Mobility-aware task scheduling based on artificial intelligence in edge-cloud systems
TL;DR
A novel hybrid framework that combines a Graph Attention Network (GAT)-based fault prediction model with a Generative Adversarial Network (GAN)-driven task migration decision model is proposed, achieving substantial reductions in task execution time and energy consumption while improving predictive accuracy and resource efficiency.
Abstract
In edge-cloud computing environments, efficient task scheduling and proactive fault management are essential for achieving high performance and resource utilization. This article proposes a novel hybrid framework that combines a Graph Attention Network (GAT)-based fault prediction model with a Generative Adversarial Network (GAN)-driven task migration decision model. The GAT component leverages historical execution data and inter-node dependencies to accurately identify potential failure points, while the GAN component generates optimal migration strategies to preemptively mitigate predicted faults. By integrating proactive fault prediction with intelligent migration decisions, the proposed approach significantly enhances fault tolerance, minimizes service latency, and improves overall system throughput. Extensive experiments conducted on real-world edge-cloud traces demonstrate that our method outperforms state-of-the-art fault prediction and task migration techniques, achieving substantial reductions in task execution time and energy consumption while improving predictive accuracy and resource efficiency.