Open AccessDesign and analysis of genetic algorithm and BP neural network based PID control for boost converter applied in renewable power generations
Author(s) -
Wang Qingsong,
Xi Haoyu,
Deng Fujin,
Cheng Ming,
Buja Giuseppe
Publication year - 2021
Publication title -
iet renewable power generation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.005
H-Index - 76
eISSN - 1752-1424
pISSN - 1752-1416
DOI - 10.1049/rpg2.12320
Subject(s) - pid controller , photovoltaic system , control theory (sociology) , artificial neural network , computer science , genetic algorithm , controller (irrigation) , voltage , renewable energy , boost converter , control engineering , electronic engineering , engineering , temperature control , control (management) , artificial intelligence , electrical engineering , machine learning , agronomy , biology
Abstract Recently, solar power generation systems are more and more popular and widely used in grid connected power generation, intelligent buildings, and power supply in remote areas. For photovoltaic panels, due to the influence of factors such as light intensity and ambient temperature, their output voltage and current become uns, and the output voltage of a single photovoltaic panel is considerably low. As a result, Boost circuits are needed for voltage boosting. PID controller is commonly used for Boost converter because it can effectively control the controlled object according to the characteristics of the controlled object. However, when the controlled object is complex and variable, the appropriate parameters are hardly to be selected by experience, and the fixed controller parameters may lead to unexpected performances under different working conditions. Here, a genetic algorithm combined with BP neural network PID control (GA‐BPPID) is proposed to improve both dynamic and anti‐interference performances of Boost circuit by introducing the global optimization ability of genetic algorithm and the adaptive adjustment characteristics of BP neural network. System modelling and detailed controller design procedures are provided. Finally, the theoretical analysis and controller design are validated by simulation results.