Abstract: It may be impossible to re-execute the whole test suite in regression testing with the increasing size of software．In such a case,prioritizing test cases is vital to software regression testing．Test cases prioritization is a technique to search the best sequence of test cases execution．In regression testing for real projects,single-objective test cases prio-ritization has been gradually replaced by multi-objective prioritization,where the application of Evolution Algorithms to address multi-objective optimization problems is a hot spot in current research．However EAs are based on population genetic iterations in which the mechanism of exchanging information among populations is relatively complex,and consequently the efficiency of test suite prioritization based on EAs is sharply declining with the increase in the scale of the population．To address this problem,the paper presented a test suite prioritization technique based on Particle Swarm Optimization, proposed the corresponding particle representation,position and speed updated methods．Empirical studies were conducted to study the effect caused by different types of particle updating methods and size of particle swarm．Compared to the NSGA-Ⅱ based test case prioritization,the proposed technique is more efficient in test suite prioritization in real programs.