Datasets and source code for a pipeline architecture for feature-based unsupervised clustering using multivariate time series from HPC jobs

Published: 17 November 2022| Version 1 | DOI: 10.17632/hgkv9cpnmn.1
José Fuentes,


This repository contains 2 compressed files: - code.tar.gz, containing the source code that implements the pipeline, as well as auxiliary files needed to retrieve time series or to create the plots - data.tar.gz, which contains 3 directories: + jobs: All the resource plots for all the HPC jobs, each job contains several computing nodes and each node several possible resource time series + plots: All the plots for all the predictions (e.g., Scatter plots), as well as other evaluation plots (e.g., heatmaps, Andrews curves, dendrograms) + datasets: The datasets of the experiments, all the intermediary files and the files that contain the results and evaluations



Centro de Supercomputacion de Galicia, Universidade da Coruna


High Performance Computing, Unsupervised Learning, Time Series Analysis