用机器学习加速大规模任务调度，预测精度超97%。
Accelerating Divisible Load Processing Through Machine Learning: A Practical Framework for Large-Scale Workloads
- 用16个特征的神经网络学习任务分配规律，跳过复杂公式推导。
- 预测误差仅1%-5%，单次推理快于1毫秒，准确率97%-99%。
- 适合实时调度、云资源分配等需快速决策的场景。
本文提出首个基于机器学习的框架，用于在单层树网络（SLTN）架构下预测可分负载理论（DLT）中的最优处理时间。通过一个包含16个工程特征的前馈神经网络（FNN），在10万组合成配置上进行训练，无需显式求解DLT方程即可预测最优处理时间。模型在测试中达到97%-99%的决定系数（R-square），平均绝对百分比误差为1%-5%，表明神经网络能有效捕捉复杂的负载分配关系。特征重要性分析显示，模型隐式学习到了负载守恒和同步完成等数学约束。推理时间低于1毫秒，显著优于传统计算方式，适用于实时调度、设计空间探索与云资源分配。该方法在系统规模n=3至20、负载大小1-100 GB范围内表现良好，对极大规模或高度异构系统性能略有下降。本工作验证了机器学习在加速分布式优化中的可行性，并保持近似最优精度。
原文摘要 · Abstract (English)
In this paper, we introduce the first machine learning framework for predicting optimal processing times in Single-Level Tree Network (SLTN) architectures for the Divisible Load Theory (DLT) paradigm. Using a feedforward neural network(FNN) with 16 engineered features, we train a model on 100,000 synthetically generated configurations to predict optimal processing times without explicit formulation of DLT equations. The model achieves 97-99% accuracy (R-square factor) with mean absolute percentage error of 1-5%, demonstrating that neural networks can effectively learn complex load distribution relationships. Feature importance analysis reveals that the model implicitly captures DLT mathematical structure, including load conservation and simultaneous finishing constraints. With inference times under 1 millisecond, the approach serves as a viable option over traditional DLT computation, enabling applications in real-time scheduling, design space exploration, and cloud resource allocation. The method generalizes well across diverse system configurations (n=3 to 20, load size =1 to 100 GB) with consistent accuracy, though performance degrades slightly for very large or highly heterogeneous systems. This work demonstrates the feasibility of using machine learning to accelerate distributed computing optimization while maintaining near-optimal accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。