Ksurf:面向高度可变云工作负载预测的注意力卡尔曼滤波器与主成分分析
Ksurf: Attention Kalman Filter and Principal Component Analysis for Prediction under Highly Variable Cloud Workloads
AI总结:
针对云工作负载高可变性和噪声导致预测困难的问题,提出结合注意力机制、主成分分析与卡尔曼滤波器的 Ksurf 模型,显著提升了预测准确率并改善了 Apache Kafka 的缩放稳定性。
摘要:
云平台已成为在线快速部署应用系统以服务大量用户的关键基础设施。资源估计与工作负载预测在云数据中心中至关重要。由于虚拟机数量不断变化导致的云提供商环境复杂性,给工作负载和资源使用引入了高度可变性,使得使用最先进的模型进行资源预测变得困难,因为这些模型无法处理非线性特征。在受未知外部动态影响的分组网络上,估计和预测云系统的资源指标是一项受高测量噪声和方差影响的任务。解决这些问题的理想方案是卡尔曼滤波器,这是一种方差最小化估计器,用于系统状态估计和高效的低延迟系统状态预测。对于具有高斯状态空间特征(如互联网工作负载)的高度可变数据,卡尔曼滤波器是最佳估计器。本工作通过以下贡献提供了解决方案:i) 引入并评估了基于卡尔曼滤波器的模型参数预测方法,该方法结合了主成分分析和注意力机制来处理含噪云数据;ii) 在 Google Cloud 基准上评估该方案,并在预测任务中与最先进的 Bi-directional Grid Long Short-Term Memory 网络模型进行比较;iii) 应用这些技术展示了在 Apache Kafka 的实时消息系统自动缩放器上的准确性和稳定性提升。在含噪信号预测任务中,新方案比最先进的卡尔曼滤波器将预测准确率提高了 37%。它将神经网络模型的预测误差降低了 40% 以上。结果表明,它使基于 Apache Kafka 工作负载的缩放稳定性提高了 58%。
英文摘要:
Cloud platforms have become essential in rapidly deploying application systems online to serve large numbers of users. Resource estimation and workload forecasting are critical in cloud data centers. Complexity in the cloud provider environment due to varying numbers of virtual machines introduces high variability in workloads and resource usage, making resource predictions problematic using state-of-the-art models that fail to deal with nonlinear characteristics. Estimating and predicting the resource metrics of cloud systems across packet networks influenced by unknown external dynamics is a task affected by high measurement noise and variance. An ideal solution to these problems is the Kalman filter, a variance-minimizing estimator used for system state estimation and efficient low latency system state prediction. Kalman filters are optimal estimators for highly variable data with Gaussian state space characteristics such as internet workloads. This work provides a solution by making these contributions: i) it introduces and evaluates the Kalman filter-based model parameter prediction using principal component analysis and an attention mechanism for noisy cloud data, ii) evaluates the scheme on a Google Cloud benchmark comparing it to the state-of-the-art Bi-directional Grid Long Short-Term Memory network model on prediction tasks, iii) it applies these techniques to demonstrate the accuracy and stability improvements on a realtime messaging system auto-scaler in Apache Kafka. The new scheme improves prediction accuracy by $37\%$ over state-of-the-art Kalman filters in noisy signal prediction tasks. It reduces the prediction error of the neural network model by over $40\%$. It is shown to improve Apache Kafka workload-based scaling stability by $58\%$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。