Production systems are stochastic systems. They are subject to continuous fluctuations. Fluctuations in production are provoked internally as well as externally. They are the cause of planned and unplanned events. The result of fluctuations are deviations between planned and actual data. In addition, fluctuations in production reduce system performance. In order to be able to control fluctuations, information about them must be available. Currently, such information is insufficient or missing. One reason may be the limited availability of data to date. New technologies in the age of digital transformation are opening up opportunities to solve this problem. The technologies provide tools that reveal enormous potential for the collection, processing and provision of data. The goal of the research project presented here is to demonstrate an approach for automated identification, measurement and quantification of variability in production systems. The first step of the implementation is the creation of a theoretical model for generic application.