From 882e8de984b8d0450ab5ffb531416a3178abb876 Mon Sep 17 00:00:00 2001 From: Ola Spjuth Date: Tue, 14 Nov 2023 13:39:17 +0100 Subject: [PATCH] Update 2022-management-scientific-dataset-hierarchical-storage-reinforcement-learning.md --- ...aset-hierarchical-storage-reinforcement-learning.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/content/publication/2022-management-scientific-dataset-hierarchical-storage-reinforcement-learning.md b/content/publication/2022-management-scientific-dataset-hierarchical-storage-reinforcement-learning.md index 9b71e2d62..dd1c2d709 100644 --- a/content/publication/2022-management-scientific-dataset-hierarchical-storage-reinforcement-learning.md +++ b/content/publication/2022-management-scientific-dataset-hierarchical-storage-reinforcement-learning.md @@ -3,13 +3,13 @@ bibtex_type = "article" author="Zhang T, Gupta A, Rodríguez MAF, Spjuth O, Hellander A and Toor S." title="Management of Scientific Datasets in Hierarchical Storage Using Reinforcement Learning" journal="Expert Systems With Applications" -year="2023" +year="2024" date="2023-09-05T00:00:00+02:00" -volume="Accepted" -number="" +volume="237" +number="121443" preprint = false pages="" -abstract="" -doi="" +abstract="In many areas of data-driven science, large datasets are generated where the individual data objects are images, matrices, or otherwise have a clear structure. However, these objects can be information-sparse, and a challenge is to efficiently find and work with the most interesting data as early as possible in an analysis pipeline. We have recently proposed a new model for big data management where the internal structure and information of the data are associated with each data object (as opposed to simple metadata). There is then an opportunity for comprehensive data management solutions to account for data-specific internal structure as well as access patterns. In this article, we explore this idea together with our recently proposed hierarchical storage management framework that uses reinforcement learning (RL) for autonomous and dynamic data placement in different tiers in a storage hierarchy. Our case-study is based on four scientific datasets: Protein translocation microscopy images, Airfoil angle of attack meshes, 1000 Genomes sequences, and Phenotypic screening images. The presented results highlight that our framework is optimal and can quickly adapt to new data access requirements. It overall reduces the data processing time, and the proposed autonomous data placement is superior compared to any static or semi-static data placement policies." +doi="10.1016/j.eswa.2023.121443" url_html="" +++