서강대학교

초록/요약

The rapid development of cloud infrastructure has also increased the total power usage requirement which has made the energy consumption problem really severe. Inefficient resource utilization is one of the biggest reasons for such a rise in energy utilization. Federated edge cloud (FEC) is an edge cloud environment where multiple edge servers in a single administrative domain collaborate together to provide real-time services. This environment reduces the possibility of violating the quality of service (QoS) requirements of target services by locating delay-sensitive services at nearby edge servers instead of deploying them on the clouds. As the number of edge servers increases in FEC, the amount of energy consumed by servers and network switches also increases. This creates another challenge for how to schedule delay-sensitive services over FEC, while minimizing the total energy consumption and reducing the QoS violation of service at the same time. This paper proposes an energy-efficient Reinforcement Learning (RL) based reconfiguration mechanism in FEC called FEC-RL. Unlike traditional approaches, the placement algorithm in FEC-RL places delay-sensitive services on the edge servers in nearby edge domains instead of clouds that decrease the number of network hops along the path. In addition, FEC-RL schedules services with actual traffic requirements rather than using maximum traffic requirements to ensure QoS. This increases the number of services co-located in a single server and thereby reduces the total energy consumed by the services. FEC-RL is a (Q-learning) based reconfiguration algorithm, that can dynamically adapt to a changing environment. FEC-RL has been compared with heuristic algorithms such as ESFEC-EF (energy first) and ESFEC-MF (migration first), which are more suitable for large scale scenarios. The simulation results show that the FEC-RL improves energy efficiency by up to 28% and lowers the service violation rate by up to 66% against a traditional approach and the heuristic approaches used in the edge cloud environment.