PurposeA decade and a half after the debut of pervasive computing, a large number of prototypes, applications, and interaction interfaces have emerged. However, there is a lack of consensus about the best approaches to create such systems or how to evaluate them. To address these issues, this paper aims to develop a performance evaluation framework for pervasive computing systems.Design/methodology/approachBased on the authors' experience in the Gator Tech Smart House – an assistive environment for the elderly, they established a reference scenario that was used to guide the analysis of the large number of systems they studied. An extensive survey of the literature was conducted, and through a thorough analysis, the authors derived and arrived at a broad taxonomy that could form a basic framework for evaluating existing and future pervasive computing systems.FindingsA taxonomy of pervasive systems is instrumental to their successful evaluation and assessment. The process of creating such taxonomy is cumbersome, and as pervasive systems evolve with new technological advances, such taxonomy is bound to change by way of refinement or extension. This paper found that a taxonomy for something so broad as pervasive systems is very complex. It overcomes the complexity by focusing the classifications on key aspects of pervasive systems, decided purely empirically and based on the authors own experience in a real‐life, large‐scale pervasive system project.Originality/valueThere are currently no methods or frameworks for comparing, classifying, or evaluating pervasive systems. The paper establishes a taxonomy – a first step toward a larger evaluation methodology. It also provides a wealth of information, derived from a survey of a broad collection of pervasive systems.