TSNet-SAC: Leveraging Transformers for Efficient Task Scheduling

TL;DR

This paper introduces TSNet-SAC, a Transformer-based network with a sliding augment component for efficient, robust, and scalable task scheduling in future 6G MEC autopilot systems, outperforming traditional heuristic algorithms.

Contribution

The paper presents a novel Transformer-based scheduling network with a sliding augment component and scalability features, improving real-time performance and robustness in 6G MEC environments.

Findings

TSNet-SAC achieves higher accuracy than existing networks.

TSNet-SAC reduces scheduling latency compared to heuristic algorithms.

The approach enhances robustness and scalability in diverse scenarios.

Abstract

In future 6G Mobile Edge Computing (MEC), autopilot systems require the capability of processing multimodal data with strong interdependencies. However, traditional heuristic algorithms are inadequate for real-time scheduling due to their requirement for multiple iterations to derive the optimal scheme. We propose a novel TSNet-SAC based on Transformer, that utilizes heuristic algorithms solely to guide the training of TSNet. Additionally, a Sliding Augment Component (SAC) is introduced to enhance the robustness and resolve algorithm defects. Furthermore, the Extender component is designed to handle multi-scale training data and provide network scalability, enabling TSNet to adapt to different access scenarios. Simulation demonstrates that TSNet-SAC outperforms existing networks in accuracy and robustness, achieving superior scheduling-making latency compared to heuristic algorithms.