PPO2: Location Privacy-Oriented Task Offloading to Edge Computing Using Reinforcement Learning for Intelligent Autonomous Transport Systems

AI-empowered 5G/6G networks play a substantial role in taking full advantage of the Internet of Things (IoT) to perform complex computing by offloading tasks to edge services deployed in intelligent transport systems. However, offloading behavior has a certain regularity, and the real-time location of users can easily be inferred by attackers who have historical user data during the data transmission process. To address this problem, a privacy-oriented task offloading method that can resist attacks from privacy attackers with prior knowledge is proposed. First, the local computing model, channel model, and privacy loss model are defined and used to quantify evaluation indicators, such those related to privacy, time, and energy. Among them, privacy loss is formalized as the probability of a successful attack by an attacker with prior knowledge. Second, the process of solving an optimal task offloading decision problem is formalized into a Markov decision process (MDP). Finally, the deep reinforcement learning (DRL) method PPO2 is proposed to solve the planning problem of task offloading with good generalization and convergence speed, where we focus on the location privacy requirement. Experiments show that our method can handle large-scale task offloading and obtain offloading policies with reduced privacy loss, energy consumption and time delays.

I. Introduction

With the development of the Internet of Things (IoT), Internet of Vehicles (IoV), and 5G/6G networks, more complex edge computing scenarios will emerge. In the edge computing environment, devices have the characteristics of limited energy, limited computing resources, and real-time changes in geographic location [1]. Services will face problems such as instability, low quality, and failure. To address these problems and exploit the advantages of V2X (Vehicle to Everything), a large number of studies have focused on computing offloading to reduce time delay, reduce energy consumption, and minimize costs. However, few studies focus on privacy-oriented computing offloading in intelligent autonomous transport systems. During the data transmission process of offloading the service to the edge server, there is a risk of leakage of private data, including the user’s location and sensitive information. For example, complex computing tasks generated by autonomous vehicles can be offloaded to other vehicles or roadside units (RSUs) to improve the computing efficiency in the IoV [2], [3]. However, in this process, the real-time location of the vehicle may be leaked. To avoid this risk and improve the reliability and security of the service, it is necessary to develop a computing offloading method to improve computing performance while protecting user privacy.