A Smart Home Electricity Meter Based on IoT with Bill Prediction Using Random Forest Algorithm

muhtaredi Muhtaredi

Authors

muhtaredi Muhtaredi Universitas Global Jakarta

Keywords:

smart meter, Internet of Things, electricity monitoring, Random Forest, bill prediction

Abstract

Electricity consumption in households continues to increase along with the growth of electrical appliances used in daily activities. However, most users do not have real-time information about their electricity usage, which often results in inefficient energy consumption and unexpected electricity bills. This study aims to design and implement a smart electricity metering system based on the Internet of Things (IoT) with a billing prediction feature using the Random Forest algorithm. The proposed system measures electrical parameters such as voltage, current, and power consumption using sensors connected to a microcontroller. The collected data are transmitted to an IoT platform to provide real-time monitoring of electricity usage through a mobile application. Furthermore, the Random Forest algorithm analyzes the collected data to predict future electricity bills. The results show that the developed system can monitor electricity consumption in real time and provide accurate billing predictions. The prediction model achieved a Root Mean Squared Error (RMSE) of 0.31% with an accuracy level of 99.69%. The system also provides electricity consumption information for three selected rooms in the household.

References

[1] N. Abdurrahman, A. Jaenul, and D. J. Vresdian, “Rancang Bangun Sistem Monitoring Stasiun Pengisian Listrik Umum (SPLU) Hybrid Berbasis IoT di SMKN 2 Kota Bekasi,” vol. 2, no. 1, pp. 18–31, 2019.

[2] N. Aini, M. Arif, I. T. Agustin, and Z. B. Toyibah, “Implementasi Algoritma Random Forest untuk Klasifikasi Bidang MSIB di Prodi Pendidikan Informatika,” vol. 11, no. 1, 2024.

[3] W. T. Amalia, “Studi Perbandingan KWh Meter Prabayar dan KWh Meter Pascabayar,” 2022.

[4] Andreansyah, “Prototype Smart Home Sistem Monitoring Arus Listrik Menggunakan Sensor PZEM-004T Berbasis IoT,” 2024.

[5] A. Nugroho et al., “Teknik Random Forest untuk Meningkatan Akurasi Data Tidak Seimbang,” vol. 2, no. 2, pp. 128–140, 2024.

[6] D. Aribowo et al., “Edusaintek: Jurnal Pendidikan, Sains dan Teknologi,” vol. 8, no. 1, pp. 67–81, 2021.

[7] S. Fasa et al., “Pengaruh Variasi Tegangan dan Arus pada KWh Meter Mekanik dan Digital,” vol. 3, no. 1, pp. 32–46, 2024.

[8] A. Kurniawan, R. Putra, and M. Hidayat, “Perancangan Sistem Monitoring Konsumsi Daya Listrik Berbasis Android,” 2022.

[9] K. A. Yasa, I. M. Purbhawa, I. M. S. Yasa, I. W. Teresna, A. Nugroho, and S. Winardi, “Prototype Pemantauan Konsumsi Energi Listrik pada Firebase Menggunakan PZEM-004T,” Jurnal Eksplora Informatika, vol. 12, no. 2, pp. 104–112, 2023.

[11] J. Brownlee, Machine Learning Algorithms From Scratch with Python. Machine Learning Mastery, 2020.

[12] A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd ed. O’Reilly Media, 2020.

[13] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, Updated Edition, 2021.

[14] A. Rajput and M. Singh, “IoT Based Smart Energy Meter for Smart Grid Applications,” IEEE Access, vol. 9, pp. 105189–105200, 2021.

[15] M. A. Al-Garadi et al., “A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 1646–1685, 2020.

[16] S. Madakam and R. Ramaswamy, “Internet of Things (IoT): A Review of Architectures, Applications, and Security Issues,” Future Internet, vol. 13, no. 2, 2021.

[17] N. Kumar and A. Sharma, “IoT-Based Smart Energy Meter Monitoring System,” International Journal of Electrical and Computer Engineering, vol. 11, no. 5, pp. 4185–4192, 2021.

[18] H. Ning and H. Liu, Internet of Things: From Theory to Applications. Springer, 2021.

[19] O. Vermesan and P. Friess, Internet of Things – The Call of the Edge: Everything Intelligent Everywhere. River Publishers, 2020.

[20] S. Li, L. Da Xu, and S. Zhao, “The Internet of Things: A Survey,” Information Systems Frontiers, vol. 22, pp. 243–259, 2020.

[21] R. Buyya and A. V. Dastjerdi, Internet of Things: Principles and Paradigms, Updated Edition. Morgan Kaufmann, 2021.

[22] F. Chollet, Deep Learning with Python, 2nd ed. Manning Publications, 2021.

[23] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Pearson, 2021.

[24] A. Géron, “Machine Learning for Predictive Analytics in Energy Systems,” IEEE Access, vol. 10, pp. 55234–55248, 2022.

[25] Y. Liu et al., “Smart Energy Metering Based on Internet of Things and Machine Learning,” IEEE Internet of Things Journal, vol. 10, no. 4, pp. 3321–3332, 2023.