A GOA-RNN controller for a stand-alone photovoltaic/wind energy hybrid-fed pumping system

This paper presents a control scheme for a stand-alone photovoltaic/wind energy hybrid pumping system. The proposed control scheme is the joined execution of grasshopper optimization algorithm and recurrent neural network (GOA-RNN). The objective of the proposed control technique is to satisfy the load power demand and to maintain the power regulation (or) maximum energy conversion of the wind and solar subsystems. In the proposed system, the GOA is utilized to optimizing the combination of the resource parameters based on the solar irradiation and wind power uncertainty. Based on the optimal datasets, the RNN gives the best control signals, i.e., duty cycle. The RNN learning process is enhanced by using the GOA algorithm in perspective of the minimum error objective function. To validate the effectiveness of the proposed approach, the solar irradiation, wind uncertainty and load faults is studied. The proposed method is actualized in MATLAB/Simulink stage and evaluated their performance. To validate the advantage of the proposed approach, three test cases are studied and compared with different existing techniques. In the proposed approach the maximum generated power of PV, Wind and Load power under solar irradiance change condition is 800 W, 350 W and 1100 W. Under wind uncertainty is 810 W, 350 W and 1400 W. Under load fault condition is 900 W, 350 W and 1400 W. The comparison reveals that the proposed technique has the capability for maximizing the energy conversion of wind and PV generation system with less THD. Overall the results demonstrate that technically the stand-alone photovoltaic/wind energy hybrid pumping system is an ideal solution to achieve 97% energy autonomy in remote communities.