Internet of Things (IoT) based Microgrid System for Optimal Scheduling: Case Study Kadoma-Zimbabwe

The electricity demand is increasing day by day due to industrial growth and the rise in the living standards of human beings in Kadoma, Zimbabwe. Electricity generation cannot only be dependent on fossil fuels because of carbon dioxide emissions to the atmosphere, which causes global warming and its devastating effects. In the context of distributed generation, renewable energies (RE)-based Microgrids (MGs) could be sourced to meet the electricity demand. However, the unpredictable nature of RE resources may pose a significant risk of unavailable and/or unreliable electricity supply. This paper proposes optimal scheduling by making use of Internet of Things (IoT) devices in the MG. The MG system comprised a solar farm, wind farm, battery storage system (BSS), diesel generator, and a residential load. The proposed decision-making algorithm was developed using python and was implemented to improve scheduling in the MG system. Additionally, a comparison between three machine learning algorithms (Artificial Neural Network, Random Forest and Extreme Gradient Boosting) was implemented to determine the superior algorithm when it comes to accurately predict the sources to give power at a certain time to satisfy the load. The results indicated that the availability of electricity was enhanced by the use of IoTs in the microgrid. For accuracy prediction, the Extreme Gradient Boosting machine learning algorithm outperformed the Artificial Neural Network and Random Forest machine learning algorithms.