Computer Science and Information Systems 2023 Volume 20, Issue 4, Pages: 1661-1685
https://doi.org/10.2298/CSIS230401057V
Full text ( 1165 KB)


Systematic exploitation of parallel task execution in business processes

Varvoutas Konstantinos (Department Of Informatics, Aristotle University of Thessaloniki Thessaloniki, Greece), [email protected]
Kougka Georgia (Department Of Informatics, Aristotle University of Thessaloniki Thessaloniki, Greece), [email protected]
Gounaris Anastasios (Department Of Informatics, Aristotle University of Thessaloniki Thessaloniki, Greece), [email protected]

Business process re-engineering (or optimization) has been attracting a lot of interest, and it is considered as a core element of business process management (BPM). One of its most effective mechanisms is task re-sequencing with a view to decreasing process duration and costs, whereas duration (aka cycle time) can be reduced using task parallelism as well. In this work, we propose a novel combination of these two mechanisms, which is resource allocation-aware. Starting from a solution where a given resource allocation in business processes can drive optimizations in an underlying BPMN diagram, our proposal considers resource allocation and model modifications in a combined manner, where an initially suboptimal resource allocation can lead to better overall process executions. More specifically, the main contribution is twofold: (i) to present a proposal that leverages a variant of representation of processes as Refined Process Structure Trees (RPSTs) with a view to enabling novel resource allocation-driven task re-ordering and parallelisation in a principled manner, and (ii) to introduce a resource allocation paradigm that assigns tasks to resources taking into account the re-sequencing opportunities that can arise. The results show that we can yield improvements in a very high proportion of our experimental cases, while these improvements can reach a 45% decrease in cycle time.

Keywords: business process optimization, process models, resequencing, parallelism, resource allocation

Show references