ALFA: automated load forecasting assistant
- 1 August 1988
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 3 (3) , 908-914
- https://doi.org/10.1109/59.14540
Abstract
ALFA, an expert system for forecasting short-term electricity demand is presented. ALFA is in operation at the Energy Management System center at Niagara Mohawk Power Corporation in upstate New York, generating, in real time, hourly load forecasts for up to 48 hours in advance. ALFA uses an extensive 10-year historical database of hourly observations of 12 weather variables and a rule base that takes into account daily, weekly, and seasonal variations of load, as well as holidays, special events, and load growth. A satellite interface for the real-time acquisition of weather data, and the machine-operator interface are also discussed.<>Keywords
This publication has 2 references indexed in Scilit:
- Forecasting of Hourly Load By Pattern Recognition A Deterministic ApproachIEEE Transactions on Power Apparatus and Systems, 1982
- Techniques for load prediction in the electricity-supply industryProceedings of the Institution of Electrical Engineers, 1968