Scholarlink

<p>Federated learning (FL) has emerged as a promising method for reducing communication overhead and preserving data privacy in distributed systems. In edge computing, task offloading (TO) has garnered increasing attention to enhance efficiency, reduce communication costs, and protect user privacy. However, despite the growing adoption of FL, comprehensive reviews that systematically examine its variants for TO optimization remain limited. This paper addresses that gap by reviewing FL approaches applied to TO optimization from 2017 to 2025. We analyze major TO application scenarios, outline key optimization objectives, and discuss current challenges. Additionally, we examine FL methods and strategies designed explicitly for TO optimization and evaluate their effectiveness using performance metrics. The review also categorizes research methodologies based on model aggregation techniques, highlighting the strengths and limitations of different approaches. Finally, we identify emerging trends and propose directions for future research in this field.</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

Federated learning for task offloading optimization: a systematic review in edge computing environments

  • 期刊论文

  • 发表日期：

    2026年7月23日

查看全文
  • Peng Kong,
  • Kartinah Zen,
  • Sei Ping Lau

摘要

Federated learning (FL) has emerged as a promising method for reducing communication overhead and preserving data privacy in distributed systems. In edge computing, task offloading (TO) has garnered increasing attention to enhance efficiency, reduce communication costs, and protect user privacy. However, despite the growing adoption of FL, comprehensive reviews that systematically examine its variants for TO optimization remain limited. This paper addresses that gap by reviewing FL approaches applied to TO optimization from 2017 to 2025. We analyze major TO application scenarios, outline key optimization objectives, and discuss current challenges. Additionally, we examine FL methods and strategies designed explicitly for TO optimization and evaluate their effectiveness using performance metrics. The review also categorizes research methodologies based on model aggregation techniques, highlighting the strengths and limitations of different approaches. Finally, we identify emerging trends and propose directions for future research in this field.