Machine Learning-Driven Techno-Economic Optimization of Hybrid Renewable Energy Systems with Hydrogen Storage for rural electrification in developing countries

Achieving net-zero targets in developing countries requires deploying renewable energy in off-grid areas where grid expansion is impractical. High capital costs for renewable energy and hydrogen storage hinder adoption, with many systems being inefficient due to poor sizing or curtailment. This research focuses on developing a hybrid AI and optimization framework to enhance the sizing and economic analysis of renewable energy systems. It aims to create a cost-effective Hybrid Renewable Energy System (HRES) for off-grid electrification in Nigeria or similar locations in Canada or globally. Building predictive models using Linear Regression, Tree Support vector Machines (SVM), Ensemble, Gaussian Process Regression, neural Network, and Kernel models is proposed for estimating the Levelized Cost of Electricity (LCOE) of the systems. By leveraging innovative AI solutions, the study aims to promote net-zero technologies and address barriers to transitioning to a low-carbon economy.

Faculty Supervisor:

Raphael Idem

Student:

Partner:

Monash University Malaysia

Discipline:

Engineering

Sector:

Green/Alternative Energy; Clean Technology; Sustainability and the Environment

University:

University of Regina

Program: