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!
|
| _version_ | 1823856409809256448 |
|---|---|
| author | Dhivagar Shanmugam V Ramana |
| author_facet | Dhivagar Shanmugam V Ramana |
| author_sort | Dhivagar Shanmugam |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-300420b3a6e5418f83d90aa81078b7fc |
| institution | Kabale University |
| issn | 2821-0263 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Advances in Engineering and Intelligence Systems |
| spelling | doaj-art-300420b3a6e5418f83d90aa81078b7fc2025-02-12T08:47:56ZengBilijipub publisherAdvances in Engineering and Intelligence Systems2821-02632024-06-0100302638210.22034/aeis.2024.458715.1198199135Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption ForecastingDhivagar Shanmugam0V Ramana1Department of Electrical and Electronics Engineering, K. S. R. College of Engineering, Tiruchengode, Tamil Nadu, 637215, IndiaDepartment of Computer Science and Engineering, K.S.R.M. College of Engineering (UGC-Autonomous), Kadapa, Andhra Pradesh, 516005, IndiaAccurate 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.https://aeis.bilijipub.com/article_199135_3b1bc65dac1b0209276a01cae0fd629d.pdfadvanced gray wolf optimizationshort-term electricity consumption forecastinghybrid methodsradial basis function neural networkparticle swarm optimizer |
| spellingShingle | Dhivagar Shanmugam V Ramana Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting Advances in Engineering and Intelligence Systems advanced gray wolf optimization short-term electricity consumption forecasting hybrid methods radial basis function neural network particle swarm optimizer |
| title | Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting |
| title_full | Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting |
| title_fullStr | Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting |
| title_full_unstemmed | Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting |
| title_short | Different Meta-Heuristic Optimized Radial Basis Function Neural Network Models for Short-Term Power Consumption Forecasting |
| title_sort | different meta heuristic optimized radial basis function neural network models for short term power consumption forecasting |
| topic | advanced gray wolf optimization short-term electricity consumption forecasting hybrid methods radial basis function neural network particle swarm optimizer |
| url | https://aeis.bilijipub.com/article_199135_3b1bc65dac1b0209276a01cae0fd629d.pdf |
| work_keys_str_mv | AT dhivagarshanmugam differentmetaheuristicoptimizedradialbasisfunctionneuralnetworkmodelsforshorttermpowerconsumptionforecasting AT vramana differentmetaheuristicoptimizedradialbasisfunctionneuralnetworkmodelsforshorttermpowerconsumptionforecasting |