Machine-Learning-Based Efficient and Secure RSU Placement Mechanism for Software-Defined-IoV

The massive increase in computing and network capabilities has resulted a paradigm shift from vehicular networks to the Internet of Vehicles (IoV). Owing dynamic heterogeneous nature IoV, it requires efficient resource management using smart technologies, such as software-defined (SDN), machine learning (ML), so on. Roadside units (RSUs) software-defined-IoV (SD-IoV) are responsible for efficiency offer several safety functions. However, is not viable deploy enough RSUs, also existing RSU placement lacks universal coverage within region. Furthermore, any disruption performance or security impacts activities severely. Thus, this work aims improve through optimal enhance with malicious IoV detection algorithm an SD-IoV network. Therefore, memetic-based (M-RSU) proposed reduce communication delay area among devices optimum deployment. Besides M-RSU algorithm, proposes distributed ML (DML)-based intrusion system (IDS) that prevents disastrous failures. simulation results show reduces transmission delay. DML-based IDS detects accuracy 89.82% compared traditional algorithms.