Computational Intelligence: Principles, Techniques and Applications
Computational Intelligence: Principles, Techniques and Applications
A TSK type fuzzy rule based system for stock price prediction
Expert Systems with Applications: An International Journal
Multiple-step-ahead prediction in control systems with Gaussian process models and TS-fuzzy models
Engineering Applications of Artificial Intelligence
Engineering Applications of Artificial Intelligence
Engineering Applications of Artificial Intelligence
Electric load forecasting using a fuzzy ART&ARTMAP neural network
Applied Soft Computing
Engineering Applications of Artificial Intelligence
Expert Systems with Applications: An International Journal
Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting
Knowledge-Based Systems
Hi-index | 0.00 |
Intelligent solutions, based on artificial intelligence (AI) technologies, to solve complicated practical problems in various sectors are becoming more and more widespread nowadays. On the other hand, electrical load prediction is one of the important concerns of power systems so development of intelligent prediction tools for performing accurate predictions is essential. This study presents an intelligent hybrid approach called ACO-SA by hybridization of Ant Colony Optimization (ACO) and Simulated Annealing (SA). The hybrid approach consists of two general stages. At the first stage time series inputs will be fed into ACO and it performs a global search to find a globally optimum solution. At the second stage, ACO's outcome will be fed into SA as initial solution and then SA starts local search around the ACO's global optimum and performs the tuning process on the initial solution. The superiority and applicability of the ACO-SA approach is shown for Iranian monthly load prediction problem and outcomes of the hybrid method are compared with Single ACO, Single SA and ANN technique (which is a common technique in the field of load prediction). Results show that ACO-SA approach outperforms rest of the methods regarding to prediction accuracy, so it can be considered as a promising alternative for load prediction studies.