Editor/Reviewer loginFrequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
IJCATR Volume 6 Issue 12
A Novel Combined Approach for Daily Electric Load Forecasting Based on Artificial Neural Network and Modified Bat Algorithm
Eduardo Capra , Hugo Ribeiro
10.7753/IJCATR0612.1001
keywords : Short-Term Load Forecasting, Bat Algorithm, Artificial Neural Network, Intelligent Systems, Optimization Algorithm
In this paper a novel combined method based on Modified Bat Algorithm (MBA) and Neural Network algorithm has proposed in order to forecast the electric peak load power. In the proposed method, Bat Algorithm is employed as a popular optimization method and Artificial Neural Network is also utilized as a powerful mathematic method in mapping nonlinear relationship among model variables for the purpose of electric daily load prediction. Additionally, in order to improve the performance of the bat algorithm with regards to avoiding tapping into the local optimal and increasing the convergence speed, some modification has performed in bat algorithm which is called as SAMBA. Experimental results indicate that the proposed method has superiority performance in comparison with other traditional machine learning algorithms
@artical{e6122017ijcatr06121001,
Title = "A Novel Combined Approach for Daily Electric Load Forecasting Based on Artificial Neural Network and Modified Bat Algorithm",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "6",
Issue ="12",
Pages ="467 - 472",
Year = "2017",
Authors ="Eduardo Capra , Hugo Ribeiro"}
The paper proposed a new method for short term load forecasting
The proposed hybrid method is based on Artificial Neural Network and Modified Bat Algorithm
The Modification in Bat Algorithm is introduced to avoid tapping in local optima and increasing convergence speed
The modified Bat Algorithm is utilized to tune the weight and adjusting factors of Neural Network.