SLEEPY-rApp: Delay-aware Sleep Scheduling for Energy Efficiency in MEC-enabled O-RAN

Abstract: This paper presents a novel resource allocation and MEC server deactivation strategy for MEC-enabled O-RAN networks, with the objective of optimizing energy consumption while satisfying strict delay requirements. Our approach leverages an intelligent orchestration application, SLEEPY-rApp, deployed in the SMO layer to dynamically control MEC server activation and request routing. We formulate a joint optimization problem that simultaneously considers computing capacity, end-to-end delay, and energy consumption. To address the NP-hard nature of this problem in real time, we propose a low-complexity heuristic that adapts to varying network conditions and workload patterns. Simulation results indicate that our method significantly reduces energy usage—particularly during peak operating periods—while maintaining the required quality of service. These findings underscore the potential of intelligent orchestration in enhancing the energy efficiency of future MECenabled O-RAN systems.