Predicting change impact in architecture design with Bayesian belief networks

Research into design rationale in the past has focused on the representation of reasons and has omitted the connections between design rationales and design artefacts. Without such connections, designers and architects cannot easily assess how changing requirements or designs may affect the system. In this paper, we introduce a model called Architecture Rationale and Element Linkage (AREL) to represent the causal relationship between architecture elements and decisions. We further model AREL as a Bayesian Belief Network (BBN) to capture the probabilistic relationships between architecture elements and decisions in an architecture design model. Such probabilistic modelling enables architects to quantitatively predict and diagnose impact of change when part of the requirements or designs are changing. Using a partial design of a cheque image processing system, we illustrate how AREL is used to represent the decision model and how BBN is used to predict and diagnose change in the architecture design. We use a UML tool to capture the AREL model and a BBN tool to compute the probabilities of change impact