ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset

2025-09-04

AI Summary

To address the lack of structured benchmarks for service-level signal forecasting and anomaly detection in microservice production environments, this paper introduces ChronoGraph: the first graph-structured temporal benchmark integrating explicit machine-readable dependency graphs, multivariate time series (e.g., CPU, memory, network), and real-world incident-annotated anomaly windows. Each node represents a microservice; directed edges encode invocation dependencies, enabling structure-aware forecasting and event-aware evaluation. Distinct from prior work, ChronoGraph unifies these three critical components—dependency structure, temporal dynamics, and ground-truth anomalies—for the first time. Leveraging ChronoGraph, we systematically evaluate pre-trained time-series foundation models, graph neural network predictors, and mainstream anomaly detection algorithms, assessing their robustness under runtime disruptions. Our comprehensive multi-model baseline results establish a new standard for structured temporal analysis in realistic microservice systems.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

We present ChronoGraph, a graph-structured multivariate time series forecasting dataset built from real-world production microservices. Each node is a service that emits a multivariate stream of system-level performance metrics, capturing CPU, memory, and network usage patterns, while directed edges encode dependencies between services. The primary task is forecasting future values of these signals at the service level. In addition, ChronoGraph provides expert-annotated incident windows as anomaly labels, enabling evaluation of anomaly detection methods and assessment of forecast robustness during operational disruptions. Compared to existing benchmarks from industrial control systems or traffic and air-quality domains, ChronoGraph uniquely combines (i) multivariate time series, (ii) an explicit, machine-readable dependency graph, and (iii) anomaly labels aligned with real incidents. We report baseline results spanning forecasting models, pretrained time-series foundation models, and standard anomaly detectors. ChronoGraph offers a realistic benchmark for studying structure-aware forecasting and incident-aware evaluation in microservice systems.

Problem

• Forecasting multivariate performance metrics in microservice systems
• Detecting anomalies during operational disruptions using incident labels
• Studying structure-aware forecasting with explicit service dependency graphs

Innovation

• Graph-structured multivariate time series from microservices
• Service dependency graphs with performance metrics
• Expert-annotated incident windows for anomaly detection