Intelligent Multi Agent System for Energy Management in the Classrooms with Grid Connected PV

This paper presents an application of the Multi Agent System (MAS) in the Building Energy Management System, more specifically to manage the energy in the classrooms of a university. The grid connected photovoltaic (PV) is used as the electrical generation system to supply the loads in the classrooms. The objective is to minimize the electricity cost while maintaining user comfort. The MAS consists of the PV Agent, the Utility Agent, the Load Agent and the Central Control Agent. In addition, the Course Scheduler Unit is employed to inform the utilization or occupancy of the classrooms. The proposed system provides a new method to manage the energy usage from the PV by changing the temperature set-point of the air conditioner system using the Fuzzy Logic Controller. The simulation results show that the proposed system provides the highest performance index of 0.9902 in the optimization of the electricity cost and temperature comfort compared to the conventional method using a fixed temperature set-point.