Main
Workshops/Tracks
Call for Papers
Proceedings
Conference Schedule
Accepted Papers
Contacts
Program Committee
Invited Presentations and Tutorials
Travel Information
Accomodation
Registration
Sponsors
EPIA'03 - 11th Portuguese Conference on Artificial Intelligence

EKDB -- International Workshop on Extraction of Knowledge from Data Bases

 Session: December 5, 10:0-11:30, Room A
Title: Influence of kNN-Based Load Forecasting Errors on Optimal Energy Production
Alicia Troncoso Lora, José Riquelme Santos, José Luís Martínez Ramos, Jesús Riquelme Santos, Antonio Gómez Expósito
Abstract: This paper presents a study of the influence of the accuracy of hourly load forecasting on the energy planning and operation of electric generation utilities. First, a $k$ Nearest Neighbours (kNN) classification technique is proposed for hourly load forecasting. Then, obtained prediction errors are compared with those obtained results by using a M5'. Second, the obtained kNN-based load forecast is used to compute the optimal on/off status and generation scheduling of the units. Finally, the influence of forecasting errors on both the status and generation level of the units over the scheduling period is studied.
Back to schedule.