Validation and Evaluation of Computation Offloading in Campus Networks Using a Real 5G Setup

In the context of Industry 4.0, cutting-edge technologies such as Computational Offloading and Machine Learning, particularly Reinforcement Learning (Q-Learning), demand exceptionally low latency. These technologies are essential for mission-critical applications. To meet these demands, Edge Computing (EC) has been integrated, deploying robust devices at the network's edge. However, latency issues persist within the industrial infrastructure due to the inherent limitations of existing network technologies. Despite significant progress in mobile communication, including Fourth Generation (4G), Long Term Evolution (LTE), LTE-Advanced (LTE-A), and wireless protocols such as Wireless Fidelity (Wi-Fi), the industrial environment necessitates superior communication technology with exceptional Key Performance Indicators (KPIs). In this regard, 5G technology is ideally suited to address these requirements. The effectiveness of Computational Offloading is not always guaranteed. Its advantages depend on the availability of system resources and network bandwidth. To ensure a successful offloading process, the decision-making agent must address four critical questions: when, what, where, and how to offload. In this paper, we focus on tackling the “When to offload?” question and investigate how Reinforcement Learning (RL) agents can provide solutions. Our evaluation is based on whether the offloading decision made by the RL agent results in a positive or negative gain for the selected application. To fortify our findings, we compare the accuracy of our RL agent's decisions with theoretical models and an Oracle-based approach. Furthermore, we assess the decision-making efficiency of the RL agent in both emulated and real-world industrial network environments.