An Edge–Cloud Integrated Smart Monitoring System for Sustainable Freshwater Fishpond Management

Abstract

Water quality is a critical determinant of fish health and productivity in freshwater aquaculture, with parameters such as pH, dissolved oxygen (DO), temperature, and turbidity directly influencing growth, metabolism, and disease susceptibility. Traditional monitoring methods, based on manual sampling and laboratory analysis, are often slow, labor-intensive, and unable to detect rapid environmental changes. This paper presents the design and implementation of a hybrid edge–cloud integrated smart monitoring system for sustainable freshwater fishpond management. The system employs an ESP32-based edge node to collect real-time water quality data, detect threshold violations locally, and trigger immediate responses, including LED/buzzer alarms and actuator activation, while simultaneously sending email alerts via SMTP. Long-term data storage, visualization, and remote access are enabled through a cloud platform integrated with MQTT-based data publishing. Experimental evaluation demonstrated a total detection-to-action latency of 3.4 s, local alerts in 1.0 s, email notifications within 7.0 s, and cloud synchronization latency of 150 ms. Sensor measurements achieved high accuracy, with maximum deviations of only ±0.11 pH units, 0.3 mg/L DO, 0.21 NTU turbidity, and 0.2°C temperature. The system maintained 100% uptime during stable network conditions, confirming its reliability for continuous aquaculture monitoring. By combining low-latency local decision-making with cloud-based analytics, the proposed solution enhances operational efficiency, supports proactive management, and aligns with SDG 6 (Clean Water and Sanitation) and SDG 14 (Life Below Water). Future work will focus on integrating machine learning models for predictive water quality analysis and expanding the platform to other aquaculture and smart farming applications.