A Machine-Learning Based Time Constrained Resource Allocation Scheme for Vehicular Fog Computing

• 作 者: Xiaosha Chen Supeng Leng Ke Zhang Kai Xiong
• 机 构: School of Information and Communication Engineering, University of Electronic Science and Technology
• 出 处: 中国通信（英文版）
• 发表日期: 2019年11期
• 关键词: deep reinforcement learning information-centric networking intelligent transport

Through integrating advanced com-munication and data processing technologies into smart vehicles and roadside infrastruc-tures, the Intelligent Transportation System (ITS) has evolved as a promising paradigm for improving safety, efficiency of the trans-portation system. However, the strict delay requirement of the safety-related applications is still a great challenge for the ITS, especially in dense traffic environment. In this paper, we introduce the metric called Perception-Reac-tion Time (PRT), which reflects the time con-sumption of safety-related applications and is closely related to road efficiency and security. With the integration of the incorporating in-formation-centric networking technology and the fog virtualization approach, we propose a novel fog resource scheduling mechanism to minimize the PRT. Furthermore, we adopt a deep reinforcement leing approach to design an on-line optimal resource allocation scheme. Numerical results demonstrate that our proposed schemes is able to reduce about 70% of the RPT compared with the traditional approach.