A review of intelligent task scheduling models for fog computing in large-scale internet of things networks

Abstract

The rapid growth of internet of things (IoT) applications has generated an urgent demand for efficient task scheduling mechanisms that feature low latency, scalability, and resource awareness. While fog computing can meet this demand by extending computing and storage resources to the vicinity of data sources, it still confronts four core challenges: resource heterogeneity, dynamic workloads, mobility, and security constraints. To address these issues, this study conducts a systematic review of intelligent task scheduling for fog-enabled IoT systems. It classifies the included eligible studies into five scheduling paradigms, and innovatively proposes a cross-domain framework that integrates three types of awareness, including priority awareness. The subsequent work of this study will sort out the core strengths and limitations of existing relevant methods. Finally, open challenges and emerging research directions, including edge artificial intelligence (AI), federated learning, blockchain-assisted scheduling, and hardware-accelerated implementations are discussed. The findings provide useful guidance for developing scalable, secure, and adaptive scheduling frameworks for next-generation fog-enabled IoT systems.