Efficient software test case generation using genetic algorithm based graph theory

In orthodox software testing approach we generally use modeling based testing approach for generating the test cases of a given problem. This leads to confusion of the test input and the expected output for a given test case. More over we also can miss some of the test cases due to lack of clarity in the test paths. To over come such sort of predictive modeling we propose graph theory based genetic approach to generate test cases for software testing. At first we will create a directed graph of all the intermediate state of the system for the expected behavior of the system. Then we will create a population of all the nodes of the graph as the base population of genetic algorithm. From this population we can find a pair of node the parents and perform genetic crossover and mutation on them for the getting the optimum child nodes as the out put. We should continue this process of genetic operation until all the nodes are covered or any of the nodes, which are visited more than once, should be discarded form the population. Then follow the same process for the generation of test case in the real time system. This technique will be more concrete in case of network testing or any of the system testing where the predictive model based tests are not optimized to produced the out put. © 2008 IEEE.