Reliable power supply units are essential for Automatic Weather Stations (AWS) to maintain continuous data collection. However, traditional maintenance schedules often fail to prevent sudden equipment downtime. While machine learning can enable predictive maintenance, standard standalone models typically struggle to capture both immediate short-term anomalies and slow, long-term degradation. To address this gap, this study aims to evaluate and propose a hybrid Temporal Convolutional Network (TCN) and Long Short-Term Memory (LSTM) architecture specifically designed for AWS power supply forecasting. Using empirical time-series data, we monitored five operational parameters at 10-minute intervals from September 2023 to November 2024. Correlation analysis established battery temperature as a primary health indicator due to its strong inverse relationship with voltage (r = –0.87). Comparative evaluations demonstrated that while individual TCN and LSTM models exhibited architectural trade-offs, the proposed hybrid TCN-LSTM model achieved the highest predictive accuracy (R² = 0.9497; MAPE = 0.05%). The findings confirm that integrating these networks effectively balances rapid anomaly detection with stable long-term trend forecasting. Practically, this hybrid model can be integrated into AWS telemetry systems as a robust diagnostic tool, providing automated early warnings to prevent critical power failures.
Marzuki Sinambela, Rifqi Daffa Ul haq, Dibyo Susanto et al.· Indonesian Physical Review· 0 citations
The designed system successfully improved installation safety and reduced the risk of equipment damage and fire and was developed using an ESP32 microcontroller integrated with a PZEM-004T sensor, a DHT22 sensor, and an MQ-2 sensor.
I. M. D. P. Putra, Nardi Nardi, Dibyo Susanto et al.· Internet of Things and Artif...· 0 citations
The server room at the Class I Climatology Station of East Java requires reliable monitoring of temperature, humidity, flame detection, and electrical voltage; however, monitoring is still conducted manually without automatic electrical protection. This study aims to design and implement an Internet of Things (IoT)-based environmental condition monitoring and automatic electrical protection system using an ESP32 integrated with BME280, KY-026, and ZMPT101B sensors. The system applies a two-level threshold structure—warning and critical—to trigger notifications as well as automatic power disconnection via relays. The research methodology includes system design, sensor calibration of the BME280 and ZMPT101B using a comparative method, functional testing of the KY-026, and a 14-day field test. The test results demonstrated a temperature correction of -0.21 °C, a humidity correction of -0.80% RH, and an average voltage error of 1.05%. The system recorded two warning-status readings for humidity without reaching critical conditions and successfully transmitted and stored 114,903 data points during the testing period. The reading interval was designed to be 5 seconds, whereas the actual transmission interval was influenced by network conditions. The results indicate that the system can effectively support environmental monitoring and automatic electrical protection for server rooms.
Rizaldi Wisnu Wardana, Adi Widiatmoko Wastumirad, Benyamin Heryanto Rusanto et al.· Internet of Things and Artif...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
