Runtime Integration of Machine Learning and Simulation for Business Processes

Recent research in Computer Science has investigated the use of Deep Learning (DL) techniques to complement outcomes or decisions within a Discrete Event Simulation (DES) model. The main idea of this combination is to maintain a white box simulation model but to complement it with information provided by DL models. State-of-the-art techniques in BPM combine Deep Learning and Discrete event simulation in a post-integration fashion: first an entire simulation is performed, and then a DL model is used to add waiting times and processing times to the events produced by the simulation model. In this paper, we aim at taking a step further by introducing RIMS (Runtime Integration of Machine Learning and Simulation). Instead of complementing the outcome of a complete simulation with the results of predictions "a posteriori", RIMS provides a tight integration of the predictions of the DL model at runtime during the simulation. This runtime-integration enables us to fully exploit the specific predictions thus enhancing the performance of the overall system both w.r.t. the single techniques (Business Process Simulation and DL) separately and the post-integration approach. The runtime-integration enables us to also incorporate the queue as an intercase feature in the DL model, thus further improving the performance in process scenarios where the queue plays an important role.