Joint container orchestrating and request routing for serverless edge computing-based simulation applications

Serverless edge computing dynamically invokes functions based on events, enabling on-demand code execution at the network edge and minimizing infrastructure management overhead. This computing paradigm is naturally suitable for event-driven distributed simulation applications, which involves frequent event interactions and stringent latency constraints. When running on top of geographically dispersed edge clouds, container orchestration and request routing have a significant impact on the performance of serverless edge computing-based simulations. In this paper, we propose an online orchestration framework for cross-edge serverless computing-based-simulations, which aims to minimize the resource cost and carbon emission under performance (i.e., latency) constraint, via jointly optimizing the container retention and requesting routing on-the-fly. This long-term cost minimization problem is difficult since it is NP-hard and involves future uncertain information. To simultaneously address these dual challenges, we carefully combine an online optimization technique with an approximate optimization method in a joint optimization framework. This framework first temporally decomposes the long-term time-coupling problem into a series of one-shot fractional problem via Lyapunov optimization, and then applies randomized dependent scheme to round the fractional solution to a near-optimal integral solution. The resulting online algorithm achieves an outstanding performance, as verified by extensive trace-driven simulations.