Forecasting hydrogen production potential in islamabad from solar energy using water electrolysis

The focus of this study is the use of Machine Learning methods to forecast Solar Hydrogen production potential for the Islamabad region of Pakistan. For this purpose, we chose a Photovoltaic-Electrolytic (PV-E) system to forecast electricity and, hence, hydrogen production. The weather data used for forecasting and simulation were recorded with precise meteorological instruments stationed in Islamabad, over the course of 13 and a half months. Out of the three tested algorithms, Prophet performs the best with Mean Absolute Percentage Error of 3.7%, forecasting a daily average Hydrogen production of 93.3 x 10(3) kg/Km(2). Although, the forecast in this study is made for the month of August and September, during which the local season moves towards winter, this study demonstrates solar hydrogen production, as a green energy source, has a tremendous potential in this region. (C) 2020 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

Automated summary

This study forecasts the solar hydrogen production potential in the Islamabad region using machine learning methods, demonstrating significant potential for green energy production in the area.