Multi-Attribute Utility Theory for Estimation of Optimal Release Time and Change-Point

Abstract

Existing optimal software release problems have been discussed by using an evaluation criterion such as cost, reliability, delivery. When we use the methods by those evaluation criteria, the optimal release time is determined by an evaluation criterion. However, it is more realistic that we determine the optimal release time with multiple attributes. Therefore, in this study, we estimate the optimal release time by using multi-attribute utility theory (MAUT). Since MAUT is one of utility theories, we can estimate an optimal release time and change-point from the perspective of utility by maximizing the multi-attribute utility function. Especially, we consider the both of two attributes: cost and reliability. Then, we apply a software reliability growth model (SRGM) with change-point to represent the cost and reliability attributes. Concretely, we use an exponential SRGM with change-point. That is, we can estimate not only the optimal release time but also change-point. Finally, we show numerical examples by using actual data sets. Especially, we check the behavior of the optimal release time, change-point, total software cost and utility.