SkyNetPredictor: Network Performance Prediction in Avionic Communication using AI

TL;DR

This work tackles the problem of predicting network performance for avionic satellite communications along flight paths by introducing ML-based preflight predictions. It develops LSTM and KNN models to map a rich set of positional and network features to a network-performance score in the range of $1$ to $10$, and benchmarks against a rule-based baseline. The dataset combines handover region information, historical SNR/MIR, beam metrics, and augmented temporal features from GEO Ku-band data, with careful preprocessing and sequence framing. Results show that both ML models outperform the rule-based approach, with KNN achieving the highest accuracy at the cost of longer inference time, while LSTM offers a favorable trade-off between accuracy and speed, making it suitable for offline and near-real-time planning. The work enables proactive path selection in business aviation, potentially improving reliability and user experience by forecasting performance across candidate flight paths before departure.

Abstract

Satellite-based communication systems are integral to delivering high-speed data services in aviation, particularly for business aviation operations requiring global connectivity. These systems, however, are challenged by a multitude of interdependent factors such as satellite handovers, congestion, flight maneuvers and seasonal trends, making network performance prediction a complex task. No established methodologies currently exist for network performance prediction in avionic communication systems. This paper addresses the gap by proposing machine learning (ML)-based approaches for pre-flight network performance predictions. The proposed models predict performance along a given flight path, taking as input positional and network-related information and outputting the predicted performance for each position. In business aviation, flight crews typically have multiple flight plans to choose from for each city pair, allowing them to select the most optimal option. This approach enables proactive decision-making, such as selecting optimal flight paths prior to departure.

Figures (5)

• Figure 1: LSTM model block diagram
• Figure 2: Plots displaying accuracy of model predictions. Left: KNN. Center: LSTM. Right: Rule Based Approach
• Figure 3: Confusion Matrices for KNN and LSTM models
• Figure 4: Plot displaying the distribution of the true and predicted classes
• Figure 5: Distribution of correlation coefficients