Prasetiyo, Tri Ilham (2026) Penggunaan Algoritma Genetika Dalam Optimasi Penyeimbangan Beban Listrik 3 Fasa Dengan Sistem Monitoring IoT Di Gedung Workshop Balai Pelatihan Vokasi dan Produktivitas Samarinda. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6022231017-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6022231017-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (15MB) | Request a copy |
Abstract
Balai Latihan Kerja dan Produktivitas (BPVP) Samarinda merupakan Unit Pelaksana Teknologi Pusat yang berperan strategis dalam pengembangan sumber daya manusia. Sebagai pusat kegiatan pelatihan intensif, gedung-gedung di BPVP, terutama area workshop, mengalami konsumsi energi yang sangat dinamis. Sayangnya, pengelolaan energi di fasilitas ini belum sepenuhnya optimal. Salah satu masalah kritis dan sering terjadi adalah ketidakseimbangan beban pada jaringan listrik tiga fasa. Ketidakseimbangan ini tidak hanya berdampak teknis tetapi juga menyebabkan ketidakstabilan sistem, pemborosan energi, dan potensi kerusakan pada peralatan pelatihan vital. Upaya penyeimbangan beban secara manual seringkali tidak efektif dalam menangani fluktuasi beban yang cepat. Oleh karena itu, studi ini mengusulkan pendekatan yang lebih cerdas dengan mengembangkan sistem pemantauan berbasis Internet of Things (IoT) yang terintegrasi dengan basis data berkinerja tinggi, TimescaleDB. Sistem ini dirancang untuk memantau kondisi kelistrikan secara real-time menggunakan mikrokontroler ESP32 dan sensor presisi PZEM-004T. Berbeda dengan metode tradisional yang hanya mengandalkan satu pendekatan, studi ini melakukan analisis komparatif mendalam terhadap lima algoritma meta-heuristik: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), Ant Colony Optimization (ACO), dan Salp Swarm Algorithm (SSA). Tujuannya adalah untuk mengidentifikasi algoritma yang paling tangguh dan efisien untuk karakteristik beban di BPVP Samarinda. Uji statistik menunjukkan bahwa Algoritma Genetika (GA) berkinerja unggul, secara signifikan mengurangi ketidakseimbangan beban dan waktu komputasi. Berdasarkan hasil ini, Algoritma Genetika diimplementasikan sebagai mesin analisis utama dalam sistem. Sistem ini menghasilkan sistem pendukung keputusan yang memberikan rekomendasi teknis kepada teknisi yang melakukan penyeimbangan beban manual. Pendekatan ini dipilih untuk meningkatkan keamanan dan keandalan pasokan listrik selama kegiatan pelatihan sekaligus meningkatkan efisiensi energi operasional gedung.
===================================================================================================================================
The Samarinda Vocational Training and Productivity Centre (BPVP) is a Central Technology Implementation Unit that plays a strategic role in human resource development. As a hub for intensive training activities, the centre's buildings, particularly the workshop areas, experience highly dynamic energy consumption. Unfortunately, energy management at this facility has not yet been fully optimized. A critical and frequently occurring problem is load imbalance in the three-phase electrical network. This imbalance not only has technical implications but also causes system instability, energy waste, and potential damage to vital training equipment. Manual load balancing efforts are often ineffective in handling rapid load fluctuations. Therefore, this study proposes a smarter approach by developing an Internet of Things (IoT)-based monitoring system integrated with a high-performance database, TimescaleDB. This system is designed to monitor electrical conditions in real time using an ESP32 microcontroller and a PZEM-004T precision sensor. Unlike traditional methods that rely on a single approach, this study conducted an in-depth comparative analysis of five meta-heuristic algorithms: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), Ant Colony Optimization (ACO), and Salp Swarm Optimization (SSA). The objective was to identify the most robust and efficient algorithm for load characteristics at BPVP Samarinda. Statistical tests demonstrated that the Genetic Algorithm (GA) performed superiorly, significantly reducing load imbalances and computation time. Based on these results, the Genetic Algorithm was implemented as the primary analysis engine in the system. This system generates a decision support system that provides technical recommendations to technicians performing manual load balancing. This approach was chosen to enhance the safety and reliability of the electrical supply during training activities while simultaneously increasing the building's operational energy efficiency.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Penyeimbangan Beban, Internet of Things (IoT), TimescaleDB, Algoritma Genetika, Meta-heuristik, Sistem Penunjang Keputusan, BPVP Samarinda. Load balancing, Internet of Things (IoT), TimescaleDB, Genetic algorithm, Meta-heuristic algorithm, Decision support system, BPVP Samarinda. |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1007 Electric power systems control T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3030 Electric power distribution systems T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.546 Computer algorithms |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | Tri Ilham Prasetiyo Prasetiyo |
| Date Deposited: | 22 Jan 2026 08:08 |
| Last Modified: | 22 Jan 2026 08:08 |
| URI: | http://repository.its.ac.id/id/eprint/130082 |
Actions (login required)
 |
View Item |