Hybrid Energy Storage System Dataset and Reproducibility Code for Multi-Task LSTM–GRU-Based Power Loss Prediction

Résumé fourni par la source

This repository contains the source code accompanying the study entitled “Explainable Multi-Task LSTM–GRU Framework for Power Loss Prediction and Energy Efficiency Assessment in Hybrid Renewable Energy Storage Systems.” The archived software package includes the Jupyter Notebook used for data preprocessing, sliding-window sequence generation, development and evaluation of the multi-task LSTM and GRU models, regression and efficiency-classification analyses, statistical evaluation, and SHAP- and LIME-based explainability analyses. The package also contains a README file, software requirements, and an MIT License. The exact dataset version used with this code is publicly available in the companion Zenodo dataset repository: https://doi.org/10.5281/zenodo.21805274

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.