CloudBruno: A Low-Overhead Online Workload Prediction Framework for Cloud Computing
CloudBruno: A Low-Overhead Online Workload Prediction Framework for Cloud Computing
复制标题
DOI：
10.1109/ic2e55432.2022.00027
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
V. Jayakumar;Shivani Arbat;I. Kim;Wei Wang
中科院分区：
文献类型：
--
作者：
V. Jayakumar;Shivani Arbat;I. Kim;Wei Wang
准确地预测未来对云应用程序的未来传入工作负载，例如未来的用户请求计数，对于主动自动缩放至关重要，通常对于云部署的成本效益至关重要。但是，设计一个可以准确预测任何类型的工作负载的通用预测框架是困难的，尤其是当工作负载是动态的并且可以更改为训练数据集中未观察到的模式时。但是，现有的工作负载预测解决方案通常依赖于复杂的机器学习模型，这些模型需要全面的培训数据，因此很难处理动态工作负载。此外，就时间和计算资源而言，现有工作负载预测解决方案的培训也很昂贵。本文介绍了一种通用且低成本的在线工作负载预测框架，称为Cloud Bruno，该框架将更准确的LSTM型号与较便宜但快速的SVM型号结合在一起，以实现高精度和低训练的开销。与现有预测变量相比，CloudBruno的错误至少比现有的基于深度学习的预测因子低8.8％，该预测因素对于没有全面的培训数据（即，培训数据未知）。对于具有全面培训数据的工作负载，Cloud Bruno的错误最多比优化的基于深度学习的预测指标高2.5％。更重要的是，Cloud Bruno可以有效地在免费的Cloud CPU上执行，从而可以将其用作在线工作负载预测器而无需额外的成本。
Accurate prediction of future incoming workloads to cloud applications, such as future user request count, is critical to proactive auto-scaling, and in general, critical to the cost-effectiveness of cloud deployments. However, designing a generic predictive framework that can accurately predict for any types of workloads is difficult, especially when the workload is dynamic and can change to a pattern that has not been observed in the training data sets. However, existing workload prediction solutions typically rely on complex machine learning models, which require comprehensive training data, making it difficult for them to handle dynamic workloads. Moreover, the training of existing workload prediction solutions are also expensive in terms of both time and computing resources. This paper presents a generic and low-cost online workload prediction framework, called Cloud Bruno, which combines the more accurate LSTM models with less expensive but fast SVM models to achieve high accuracy and low training overhead. When compared to existing predictors, CloudBruno had at least 8.8 % lower error than existing deep learning-based predictors for a highly-dynamic workload that does not have comprehensive training data (i.e, has changes unknown to training data). For workloads with comprehensive training data, Cloud Bruno's error was at most 2.5 % higher than optimized deep learning-based predictors. More importantly, Cloud Bruno can effectively execute on a free cloud CPU, allowing it to be used as an online workload predictor without additional cost.