Due to the intermittent nature of renewable sources, miss-matching between power generation and load power causes a deviation from the desired voltage and frequency in power supply. To solve this problem, a new contro...
详细信息
Due to the intermittent nature of renewable sources, miss-matching between power generation and load power causes a deviation from the desired voltage and frequency in power supply. To solve this problem, a new control technique has been proposed for the power flow control with the unified power flow controller (UPFC) in grid-connected hybrid renewable energy systems such as photovoltaic-wind. The proposed control technique combines the binary version of the grey wolf optimization (bGWO) and recurrent neural network (RNN). Here, bGWO is utilized to generate the dataset of control signals for shunt and series converters of the UPFC. Based on the accomplished dataset, the RNN technique performs and predicts the optimal control signals of the UPFC. Likewise, the proposed control scheme regulates the voltage deviation and minimizes the power losses simultaneously. Then, the proposed model is executed in Matrix Laboratory/Simulink working stage and the execution is assessed with the existing techniques such as fuzzy logic controller, improved particle swarm optimization and grey wolf optimization. The optimized gain parameters and elapsed time of the proposed and existing technique is also analysed. The optimized gain parameters such as KpKi of the proposed hybrid technique are 2.5 and 150. The elapsed time of the proposed technique is 30.15sec. Overall, the comparison results demonstrate the superiority of the proposed technique and confirm its potential to solve the above-mentioned problems.
暂无评论