Comprehensive forecasting based analysis using stacked stateless and stateful Gated Recurrent Unit models

TL;DR

This paper explores solar irradiance forecasting using stacked stateful and stateless Gated Recurrent Unit models across four regions, demonstrating that stateful models significantly improve prediction accuracy for renewable energy planning.

Contribution

It introduces a novel application of stacked stateful and stateless GRU models for solar irradiance forecasting, highlighting the superior accuracy of stateful models.

Findings

Stateful stacked GRU models outperform stateless models in accuracy.

Forecasting models effectively predict solar irradiance considering regional parameters.

The approach aids in better renewable energy resource planning.

Abstract

Photovoltaic power is a renewable source of energy which is highly used in industries. In economically struggling countries it can be a potential source of electric energy as other non-renewable resources are already exhausting. Now if installation of a photovoltaic cell in a region is done prior to research, it may not provide the desired energy output required for running that region. Hence forecasting is required which can elicit the output from a particular region considering its geometrical coordinates, solar parameter like GHI and weather parameters like temperature and wind speed etc. Our paper explores forecasting of solar irradiance on four such regions, out of which three is in West Bengal and one outside to depict with using stacked Gated Recurrent Unit (GRU) models. We have checked that stateful stacked gated recurrent unit model improves the prediction accuracy significantly.