http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
DRL-based Resource Management in Network Slicing for Vehicular Applications
Tairq Muhammad Ashar,말릭무함마드사드,Khan Muhammad Toaha Raza,Seo Junho,Kim Dongkyun 한국통신학회 2023 ICT Express Vol.9 No.6
Network Slicing (NS) was proposed as a viable solution in Release 15 of Third Generation Partnership Project (3GPP) to allocate the limited resources among different service types for improving their Quality-of-Service (QoS). However, the advanced vehicular applications such as autonomous driving, platooning, remote driving, etc. have stringent QoS demands and the standard NS architecture is not sustainable for these services. Therefore, we propose a solution compatible with the standard 3GPP NS architecture that implements an Actor-Critic based Deep Reinforcement Learning (DRL) algorithm in the Network Slice Subnet Management Function (NSSMF). The algorithm allocates and manages the limited resources among different slices based on their real-time traffic demands. We generate real-time traffic for each service type and train the algorithm to improve the QoS of each service type in the network. The proposed method is evaluated for the training performance of the proposed algorithm as well as the Service level agreement Satisfaction Ratio (SSR) of each slice. The results exhibit that the proposed method not only improves SSR of each slice, but also performs well in case of increased node density in the network.
A Comparative Analysis on Machine Learning based Intelligent Forwarding Schemes in VNDN
Ayesha Siddiqa,Muhammad Toaha Raza Khan,Md.Mahmudul Islam,Muhammad Ashar Tariq,Malik Muhammad Saad,Dongkyun Kim 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Vehicular named data networks (VNDN) schemes use predefined routing information for communication rather than dynamic network information. Therefore, the researchers encourage to integrate the machine learning (ML) algorithms in VNDN for intelligent communication. In this paper, we have discussed the machine learning (ML) based vehicular named data network (VNDN) schemes for intelligent packet forwarding in highly dynamic topology. We have discussed the intelligent ML-VNDN forwarding schemes which take dynamic network information for interest/data forwarding to increase communication efficiency. Moreover, this article explains the comparative analysis between naïve VNDN schemes and ML-based NDN schemes, also discussed their future directions.
Reinforcement Learning-based UAVs Trajectory Control to assist VANETs
Md. Mahmudul Islam,Malik Muhammad Saad,Ru Yang,Muhammad Toaha Raza Khan,Junho Seo(서준호),Dongkyun Kim(김동균) 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
Intelligent transportation system (ITS) provides an efficient solution to road safety traffic. Enabling ITS requires connectivity among vehicles. However, dynamic vehicular net-works cause link disruption among vehicles. To overcome this, unmanned aerial vehicles (UAVs) are deployed to provide connectivity between vehicles that are beyond the communication range. UAVs act as a relay node in providing connectivity among vehicles. We propose multi-agent reinforcement learning to control the trajectory for the deployment of UAVs. Each UAV acts as an agent to find the optimal position, from where it can provide coverage to the maximum number of vehicles. The proposed scheme is expected to increase the packet delivery ratio (PDR) and throughput while reducing the end-to-end delay.