Maximum Efficiency Point Tracking (MEPT) for Variable Speed Small Hydropower Plant With Neural Network Based Estimation of Turbine Discharge

The paper presents the control system of a small hydropower plant (SHP) working at variable speed operation (VSO). In general, VSO increases the turbine operating discharge and gives higher efficiency over a wide operating range. It is particularly advantageous under conditions different from the original design conditions. Changing of the hydrological conditions requires adjustments to the control system; therefore, the new maximum efficiency point tracking (MEPT) algorithm is proposed. The MEPT algorithm implemented in the load controller employs the gradient method. The water level governor based on the PI controller combined with the adaptive load controller is analyzed. The troublesome measurement of the turbine discharge is replaced by the neural-network-based estimator. The correlation analysis of the system parameters was performed by using principal component analysis. The proposed algorithm was implemented in the programmable logic controller and tested on a real low-head SHP of 150 kW power with two single-regulated propeller turbines.