Symbolic Performance and Dependability Evaluation with the Tool CASPA

This paper describes the tool CASPA, a new performance evaluation tool which is based on a Markovian stochastic process algebra. CASPA uses multi-terminal binary decision diagrams (MTBDD) to represent the labelled continuous time Markov chain (CTMC) underlying a given process algebraic speci cation. All phases of modelling, from model construction to numerical analysis and measure computation, are based entirely on this symbolic data structure. We present several case studies which demonstrate the superiority of CASPA over sparse-matrixbased process algebra tools. Furthermore, CASPA is compared to other symbolic modelling tools.