Load forecasting based on neural networks and load profiling

Sousa, João; Pires Neves, Luís; H. M. Jorge

http://hdl.handle.net/10400.8/13200

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Load forecasting based on neural networks and load profiling.pdf	This work presents a novel perspective of load forecasting based on neural networks and load profiling. In addition to the variables that are typically used to predict future load demand, such as past load values, meteorological variables, seasonal effects or macroeconomic indexes, it is expected that the use of load profiles and detailed information of individual consumers could favor the forecasting process. The methodology can be extended to different temporal horizons being predicted and the eventual threat of overparametrization is attenuated by the use of neural networks since the complexity of the model does not necessarily depends on the number of its weights and biases, as some of these parameters might be found irrelevant in the process. Another way to reduce the risk of overparametrization and overfitting is through the use of a considerable number of data points (whenever historical data is available) to train the network.	549.07 KB	Adobe PDF	Download

Send Feedback

Authors

Sousa, João

Pires Neves, Luís

H. M. Jorge

Abstract(s)

This work presents a novel perspective of load forecasting based on neural networks and load profiling. In addition to the variables that are typically used to predict future load demand, such as past load values, meteorological variables, seasonal effects or macroeconomic indexes, it is expected that the use of load profiles and detailed information of individual consumers could favor the forecasting process. The methodology can be extended to different temporal horizons being predicted and the eventual threat of overparametrization is attenuated by the use of neural networks since the complexity of the model does not necessarily depends on the number of its weights and biases, as some of these parameters might be found irrelevant in the process. Another way to reduce the risk of overparametrization and overfitting is through the use of a considerable number of data points (whenever historical data is available) to train the network.

Description

Article number 5281832 - 2009 IEEE Bucharest PowerTech: Innovative Ideas Toward the Electrical Grid of the Future; Bucharest; Romania; 28 June 2009 through 2 July 2009; Category numberCFP09815-CDR; Code 78575

Keywords

Load Forecasting Load Profiling Neural Networks

URI

http://hdl.handle.net/10400.8/13200

Citation

J. C. Sousa, L. P. Neves and H. M. Jorge, "Load forecasting based on neural networks and load profiling," 2009 IEEE Bucharest PowerTech, Bucharest, Romania, 2009, pp. 1-8, doi: https://doi.org/10.1109/PTC.2009.5281832.