Design of Dual Axis Solar Tracker System Based on Fuzzy Inference Systems

Abstract

This paper presents a dual axis design for a fuzzy inference approach-based solar tracking system. The system is modeled using Mamdani fuzzy logic model and the different combinations of ANFIS modeling. Models are compared in terms of the correlation between the actual testing data output and their corresponding forecasted output. The Mean Absolute Percent Error and Mean Percentage Error are usedto measure the models error size. In order to measure the effectiveness of the proposed models, we compare the output power produced by a fixed photovoltaic panels with the output which would be produced if the dual-axis panels are used. Results show that dual-axis solar tracker system will produce 22% more power than a fixed panels system.

Deep Learning Techniques for Photovoltaic Solar Tracking Systems: A Systematic Literature Review

“…Similarly, Şahin [106] used the number of months, monthly sunshine duration, geographical coordinates of the location and previously measured optimum PV panel tilt angles. Further, the authors in [105,107,110] used LDR sensor readings and solar power data as inputs to train the proposed DL model. Additionally, the authors in [98,109,129,133] used astronomical data to train their models to predict the sun's path.…”

Pengembangan PV Solar Tracking System Dua Sumbu Putar Berbasis Model Fuzzy Sugeno Oorde Nol

“…Dari kedua kondisi tersebut maka efisiensi rata -rata panel surya berbasis Fuzzy sugeno orde nol yang dihasilkan pada penelitian ini sebesar 34,18%. Walau pengujian dilakukan pada skala lab, system dual axis solar tracker berbasis Fuzzy sugeno orde nol ini memiliki efisiensi peningkatan daya yang dihasilkan lebih unggul jika dibanding penelitian sebelumnya, seperti yang dilakukan oleh P. Pangaribuan [12] dengan PI controller sebesar 6% , I. Winarno [13] dengan metode ANFIS sebesar 21.51%, H. Hijawi [14] dengan metode fuzzy Mamdani sebesar 22%, dan D. Sinha [15] dengan metode Fuzzy-PID sebesar 29.76%. Hal tersebut disebabkan karena penggunaan aturan dasar yang disesuaikan dengan kapasitas sensor dan aktuator, meskipun aktuator hanya diatur pada kecepatan konstan dan dikendalikan secara diskrit (active high / active low), penggunaan metode Fuzzy sederhana [16] [17] secara tepat sasaran mampu menghasilkan respon yang memuaskan.…”

Correlation analysis and MLP / CMLP for optimum variables to predict orientation and tilt angles in intelligent solar tracking systems

“…Numerous intelligent principles such as fuzzy logic, cascade multilayer perceptron (MLP) neural network, multilayer perceptron (MLP) neural network, intelligent Adaptive neuro-fuzzy inference system (ANFIS), and combination of two or more of these techniques are utilized to control solar systems globally. 24,25 However, most of the published works are carried out using random-generated data, whereas other works used real-time data. The main difficulty in collecting real-time data is the long time to take measurements, where random-generated data can be found by using a simulation software.…”

“…These inefficient systems are commonly due to the inappropriate combination of solar variables and the employed intelligent driving systems. Numerous intelligent principles such as fuzzy logic, cascade multilayer perceptron (MLP) neural network, multilayer perceptron (MLP) neural network, intelligent Adaptive neuro‐fuzzy inference system (ANFIS), and combination of two or more of these techniques are utilized to control solar systems globally 24,25 . However, most of the published works are carried out using random‐generated data, whereas other works used real‐time data.…”

“…Hijawi and Arafeh 25 designed a dual‐axis solar tracking system based on fuzzy logic and a proposed artificial fuzzy inference system. Luminous values that extracted from resistance of four light sensors were used as input attributes, whereas the outputs are horizontal and vertical motions of solar tracker.…”