面向能效感知调度的机器学习方法

Machine Learning for Energy-Performance-aware Scheduling

January 30, 2026

作者: Zheyuan Hu, Yifei Shi

cs.AI

摘要

在后邓纳德时代，嵌入式系统优化需在能效与延迟之间进行复杂权衡。传统启发式调优方法在高维非平滑参数空间中往往效率低下。本研究提出一种基于高斯过程的贝叶斯优化框架，用于自动化搜索异构多核架构的最优调度配置。我们通过逼近能耗与时间的帕累托前沿，显式处理问题的多目标特性。进一步地，通过引入敏感性分析（fANOVA）并比较不同协方差核函数（如Matérn与RBF），为黑盒模型提供物理解释性，揭示驱动系统性能的主导硬件参数。

English

In the post-Dennard era, optimizing embedded systems requires navigating complex trade-offs between energy efficiency and latency. Traditional heuristic tuning is often inefficient in such high-dimensional, non-smooth landscapes. In this work, we propose a Bayesian Optimization framework using Gaussian Processes to automate the search for optimal scheduling configurations on heterogeneous multi-core architectures. We explicitly address the multi-objective nature of the problem by approximating the Pareto Frontier between energy and time. Furthermore, by incorporating Sensitivity Analysis (fANOVA) and comparing different covariance kernels (e.g., Matérn vs. RBF), we provide physical interpretability to the black-box model, revealing the dominant hardware parameters driving system performance.