Edge-Based Predictive Data Reduction for Smart Agriculture: A Lightweight Approach to Efficient IoT Communication
Dora Krekovic, Mario Kusek, Ivana Podnar Zarko, Danh Le-Phuoc
TL;DR
This work tackles data transmission bottlenecks in Agro-IoT by deploying a lightweight LSTM predictor at the edge to forecast sensor readings and transmit only when the deviation exceeds a threshold, reducing energy use and bandwidth. It introduces a cross-site transfer strategy using satellite-derived training data to enable rapid deployment in data-scarce regions, with a cloud model ensuring data integrity. Across multiple scenarios in Croatia, the approach achieves data reductions up to 94% while maintaining MAE within a few tenths of a degree Celsius, demonstrating strong generalization for edge-based, decentralized inference. The findings suggest a scalable, energy-efficient framework for precision agriculture in connectivity-constrained environments, with promising directions for online adaptation, multivariate expansion, and adaptive thresholding.
Abstract
The rapid growth of IoT devices has led to an enormous amount of sensor data that requires transmission to cloud servers for processing, resulting in excessive network congestion, increased latency and high energy consumption. This is particularly problematic in resource-constrained and remote environments where bandwidth is limited, and battery-dependent devices further emphasize the problem. Moreover, in domains such as agriculture, consecutive sensor readings often have minimal variation, making continuous data transmission inefficient and unnecessarily resource intensive. To overcome these challenges, we propose an analytical prediction algorithm designed for edge computing environments and validated through simulation. The proposed solution utilizes a predictive filter at the network edge that forecasts the next sensor data point and triggers data transmission only when the deviation from the predicted value exceeds a predefined tolerance. A complementary cloud-based model ensures data integrity and overall system consistency. This dual-model strategy effectively reduces communication overhead and demonstrates potential for improving energy efficiency by minimizing redundant transmissions. In addition to reducing communication load, our approach leverages both in situ and satellite observations from the same locations to enhance model robustness. It also supports cross-site generalization, enabling models trained in one region to be effectively deployed elsewhere without retraining. This makes our solution highly scalable, energy-aware, and well-suited for optimizing sensor data transmission in remote and bandwidth-constrained IoT environments.