Shoffiana, Nur Alfiani (2023) Estimasi Produksi Daya Listrik pada Panel Surya Berbahan Polikristalin berdasarkan Kondisi Lingkungan Menggunakan Metode Jaringan Saraf Tiruan di Cepu, Jawa Tengah. Other thesis, Institut Teknologi Sepuluh Nopember.
Text
02311940000006-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (6MB) | Request a copy |
Abstract
Pemanfaatan panel surya sebagai upaya menerapkan energi baru dan terbarukan masih terdapat tantangan dalam mengoptimalkan performansi panel surya untuk menghasilkan daya listrik secara efisien. Oleh karena itu, diperlukan proses perencanaan dan operasional yang matang untuk memaksimalkan performanasi panel surya. Salah satu langkah yang penting untuk merencanakan dengan matang proses pemasangan panel surya adalah mengestimasi produksi daya listrik yang dihasilkan oleh panel surya. Penelitian ini dilakukan perancangan sistem estimasi produksi daya listrik pada panel surya berbahan polikristalin dengan mempertimbangkan radiasi matahari, suhu panel, suhu udara, dan kelembaban udara. Metode yang digunakan adalah analisis regresi dengan menggunakan data historis produksi daya listrik dan data lingkungan yang terkait. Parameter Root Mean Square Error (RMSE) digunakan sebagai parameter performa jaringan saraf tiruan yang digunakan, yaitu Long Short-Term Memory (LSTM). Hasil penelitian menunjukkan adanya hubungan yang signifikan antara radiasi matahari, suhu panel, suhu udara, dan kelembaban udara dengan produksi daya listrik pada panel surya berbahan polikristalin. Pengujian dan evaluasi sistem estimasi dilakukan menggunakan data independen yang belum pernah dilihat sebelumnya. Tiga variasi pasangan data masukan yang baik dalam menghasilkan estimasi produksi daya listrik dengan tingkat kesalahan yang rendah dan tingkat ketepatan yang tinggi yaitu variasi tiga dengan nilai RMSE 1.09, variasi lima dengan nilai RMSE 0.99, dan variasi enam dengan nilai RMSE 1.11.
================================================================================================================================
The use of solar panels as an effort to apply new and renewable energy still faces challenges in optimizing the performance of solar panels to generate electricity efficiently. Therefore, careful planning and operational processes are needed to maximize solar panel performance. One of the important steps to carefully plan the solar panel installation process is to estimate the production of electrical power generated by the solar panels. This research was carried out to design an estimation system for electric power production on polycrystalline solar panels by considering solar radiation, panel temperature, air temperature, and air humidity. The method used is regression analysis using historical data of electric power production and related environmental data. The Root Mean Square Error (RMSE) parameter is used as a performance parameter for the artificial neural network used, namely Long Short-Term Memory (LSTM). The results showed that there was a significant relationship between solar radiation, panel temperature, air temperature, and humidity with the production of electric power in polycrystalline solar panels. Testing and evaluation of the estimation system is carried out using independent data that has never been seen before. Three variations of the input data pair are good at producing estimates of electric power production with a low error rate and a high level of accuracy, namely variation three with an RMSE value of 1.09, variation five with an RMSE value of 0.99, and variation six with an RMSE value of 1.11.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Daya, Panel Surya, Estimasi, Root Mean Square Error (RMSE) Power, Solar Panel, Estimation, Root Mean Square Error (RMSE) |
Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TF Railroad engineering and operation > TF193 Estimates, costs, etc. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1087 Photovoltaic power generation |
Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis |
Depositing User: | Nur Alfiani Shoffiana |
Date Deposited: | 24 Jul 2023 02:34 |
Last Modified: | 24 Jul 2023 02:34 |
URI: | http://repository.its.ac.id/id/eprint/99021 |
Actions (login required)
View Item |