Maximum Power Point Tracking (MPPT) Using The Neural Network (NN) Method For Photovoltaics Affected By Partial Shadow With Capacity Of 200 Watts

Azzahra, Salsabila Shafwa (2023) Maximum Power Point Tracking (MPPT) Using The Neural Network (NN) Method For Photovoltaics Affected By Partial Shadow With Capacity Of 200 Watts. Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 10311910000076-Undergraduate_Thesis for D4 Program.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (12MB) | Request a copy

Abstract

Photovoltaic memiliki peran yang sangat penting untuk menjadi bagian dari sumber energi terbarukan. Pengoperasian photovoltaic terdapat tantangan yang harus dihadapi yaitu tertutup bayangan sebagian, beberapa faktor tertutup bayangan seperti pohon, gedung, dan masih banyak lagi. Bayangan yang menutupi sebagian permukaan PV dapat menyebabkan daya yang dihasilkan kurang maksimal. Proyek Akhir ini menggunakan Neural Network untuk mendapatkan dutycycle terbaik untuk menghasilkan titik Global Maximum Power Point (GMPP). Neural Network menyerupai jaringan syaraf biologi karena dapat digambarkan seperti neuron yang saling berhubungan dan membentuk jaringan syaraf. Neural Network digunakan untuk mendapatkan nilai dutycycle yang secara eksperimen akan berpengaruh pada titik GMPP untuk kurva P-V. Proyek Akhir ini dilakukan dua buah metode pengujian yaitu pelatihan menggunakan NN dan eksperimen tanpa NN menggunakan PV berkapasitas 240 watt peak. Hasil pengujian menunjukan bahwa penggunaan metode Neural Network membutuhkan waktu untuk mentraining dalam 8 sampai 23 detik, pengujian tersebut dapat dikatakan daya maksimum pada titik MPP global yang dicapai dalam berbagai kondisi PV terletak pada dutycycle 60%.
=================================================================================================================================
Photovoltaic has a very important role to play as part of a renewable energy source. In its operation there are challenges that must be faced, namely, being partially covered by shadows. Many factors can cause PV to be covered by shadows, such as trees, buildings, and many more. Shadows that cover part of the PV surface can cause the power generated to be less than optimal. This Final Project uses Neural Network to get the best dutycycle to generate GMPP points. Neural Network resembles a biological Neural Network because it can be described as neurons that are interconnected and form a Neural Network. The Neural Network in the Final Project is used to obtain a dutycycle value that will experimentally affect the GMPP point for the P-V curve. This Final Project conducted two test methods, namely training and experimentation using PV with a capacity of 240 watts peak and training using NN. The test results show that the use of the Neural Network method takes time to train in 8 to 23 seconds, the test can be said that the maximum power at the global MPP point achieved in various PV conditions is located at 60% dutycycle.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Photovoltaic, Maximum Power Point Tracking, Tetutup Bayangan Sebagian, Photovoltaic, Neural Network, Partially Shaded Conditions.
Subjects:	T Technology > T Technology (General) > T57.62 Simulation T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1056 Solar power plants. Ocean thermal power plants T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1087 Photovoltaic power generation T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5103.8 Switching systems
Divisions:	Faculty of Vocational > 36304-Automation Electronic Engineering
Depositing User:	Salsabila Shafwa Azzahra
Date Deposited:	20 Nov 2023 01:55
Last Modified:	20 Nov 2023 02:02
URI:	http://repository.its.ac.id/id/eprint/101653

Actions (login required)

View Item