A Prediction Method of CAN Data Cache Switching for Autonomous Mobility

DOI

Bibliographic Information

Other Title
  • 自動運転車のためのCANデータキャッシュ切り替え予測方式

Abstract

Interest has recently been growing in collecting CAN data from autonomous vehicles in a Cyber-Physical System to achieve advanced self-driving. In this paper, I propose a prediction method of CAN data cache switching for CAN data collection infrastructure using MEC (Multi-access Edge Computing). The proposed method maximizes compression efficiency and QoE by predicting the mobility pattern of an autonomous vehicle using a machine learning model and replacing the CAN data cache on the optimal MEC server in advance. As a result of simulation evaluation, the proposed method can predict the optimal MEC server with 89% accuracy and improve the cache hit ratio by 20%.

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top