Esipaneelil põhinev ennustav protsesside jälgimise süsteem
Failid
Kuupäev
2017
Autorid
Ajakirja pealkiri
Ajakirja ISSN
Köite pealkiri
Kirjastaja
Abstrakt
Protsesside jälgimine moodustab keskse osa äriprotsesside juhtimisest. See sisaldab tegevusi, milles kogutakse ja analüüsitakse protsessi täideviimise andmeid, et mõõta protsesside tulemuslikkust, võttes arvesse soorituse eesmärke. Tavaliselt on protsesside jälgimist sooritatud käitluse ajal, võimaldades reaalajalist ülevaadet protsessi sooritusest ja tuvastades protsessi vaidlusküsimused nende tekkimise hetkel. Viimasel ajal logimisvõimetega töövoo juhtimise süsteemide laialdane omaksvõtt on loonud aktiivse andmetest ajendatud ennustava protsesside jälgimise, mis kasutab varasemat protsesside jooksutamise andmestikku, et ennustada käimasolevate äriprotsesside tulevikusuunda. Seega potentsiaalselt hälbiva protsessi kulgu saab ette ennustada ja lahendada. Tüüpiliste protsesside jälgimise probleemidega tegelemiseks on välja pakutud erinevaid lähenemisi, nagu kas parasjagu käiva protsessi instants vastab selle soorituse eesmärkidele või millal instantsiga lõpule jõutakse. Need lähenemised on siiski seni jäänud akadeemilisse valdkonda ning neid pole rakendatud tööstuse sätetesse. Selles lõputöös me disainisime ja teostasime ennustava protsessi jälgimise mootori prototüübi. Arendatud lahendus on konfigureeritav täispinu veebiraamistik, mis võimaldab mitme soorituse indikaatori ennustamist ja mida saab kerge vaevaga laiendada teiste indikaatorite jaoks uute ennustavate mudelitega. Lisaks võimaldab see mitmest äriprotsessist pärinevate sündmusvoogude käsitlemist. Nii ennustuste tulemused kui protsesside täitmise reaalaja statistika kokkuvõtted kuvatakse esipaneelil, mis võimaldab mitut erinevat alternatiivset visualiseerimise valikut. Lahendus on kahte tõsielu äriprotsessi kasutades edukalt valideeritud, arvestades defineeritud funktsionaalseid ja mittefunktsionaalseid nõudeid.
Process monitoring forms an integral part of business process management. It involves activities in which process execution data are collected and analyzed to measure the process performance with respect to the performance objectives. Traditionally, process monitoring has been performed at runtime, providing a real-time overview of the process performance and identifying performance issues as they arise. Recently, the rapid adop- tion of workflow management systems with logging capabilities has spawned the active development of data-driven, predictive process monitoring that exploits the historical process execution data to predict the future course of ongoing instances of a business process. Thus, potentially deviant process behavior can be anticipated and proactively addressed.To this end, various approaches have been proposed to tackle typical predictive monitoring problems, such as whether an ongoing process instance will fulfill its per- formance objectives, or when will an instance be completed. However, so far these approaches have largely remained in the academic domain and have not been widely applied in industry settings, mostly due to the lack of software support. In this the- sis, we have designed and implemented a prototype of a predictive process monitor- ing engine. The developed solution, named Nirdizati, is a configurable full-stack web framework that enables the prediction of several performance indicators and is easily extensible with new predictive models for other indicators. In addition, it allows han- dling event streams that originate from multiple business processes. The results of the predictions, as well as the real-time summary statistics about the process execution, are presented in a dashboard that offers multiple alternative visualization options. The dashboard updates periodically based on the arriving stream of events. The solution has been successfully validated with respect to the established functional and non-functional requirements using event streams corresponding to two real-life business processes.
Process monitoring forms an integral part of business process management. It involves activities in which process execution data are collected and analyzed to measure the process performance with respect to the performance objectives. Traditionally, process monitoring has been performed at runtime, providing a real-time overview of the process performance and identifying performance issues as they arise. Recently, the rapid adop- tion of workflow management systems with logging capabilities has spawned the active development of data-driven, predictive process monitoring that exploits the historical process execution data to predict the future course of ongoing instances of a business process. Thus, potentially deviant process behavior can be anticipated and proactively addressed.To this end, various approaches have been proposed to tackle typical predictive monitoring problems, such as whether an ongoing process instance will fulfill its per- formance objectives, or when will an instance be completed. However, so far these approaches have largely remained in the academic domain and have not been widely applied in industry settings, mostly due to the lack of software support. In this the- sis, we have designed and implemented a prototype of a predictive process monitor- ing engine. The developed solution, named Nirdizati, is a configurable full-stack web framework that enables the prediction of several performance indicators and is easily extensible with new predictive models for other indicators. In addition, it allows han- dling event streams that originate from multiple business processes. The results of the predictions, as well as the real-time summary statistics about the process execution, are presented in a dashboard that offers multiple alternative visualization options. The dashboard updates periodically based on the arriving stream of events. The solution has been successfully validated with respect to the established functional and non-functional requirements using event streams corresponding to two real-life business processes.