Anomaly-Aware Energy-Efficient IoT Framework for Real-Time Environmental Monitoring Using Edge Intelligence

The Internet of Things (IoT) has played a vital role in providing continuous environmental monitoring by constantly tracking different types of environmental parameters like temperature, moisture levels, pollution levels, and noise levels. Environmental Monitoring continues to be an important application for Building Smart Cities and for Industries Using IoT. Traditional monitoring systems in IoT use a static sensing model and then send and process all the information to the Cloud, which leads to excessive energy waste, excessive communications overhead, and greater latency between devices especially when there are many devices deployed in a system. This paper presents a new anomaly-aware energy-efficient IoT framework for real-time environmental monitoring using edge intelligence to provide an effective solution to these existing problems. The proposed solution leverages a Light Weight Auto Encoder with a Temporal Attention mechanism on edge devices to detect environmental anomalies from multivariate sensor data. The method adjusts sensor frequency and data transmission rates based on changes in environment conditions. Lastly, extensive experimental evaluations of the accuracy, recall, and F1-measure have validated the proposed method with accuracies of 90.2%, recall rates of 88.7% and F1-measure rates of 89.4%, while simultaneously confirming a good level of scalability. Similarly, the proposed method has been shown to decrease energy consumption by up to 38%, reduce network traffic by up to 42% and lower end-to-end latency by up to 45% when measured against the traditional static IoT monitoring, as well as all prior techniques based on machine-learning methods. The findings demonstrate that the systematic framework provides excellent detection accuracy, while still maintaining maximum energy efficiency and low latency, thus providing an ideal foundation for next-generation Intelligent Environmental Monitoring Systems.