Network Resource Optimization for ML-Based UAV Condition Monitoring with Vibration Analysis

TL;DR

This paper presents a framework for optimizing network resource usage in ML-based UAV condition monitoring by using feature aggregation and dimensionality reduction, significantly reducing network load while maintaining model effectiveness.

Contribution

It introduces a novel approach combining feature aggregation and dimensionality reduction to minimize network resource consumption in UAV condition monitoring systems.

Findings

Achieved 99.9% reduction in network resource consumption.

Optimized ML model selection based on feature aggregation intervals.

Demonstrated effectiveness using experimental data.

Abstract

As smart cities begin to materialize, the role of Unmanned Aerial Vehicles (UAVs) and their reliability becomes increasingly important. One aspect of reliability relates to Condition Monitoring (CM), where Machine Learning (ML) models are leveraged to identify abnormal and adverse conditions. Given the resource-constrained nature of next-generation edge networks, the utilization of precious network resources must be minimized. This work explores the optimization of network resources for ML-based UAV CM frameworks. The developed framework uses experimental data and varies the feature extraction aggregation interval to optimize ML model selection. Additionally, by leveraging dimensionality reduction techniques, there is a 99.9% reduction in network resource consumption.