AI/ML-based Load Prediction in IEEE 802.11 Enterprise Networks

Enterprise Wi-Fi networks can greatly benefit from Artificial Intelligence and Machine Learning (AI/ML) thanks to their well-developed management and operation capabilities. At the same time, AI/ML-based traffic/load prediction is one of the most appealing data-driven solutions to improve the Wi-Fi experience, either through the enablement of autonomous operation or by boosting troubleshooting with forecasted network utilization. In this paper, we study the suitability and feasibility of adopting AI/ML-based load prediction in practical enterprise Wi-Fi networks. While leveraging AI/ML solutions can potentially contribute to optimizing Wi-Fi networks in terms of energy efficiency, performance, and reliability, their effective adoption is constrained to aspects like data availability and quality, computational capabilities, and energy consumption. Our results show that hardware-constrained AI/ML models can potentially predict network load with less than 20% average error and 3% 85th-percentile error, which constitutes a suitable input for proactively driving Wi-Fi network optimization.

I. Introduction

Generation after generation Wi-Fi is including new capabilities to embrace novel use cases like immersive communications, digital twins for manufacturing, or cooperative robotics [1]. These use cases come along with ever-increasing and expanded network requirements such as ultra-low-latency, superior reliability, and mobility [2]. Such stringent requirements demand extremely fast-responding network management and operation, able to flexibly adapt to rapidly varying situations. And to that end, Artificial Intelligence and Machine Learning (AI/ML)-based traffic prediction stands as an appealing tool for driving autonomous network optimization [3] by unlocking key applications like proactive mobility management, resource allocation, or energy efficiency.