TY  - CONF
AV  - none
CY  - Auckland
KW  - Approximation capabilities; Combined forecasts; Comparative studies; Different structure; Forecasting performance; forecasts combination; Load demand; Load forecasting; Neural network model; Real world data; Short term load forecasting; Short-term forecasting; Training algorithms
KW  -  Electric load forecasting; Neural networks
KW  -  Forecasting
ID  - scholars2615
TI  - Improving load forecasting accuracy through combination of best forecasts
N1  - cited By 5; Conference of 2012 IEEE International Conference on Power System Technology, POWERCON 2012 ; Conference Date: 30 October 2012 Through 2 November 2012; Conference Code:95313
N2  - Neural network (NN) models have been widely used in the literature for short-term load forecasting. Their popularity is mainly due to their excellent learning and approximation capability. However, their forecasting performance significantly depends on several factors including initializing parameters, training algorithm, and NN structure. To minimize negative effects of these factors, this paper proposes a practically simple, yet effective and an efficient method to combine forecasts generated by NN models. The proposed method includes three main phases: (i) training NNs with different structures, (ii) selecting best NN models based on their forecasting performance for a validation set, and (iii) combination of forecasts for selected best NNs. Forecast combination is performed through calculating the mean of forecasts generated by best NN models. The performance of the proposed method is examined using real world data set. Comparative studies demonstrate that the accuracy of combined forecasts is significantly superior to those obtained from individual NN models. © 2012 IEEE.
SN  - 9781467328685
Y1  - 2012///
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84873291814&doi=10.1109%2fPowerCon.2012.6401332&partnerID=40&md5=4617967756fb43c0d39b56a324445bea
A1  - Hassan, S.
A1  - Khosravi, A.
A1  - Jaafar, J.
ER  -