Scholarlink

<p>Optimizing the scheduling of Automated Guided Vehicles (AGVs) is a critical task in the context of smart manufacturing, particularly in Industry 4.0, where operational efficiency, sustainability, and adaptability are key drivers of innovation. This paper introduces an innovative scheduling model incorporating real-time AGV battery status as a key parameter, using a machine learning algorithm to predict energy consumption and optimize task allocation accordingly. The primary objective is to extend AGV battery life, reduce energy consumption, and contribute to environmental sustainability, all while maintaining high operational efficiency. In addition to the scheduling algorithm, we present a comprehensive application framework designed to integrate this optimization model into real-world factory environments. This architecture leverages cloud-edge computing to process real-time data from AGVs, enabling dynamic scheduling adjustments and seamless execution of tasks. The proposed approach has been experimentally validated, demonstrating improvements in energy efficiency when compared to a conventional AGV scheduling strategy. This result demonstrates the effectiveness of our solution in improving energy efficiency while maintaining high performance in AGV operations. By providing the necessary infrastructure for data input, processing, and output implementation, the framework ensures that the algorithm can be effectively deployed and scaled in industrial settings. This research offers a robust solution for AGV scheduling, balancing operational efficiency with sustainability.</p>

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

Leveraging artificial intelligence and optimization for agile AGV scheduling in an edge-to-cloud manufacturing framework

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月1日

查看全文
  • Mario Lepore,
  • Domenico Serra,
  • Raffaele Maccioni

摘要

Optimizing the scheduling of Automated Guided Vehicles (AGVs) is a critical task in the context of smart manufacturing, particularly in Industry 4.0, where operational efficiency, sustainability, and adaptability are key drivers of innovation. This paper introduces an innovative scheduling model incorporating real-time AGV battery status as a key parameter, using a machine learning algorithm to predict energy consumption and optimize task allocation accordingly. The primary objective is to extend AGV battery life, reduce energy consumption, and contribute to environmental sustainability, all while maintaining high operational efficiency. In addition to the scheduling algorithm, we present a comprehensive application framework designed to integrate this optimization model into real-world factory environments. This architecture leverages cloud-edge computing to process real-time data from AGVs, enabling dynamic scheduling adjustments and seamless execution of tasks. The proposed approach has been experimentally validated, demonstrating improvements in energy efficiency when compared to a conventional AGV scheduling strategy. This result demonstrates the effectiveness of our solution in improving energy efficiency while maintaining high performance in AGV operations. By providing the necessary infrastructure for data input, processing, and output implementation, the framework ensures that the algorithm can be effectively deployed and scaled in industrial settings. This research offers a robust solution for AGV scheduling, balancing operational efficiency with sustainability.