000862006 001__ 862006
000862006 005__ 20210130001132.0
000862006 020__ $$a978-1-61208-700-9
000862006 037__ $$aFZJ-2019-02380
000862006 1001_ $$0P:(DE-Juel1)144343$$aRybicki, Jedrzej$$b0$$eCorresponding author$$ufzj
000862006 1112_ $$aThe Fifth International Conference on Big Data, Small Data, Linked Data and Open Data$$cValencia$$d2019-03-24 - 2019-03-28$$gALLDATA 2019$$wSpain
000862006 245__ $$aTowards Predictive Monitoring of Research Infrastructures
000862006 260__ $$bIARIA$$c2019
000862006 29510 $$aALLDATA 2019, The Fifth International Conference on Big Data, Small Data, Linked Data and Open Data
000862006 300__ $$a37-40
000862006 3367_ $$2ORCID$$aCONFERENCE_PAPER
000862006 3367_ $$033$$2EndNote$$aConference Paper
000862006 3367_ $$2BibTeX$$aINPROCEEDINGS
000862006 3367_ $$2DRIVER$$aconferenceObject
000862006 3367_ $$2DataCite$$aOutput Types/Conference Paper
000862006 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1554290844_1356
000862006 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000862006 520__ $$aNowadays, both modern computing infrastructures, as well as their scientific workloads exhibit far reaching complexity and diversity. Therefore, it is increasingly hard to comprehend and manage them in an efficient manner. In particular, it can lead to under- or overuse of resources. A prerequisite for efficient resource allocation is the ability to predict their usage. In this paper, we use real world workloads recorded in a modern research infrastructure to conduct load prediction. We use well established statistical model (ARIMA) and achieve good results in predictions. The big data challenge is here given not by the sheer size but rather by the speed of data collection and processing. The quicker the prediction is made, the more time is available for actions. Such predictions can be included in monitoring systems to give human operators better insights into the status of their infrastructures and lead to better load distribution.
000862006 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000862006 8564_ $$uhttps://www.thinkmind.org/index.php?view=article&articleid=alldata_2019_5_10_80022
000862006 8564_ $$uhttps://juser.fz-juelich.de/record/862006/files/alldata_2019_5_10_80022.pdf$$yRestricted
000862006 8564_ $$uhttps://juser.fz-juelich.de/record/862006/files/alldata_2019_5_10_80022.pdf?subformat=pdfa$$xpdfa$$yRestricted
000862006 909CO $$ooai:juser.fz-juelich.de:862006$$pVDB
000862006 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)144343$$aForschungszentrum Jülich$$b0$$kFZJ
000862006 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000862006 9141_ $$y2019
000862006 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000862006 980__ $$acontrib
000862006 980__ $$aVDB
000862006 980__ $$acontb
000862006 980__ $$aI:(DE-Juel1)JSC-20090406
000862006 980__ $$aUNRESTRICTED