Gayatri Dwi Santika, Wayan Firdaus Mahmudy, Agus Naba
The need for accurate load forecasts will increase in the future because of the dramatic changes occurring in the electricity consumption. Sugeno fuzzy inference system (FIS) can be used for short-term load forecasting. However, challenges in the electrical load forecasting are the data used the data trend. Therefore, it is difficult to develop appropriate fuzzy rules for Sugeno FIS. This paper proposes Evolution Strategy method to determine appropriate rules for Sugeno FIS that have minimum forecasting error. Root Mean Square Error (RMSE) is used to evaluate the goodness of the forecasting result. The numerical experiments show the effectiveness of the proposed optimized Sugeno FIS for several test-case problems. The optimized Sugeno FIS produce lower RMSE comparable to those achieved by other well-known method in the literature Copyright © 2017 Institute of Advanced Engineering and Science. All rights reserved.
Faculty of Computer Science, Universitas Brawijaya, Veteran Road, Malang, 65145, Indonesia; Study Program of Instrumentation, Department of Physics, Universitas Brawijaya Malang, Indonesia
