Structural Learning of Two Layer Boltzmann Machine and Its Application to Power System Investment Planning

Abstract

In order to solve a problem efficiently, a structural learning of Boltzmann machine had been proposed and this method enables researcher to solve the problem defined in terms of mixed integer quadratic programming. From this proposed method, an effective selection of results was obtained. In this research, an analysis was performed by using the concepts of the reliability and risks of units evaluated using a variance-covariance matrix. In addition, the effect and expanses of replacement are also measured. Mean-variance analysis is formulated as a mathematical programming with two objectives to minimize the risk and maximize the expected return. Then, a Boltzmann machine was employed to solve the mean-variance analysis efficiently. Findings from this study show that the result of the structural learning of Boltzmann machine method was exemplified. For this reason, the effectiveness of the decision making process can be enhanced.