Periodic Prediction Based Integrated Solutions for Wireless Communication and Edge Computing in Smart Railway Systems

Abstract

This paper addresses the challenges of wireless communication and intelligence in smart railway system under high-speed mobile environments, particularly the issues of Doppler effect and dynamic variability. Solutions that integrate wireless communication and edge computing is proposed. The system model based on the operational characteristics of high-speed trains is established. By analyzing historical data and employing statistical methods, the probability distribution of high-speed train operation times is studied, revealing the operational patterns across different intervals. On this foundation, an intelligent task allocation model is proposed, which optimizes the deployment of edge servers and task allocation strategies to minimize task processing costs while ensuring the stability of communication links. To address the Doppler effect and selective channel enhancement issues in high-speed mobile environments, channel prediction with periodic information is used to reduce interference and ensure the reliability of data transmission. Furthermore, intelligent scheduling system based on edge computing with predictive models is established, supporting advanced scheduling and optimizes train timetables. The algorithm is based on established scheduling rules, effectively managing the high-speed railway system and improving system efficiency. Compared with existing scheduling algorithms, the proposed method demonstrates significant advantages in reducing signal distortion, enhancing signal reliability, and optimizing resource utilization and costs.