{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:54:50Z","timestamp":1765828490804,"version":"build-2065373602"},"reference-count":19,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Development Project of Jilin Province, China","award":["20220201150GX"],"award-info":[{"award-number":["20220201150GX"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>In recent years, the increasing adoption of High-Performance Computing (HPC) clusters in scientific research and engineering has exposed challenges such as resource imbalance, node idleness, and overload, which hinder scheduling efficiency. Accurate multidimensional task prediction remains a key bottleneck. To address this, we propose a hybrid prediction model that integrates Informer, Long Short-Term Memory (LSTM), and Graph Neural Networks (GNN), enhanced by a hierarchical attention mechanism combining multi-head self-attention and cross-attention. The model captures both long- and short-term temporal dependencies and deep semantic relationships across features. Built on a multitask learning framework, it predicts task execution time, CPU usage, memory, and storage demands with high accuracy. Experiments show prediction accuracies of 89.9%, 87.9%, 86.3%, and 84.3% on these metrics, surpassing baselines like Transformer-XL. The results demonstrate that our approach effectively models complex HPC workload dynamics, offering robust support for intelligent cluster scheduling and holding strong theoretical and practical significance.<\/jats:p>","DOI":"10.3390\/computers14080335","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T13:28:22Z","timestamp":1755523702000},"page":"335","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HPC Cluster Task Prediction Based on Multimodal Temporal Networks with Hierarchical Attention Mechanism"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7718-2185","authenticated-orcid":false,"given":"Xuemei","family":"Bai","sequence":"first","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University of Science and Technology, Weixing Road No. 7089, Changchun 130022, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9145-6501","authenticated-orcid":false,"given":"Jingbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University of Science and Technology, Weixing Road No. 7089, Changchun 130022, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1302-5838","authenticated-orcid":false,"given":"Zhijun","family":"Wang","sequence":"additional","affiliation":[{"name":"High Performance Computing Center, Changchun Normal University, North Changji Road No. 677, Changchun 130032, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.future.2016.08.010","article-title":"Job placement advisor based on turnaround predictions for HPC hybrid clouds","volume":"67","author":"Cunha","year":"2017","journal-title":"Future Gener. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11227-017-2038-2","article-title":"Runtime prediction of parallel applications with workload-aware clustering","volume":"73","author":"Park","year":"2017","journal-title":"J. Supercomput."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.future.2018.05.086","article-title":"An ontology for heterogeneous resources management interoperability and HPC in the cloud","volume":"87","author":"Castane","year":"2018","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103498","DOI":"10.1016\/j.compind.2021.103498","article-title":"A survey on anomaly detection for technical systems using LSTM networks","volume":"131","author":"Lindemann","year":"2019","journal-title":"Comput. Ind."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4147","DOI":"10.1007\/s12652-020-01794-6","article-title":"Dynamic resource allocation with optimized task scheduling and improved power management in cloud computing","volume":"72","author":"Praveenchandar","year":"2021","journal-title":"J. Ambient Intell. Hum. Comput."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.future.2017.02.040","article-title":"A runtime estimation framework for ALICE","volume":"72","author":"Pumma","year":"2017","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/TC.2020.2964767","article-title":"Automated performance modeling of HPC applications using machine learning","volume":"69","author":"Sun","year":"2020","journal-title":"IEEE Trans. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1109\/TPDS.2019.2921337","article-title":"Efficient data placement and replication for QoS-aware approximate query evaluation of big data analytics","volume":"30","author":"Xia","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_9","first-page":"3317","article-title":"MapReduce task scheduling in heterogeneous geo-distributed data centers","volume":"14","author":"Li","year":"2021","journal-title":"IEEE Trans. Serv. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/s11227-021-03915-0","article-title":"Amended hybrid multi-verse optimizer with genetic algorithm for solving task scheduling problem in cloud computing","volume":"78","author":"Abualigah","year":"2022","journal-title":"J. Supercomput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4002","DOI":"10.1109\/TNSM.2021.3125395","article-title":"Real-time multiple-workflow scheduling in cloud environments","volume":"18","author":"Ma","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_12","first-page":"34","article-title":"Deep learning research and development platform: Characterizing and scheduling with QoS guarantees on GPU clusters","volume":"30","author":"Chen","year":"2019","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.knosys.2018.01.004","article-title":"Dual channel LSTM based multi-feature extraction in gait for diagnosis of neurodegenerative diseases","volume":"145","author":"Zhao","year":"2018","journal-title":"Knowl.-Based Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3799","DOI":"10.1109\/JIOT.2021.3100117","article-title":"Multiuser computation offloading and resource allocation for cloud-edge heterogeneous network","volume":"9","author":"Chen","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1109\/TWC.2019.2896999","article-title":"D2D communications meet mobile edge computing for enhanced computation capacity in cellular networks","volume":"18","author":"He","year":"2019","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_17","first-page":"2238","article-title":"When deep reinforcement learning meets federated learning: Intelligent multitimescale resource management for multiaccess edge computing in 5G ultradense networks","volume":"7","author":"Yu","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.future.2024.06.058","article-title":"Integrating quantum computing resources into scientific HPC ecosystems","volume":"151","author":"Beck","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_19","first-page":"4375","article-title":"Multi-agent deep reinforcement learning-based resource allocation in HPC\/AI converged cluster","volume":"71","author":"Narantuya","year":"2022","journal-title":"Comput. Mater. Contin."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/8\/335\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:29:53Z","timestamp":1760034593000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/8\/335"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":19,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["computers14080335"],"URL":"https:\/\/doi.org\/10.3390\/computers14080335","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,8,18]]}}}