Pengaturan Energi Rumah Tangga Dengan Mempertimbangkan Pengaruh Dynamic Pricing dan Photovoltaic Solar Rooftop Menggunakan Artificial Neural Network

Nugroho, Arvianto (2021) Pengaturan Energi Rumah Tangga Dengan Mempertimbangkan Pengaruh Dynamic Pricing dan Photovoltaic Solar Rooftop Menggunakan Artificial Neural Network. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 07111740000036-Undergraduate_Thesis.pdf] Text
07111740000036-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (5MB) | Request a copy

Abstract

Usaha penyediaan energi listrik mulai beralih ke sumber energi terbarukan khususnya photovoltaic solar rooftop skala rumah tangga. Tingginya biaya investasi solar rooftop membuat pengaturan energi rumah tangga menjadi salah satu sistem yang penting untuk diterapkan. Pengaturan energi memungkinkan konsumen untuk menghemat biaya listrik, dengan cara mengatur rasio penggunaan sumber energi dan menjadwalkan konsumsi energi per jamnya menyesuaikan daya output solar rooftop dan tarif listrik yang dinamis (dynamic pricing). Pada penelitian tugas akhir ini dilakukan pengembangan sistem pengaturan energi skala rumah tangga yang mampu menghasilkan rasio penggunaan sumber energi dan penjadwalan beban per jamnya yang optimal agar dihasilkan biaya listrik total terendah berdasarkan prediksi daya output solar rooftop dan tarif listrik dinamis. Proses optimasi menggunakan Mixed Integer Linear Programming (MILP) untuk menghasilkan data pengaturan energi optimal yang akan digunakan sebagai data training untuk implementasi dengan Artificial Neural Network (ANN). Hasil simulasi menunjukkan adanya penghematan biaya listrik total selama 1 tahun sebesar 33.93% dengan pengaturan sumber energi saja dan 38.41% dengan pengaturan sumber energi dan penjadwalan beban. Penghematan ini mempercepat waktu kembali modal / Break-Even Point (BEP) pada investasi sistem solar rooftop dari 12.25 tahun tanpa menggunakan sistem pengaturan energi, menjadi 8 tahun dengan pengaturan sumber energi saja dan 7 tahun dengan pengaturan sumber energi dan penjadwalan beban.
==================================================================================================
The effort of providing electrical energy has begun to shift to renewable energy sources, especially photovoltaic solar rooftop at household scale. The high cost of solar rooftop investment makes household energy regulation is one of the most important systems to implement. Energy regulation allows consumers to save on electricity costs, by adjusting the ratio of the use of energy sources and scheduling energy consumption per hour according to the solar rooftop output power and dynamic electricity rates or dynamic pricing. In this final project research, a household-scale energy regulation system is developed that is able to produce an optimal ratio of energy source usage and hourly load scheduling to produce the lowest total electricity costs based on predictions of rooftop solar output power and dynamic electricity rates. The optimization process uses Mixed Integer Linear Programming (MILP) to produce optimal energy control data that will be used as training data for implementation with Artificial Neural Network (ANN). The simulation results show that there is a saving in total electricity costs for 1 year of 33.93% with only energy source control and 38.41% with energy source control and load scheduling. These savings accelerate the break-even point (BEP) investment in solar rooftop systems from 12.25 years without using an energy management system, to 8 years with only energy source control and 7 years with energy source control and load scheduling.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Artificial Neural Network, Dynamic Pricing, Energy Control, Mixed Integer Linear Programming, Solar Rooftop, Jaringan Saraf Tiruan, Tarif Dinamis, Pengaturan Energi, Pemrograman Integer Linear Campuran, Atap Surya
Subjects: T Technology > T Technology (General) > T57.74 Linear programming
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1001 Production of electric energy or power
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1087 Photovoltaic power generation
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2941 Storage batteries
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3070 Automatic control
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User: Arvianto Nugroho
Date Deposited: 16 Aug 2021 04:13
Last Modified: 16 Aug 2021 04:13
URI: http://repository.its.ac.id/id/eprint/86459

Actions (login required)

View Item View Item