Day-Ahead Price Forecasting of Electricity Markets by a New Fuzzy Neural Network

TLDR

The model combines fuzzy logic with an efficient learning algorithm to capture nonstationary behavior and outliers in electricity price series. The study proposes a new fuzzy neural network to forecast hourly day‑ahead electricity market prices. The fuzzy neural network employs an inter‑layer, feed‑forward architecture with a novel hypercubic training mechanism that integrates fuzzy logic and efficient learning to model nonstationary price dynamics, and is tested on the Spanish electricity market. The proposed method outperforms ARIMA, wavelet‑ARIMA, MLP, and RBF neural networks in forecasting accuracy for the Spanish day‑ahead electricity market.

Abstract

In this paper, an efficient method based on a new fuzzy neural network is proposed for short-term price forecasting of electricity markets. This fuzzy neural network has inter-layer and feed-forward architecture with a new hypercubic training mechanism. The proposed method predicts hourly market-clearing prices for the day-ahead electricity markets. By combination of fuzzy logic and an efficient learning algorithm, an appropriate model for the nonstationary behavior and outliers of the price series is presented. The proposed method is examined on the Spanish electricity market. It is shown that the method can provide more accurate results than the other price forecasting techniques, such as ARIMA time series, wavelet-ARIMA, MLP, and RBF neural networks.