An efficient maximum power point tracking in hybrid solar and wind energy system: A combined MDA-RNN technique

• Published in: Journal of intelligent & fuzzy systems Vol. 37; no. 4; pp. 5495 - 5514
• Main Authors: Nair, Shyni P., Mary Linda, M.
• Format: Journal Article
• Language: English
• Published: Amsterdam IOS Press BV 01.01.2019
• Subjects: Algorithms; Alternative energy; Control algorithms; Control theory; Converters; Hybrid systems; Learning; Maximum power tracking; Particle swarm optimization; Photovoltaic cells; Power flow; Recurrent neural networks; Renewable energy; Renewable resources; Tracking control; Voltage converters (DC to DC); Wind power
• ISSN: 1064-1246; 1875-8967
• DOI: 10.3233/JIFS-190591

This paper proposes a hybrid strategy based maximum power point tracking (MPPT) control algorithm technique to extricate maximum power from the high infiltrating hybrid renewable energy system. The proposed hybrid strategy is the mix of Modified Dragonfly Algorithm (MDA) and Recurrent Neural Network (RNN) named as MDA-RNN. In the proposed MDA learning based RNN approach, the learning process of the RNN is upgraded by the MDA optimization process dependent on the minimum error objective function. Here, the proposed procedure precisely tracks the duty cycles of the hybrid renewable energy system utilizing Enhanced High Boost (EHB) DC-DC converter to extricate the maximum power output from the sources. To achieve this MPPT procedure, the proposed technique requires the hybrid renewable energy system power flow parameters varieties like voltage and current at each time interim. This control system additionally consolidates a Particle Swarm Optimization (PSO) and levy flight approaches to deal with minimizing the losses in the generator and subsequently to improve the productivity of the wind and PV system. At long last, the execution of the proposed MPPT control of wind and PV power generation plans is executed in MATLAB/Simulink working stage and the execution is surveyed with the current systems.