Design of Home Power Energy Management System Using Mixed Integer Linear Programming (MILP) Based on Extreme Learning Machine (ELM) Dynamic Pricing
Dimas Fajar Uman Putra, Muhammad Ali Fikri, Akhmad Rizki Hidayatullah, Adi Soeprijanto · International Review of Automatic Control (IREACO) · 2019
Indonesia's electricity consumption has grown at an average of 4.2% per year over the past 15 years. This causes several problems such as environmental pollution and depletion of fossil energy sources. In order to overcome these problems, one of the things that can be done is saving electricity consumption. In this paper, home power management system (HPMS) application is developed with the goal for saving electricity consumption in order to minimize the daily operation cost. The HPMS system consists of smart electrical appliances, power units (grid and photovoltaic systems with energy storage), main controllers, web applications and communication networks. At the beginning of the day, the main controller will collect electricity equipment operation schedules and electricity prices from the grid and PV. Moreover, MILP, which is formulated with the operating constraints for electrical equipment, electricity prices (obtained from ELM predictions), and power resources, is used for solving the problem and will recommend the schedule of electricity resources with the most optimal costs for consumers. The simulation has been successfully tested with the results that HPMS can reduce electricity costs by more than 30%.