A Review of Applications of Artificial Intelligence Technologies to Energy Fields

Abstract

Recently, many countries focus on achieving carbon neutral by 2050, and researches on optimal operation of energy plants in factories and large commercial buildings have been conducted for energy saving and reduction of CO2 emissions. Since the optimal operation problem of energy plants can be formulated as a mixed integer nonlinear optimization problem, evolutionary computation techniques, which is one of artificial intelligence (AI) techniques, have been applied. On the other hand, in energy facilities, when AI techniques are required, the Least Squares Method (LSM) has been applied in various problems. One of the main purposes to apply the LSM is to solve the problems only using measured data without experts' knowledge. However, in practical fields, outliers may be included in the measured data because of setting errors of sensors, radio interference, and so on. When LSM is applied with the outliers, inappropriate results may be obtained. Maximum Correntropy Criterion (MCC) is one of the technology trends to tackle the challenge. This paper reviews researches on applications of evolutionary computation techniques to optimal operation of energy plants and presents applications of MCC with AI techniques to energy problems.