Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 25, 2026EnergiesOpen Access

A Hybrid Deep Learning Framework for National Level Power Generation Forecasting of Different Energy Sources Including Renewable Energy and Fossil Fuel

View Full Paper
Ask AI
Bookmark
Share

Authors

RDRemon DasWestern Carolina UniversityTKTarek KandilWestern Carolina UniversityAHAdam HarrisWestern Carolina University

Discussion

Loading...

Member takes

Overview

Presents a hybrid framework for forecasting electricity generation in different energy sources, indicating improved accuracy and reliability.

Key Points

  • The aim is to develop an advanced forecasting method for national electricity generation that accommodates both renewable and fossil fuel sources.
  • Proposed a hybrid deep learning framework combining CNN, LSTM, and Bi-LSTM models.
  • Utilized seasonal-trend decomposition with loess for extracting trend, seasonal, and residual components.
  • Developed source-specific architectures for each energy source based on performance.
  • Achieved a total power forecasting accuracy with MAPE of 2.60%.
  • Best results from CNN-Bi-LSTM model yielding RMSE of 13,745 MWh and MAE of 9,542 MWh.
  • Bi-LSTM models outperformed for forecasting wind, biomass, geothermal, and nuclear energy.

Cite This Study

Das et al. (2026) studied this question.

synapsesocial.com/papers/69c37be2b34aaaeb1a67eab5https://doi.org/10.3390/en19061564
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Hybrid Deep Learning Model for Wind and Solar Power Forecasting in Smart Grids2025 · 2 citations
  2. 2Comprehensive Assessment and Comparative Analysis of Deep Learning Models for Large-Scale Renewable Energy Power Generation Prediction: A National Perspective2024
  3. 3A Hybrid Deep Learning Approach for Multi‐Output Short‐Term Electricity Demand Forecasting2025 · 25 citations
  4. 4Hybrid Deep Learning Models for Energy Consumption Forecasting: A CNN-LSTM Approach for Large-Scale Datasets2025 · 2 citations
  5. 5Hybrid Deep Learning Approaches for Accurate Electricity Price Forecasting: A Day-Ahead US Energy Market Analysis with Renewable Energy2025