Energy Efficient Secure Offloading in NOMA-aided Vehicular Networks Using A3C Learning

High-speed computation resources are provided by mobile edge computing (MEC) to boost various delay-sensitive vehicular applications. However, compared to computing tasks locally, the MEC approach consumes extra energy in the offloading process. In this paper, an asynchronous deep reinforcement learning-based energy-efficient secure offloading (EESO) is proposed to enhance the energy efficiency and security of the vehicular edge computing (VEC) network in the presence of multiple malicious eavesdropper vehicles. To secure the wireless offloading process of the information, a group of jammer vehicles is scheduled to form a NOMA cluster with each user vehicle for providing jamming signals to the eavesdropper vehicles while not interfering with the legitimate user vehicle. We minimize the system energy consumption with the computation delay constraint by jointly optimizing the transmit power, the computation resource allocation, and the selection of jammer vehicles in each NOMA cluster. Then we adopt an asynchronous advantage actor-critic (A3C) learning algorithm to solve the optimization problem. With proper training, the A3C-based EESO scheme can reduce the system energy consumption and improve offloading security.

I. Introduction

With the high development of vehicular networks, vehicular applications generate a large amount of data-hungry and delay-sensitive tasks, including traffic flow prediction and automatic driving. Nowadays, mobile edge computing (MEC) has become a promising technology in the Internet of Vehicle (10 V) [1], [2]. Therefore, multiple vehicles can offload their tasks to MEC servers such as base stations or roadside units. Accordingly, the great potential of MEC has drawn lots of attention [3]. In this field of research, energy consumption is a crucial concern because MEC involves the transmission energy consumption in the offloading process. In [3], the authors propose a reinforcement learning (RL) based scheme to get a low communication overhead in the MEC system.