Maximum power point tracking using decision-tree machine-learning algorithm for photovoltaic systems

作     者：P.Venkata Mahesh S.Meyyappan RamaKoteswara Rao Alla 

作者机构：Department of Electronics and Instrumentation EngineeringAnnamalai UniversityChidambaramIndia Department of Instrumentation EngineeringMadras Institute of TechnologyChennaiIndia Department of EEERVR&JC College of EngineeringGunturIndia 

出 版 物：《Clean Energy》 (清洁能源（英文）)

年 卷 期：2022年第6卷第5期

页      面：762-775页

核心收录：

学科分类：08[工学] 0807[工学-动力工程及工程热物理] 

主　　题：boost converter decision tree maximum power point tracking photovoltaic system regression machine learning 

摘      要：This work presents a machine-learning(ML)algorithm for maximum power point tracking(MPPT)of an isolated photovoltaic(PV)*** to the dynamic nature of weather conditions,the energy generation of PV systems is *** there is no specific method for effectively dealing with the non-linear data,the use of ML methods to operate the PV system at its maximum power point(MPP)is desirable.A strategy based on the decision-tree(DT)regression ML algorithm is proposed in this work to determine the MPP of a PV *** data were gleaned from the technical specifications of the PV module and were used to train and test the *** algorithms predict the maximum power available and the associated voltage of the module for a defined amount of irradiance and *** boost converter duty cycle was determined using predicted *** simulation was carried out for a 10-W solar panel with a short-circuit current of 0.62 A and an open-circuit voltage of 21.50 V at 1000 W/m^(2) irradiance and a temperature of 25℃.The simulation findings demonstrate that the proposed method compelled the PV panel to work at the MPP predicted by DTs compared to the existing topologies such asβ-MPPT,cuckoo search and artificial neural network *** the proposed algorithm,efficiency has been improved by93.93%in the steady state despite erratic irradiance and temperatures.