network (D3QN) for spectrum access and power control for V2V link to maximize the cellular link transmission rate and meet the reliability and delay requirements of V2V communication.…”

Section: Introductionmentioning

confidence: 99%

An LSTM-based hybrid proximal policy optimization spectrum access algorithm in vehicular network

Kang,

Chen,

Wang

et al. 2024

IJICC

View full text Add to dashboard Cite

PurposeIn order to meet the different quality of service (QoS) requirements of vehicle-to-infrastructure (V2I) and multiple vehicle-to-vehicle (V2V) links in vehicle networks, an efficient V2V spectrum access mechanism is proposed in this paper.Design/methodology/approachA long-short-term-memory-based multi-agent hybrid proximal policy optimization (LSTM-H-PPO) algorithm is proposed, through which the distributed spectrum access and continuous power control of V2V link are realized.FindingsSimulation results show that compared with the baseline algorithm, the proposed algorithm has significant advantages in terms of total system capacity, payload delivery success rate of V2V link and convergence speed.Originality/valueThe LSTM layer uses the time sequence information to estimate the accurate system state, which ensures the choice of V2V spectrum access based on local observation effective. The hybrid PPO framework shares training parameters among agents which speeds up the entire training process. The proposed algorithm adopts the mode of centralized training and distributed execution, so that the agent can achieve the optimal spectrum access based on local observation information with less signaling overhead.

show abstract

Anti-jamming transmission in softwarization UAV network: a federated deep reinforcement learning approach

Li,

Lv,

Zhang

et al. 2023

Wireless Netw

View full text Add to dashboard Cite

Joint spectrum allocation and power control in vehicular communications based on dueling double DQN

Cited by 7 publications

References 24 publications

Slice admission control in 5G cloud radio access network using deep reinforcement learning: A survey

Slice admission control in 5G cloud radio access network using deep reinforcement learning: A survey

An LSTM-based hybrid proximal policy optimization spectrum access algorithm in vehicular network

Anti-jamming transmission in softwarization UAV network: a federated deep reinforcement learning approach

Contact Info

Product

Resources

About