Control energy management system for photovoltaic with bidirectional converter using deep neural network

Widjonarko Widjonarko, Wahyu Mulyo Utomo, Saodah Omar, Fatah Ridha Baskara, Marwan Rosyadi


Rapid population growth propels technological advancement, heightening electricity demand. Obsolete fossil fuel-based power facilities necessitate alternative energy sources. Photovoltaic (PV) energy relies on weather conditions, posing challenges for constant energy consumption. This hybrid energy source system (HESS) prototype employs extreme learning machine (ELM) power management to oversee PV, fossil fuel, and battery sources. ELM optimally selects power sources, adapting to varying conditions. A bidirectional converter (BDC) efficiently manages battery charging, discharging, and secondary power distribution. HESS ensures continuous load supply and swift response for system reliability. The optimal HESS design incorporates a single renewable source (PV), conventional energy (PNL and genset), and energy storage (battery). Supported by a BDC with over 80% efficiency in buck and boost modes, it stabilizes voltage and supplies power through flawless ELM-free logic verification. Google Colab online testing and hardware implementation with Arduino demonstrate ELM's reliability, maintaining a direct current (DC) 24 V interface voltage and ensuring its applicability for optimal HESS.


Energy storage; Extreme learning machine; Hybrid energy source system; Power management system; Renewable energy

Full Text:



Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578

This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).