Multi-kernel anticipatory approach to intelligent control with application to load management of electrical appliances
Miltiadis Alamaniotis, Lefteri H. Tsoukalas · 2016
Anticipatory systems are systems whose change of state depends on present and future information about the system itself as well as its environment. Making control decisions based on prediction of the possible outcomes is an inherent feature of human decision making process. The advent of the big data era followed by technological advancements in machine intelligence has provoked us to revisit the role of intelligent control systems and their role in decision making. In this manuscript, a multi-kernel anticipatory system for intelligent control is proposed. In particular, multiple kernel-modeled Gaussian processes are integrated with fuzzy logic rules in order to make decisions. In the current paper, the architecture of the system is described and functionality of individual parts is explained. Finally, its application on load control in electrical appliances connected to smart power grid with data taken from GRIDLAB-d demonstrating the advantages of the proposed control system is shown.