Rancang Bangun Gateway Edge Berbasis Raspberry Pi Zero 2W Dengan Komunikasi LoRa SX1278 Untuk Prediksi Dan Pengendalian Penyiraman Tanaman Menggunakan TinyML
DOI:
https://doi.org/10.61722/jssr.v4i6.12831Keywords:
Gateway Edge, LoRa SX1278, TinyML, Random Forest, Raspberry Pi Zero 2W, ESP32, Smart FarmingAbstract
Sistem irigasi manual pada pertanian skala rumah tangga memiliki keterbatasan dalam memantau kondisi lingkungan tanaman secara dinamis dan real-time. Penelitian ini merancang dan membangun sistem gateway edge berbasis Raspberry Pi Zero 2W dengan komunikasi LoRa SX1278 untuk prediksi dan pengendalian penyiraman tanaman menggunakan TinyML, dengan tanaman mint (Mentha sp.) sebagai objek pengujian. Node sensor berbasis ESP32 membaca lima parameter lingkungan yaitu kelembaban tanah, suhu udara, kelembaban udara, tekanan udara, dan intensitas cahaya, kemudian mengirimkan data ke gateway edge melalui komunikasi LoRa SX1278 secara point-to-point. Gateway edge menjalankan inferensi model Random Forest berbasis TinyML secara lokal menggunakan library joblib tanpa memerlukan koneksi internet maupun layanan cloud. Model dilatih menggunakan dataset synthetic 1.200 sampel yang terdistribusi seimbang ke dalam tiga kelas kondisi tanaman yaitu Kering, Normal, dan Basah. Hasil pengujian menunjukkan model Random Forest mencapai akurasi 99,17% dengan nilai precision, recall, dan F1-score rata-rata masing-masing sebesar 0,9919, 0,9917, dan 0,9917. Pengujian komunikasi LoRa di dua lokasi berbeda di Kota Medan menunjukkan packet loss 0% pada seluruh titik pengujian hingga jarak ±100 meter. Sistem kendali pompa berhasil mengaktifkan pompa secara otomatis dengan tingkat keberhasilan 75% dan waktu respons kurang dari 2 detik. Web dashboard berbasis Flask 3.1.3 berhasil menyajikan monitoring real-time dan kendali pompa melalui jaringan WiFi lokal tanpa koneksi internet.
References
Alajlan, N. N., & Ibrahim, D. M. (2022). TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications. Micromachines, 13(6). https://doi.org/10.3390/mi13060851
Bafdal, N., Ardiansah, I., & Asmara, S. (2022). Application of Internet of Things (IoT) on Microclimate Monitoring System in The ALG Unpad Greenhouse Based on Raspberry Pi. Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering), 11(3), 518. https://doi.org/10.23960/jtep-l.v11i3.518-530
Baseca, C. C., Dionísio, R., Ribeiro, F., & Metrôlho, J. (2025). Edge-Computing Smart Irrigation Controller Using LoRaWAN and LSTM for Predictive Controlled Deficit Irrigation. Sensors, 25(22), 1–15. https://doi.org/10.3390/s25227079
Basri, M. (2025). A Comparative Study : Predicting Customer Churn in Banking Using Logistic Regression & Random Forest. Ultimatics : Jurnal Teknik Informatika, 17(1), 72–81. https://doi.org/10.31937/ti.v17i1.4075
Boralkar, R. R., & Kulkarni, S. S. (2024). IoT Based Smart Agriculture System Using ESP32. Interdisciplinary Conference on Electrics and Computer, INTCEC 2024, (June), 11–13. https://doi.org/10.1109/INTCEC61833.2024.10602915
Dafonte, J., González, M. Á., Comesaña, E., Teijeiro, M. T., & Cancela, J. J. (2024). Soil Water Status Monitoring System with Proximal Low-Cost Sensors and LoRa Technology for Smart Water Irrigation in Woody Crops. Sensors, 24(24). https://doi.org/10.3390/s24248104
Enock, K. S., Sagali, M. J., Jeannick, U. I., & Chen, D. (2025). LoRa-Based Smart Agriculture Monitoring and Automatic Irrigation System. Journal of Computer and Communications, 13(03), 1–20. https://doi.org/10.4236/jcc.2025.133001
Jeya Agastin K, P Hareesh Kumar, Hariharan K, & Kailash Aravind K. (2025). Real-Time Object Detection Using Raspberry Pi Zero 2W: An Optimized Approach. International Research Journal on Advanced Engineering and Management (IRJAEM), 3(12), 3401–3405. https://doi.org/10.47392/irjaem.2025.0537
Joice, A., Tufaique, T., Tazeen, H., Igathinathane, C., Zhang, Z., Whippo, C., Hendrickson, J., & Archer, D. (2025). Applications of Raspberry Pi for Precision Agriculture—A Systematic Review. Agriculture (Switzerland), 15(3), 1–31. https://doi.org/10.3390/agriculture15030227
Premkumar, S., & Sigappi, A. N. (2022). IoT-enabled edge computing model for smart irrigation system. Journal of Intelligent Systems, 31(1), 632–650. https://doi.org/10.1515/jisys-2022-0046
Downloads
Published
Issue
Section
License
Copyright (c) 2026 JOURNAL SAINS STUDENT RESEARCH

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.











