Electricity Price Forecasting in Deregulated Power Markets using Wavelet-ANFIS-KHA

• Published in: 2018 International Conference on Computing, Power and Communication Technologies (GUCON) pp. 982 - 987
• Main Authors: Karri, Chandram, Durgam, Rajababu, K., Raghuram
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2018
• Subjects: Adaptive Neuro Fuzzy Inference System; Discrete wavelet transforms; Electricity price forecasting; Firing; Forecasting; Inference algorithms; Krill herd algorithm; Power markets; Prediction algorithms; Wavelet
• DOI: 10.1109/GUCON.2018.8674980

This article presents a hybrid method by combining Wavelet-ANFIS-KHA for forecasting the prices of electricity in the power markets under deregulation. Electricity prices in the power market exhibits highly non-linear and non-stationary that makes forecasting the electricity prices very difficult. Three major stages are involved in the proposed algorithms to forecast the electricity prices. In stage I, discrete wavelet transform (db4, level 3) is applied for decomposing the prices of electricity data to a set of constitutive for reducing the variation in the prices data. In stage II, ANFIS is used to forecast the electricity prices. KHA has been adopted in updating the various weights in the ANFIS to get better accuracy. The code of the hybrid algorithm has been developed in MATLAB. The proposed Wavelet-KHA-ANFIS has been tested on the real time system. The simulation results in terms of MAPE, MRSE and APE have been presented. It has been found that the proposed algorithm provides best accuracy in comparison with the existing algorithms.