关键词: 参数变化, 执行时间预测, 云应用程序, 静态预估

Abstract: It proposes a static forecast method on the basis of the change of parameter to forecast execution time of programs, according to the number of code executed. It obtains the number of code executed by analysing source code of task and resource evaluation, draws the trend of number of code executed changed with parameter by automatic curve fitting, finds out the relationship between the number of code executed and running time by operating applications practically, and program running time with the tendency of changes in parameters is obtained. It uses PASCAL Hanoi program to verify this forecast method, measures the program run time with the change of parameters by fitting test and running program. The results show that the predicted run time is very close to the real running time.

Key words: parameters change, execution time prediction, cloud application, static forecast