A Systematic Approach to a Time Series Neural Model Development for River Flow Forecasting

Abstract

This paper aims to apply a systematic approach to a time series neural model development procedure. The model is developed for flow forecasting of river Cetina, techno- economically the most important basin in Croatia according to the annual energy production. Multi-Layer Perceptron was used to model hydrological time series of a measured daily river flow. The best model was determined through an experiment based on a values comparison of different error measures (SEE, RMSE, MAE, and CE). In order to determine the best model, 780 MLP neural networks were trained using Levenberg-Marquardt training algorithm. Simulation results indicate high accuracy of flow forecast for one-step-ahead and therefore provide encouragement for further research.

Ozren Bego

Associate Professor | Department of Electrical Drives and Industrial Control

Ranko Goić

Full Professor | Department of Power Grids and Substations

Full professor at the Faculty of Electrical Engineering, Mechanical Engineering, and Naval Architecture in Split exeperienced in transmission and distribution networks, renewable energy sources (RES), power system planing and economics