Neural-wavelet Methodology for Load Forecasting

Authors:
Rong Gao;Lefteri H. Tsoukalas
Affiliations:
Appllied Intelligence Systems Lab, School of Nuclear Engineering, Purdue University, W. Lafayette, IN 47907, USA/ e-mail: gao@purdue.edu;Appllied Intelligence Systems Lab, School of Nuclear Engineering, Purdue University, W. Lafayette, IN 47907, USA/ e-mail: tsoukala@ecn.purdue.edu
Venue:
Journal of Intelligent and Robotic Systems
Year:
2001

Citing 1
Cited 4

Toward Self-Healing Infrastructure Systems

Computer

Application of bacterial foraging technique trained artificial and wavelet neural networks in load forecasting

Neurocomputing
Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

Engineering Applications of Artificial Intelligence
Kernel regression based short-term load forecasting

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Wavelet neural networks: A practical guide

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Intelligent demand-side management represents a future trend of power system regulation. A key issue in intelligent demand-side management is accurate prediction of load within a local area grid (LAG), which is defined as a set of customers with an appropriate residential, commercial and industrial mix. Power consumption is deemed to be unpredictable in some sense due to the idiosyncratic behaviors of individual customers. However, the overall pattern of a group of consumers is possible to predict. The developed neural-wavelet approach is shown capable of handling the nonlinearities involved and provides a unique tool for intelligent demand-side management. The paper presents the neural-wavelet approach and its implementation to load identification and forecasting.