No abstract

No abstract

Business process integration and monitoring provides an invaluable means for an enterprise to adapt to changing conditions. However, developing such applications using traditional methods is challenging because of the intrinsic complexity of integrating large-scale business processes and existing applications. Model Driven Developmente (MDDe) is an approach to developing applications-from domainspecific models to platform-sensitive models-that bridges the gap between business processes and information technology. We describe the MDD framework and methodology used to create the IBM Business Performance Management (BPM) solution. We describe how we apply model-driven techniques to BPM and present a scenario from a pilot project in which these techniques were applied. Technical details on models and transformation are presented. Our framework uses and extends the IBM business observation metamodel and introduces a data warehouse metamodel and other platform-specific and transformational models. We discuss our lessons learned and present the general guidelines for using MDD to develop enterprise-scale applications.

In this paper, we present a model-driven approach to Business Performance Management (BPM). BPM is a new frontier in IT-enabled enterprise that supports the monitoring and control of business operations. BPM solutions must be able to efficiently process business events, compute business metrics, detect business situations, and provide the real-time visibility of key performance indicators. In addition, system support is required for the rapid development of BPM solutions and the adaptation of the solutions to the dynamic business environment. We have adopted a metamodel, dubbed the observation meta-model, for capturing the business requirements for BPM, which frees solution developers from low-level programming concerns. We have also used a hybrid compilation-interpretation approach to map an observation model to the runtime executable. First, we extract and refactor the data aspect of the observation model to facilitate runtime access. Second, we compile the operational aspect of the model, such as logic for metric computation and situation detection, into Java code. Third, we develop a runtime engine that interprets the refactored model and dynamically loads the generated code, according to the meta-model. Our framework further enables the evolution and hot deployment of the observation model and provides the platform for several on-going customer engagement efforts.

No abstract