Integration of Root Cause Analysis into a Model-Based Testing Process of a Mobile Switching Server

Abstract

Model-based testing of software has proved effective for automation of testing and efficient error discovery, by utilizing modeled behavior of the system under test and automated test case generation. One of the important challenges in model-based testing is locating the fundamental sources of encountered errors. A root cause analysis solution should be able to find the causes of errors among different components in a model-based testing process, while automating the analysis to eliminate daunting data-intensive manual work. We present a design for a Root Cause Analyzer (RCA) component, aimed at automated test analysis utilizing the outputs generated in a model-based testing process, and producing human and machine readable analysis reports. A prototype RCA implementation is integrated into a tool chain used for offline functional testing of a Mobile Switching Server (MSS) in cellular networks. The RCA prototype is shown to discover causes of errors encountered during testing and pinpointing them in several components of the testing environment. The RCA design also demonstrates potential for integration into other model-based testing processes.