Evolutionary algorithms' performance can be enhanced significantly by using suitable parameter configurations when solving optimization problems. Most existing parameter-tuning methods are inefficient, which tune algorithm's parameters using whole benchmark function set and only obtain one parameter configuration. Moreover, the only obtained parameter configuration is likely to fail when solving different problems. In this paper, we propose a framework that applying portfolio for parameter-tuned algorithm (PPTA) to address these challenges. PPTA uses the parameter-tuned algorithm to tune algorithm's parameters on one instance of each problem category, but not to all functions in the benchmark. As a result, it can obtain one parameter configuration for each problem category. Then, PPTA combines several instantiations of the same algorithms with different tuned parameters by portfolio method to decrease the risk of solving unknown problems. In order to analyse the performance of PPTA framework, we embed several test algorithms (i.e. GA, DE and PSO) into PPTA framework constructing algorithm instances. And the PPTA instances are compared with default test algorithms on BBOB2009 and CEC2005 benchmark functions. The experimental results has shown PPTA framework can significantly enhance the basic algorithm's performance and reduce its optimization risk as well as the algorithm's parametertuning time.