An Energy-Efficient Hybrid LoRa-Wi-Fi Architecture for Real- Time Water Quality Monitoring and Machine Learning-Based...

Area of Science:

• Environmental Science
• Computer Science
• Electrical Engineering

Background:

• Large-scale water quality management is hindered by manual sampling latency and IoT energy constraints.
• Traditional IoT deployments face energy-connectivity trade-offs, limiting real-time monitoring capabilities.

Purpose of the Study:

• To propose HydroSense AI, a robust three-tier IoT framework for real-time multi-parameter water quality monitoring and predictive analytics.
• To address energy autonomy challenges in remote sensing nodes for sustainable water management.

Main Methods:

• Implemented a heterogeneous sensing layer (pH, TDS, turbidity, temperature) with a hybrid LoRa/ESP32 communication architecture.
• Utilized hardware-synchronized duty cycling with a DS3231 Real-Time Clock (RTC) for precise deep-sleep scheduling and extended battery life.
• Integrated AI-driven trend-forecasting and anomaly-detection models with a Telegram-based alert system.

Main Results:

• Achieved high measurement stability with a one-step normalised RMSE of 0.0063 for pH and 0.0298 for TDS in forecasting.
• Demonstrated extended battery operational life, estimating 46 days of unattended operation on a 2500 mAh cell.
• Reported a 99.8% packet delivery ratio, highlighting the efficiency of the hybrid architecture.

Conclusions:

• HydroSense AI provides a sustainable solution for real-time water quality monitoring and predictive analytics in institutional infrastructures.
• Hardware-synchronized duty cycling is crucial for optimizing energy consumption in sensor-dominated IoT nodes.
• The proposed framework effectively balances performance, energy efficiency, and real-time data delivery for enhanced water management.