Modeling Anomaly Detection in Cloud Services: Analysis of the Properties that Impact Latency and Resource Consumption

TL;DR

This paper models how different properties of anomaly detectors in cloud services affect latency and resource use, providing insights into optimizing detection strategies for better performance-cost balance.

Contribution

It introduces a stochastic model to analyze the impact of detector precision, recall, and frequency on cloud service performance and resource consumption.

Findings

High precision with frequent detection yields good performance-cost balance.

Infrequent detection makes recall more critical for performance.

Optimal detection parameters depend on detection frequency.

Abstract

Detecting and resolving performance anomalies in Cloud services is crucial for maintaining desired performance objectives. Scaling actions triggered by an anomaly detector help achieve target latency at the cost of extra resource consumption. However, performance anomaly detectors make mistakes. This paper studies which characteristics of performance anomaly detection are important to optimize the trade-off between performance and cost. Using Stochastic Reward Nets, we model a Cloud service monitored by a performance anomaly detector. Using our model, we study the impact of detector characteristics, namely precision, recall and inspection frequency, on the average latency and resource consumption of the monitored service. Our results show that achieving a high precision and a high recall is not always necessary. If detection can be run frequently, a high precision is enough to obtain a good performance-to-cost trade-off, but if the detector is run infrequently, recall becomes the most important.