当前位置: X-MOL 学术arXiv.cs.DC › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Optimal Accuracy-Time Trade-off for Deep Learning Services in Edge Computing Systems
arXiv - CS - Distributed, Parallel, and Cluster Computing Pub Date : 2020-11-17 , DOI: arxiv-2011.08381
Minoo Hosseinzadeh, Andrew Wachal, Hana Khamfroush, Daniel E. Lucani

With the increasing demand for computationally intensive services like deep learning tasks, emerging distributed computing platforms such as edge computing (EC) systems are becoming more popular. Edge computing systems have shown promising results in terms of latency reduction compared to the traditional cloud systems. However, their limited processing capacity imposes a trade-off between the potential latency reduction and the achieved accuracy in computationally-intensive services such as deep learning-based services. In this paper, we focus on finding the optimal accuracy-time trade-off for running deep learning services in a three-tier EC platform where several deep learning models with different accuracy levels are available. Specifically, we cast the problem as an Integer Linear Program, where optimal task scheduling decisions are made to maximize overall user satisfaction in terms of accuracy-time trade-off. We prove that our problem is NP-hard and then provide a polynomial constant-time greedy algorithm, called GUS, that is shown to attain near-optimal results. Finally, upon vetting our algorithmic solution through numerical experiments and comparison with a set of heuristics, we deploy it on a test-bed implemented to measure for real-world results. The results of both numerical analysis and real-world implementation show that GUS can outperform the baseline heuristics in terms of the average percentage of satisfied users by a factor of at least 50%.

中文翻译:

边缘计算系统中深度学习服务的最佳精度-时间权衡

随着对深度学习任务等计算密集型服务的需求不断增加,边缘计算 (EC) 系统等新兴分布式计算平台正变得越来越流行。与传统云系统相比,边缘计算系统在减少延迟方面显示出了可喜的成果。然而,它们有限的处理能力在潜在的延迟减少和计算密集型服务(例如基于深度学习的服务)中实现的准确性之间进行了权衡。在本文中,我们专注于寻找在三层 EC 平台中运行深度学习服务的最佳准确度-时间权衡,该平台有多个具有不同准确度级别的深度学习模型可用。具体来说,我们将问题转换为整数线性规划,其中做出最佳任务调度决策,以在准确性-时间权衡方面最大限度地提高整体用户满意度。我们证明了我们的问题是 NP 难的,然后提供了一个多项式常数时间贪婪算法,称为 GUS,它被证明可以获得近乎最优的结果。最后,在通过数值实验和与一组启发式比较来审查我们的算法解决方案后,我们将其部署在测试台上,以测量真实世界的结果。数值分析和实际实施的结果表明,就满意用户的平均百分比而言,GUS 的性能比基线启发式算法至少高出 50%。这被证明可以达到接近最佳的结果。最后,在通过数值实验和与一组启发式比较来审查我们的算法解决方案后,我们将其部署在用于测量真实世界结果的测试台上。数值分析和实际实施的结果表明,就满意用户的平均百分比而言,GUS 的性能比基线启发式算法至少高出 50%。这被证明可以达到接近最佳的结果。最后,在通过数值实验和与一组启发式比较来审查我们的算法解决方案后,我们将其部署在测试台上,以测量真实世界的结果。数值分析和实际实施的结果表明,就满意用户的平均百分比而言,GUS 的性能比基线启发式算法至少高出 50%。
更新日期:2020-11-18
down
wechat
bug