Integrating Performance Prediction, Anomaly Prediction and Root-Cause Localization for Self-Healing Software Systems
FULL
This program is tentative and subject to change.
Engineering self-adaptive systems for software applications necessitates accurate predictions about the state of the underlying application. These predictions can then be used to enable automated cloud operations, such as scaling services in microservices architectures. However, designing an effective self-adaptive system for software applications requires simultaneous predictions across multiple dimensions, including performance, anomalies, and their root causes. While numerous algorithms have been proposed to address performance prediction and anomaly detection, these models typically focus on a single dimension. In this paper, we propose SystemLENS, a novel approach that integrates performance prediction, anomaly detection, and root-cause localization within a unified framework for microservice applications. SystemLENS utilizes Graph Neural Networks (GNNs) and Gated Recurrent Units (GRUs) to first predict latency distributions for traces and the microservice calls involved in generating those traces. These latency distributions are further processed to identify trace-based anomalies and their root causes. By consolidating these tasks into a single model, SystemLENS facilitates comprehensive system monitoring with improved correlations between predictions. We evaluate SystemLENS on benchmark datasets from the domains of performance modeling and anomaly detection, demonstrating its effectiveness in providing an integrated and proactive monitoring solution.
This program is tentative and subject to change.
Mon 28 AprDisplayed time zone: Eastern Time (US & Canada) change
14:00 - 15:30 | |||
14:00 25mTalk | Dynamic Resource Allocation for Deadline-Constrained Neural Network TrainingFULL Research Track Luciano Baresi Politecnico di Milano, Marco Garlini Politecnico di Milano, Giovanni Quattrocchi Politecnico di Milano Pre-print | ||
14:25 25mTalk | Integrating Performance Prediction, Anomaly Prediction and Root-Cause Localization for Self-Healing Software SystemsFULL Research Track | ||
14:50 25mTalk | WasteLess: An Optimal Provisioner for Self-Adaptive Second-Generation Serverless ApplicationsFULL Research Track Emilio Incerto IMT School for Advanced Studies Lucca, Roberto Pizziol IMT School for Advanced Studies Lucca, Gabriele Russo Russo University of Rome Tor Vergata, Italy, Mirco Tribastone IMT Institute for Advanced Studies Lucca, Italy | ||
15:15 15mOther | Discussion Session 3 Research Track |