HADI, Soiful and Syafei, Wahyul Amien and Wibowo, Adi (2026) BLOCKCHAIN DECENTRALIZED DATA SHARING UNTUK DETEKSI PENYALAHGUNAAN KONSUMSI DAYA LISTRIK BERBASIS IOT. Doctoral thesis, UNIVERSITAS DIPONEGORO.
|
Text
cover aja.pdf Download (124kB) |
|
|
Text
COVER LENGKAP.pdf Restricted to Repository staff only Download (1MB) |
|
|
Text
BAB I.pdf Download (370kB) |
|
|
Text
BAB II.pdf Download (887kB) |
|
|
Text
BAB III.pdf Restricted to Repository staff only Download (2MB) |
|
|
Text
BAB IV.pdf Restricted to Repository staff only Download (2MB) |
|
|
Text
BAB V.pdf Restricted to Repository staff only Download (306kB) |
|
|
Text
DAFTAR PUSTAKA.pdf Download (304kB) |
|
|
Text
LAMPIRAN.pdf Restricted to Repository staff only Download (752kB) |
Abstract
Penyalahgunaan listrik dan inefisiensi energi masih menjadi masalah terbuka dalam sistem jaringan pintar, yang menuntut mekanisme deteksi anomali berkinerja tinggi. Dalam makalah ini, kami mengusulkan sistem pemantauan listrik berkemampuan IoT yang menggabungkan machine learning (LightGBM) dan blockchain (Polygon Network) untuk deteksi anomali waktu nyata, penyimpanan data yang aman, dan pelacakan energy yang transparan. Smart meter IoT digunakan untuk memantau data penggunaan listrik secara real-time, sedangkan LightGBM mengklasifikasikan anomali secara efisien dengan presisi tinggi. Inovasi utamanya adalah penggunaan blockchain untuk pencatatan anomali yang terdesentralisasi dengan catatan anti-rusak dan meningkatkan kepercayaan. Tidak seperti pendekatan terpusat, blockchain Polygon secara permanen menyimpan data listrik, memberikan catatan anomali yang dapat diverifikasi. Dengan menggunakan dasbor IoT interaktif, pengguna dapat memantau pola konsumsi dan merespons anomaly secara efisien. Sistem yang diusulkan mencapai akurasi 96,77%, AUC-ROC 0,99, dan skor F1 96,69%, mengungguli CNN-LSTM dan CNN-XGBoost dalam hal akurasi dan penggunaan sumber daya komputasi. Terlepas dari keunggulan ini, biaya transaksi blockchain (0,001996 POL per transaksi) dan kompleksitas integrasi IoT-wallet menimbulkan tantangan. Pekerjaan di masa depan akan mengeksplorasi pengoptimalan blockchain yang mengurangi biaya seperti meta-transaction dan relay, bersama dengan peningkatan model untuk skalabilitas IoT. Pendekatan ini memberikan solusi berbiaya rendah, terukur, dan aman untuk manajemen energi pintar, meningkatkan keamanan jaringan dan keberlanjutan.
Kata Kunci: Penyalahgunaan Listrik, Deteksi Anomali, Internet of Things (IoT), Blockchain, Smart Contract
Electricity misuse and energy inefficiency are still open problems in smart grid systems, which demand high-performance anomaly detection mechanisms. In this paper, we propose an IoT-enabled electricity monitoring system that combines machine learning (LightGBM) and blockchain (Polygon network) for real-time anomaly detection, secure data storage, and transparent energy tracking. IoT smart meters are used to monitor realtime electricity usage data, while LightGBM efficiently classifies anomalies with high precision. The key innovation is the use of blockchain for decentralized anomaly recording with tamper-proof records and enhanced trust. Unlike centralized approaches, Polygon's blockchain permanently stores electricity data, providing a verifiable record of anomalies. Using interactive IoT dashboards, users can monitor consumption patterns and respond to anomalies efficiently. The proposed system achieved an accuracy of 96.77%, AUC-ROC of 0.99, and F1 score of 96.69%, outperforming CNN-LSTM and CNN-XGBoost in terms of accuracy and computational resource utilization. Despite these advantages, blockchain transaction costs (0.001996 POL per transaction) and the complexity of IoT-wallet integration pose challenges. Future work will explore costreducing blockchain optimizations such as meta-transactions and relays, along with model improvements for IoT scalability. This approach provides a low-cost, scalable, and secure solution for smart energy management, improving grid security and sustainability.
Keywords: Electricity Misuse, Anomaly Detection, Internet of Things (IoT), Blockchain, Smart Contracts
| Item Type: | Thesis (Doctoral) |
|---|---|
| Uncontrolled Keywords: | Penyalahgunaan Listrik, Deteksi Anomali, Internet of Things (IoT), Blockchain, Smart Contract |
| Subjects: | Sciences and Mathemathic |
| Divisions: | Postgraduate Program > Doctor Program in Information System |
| Depositing User: | ekana listianawati |
| Date Deposited: | 23 Jun 2026 04:52 |
| Last Modified: | 23 Jun 2026 04:52 |
| URI: | https://eprints2.undip.ac.id/id/eprint/53477 |
Actions (login required)
![]() |
View Item |
