Run-based exception prediction for workflows

A run-based exception prediction algorithm for workflows is proposed.Structured, nested, and simple crossing loops in workflow models are considered.Finer control of prediction process is enabled by using thresholds and probabilities.Five workflow models having different characteristics are used for evaluation.The proposed approach achieves significant results in prediction accuracy. Events such as iteration of activities or lack of available resources can cause temporal exceptions in business processes. Exception prediction can improve the quality of workflow execution since preventive actions can be taken to reduce the occurrence of exceptions. Thus, it is crucial to provide an accurate and efficient temporal exception prediction capability for workflow management systems. In this paper, we propose a run-based exception prediction algorithm to predict temporal exceptions in workflows. The proposed algorithm is divided into two phases, design-time and run time. At design-time, all possible runs are generated from a workflow and their estimated execution time and mapping probability are calculated. At run time, temporal exceptions are predicted by analyzing the runs. Simulation experiments are performed to evaluate the proposed approach using five workflow models having different characteristics. Simulation experiments show that our approach is efficient and produces good results in prediction accuracy.