Enhanced MPPT method based on ANN-assisted sequential Monte–Carlo and quickest change detection

• Published in: IET Smart Grid Vol. 2; no. 4; pp. 635 - 644
• Main Authors: Chen, Leian, Wang, Xiaodong
• Format: Journal Article
• Language: English
• Published: Durham The Institution of Engineering and Technology 01.12.2019; John Wiley & Sons, Inc; Wiley
• Subjects: ANN model; artificial neural network; Artificial neural networks; B0260 Optimisation techniques; B8250 Solar power stations and photovoltaic power systems; B8360D DC‐DC power convertors; C5290 Neural computing techniques; Change detection; Circuits; Efficiency; Electricity; enhanced MPP tracking method; enhanced MPPT method; environmental conditions; global MPP; Incremental conductance; incremental conductance MPPT approach; Irradiance; irradiance data; Machine learning; Mathematical models; Maximum power; maximum power point; maximum power point trackers; Methods; Monte Carlo methods; neural nets; observed voltage; optimal performance; partial shading; perturbation techniques; photovoltaic power systems; photovoltaic system; quick irradiance change detection method; quickest change detection; rapid irradiance change; Research Article; sequential estimation; sequential Monte–Carlo filtering; Shading; SMC‐based MPPT method resorts; Solar energy; State estimation; state-space model; incremental conductance MPPT approach; perturbation techniques; artificial neural network; enhanced MPP tracking method; photovoltaic system; Monte Carlo methods; environmental conditions; SMC-based MPPT method resorts; partial shading; observed voltage; quick irradiance change detection method; rapid irradiance change; optimal performance; photovoltaic power systems; global MPP; state-space model; maximum power point; maximum power point trackers; quickest change detection; sequential Monte–Carlo filtering; state estimation; ANN model; enhanced MPPT method; sequential estimation; irradiance data; neural nets
• ISSN: 2515-2947; 2515-2947
• DOI: 10.1049/iet-stg.2019.0012

The performance of a photovoltaic system is subject to varying environmental conditions, and it becomes more challenging to track the maximum power point (MPP) and maintain the optimal performance when partial shading occurs. In this study, an enhanced MPP tracking (MPPT) method is proposed utilising the state estimation by the sequential Monte–Carlo (SMC) filtering, which is assisted by the prediction of MPP via an artificial neural network (ANN). A state-space model for the sequential estimation of MPP is proposed in the framework of incremental conductance MPPT approach, and the ANN model based on the observed voltage and current or irradiance data predicts the global MPP to refine the estimation by SMC. Moreover, a quick irradiance change detection method is applied, such that the SMC-based MPPT method resorts to the assistance from ANN only when partial shading is detected. Simulation results show that the proposed enhanced MPPT method achieves high efficiency and is robust to rapid irradiance change.