ADAPTIVE TASK SCHEDULING AND LOAD OPTIMIZATION IN FOG NETWORKS FOR HEALTHCARE

Abstract

In healthcare, real-time decision making is crucial for patient care, but traditional computing infrastructures suffer from inherent latency. This paper proposes a novel framework that utilizes Deep Reinforcement Learning (DRL) to advance task scheduling in fog computing for crucial healthcare. The fog architecture addresses the limitations of cloud systems by reducing transmission latency, achieved by placing processing nodes close to the source of data generation, such as IoT-enabled healthcare devices. The foundation of this approach is a DRL model, which is designed to dynamically optimize the partition of computational tasks across fog nodes to improve both data throughput and operational response times. The proposed DRL model reduces the make span by up to 30% compared to traditional scheduling approaches. Comparative analysis indicates a 40% reduction in operational latency and a 25% improvement in fault tolerance.