基于Holt指数平滑模型的软件可靠性预测

SOFTWARE RELIABILITY PREDICTION BASED ON HOLT EXPONENTIAL SMOOTHING MODEL

随着软件规模的日益增大,软件可靠性对软件质量保证起着举足轻重的作用。为了更好地对软件可靠性进行预测,本文首先对常用的指数平滑模型——Holt模型和阻尼Holt模型进行分析,然后根据软件可靠性准则误差平方和(SSE)建立数学模型,并分别计算出最小SSE值对应的最优的平滑系数。实验表明采用Holt模型进行软件可靠性预测的精度较高,且阻尼Holt模型的预测结果优于Holt模型,预测结果从平滑系数的经验选取法和软件可靠性的PRR准则上都得到了验证。由此得出结论,将Holt和阻尼Holt指数平滑模型用于软件可靠性的预测有很高的拟合度。

Software reliability plays a very important role in software quality assurance with the increasing scale of the software.So, the prediction of software reliability is discussed in the paper. Firstly, the paper analyzes exponential smoothing model which is widely used—Holt model and damped Holt model. Then mathematical model is built based on the sum of squared errors of software reliability rule. Finally the best smoothing factor is calculated while the minimum value of SSE is aquired. The experiment shows that the Holt model has precision in software reliability prediction, and the result of damped Holt model is better than Holt model, which is validated from the smoothing factor decided by experience and the prediction of risk rate of software reliability rule. Holt and damped Holt exponential smoothing model which is used to predict the reliability of software have a very high degree of fitting in conclusion.