Ridho, Ainur Rosyid (2026) Energy Management System Berbasis Adaptive Neuro-Fuzzy Inference System Pada Sistem Pembangkit Renewable Energy Integration Demonstrator of Indonesia. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6022232007-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6022232007-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy |
Abstract
Penelitian ini menyajikan perancangan dan evaluasi Energy Management System (EMS) berbasis Adaptive Neuro-Fuzzy Inference System (ANFIS) pada sistem pembangkit energi terbarukan di Renewable Energy Integration Demonstrator of Indonesia (REIDI). EMS dikembangkan untuk mengatur aliran daya antara photovoltaik (PV), baterai dan grid, sehingga operasi sistem tetap stabil sekaligus meningkatkan pemanfaatan energi terbarukan. ANFIS menggunakan tiga parameter input yaitu daya PV, daya beban, dan State of Charge (SOC) baterai untuk menghasilkan referensi daya baterai yang menentukan mode charging atau discharging secara adaptif. Model ANFIS dilatih menggunakan sekitar 1987 data operasi dengan proporsi 75% data pelatihan dan 35% data pengujian. Hasil pelatihan dan pelatihan menghasilkan nilai root-mean-square error (RMSE) sebesar 0.00807 dan 0.0313 dengan regresi 0.9848 dan pengujian 0.9647. Pengujian EMS dilakukan melalui tiga skenario: beban konstan dengan iradiasi bervariasi, iradiasi konstan dengan beban bervariasi, serta beban dan iradiasi yang bervariasi. Hasil simulasi menunjukkan bahwa EMS berbasis ANFIS mampu menjaga keseimbangan daya, mencegah overcharge maupun deep discharge, serta menjaga SOC dalam rentang aman 20–90%. Selain itu juga dapat mengoptimalkan pembagian daya antara PV, baterai, dan grid sehingga sumber energi terbarukan dapat dimanfaatkan maksimal. Secara keseluruhan, EMS berbasis ANFIS memberikan kinerja adaptif dan stabil, sehingga sesuai untuk aplikasi smart microgrid.
==================================================================================================================================
This study presents the design and performance evaluation of an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based Energy Management System (EMS) implemented in the Renewable Energy Integration Demonstrator of Indonesia (REIDI). The proposed EMS is developed to coordinate power flow among the photovoltaic (PV), battery energy storage system, and the utility grid, ensuring stable system operation and enhancing renewable energy utilization. The ANFIS controller employs three input parameters PV power, load power, and battery state of charge (SOC) to generate the battery reference power, which governs the charging and discharging modes adaptively.The ANFIS model was trained using approximately 1987 operational data samples, with 75% allocated for training and 25% for testing. The training and testing process achieved a final root-mean-square error (RMSE) of 0.00807 and 0.0313 with regression 0.9848 and 0.9647. System validation was conducted through three scenarios: constant load with varying irradiance, constant irradiance with varying load, and simultaneous variations of both load and. Simulation results demonstrate that the ANFIS-based EMS effectively maintains power balance, prevents overcharging and deep discharging, and keeps the SOC within a safe operating range of 20–90%. Moreover, the controller optimizes power sharing among the PV system, battery, and grid, resulting in reduced grid dependency. Overall, the proposed EMS exhibits adaptive, stable, and intelligent performance suitable for smart microgrid applications.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | ANFIS, Baterai, Energy Management, PV, Renewable Energy, ANFIS, Battery, Energy Management, PV, Renewable Energy |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1007 Electric power systems control 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 > TK2941 Storage batteries |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | Ainur Rosyid Ridho |
| Date Deposited: | 21 Jan 2026 06:15 |
| Last Modified: | 21 Jan 2026 06:15 |
| URI: | http://repository.its.ac.id/id/eprint/129959 |
Actions (login required)
 |
View Item |