A Highly-Efficient Fuzzy-Based Controller With High Reduction Inputs and Membership Functions for a Grid-Connected Photovoltaic System

Abstract

Most conventional Fuzzy Logic Controller (FLC) rules are based on the knowledge and experience of expert operators: given a specific input, FLCs produce the same output. However, FLCs do not perform very well when dealing with complex problems that comprise several input variables. Hence, an optimization tool is highly desirable to reduce the number of inputs and consequently maximize the controller performance, leading to easier maintenance and implementation. This paper, presents an enhanced fuzzy logic controller applied to a photovoltaic system. Specifically, both inputs and membership functions are reduced, resulting in a Highly Reduced Fuzzy Logic Controller (HRFLC), to model a 100kW gridconnected Photovoltaic Panel (PV) as part of a Maximum Power Point Tracking (MPPT) scheme. A DC to DC boost converter is included to transfer the total energy to the grid over a three-level Voltage Source Converter (VSC), which is controlled by varying its duty cycle. FLC generates control parameters to simulate different weather conditions. In this study, only one input representing the current variation (I) of the FLC is used to provide an effective and accurate solution. This reduction in simulation inputs results in a novel HRFLC which simplifies the solar electric system design with output Membership Functions (MFs). Both are achieved by grouping two rules instead of using an existing state-of-the-art method with twenty-five MFs. To the best of our knowledge, this is the first FLC able to provide such rules compression. Finally, a comparison with different techniques such as Perturb and Observe (P&O) shows that HRFLC can improve the dynamic and the steady state performance of the PV system. Notably, experimental results report a steady state error of 0.119%, a transient time of 0.28s and an MPPT tracking accuracy of 0.009s.

Long Short Term Memory Tracker‐Based Modified DC‐DC Converter for Power Quality Improvement in Grid‐PV Systems under Uniform and Partial Shading Environments

“…It shows that the proposed LSTM provides 99.8% accuracy, TOANC has 99.12%, FLC model has 91.51%, PID‐IC model has 87.67%, and PID‐HC has 84.01%. [ 38 ] This comparison shows that the proposed model provides a high efficiency with low tracking error value.…”

Fuzzy Mathematics-Based Outer-Loop Control Method for Converter-Connected Distributed Generation and Storage Devices in Micro-Grids

“…Several applications are presented next: in [17,18], a general-purpose fuzzy controller for dc-dc converters was analysed. Additionally, [19] analysed a fuzzy-based control method for the maximum-power point tracking operation of a photo-voltaic system.…”

iWorksafe: Towards Healthy Workplaces During COVID-19 With an Intelligent Phealth App for Industrial Settings

“…With the recent advancement of computing and better understanding of artificial intelligence (AI), various types of rule base [12]- [15], bio/brain-inspired [16] and machine learning (ML) approaches [17], [18] have acquired unrivalled concentration of the researchers in the last decade for the biological and healthcare big data mining [17], disease prediction and detection [19]- [23], anomaly detection [24]- [27], personalized treatment planning for risk prediction [28]- [30], clinical decision support system [31], [32], text processing [33], [34], disease management [14], [35] and mobile health based app [36]- [38]. During this COVID-19 outbreak, AI and ML have also been used in infection detection, self-testing and spread prevention in home, clinic and office settings.…”