Dynamic Resource Management and Task Offloading Framework for Fog Computing

Abstract Fog computing has emerged as a pivotal paradigm for enabling low-latency, high-performance applications by positioning computational resources closer to the network edge. However, task offloading in fog environments poses significant challenges because of the dynamic and heterogeneous nature of fog nodes, which are influenced by fluctuating computational loads, channel conditions, and mobility patterns. This paper introduces a dynamic task-offloading framework leveraging deep Q-learning (DQL), a reinforcement learning technique tailored to optimize task allocation and enhance system performance in such complex settings. The proposed framework models the offloading problem as a Markov decision process (MDP), enabling the DQL agent to learn optimal strategies adaptively by incorporating factors such as task demands, node states, and channel quality. Performance evaluations against state-of-the-art scheduling methods reveal that the DQL-based approach consistently outperforms competing techniques, achieving superior efficiency and reliability. Furthermore, the framework demonstrates scalability and robustness in dynamic fog networks, making it highly suitable for diverse real-time applications. This study highlights the potential of DQL as a transformative solution for dynamic task offloading in fog computing, offering efficient resource management and system stability. Its applicability to domains such as intelligent transportation systems, smart cities, and the IoT underscores its practical relevance and future impact.