Handover-Enabled Dynamic Computation Offloading for Vehicular Edge Computing Networks

Maleki, Homa; Başaran, Mehmet; Durak–Ata, Lütfiye

doi:10.1109/tvt.2023.3247889

Cited by 12 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 5G/6G networks, handover decision techniques are critical in identifying when and which cell, a user should be handed over to provide uninterrupted and high-quality communication [115]. While specific techniques for handover decision-making in future networks are still in the development process, here are some common techniques that can be used for algorithmic design in 5G/6G, i.e., the Received signal strength (RSS) [116], Signal-to-interference-plusnoise ratio (SINR) [117], Quality of Service (QoS) [118] and Hybrid Approach based on SINR, QoS requirements for load balancing to determine the most suitable target cell for handover [119].…”

Section: Mobility and Handover In Ai-ran 6gmentioning

confidence: 99%

AI-RAN in 6G Networks: State-of-the-Art and Challenges

Khan,

Schmid

2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

6G is a next-generation cellular communication technology that builds up on existing 5G networks which are currently rolled out worldwide. Through incorporation of artificial intelligence (AI) and machine learning (ML), the core 5G network is advanced into an intelligent 6G network. The 6G Artificial Intelligence Radio Access Network (AI-RAN) is anticipated to offer advanced features like reduced latency, improved bandwidth, data rates and coverage. Furthermore, AI-RAN is expected to support complex use cases such as extreme connectivity, multi-user communications and dynamic spectrum access. This paper provides a detailed survey and thorough assessment of AI-RAN's vision and state-of-the-art challenges. We first present a concise introduction to 6G AI-RAN followed by background information on the current 5G RAN and its challenges that must be overcome to implement 6G AI-RAN. The paper then examines trending research issues in AI-RAN, i.e., challenges related to spectrum allocation, network architecture, and resource management. We discuss the methods to overcome these challenges which include the adoption of advanced machine learning and edge computing technologies to boost the performance of 6G AI-RAN. We conclude by stating open research directions.

show abstract

Section: Mobility and Handover In Ai-ran 6gmentioning

confidence: 99%

AI-RAN in 6G Networks: State-of-the-Art and Challenges

Khan,

Schmid

2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…This framework aims to minimize the energy consumption of roadside units under task latency constraints. Maleki et al [19] Consider energy consumption, transmission delay and processing delay during offloading as offloading costs. A switchable offloading strategy is proposed to improve service quality and user experience.…”

Section: Related Workmentioning

confidence: 99%

Dependency-aware Online Task Offloading based on Deep Reinforcement Learning for IoV

Liu,

Wang,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

The integration of artificial intelligence with vehicle wireless communicationtechnology willing meet the intelligent communication needs of the Internetof Vehicles (IoV), supporting more sophisticated vehicle applications. However,making real-time dependency-aware task offloading decisions is difficult due tothe high mobility of vehicles and the dynamic nature of the network environment.This leads to additional application computation time and energy consumption,increasing the risk of offloading failures for computationally intensive andlatency-sensitive applications. In this paper, an offloading strategy for vehicleapplications that jointly considers latency and energy consumption in the basestation cooperative computing model is proposed. Firstly, we establish a collaborativeoffloading model involving multiple vehicles, multiple base stations,and multiple edge servers. Transferring vehicular applications to the applicationqueue of edge servers and prioritizing them based on their completion deadlines.Secondly, each vehicular application is modeled as a directed acyclic graph(DAG) task with data dependency relationships. Subsequently, we propose atask offloading method based on task dependency awareness in deep reinforcementlearning (DAG-DQN). Tasks are assigned to edge servers at different base stations, and edge servers collaborate to process tasks, minimizing vehicle applicationcompletion time and reducing edge server energy consumption. Finally,simulation results show that compared with the heuristic method, our proposedDAG-DQN method reduces task completion time by 16%, reduces system energyconsumption by 19%, and improves decision-making efficiency by 70%.

show abstract