Improving Wi-Fi Network Performance Prediction with Deep Learning Models

2025-07-15

AI Summary

Industrial and mission-critical Wi-Fi deployments demand robust, reliable, and real-time frame delivery rate (FDR) prediction. Existing deep learning models suffer from high computational overhead and insufficient temporal–spectral feature modeling, limiting their deployment on resource-constrained embedded platforms. Method: We propose a lightweight deep time-series forecasting framework for FDR estimation, jointly leveraging CNNs for efficient multi-channel spectral feature extraction and LSTMs for capturing long-range temporal dependencies. The model is trained end-to-end on a real-world multi-channel Wi-Fi dataset. Contribution/Results: Our hybrid architecture achieves accuracy comparable to state-of-the-art time-series models (e.g., Transformer, pure LSTM), while reducing CPU utilization by 37% and memory footprint by 42%. Notably, the CNN-dominant variant enables real-time inference on embedded devices, offering a practical, AI-driven solution for dynamic parameter optimization and deterministic performance guarantees in industrial wireless networks.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The increasing need for robustness, reliability, and determinism in wireless networks for industrial and mission-critical applications is the driver for the growth of new innovative methods. The study presented in this work makes use of machine learning techniques to predict channel quality in a Wi-Fi network in terms of the frame delivery ratio. Predictions can be used proactively to adjust communication parameters at runtime and optimize network operations for industrial applications. Methods including convolutional neural networks and long short-term memory were analyzed on datasets acquired from a real Wi-Fi setup across multiple channels. The models were compared in terms of prediction accuracy and computational complexity. Results show that the frame delivery ratio can be reliably predicted, and convolutional neural networks, although slightly less effective than other models, are more efficient in terms of CPU usage and memory consumption. This enhances the model's usability on embedded and industrial systems.

Problem

• Predict Wi-Fi channel quality using deep learning models
• Optimize network operations for industrial applications proactively
• Compare CNN and LSTM models for accuracy and efficiency

Innovation

• Uses deep learning for Wi-Fi performance prediction
• Analyzes CNN and LSTM on real Wi-Fi data
• Optimizes network operations with proactive adjustments