Publication

Artifact Appendix for Cloudformer: an Attention-Based Performance Prediction for Public Clouds With Unknown Workload

2026

Abstract

This artifact provides the CloudPerfTrace dataset, a collection of 206 system-level metrics captured at a one-second resolution over 317 days. Specifically designed for black-box multi-tenant cloud environments where internal VM telemetry is unavailable. The dataset enables precise prediction of performance degradation. It encompasses 11 diverse application tasks and captures the complex interplay between intrinsic workload variations and external resource interference.

Official source

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

2026

Abstract

Official source

Related concepts (9)

Cloud computing

Cloud computing is the on-demand availability of computer system resources, especially data storage (cloud storage) and computing power, without direct active management by the user. Large clouds often have functions distributed over multiple locations, each of which is a data center. Cloud computing relies on sharing of resources to achieve coherence and typically uses a pay-as-you-go model, which can help in reducing capital expenses but may also lead to unexpected operating expenses for users.

Vigilance (psychology)

In modern psychology, vigilance, also termed sustained concentration, is defined as the ability to maintain concentrated attention over prolonged periods of time. During this time, the person attempts to detect the appearance of a particular target stimulus. The individual watches for a signal stimulus that may occur at an unknown time. The study of vigilance has expanded since the 1940s mainly due to the increased interaction of people with machines for applications involving monitoring and detection of rare events and weak signals.

Feature learning

In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.