|کد مقاله||کد نشریه||سال انتشار||مقاله انگلیسی||ترجمه فارسی||نسخه تمام متن|
|5001248||1460870||2017||7 صفحه PDF||سفارش دهید||دانلود کنید|
- Boosted neural networks (BNNs) lower load forecasting error and its variation.
- The BNNs consist of iteratively training different neural network models.
- The BNNs need lower computation time compared to bagged neural networks.
- Data from the New England Pool region show the improvement offered by the BNNs.
This paper presents an improved technique for short-term electric load forecasting making use of boosted neural networks (BooNN). The BooNN consist of combining a set of artificial neural networks (ANNs) trained iteratively. At each iteration, the error between the estimated output from the ANN model trained in the previous iteration and the target output is minimized. The final predicted result is the weighted sum of output from all the trained models. This process reduces the magnitude of forecasting errors and their variation compared to a single ANN and bagged neural networks (BNN). It further significantly lowers computational time compared to BNN. Results with real data further confirm that BooNN lead to improved load forecasting performance with respect to other existing techniques.
Journal: Electric Power Systems Research - Volume 143, February 2017, Pages 431-437