Comparative Analysis of Classical and Hybrid Quantum Recurrent Models for Photovoltaic Power Forecasting
Abstract
The existing method for predicting short-term photovoltaic (PV) power generation faces difficulties because of two main issues which occur when weather conditions produce nonlinear changes,fast weather changes which impact power grid operations and energy distribution management. This study compares the classical Long Short-Term Memory (LSTM) model with the Hybrid Quantum Long Short-Term Memory (HQLSTM) model which uses a variational quantum circuit to improve its capacity for nonlinear feature representation under equivalent preprocessing and training conditions. This analysed an hourly solar power dataset which included meteorological data through a process that combined temporal resampling with zero-generation day removal,24-hour sliding window inputs, feature standardization and an 80:20 temporal train–test split method. The HQLSTM model achieves superior prediction accuracy compared to the LSTM model because its MAE value decreased from 0.0057 to 0.0352 ,RMSE value decreased from 0.0924 to 0.0693, provides better variance analysis with VAF equals 90.85 percent and R2 equals 0.9074. Hybrid quantum–classical recurrent architectures demonstrate their ability to produce precise study short-term PV power forecasts because they effectively capture both nonlinear and non-stationary generation patterns.
Read the paper
Related studies
- Chaos and quantum thermalization
- The Dalton quantum chemistry program system
- Cord Blood Leptin and Adiponectin as Predictors of Adiposity in Children at 3 Years of Age: A Prospective Cohort Study
- Quantitative metabolomics by H-NMR and LC-MS/MS confirms altered metabolic pathways in diabetes
- Stable adiabatic quantum batteries
- A novel self-lipid antigen targets human T cells against CD1c(+) leukemias
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.