THE EXTRACTION OF KNOWLEDGE RULES FROM ARTIFICIAL NEURAL NETWORKS APPLIED IN THE ELECTRIC LOAD DEMAND FORECAST PROBLEM - How Artificial Neural Networks Retain Knowledge and Make Reliable Forecasts

Tarcisio R. Steinmetz, Adelmo L. Cechin, Jose V. Canto dos Santos

2009

Abstract

We present a methodology for the extraction of rules from Artificial Neural Networks (ANN) trained to forecast the electric load demand. The rules have the ability to express the knowledge regarding the behavior of load demand acquired by the network during training process. The rules are presented to the user in an easy to read format, such as IF premise THEN consequence. Where premise relates to the input data submitted to the network (mapped as fuzzy sets), and consequence appears as a linear equation describing the output to be presented by the network, should the premise part holds true. Experimentation demonstrates the method’s capacity for acquiring and presenting high quality rules from neural networks trained to forecast electric load demand for several amounts of time in the future.

Paper Citation

in Harvard Style

R. Steinmetz T., L. Cechin A. and V. Canto dos Santos J. (2009). THE EXTRACTION OF KNOWLEDGE RULES FROM ARTIFICIAL NEURAL NETWORKS APPLIED IN THE ELECTRIC LOAD DEMAND FORECAST PROBLEM - How Artificial Neural Networks Retain Knowledge and Make Reliable Forecasts . In Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 978-989-8111-99-9, pages 195-200. DOI: 10.5220/0002198201950200

in Bibtex Style

@conference{icinco09,
author={Tarcisio R. Steinmetz and Adelmo L. Cechin and Jose V. Canto dos Santos},
title={THE EXTRACTION OF KNOWLEDGE RULES FROM ARTIFICIAL NEURAL NETWORKS APPLIED IN THE ELECTRIC LOAD DEMAND FORECAST PROBLEM - How Artificial Neural Networks Retain Knowledge and Make Reliable Forecasts },
booktitle={Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2009},
pages={195-200},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002198201950200},
isbn={978-989-8111-99-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - THE EXTRACTION OF KNOWLEDGE RULES FROM ARTIFICIAL NEURAL NETWORKS APPLIED IN THE ELECTRIC LOAD DEMAND FORECAST PROBLEM - How Artificial Neural Networks Retain Knowledge and Make Reliable Forecasts
SN - 978-989-8111-99-9
AU - R. Steinmetz T.
AU - L. Cechin A.
AU - V. Canto dos Santos J.
PY - 2009
SP - 195
EP - 200
DO - 10.5220/0002198201950200