Investigation and RL-based Optimization of Offloading Decision Making in Industrial Edge Computing Scenarios

Abstract. Computation Offloading (CO) transfers computationally intensive tasks from hardware-limited devices (clients) to more powerful servers. This enablesclients to overcome performance and power limitations and meet Quality of Service requirements. Research in CO focuses on "Why", “What”, "If/When", "Where", and"How" to offload. This work investigates the "If/When" question from a performance perspective in dynamic environments. To optimize decision making, a ReinforcementLearning (RL) agent was designed, implemented, and trained to make efficient offloading decisions. The practicality of our solution was tested by emulating real hardwarein industrial environments using 5G New Radio. Experimental results show that the proposed RL agent outperforms the existing closed-form solution from the literature, improves the total completion time of emulated apps, and reduces client device power consumption.