Neural network controlled grid interfaced solar photovoltaic power generation

• Published in: IET power electronics Vol. 7; no. 3; pp. 614 - 626
• Main Authors: Singh, Bhim, Shahani, Dilip Tekchand, Verma, Arun Kumar
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 01.03.2014; The Institution of Engineering & Technology
• Subjects: Adaline; adaptive linear element; Control theory; Converters; DC–DC boost converter; DC‐DC power convertors; Direct current; Electric potential; four‐leg VSC; grid interfaced SPV generating system; least mean‐square; load balancing; load harmonics currents elimination; maximum power point trackers; maximum power point tracking; neural network controlled grid interfaced solar photovoltaic power generation; Neural networks; neural‐network‐based control algorithm; neurocontrollers; neutral current mitigation; NN‐based control algorithm; PCC; Photovoltaic cells; photovoltaic power systems; point of common coupling; power factor correction; power generation control; power grids; reactive power; reference grid currents; Solar cells; solar photovoltaic generating system; solar power stations; SPV generating system; three‐phase four‐wire distribution system; Voltage; voltage control; voltage source converter; zero voltage regulation; load balancing; zero voltage regulation; power generation control; SPV generating system; load harmonics currents elimination; neural-network-based control algorithm; Adaline; least mean-square; neutral current mitigation; neurocontrollers; grid interfaced SPV generating system; NN-based control algorithm; power factor correction; power grids; solar power stations; neural network controlled grid interfaced solar photovoltaic power generation; voltage source converter; adaptive linear element; three-phase four-wire distribution system; photovoltaic power systems; point of common coupling; four-leg VSC; DC-DC power convertors; DC–DC boost converter; maximum power point trackers; PCC; reference grid currents; maximum power point tracking; reactive power; solar photovoltaic generating system; voltage control
• ISSN: 1755-4535; 1755-4543; 1755-4543
• DOI: 10.1049/iet-pel.2013.0166

This study deals with a NN (neural-network)-based control algorithm of a grid interfaced SPV (solar photovoltaic) generating system. The proposed grid interfaced SPV generating system utilises a NN control algorithm-based on the LMS (least mean-square), known as Adaline (adaptive linear element) to estimate reference grid currents. A DC–DC boost converter is used for achieving the maximum power point tracking between SPV and DC bus of four-leg VSC (voltage source converter) interfaced to a three-phase, four-wire distribution system. The four-leg VSC of SPV generating system is also used for the compensation of the reactive power for zero voltage regulation or for power factor correction along with load balancing, elimination of load harmonics currents and mitigation of neutral current at PCC (point of common coupling) in three-phase four-wire distribution system. The DC bus of VSC is supported by a capacitor which is fed by SPV energy through a DC–DC boost converter. A laboratory prototype of proposed grid interfaced SPV generating system is developed to validate its developed model and the NN-based control algorithm.