Implementation of Hybrid-Fuzzy Neural Network Approach for Short Term Hourly and Peak Load Forecasting Using Weather Parameters.

článek ve sborníku ve WoS nebo Scopus

angličtina

This paper presents the development and practical implementation of a hybrid fuzzy-neural network (FNN) technique, which combines neural network modeling, and techniques from fuzzy logic and fuzzy set theory for short-term hourly and peak load forecasting for the Czech Power Company (ČEZ), Czech Republic. The load has two distinct patterns: weekday and weekend-day patterns. The weekend-day pattern include Saturday, Sunday, and special days/holidays loads. Inputs to the FNN are past loads and past weather parameters i.e., temperature, humidity, wind-speed, and wind-chill and the output of the FNN is the load forecast for a given day. Simulation results are presented to illustrate the performance and applicability of this hybrid approach. This approach avoids complex mathematical calculations and training on many years of data, and is very simple to implement on a personal computer.

Short-term hourly and peak load forecasting, Hybrid fuzzy-neural network, weather parameters

KHAN, M., ŽÁK, L., ONDRŮŠEK, Č.

2001

1. 6. 2001

VUT FSI

Brno

80-214-1894-X

7th International Conference on Soft Computing.

282

287

6