Digital-Twin Enabled Time Ahead Resource Allocation for Integrated Fiber-Wireless Connected Vehicular Network  

作　　者：Akshita Gupta Saurabh Jaiswal Martin Maier Vivek Ashok Bohara Anand Srivastava 

机构地区：[1]Wirocomm Research Group,Department of Electronics&Communication Engineering,Indraprastha Institute of Information Technology Delhi(IIITD),New Delhi 110020,India [2]Department of Computer Science&Applied Mathematics,Indraprastha Institute of Information Technology Delhi(IIITD),New Delhi 110020,India [3]Optical Zeitgeist Laboratory,Institute National de la Recherche Scientifique,Montreal H5A 1K6,Canada

出　　处：《Journal of Communications and Information Networks》2024年第3期296-308,共13页通信与信息网络学报（英文）

摘　　要：The digital twin(DT)is envisaged as a catalyst for pioneering ecosystems of service provision within an immersive environment born from the convergence of virtual and physical realms.Specifically,DT could enhance the performance of edge-intelligent connected vehicular networks by allocating network resources efficiently based on the key performance indicators(KPIs)of vehicular data traffic.Consequently,this work addresses the key challenge of computation and spectrum resource allocation for vehicular networks.To allocate the optimal resource allocation,we subdivided the problem into:traffic classification,collective learning,and resource allocation scheme.In order to do so,this paper concentrates on two crucial vehicular applications:brake application and lane-change application.We utilize a random forest model to collectively learn vehicular data traffic in the upcoming time slot.Thereafter,a time-ahead resource allocation algorithm is proposed to improve the quality of service(QoS)by intelligently offloading vehicular data traffic to a DT-based integrated fiber-wireless(Fi-Wi)connected vehicular network.We evaluate the performance of the resource allocation strategy in terms of resources required by the network alongside the packet loss rate.It was observed that there was a 44.74%increase in cost as the total computation resources increased from F=50 to 100 GHz,whereas the PLR of the network decreased by 71.43%.

关 键 词：connected vehicles digital twin edgeintelligence fiber-wireless machine learning resource allocation 

分 类 号：TN92[电子电信—通信与信息系统]