Related Experiment Video
Updated: Jul 13, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.2K
Improved Giza pyramids construction algorithm for Modify the deep neural network-based method for energy demand
Xue Wang1, Saeid Razmjooy2,3
1Admissions and Employment Guidance Center, Xi'an Peihua University, Xi'an 710125, Shaanxi, China.
Heliyon
|October 16, 2023
Summary
This study introduces a new method combining deep neural networks (DNNs) with an enhanced Giza pyramid construction methodology for accurate energy demand forecasting. The novel approach significantly improves prediction accuracy across various time scales compared to existing models.
Area of Science:
- Energy Systems Engineering
- Artificial Intelligence
- Computational Science
Background:
- Accurate energy demand prediction is vital for optimizing energy systems, reducing costs, and enhancing service reliability.
- Deep Neural Networks (DNNs) are effective for energy forecasting but can be sensitive to data quality and hyperparameter selection.
- Existing forecasting models like modified BP neural network (MBPNN), Neural Network based Genetic Algorithm (NNGA), and reinforcement learning and deep neural network (RLDNN) have limitations.
Purpose of the Study:
- To propose a novel and more reliable technique for energy demand forecasting by integrating DNNs with an enhanced Giza pyramid construction methodology.
- To optimize DNN hyperparameter selection for improved forecasting accuracy and effectiveness.
- To evaluate the proposed method against state-of-the-art models using real-world energy demand data.
Main Methods:
- Developed an integrated approach combining Deep Neural Networks (DNNs) for capturing complex variable relationships and an enhanced Giza pyramid construction algorithm (IGPCA) for optimal hyperparameter tuning.
- Utilized real-world energy demand data for model evaluation.
- Benchmarked the proposed IGPCA/DNN method against MBPNN, NNGA, and RLDNN models.
Main Results:
- The proposed IGPCA/DNN method demonstrated superior energy prediction accuracy across short-term, medium-term, and long-term forecasting horizons.
- Achieved lower Mean Squared Error (MSE) scores: 0.564 (short-term), 0.587 (medium-term), and 0.629 (long-term), outperforming baseline models.
- The enhanced Giza pyramid construction methodology effectively optimized DNN hyperparameters, leading to improved forecasting performance.
Conclusions:
- The novel integration of DNNs and the enhanced Giza pyramid construction methodology provides a more reliable and effective solution for energy demand forecasting.
- The proposed approach significantly outperforms existing state-of-the-art models in terms of prediction accuracy and reliability.
- Accurate energy demand forecasting is crucial for optimizing energy system operations and reducing associated costs.
