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 ...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%.展开更多
文摘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%.
