Scholarlink

With the increasing reliance on Real-Time Systems (RTS) on multiprocessor architectures to meet stringent timing constraints, there has been significant interest in leveraging machine learning to enhance schedulability analysis. This study proposes a hybrid model that utilizes Decision Tree (DT) and Tabu Search (TS) algorithms to evaluate the schedulability of real-time tasks across multiprocessor platforms. The approach aims to improve accuracy, minimize computational overhead, and tackle the complexities of software and hardware exploration. We validated the model with real-world data from diverse areas such as automotive control and robotics, demonstrating its effectiveness in real-time scheduling scenarios.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Energy Efficiency and Schedulability Examination for Real-Time Multiprocessor Systems via Employing Machine Learning Techniques

  • 章节

  • 发表日期：

    2025年

查看全文
  • Walid Karamti

摘要

With the increasing reliance on Real-Time Systems (RTS) on multiprocessor architectures to meet stringent timing constraints, there has been significant interest in leveraging machine learning to enhance schedulability analysis. This study proposes a hybrid model that utilizes Decision Tree (DT) and Tabu Search (TS) algorithms to evaluate the schedulability of real-time tasks across multiprocessor platforms. The approach aims to improve accuracy, minimize computational overhead, and tackle the complexities of software and hardware exploration. We validated the model with real-world data from diverse areas such as automotive control and robotics, demonstrating its effectiveness in real-time scheduling scenarios.