Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting
Accurate forecasting of electricity consumption is crucial for refined planning and improved transmission and distribution efficiency. Power consumption data, being nonstationary and nonlinear, is significantly affected by factors such as seasons and holidays, making traditional computational method...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-06-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_199135_3b1bc65dac1b0209276a01cae0fd629d.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Accurate forecasting of electricity consumption is crucial for refined planning and improved transmission and distribution efficiency. Power consumption data, being nonstationary and nonlinear, is significantly affected by factors such as seasons and holidays, making traditional computational methods time-consuming and less accurate. This paper proposes a forecasting approach using a hybrid model of the Radial Basis Function (RBF) algorithm, where the hyperparameters are tuned by six meta-heuristic optimizers to enhance precision and speed. These optimizers include Grey Wolf Optimizer (GWO), Advanced Gray Wolf Optimization (AGWO), Moth-Flame Optimization Algorithm (MFO), Particle Swarm Optimization (PSO), Multi-Verse Optimizer (MVO), and Artificial Bee Colony (ABC). The results indicate that the RBF combined with AGWO performs optimally and shows lower error values compared to other optimizers. Specifically, the coefficient of determination (R²) values for the training, testing, and total datasets are 0.9994, 0.9920, and 0.9985, respectively, demonstrating that AGWO is the most precise optimizer among the studied meta-heuristic algorithms. |
|---|---|
| ISSN: | 2821-0263 |