Forecasting daily load curves using a hybrid fuzzy-neural approach

Abstract

A new approach to electric load forecasting which combines the powers of neural network and fuzzy logic techniques is proposed. Expert knowledge represented by fuzzy rules is used for preprocessing input data fed to a neural network. For training the neural network for one-day ahead load forecasting, fuzzy if-then rules such as 'If x/sub 1/ is high and x/sub 2/ is low, then y is positive small' are used, in addition to historical load and weather data that are usually employed in conventional supervised learning methods. The fuzzy front-end processor maps both fuzzy and numerical input data to a fuzzy output. The input vector to the neural network consists of these membership values to linguistic properties. To deal with the linguistic values such as high, low, and medium, an architecture of neural network that can handle fuzzy input vectors is propounded. The proposed method effectively deals with trends and special events that occur annually. The fuzzy-neural network is trained on real data from a power system and evaluated for forecasting next-day load profiles based on forecast weather data and other parameters. Simulation results are presented to illustrate the performance and applicability of this approach. A comparison of results with other commonly used forecasting techniques establishes its superiority.