A traditional application with only one design paradigm can not well adapt to the constant variations of contexts and user preferences in pervasive computing. In this paper, we argue that a pervasive computing application should support multiple design paradigms and present an approach to dynamically selecting the most appropriate paradigm at runtime according to environmental changes. Based on analyzing the characteristics of adaptive software architecture, this paper presents the general paradigm selection rules which can be combined with the specific context to automatically or semi-automatically create the applicable software (re)configuration strategies. For mobile components paradigm, a novel heuristic software partitioning algorithm is proposed to reasonably allocate a pervasive computing application among machines for resource conservation. Finally, we discuss a case study that demonstrates the flexibility and effectiveness of our approach.