Title :
GAuLF: gas automated load forecaster
Author :
Jabbour, Kamal ; Meyer, Walter
Author_Institution :
Dept. of Electr. & Comput. Eng., Syracuse Univ., NY, USA
Abstract :
An expert system for short-term forecasting of natural gas sendout is presented. GAuLF, or gas automated load forecaster, has been developed to assist Niagara Mohawk Power Corporation (NMPC) gas operators in estimating short-term demand for gas. GAuLF uses a hybrid rule-based and pattern recognition approach to forecast hourly gas sendouts up to 96 hours in advance. GAuLF presently uses a five-year historical database of weather and gas sendout, and a rule base that takes into consideration periodic variations of the sendout as well as demand growth. GAuLF´s structure and operational results are discussed
Keywords :
expert systems; load forecasting; natural gas technology; pattern recognition; public utilities; Niagara Mohawk Power Corporation; expert system; gas automated load forecaster; historical database; hybrid techniques; natural gas sendout; pattern recognition; periodic variations; rule-based approach; short-term demand; short-term forecasting; Delay systems; Demand forecasting; Educational institutions; Expert systems; Load forecasting; Multivariate regression; Natural gas; Pattern recognition; Pressure control; Weather forecasting;
Conference_Titel :
Circuits and Systems, 1989., Proceedings of the 32nd Midwest Symposium on
Conference_Location :
Champaign, IL
DOI :
10.1109/MWSCAS.1989.101785
