Dual time scale resource allocation for RAN slicing in software-defined oriented polymorphic IoV

Abstract

To effectively meet the differentiated quality of service (QoS) requirements of various vehicular applications, a dual time scale resource allocation algorithm for radio access network (RAN) slicing in software-defined polymorphic Internet of vehicles (IoV) was proposed.Considering the constraints of the minimum rate requirement of enhanced mobile broadband (eMBB) slice users, vehicle-to-vehicle (V2V) link reliability, the maximum power of nodes, the maximum number of RBs, a joint optimization problem of caching, spectrum, power allocation was formulated, with the aim of minimizing the average delay of ultra-reliable and low-latency communication (URLLC) slice users.By using the Hungarian algorithm, linear integer programming method and the double deep Q-Learning network (DDQN) algorithm, the original NP-hard problem was solved in dual time scales.The simulation results show that the proposed algorithm is superior to the traditional algorithm in ensuring the QoS requirements of different slice users and improving the spectrum utilization.

Keywords

• software-defined polymorphic
• IoV
• RAN slicing
• dual time scale
• resource allocation