An execution environment as a service for adaptive long-running workflows

Abstract

Purpose

This paper aims to present Long4Cloud (long-running workflows execution environment for cloud), a distributed and adaptive LRW execution environment delivered “as a service” solution.

Design/methodology/approach

LRWs last for hours, days or even months and their duration open the possibility of changes in business rules, service interruptions or even alterations of formal regulations of the business before the workflow completion. These events can lead to problems such as loss of intermediary results or exhaustion of computational resources used to manage the workflow execution. Existing solutions face those problems by merely allowing the replacement (at runtime) of services associated with activities of the LRW.

Findings

LONG4Cloud extends the previous works in two main aspects, namely, the inclusion of dynamic reconfiguration capabilities and the adoption of an “as a service” delivery mode. The reconfiguration mechanism uses quiescence principles, data and state management and provides multiple adaptive strategies. Long4Cloud also adopts a scenario-based analysis to decide the adaptation to be performed. Events such as changes in business rules or service failures trigger reconfigurations supported by the environment. These features have been put together in a solution delivered “as a service” that takes advantage of cloud elasticity and allows to better allocate cloud resources to fit into the demands of LRWs.

Originality/value

The original contribution of Long4Cloud is to incorporate adaptive capabilities into the LRW execution environment as an effective way to handle the specificities of this kind of workflow. Experiments using current data of a Brazilian health insurance company were carried out to evaluate Long4Cloud and show performance gains in the execution of LRWs submitted to the proposed environment.

Citation

Souza-Júnior, M.S.d., Rosa, N.S. and Lins, F.A.A. (2021), "An execution environment as a service for adaptive long-running workflows", International Journal of Web Information Systems, Vol. 17 No. 2, pp. 117-139. https://doi.org/10.1108/IJWIS-12-2020-0077