A Distributed Load Balancing Technique for Multitenant Edge Servers With Bottleneck Resources

The popularity of edge computing has risen due to the widespread use of online services on IoT and mobile devices. This technology provides geographically distributed edge servers to reduce delays, energy consumption, and bandwidth requirements. However, edge computing faces challenges due to limited computing resources on edge servers and the dynamic density of IoT and mobile device users. In this article, we propose a distributed edge resource allocation approach that can accommodate the dynamic user population on the limited computing resources of edge servers. Our proposed approach aims to balance the loads of edge servers to maximize resource utilization by moving users from overloaded edge servers to underutilized ones. This way, edge computing resources can serve the maximum number of users. In addition, the proposed approach identifies bottleneck resources on edge servers to maintain the quality of service (QoS) provided by the edge servers. Thus, this approach ensures that users' experience remains consistent and meets the required QoS standards. We also validate the performance of the proposed algorithm by simulating it and simulation results show that the approach achieves its objectives and improves the efficiency of edge computing resources compared to state-of-the-art approaches.