Design and implementation of Legendre‐based neural network controller in grid‐connected PV systems. Issue 15 (23rd October 2019)

• Record Type: Journal Article
• Authors: Arora, Ankita; Singh, Alka
• Is Part Of: IET renewable power generation. Volume 13:Issue 15(2019)
• Page Start: 2783
• Page End: 2792
• Publication Date: 2019-10-23
• Subjects: power grids -- electric current control -- recurrent neural nets -- power supply quality -- neurocontrollers -- photovoltaic power systems -- power factor -- backpropagation -- multilayer perceptrons -- compensation -- reactive power control -- control system synthesis -- adaptive control -- Legendre polynomials; Legendre‐based neural network controller -- grid‐connected PV systems -- Legendre‐based functional neural network algorithm -- shunt compensation -- photovoltaic‐based grid‐connected system -- power quality -- current control mode -- load current -- PV source -- controller design -- PQ problems -- power factor improvement -- distorted grid -- solar irradiation -- nonlinear functional Legendre expansion -- backpropagation multilayer perceptron neural network -- reactive power -- recurrent neural network -- synchronous reference frame theory; Renewable energy sources -- Periodicals; 333.79405
• DOI: 10.1049/iet-rpg.2019.0269
• Languages: English
• ISSNs: 1752-1416

Abstract

Abstract : This study presents the development of Legendre‐based functional neural network algorithm for shunt compensation in photovoltaic (PV)‐based grid‐connected system. The controller is developed for improving power quality (PQ) and the compensator is controlled to work in current control mode. It injects the requisite compensating current depending on the nature of the load current. The compensator is also interfaced with PV source and the controller design incorporates its contribution too. Some of the PQ problems studied include curtailment of harmonics, providing necessary reactive power, power factor improvement and so on. Results under distorted grid, varying solar irradiation and variety of loads have been presented. The proposed algorithm is designed using non‐linear functional Legendre expansion of load current and has not been used for compensation or PQ problem alleviation till date. Both simulation and experimental results verify that the proposed algorithm performs far better than the adaptive popular backpropagation multilayer perceptron neural network, recurrent neural network and non‐adaptive conventional synchronous reference frame theory based techniques.