TY  - CONF
KW  - Algorithms; Electric load forecasting; Forecasting; Genetic algorithms; Neural networks
KW  -  Computational costs; Computational intelligent techniques; Forecast accuracy; Load forecasting; Multi objective algorithm; Multi-layer perceptron neural networks; Network structures; Neural network topology
KW  -  Network architecture
ID  - scholars4899
TI  - Optimization of neural network architecture using genetic algorithm for load forecasting
N2  - In this paper, a computational intelligent technique genetic algorithm (GA) is implemented for the optimization of artificial neural network (ANN) architecture. The network structures are normally selected on the basis of the developer's prior knowledge or hit and trial approach is used for this purpose. ANN based models are frequently used for the prediction of future load, because of their learning and mapping ability to address the non linear nature of electrical load. The proposed technique provides a pathway to determine the best ANN architecture, prior to the training and learning process of neural network. Multi-objective algorithm is proposed in this research which optimizes the ANN architecture that leads to enhancement in load forecast accuracy and reduction in the computational cost. The results of several experiment conducted during this work, exhibits that forecast accuracy is considerably enhanced by using an optimized and reduced ANN structure. © 2014 IEEE.
N1  - cited By 33; Conference of 2014 5th International Conference on Intelligent and Advanced Systems, ICIAS 2014 ; Conference Date: 3 June 2014 Through 5 June 2014; Conference Code:107042
AV  - none
CY  - Kuala Lumpur
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84906351337&doi=10.1109%2fICIAS.2014.6869528&partnerID=40&md5=6a8e6d25720013a075c72cc181885672
A1  - Islam, B.U.
A1  - Baharudin, Z.
A1  - Raza, M.Q.
A1  - Nallagownden, P.
SN  - 9781479946549
PB  - IEEE Computer Society
Y1  - 2014///
ER  -