Predicting Power and Hydrogen Generation of a Renewable Energy Converter Utilizing Data-Driven Methods: A Sustainable Smart Grid Case Study

Abstract

This study proposes a data-driven methodology for modeling power and hydrogen generation of a sustainable energy converter. The wave and hydrogen production at different wave heights and wind speeds are predicted. Furthermore, this research emphasizes and encourages the possibility of extracting hydrogen from ocean waves. By using the extracted data from the FLOW-3D software simulation and the experimental data from the special test in the ocean, the comparison analysis of two data-driven learning methods is conducted. The results show that the amount of hydrogen production is proportional to the amount of generated electrical power. The reliability of the proposed renewable energy converter is further discussed as a sustainable smart grid application.

Sustainable Electrification—Advances and Challenges in Electrical-Distribution Networks: A Review

“…The proposal in [81] introduces a data-driven methodology to model energy and hydrogen generation from sustainable energy converters, specifically wave generators. The integration of artificial intelligence emphasizes the potential of reliable models supporting the progress of oceanic renewable energy systems.…”

“…The innovative use of artificial intelligence in [81] to predict hydrogen production from wave generators highlights the growing importance of digitization and real-time prediction in efficient energy management. These advanced approaches could become key trends for optimizing performance and real-time decision making in renewable energy systems.…”

The Research Agenda on Smart Grids: Foresights for Social Acceptance

“…The large-scale adoption of SGs might have far-reaching effects on not just our energy infrastructure but also our lifestyles and relationships with the natural environment [34,35]. Smart cities, which include networked and ecologically optimized transportation and housing systems [36,37], may be built by these grids, which have the capacity to co-ordinate a wide variety of digital devices and infrastructures, such as electric vehicles (EVs) and renewable energy systems [38,39]. SGs enable EVs to transfer excess power to the grid, thus supporting e-mobility [40].…”

Energy Efficiency Evaluation and Forecasting of the Sussex Ports to Address Climate Change Concerns: a Data-driven Decision Model

“…Balancing between cost, voltage stability in generation centers and energy consumption from end user side is a problem for renewable energy management in smart grid stability. For the end user side, prediction of energy management factors and behavior price provisioning is an important challenge that machine learning algorithms can detect and help in overcoming through developing appropriate solutions for this problem (Mirshafiee et al, 2023). Some recent review papers, like Rangel-Martinez et al ( 2021) and Zhang et al (2018), have categorized renewable energy management strategies according to existing aspects of prediction approaches such as machine learning and deep learning methods in power communication systems (Xu et al, 2022)…”