Dembski Jerzy, Kołakowska Agata, Wiszniewski Bogdan
Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Narutowicza 11/12, 80-233 Gdańsk, Poland.
Sensors (Basel). 2025 Jan 1;25(1):189. doi: 10.3390/s25010189.
A serious limitation to the deployment of IoT solutions in rural areas may be the lack of available telecommunications infrastructure enabling the continuous collection of measurement data. A nomadic computing system, using a UAV carrying an on-board gateway, can handle this; it leads, however, to a number of technical challenges. One is the intermittent collection of data from ground sensors governed by weather conditions for the UAV measurement missions. Therefore, each sensor should be equipped with software that allows for the cleaning of collected data before transmission to the fly-over nomadic gateway from erroneous, misleading, or otherwise redundant data-to minimize their volume and fit them in the limited transmission window. This task, however, may be a barrier for end devices constrained in several ways, such as limited energy reserve, insufficient computational capability of their MCUs, and short transmission range of their RAT modules. In this paper, a comprehensive approach to these problems is proposed, which enables the implementation of an anomaly detector in time series data with low computational demand. The proposed solution uses the analysis of the physics of the measured signals and is based on a simple anomaly model whose parameters can be optimized using popular AI techniques. It was validated during a full 10-month vegetation period in a real Rural IoT system deployed by Gdańsk Tech.
在农村地区部署物联网解决方案的一个严重限制可能是缺乏可用的电信基础设施，无法持续收集测量数据。一种使用携带机载网关的无人机的游牧计算系统可以解决这个问题；然而，这也带来了一些技术挑战。其中一个挑战是，受无人机测量任务天气条件影响，地面传感器的数据收集是间歇性的。因此，每个传感器都应配备软件，以便在将收集到的数据传输到飞越的游牧网关之前，清理其中错误、误导或冗余的数据，从而减少数据量，并使其适合有限的传输窗口。然而，对于在能量储备有限、微控制器计算能力不足以及无线接入技术模块传输范围短等多方面受到限制的终端设备来说，这项任务可能是一个障碍。本文提出了一种针对这些问题的综合方法，该方法能够以低计算需求在时间序列数据中实现异常检测器。所提出的解决方案利用对测量信号物理特性的分析，并基于一个简单的异常模型，其参数可以使用流行的人工智能技术进行优化。该方案在格但斯克科技大学部署的一个实际农村物联网系统的整整10个月植被期内得到了验证。
