The increasing demand for diverse emerging applications has resulted in the interconnection of multi-access edge computing (MEC) systems via metro optical networks. To cater to these diverse applications, network slicing has become a popular tool for creating specialized virtual networks. However, resource fragmentation caused by uneven utilization of multidimensional resources can lead to reduced utilization of limited edge resources. To tackle this issue, this paper focuses on addressing the multidimensional resource fragmentation problem in virtual network embedding (VNE) in MEC systems with the aim of maximizing the profit of an infrastructure provider (InP). The VNE problem in MEC systems is transformed into a bilevel optimization problem, taking into account the interdependence between virtual node embedding (VNoE) and virtual link embedding (VLiE). To solve this problem, we propose a nested bilevel optimization approach named BiVNE. The VNoE is solved using the ant colony system (ACS) in the upper level, while the VLiE is solved using a combination of a shortest path algorithm and an exact-fit spectrum slot allocation method in the lower level. Evaluation results show that the BiVNE algorithm can effectively enhance the profit of the InP by increasing the acceptance ratio and avoiding resource fragmentation simultaneously.

翻译：新兴多样化应用需求的不断增长推动了多接入边缘计算（MEC）系统通过城域光网络实现互联。为满足这些多样化应用，网络切片已成为创建专用虚拟网络的常用工具。然而，多维资源利用不均导致的资源碎片问题会降低有限边缘资源的利用率。为应对这一挑战，本文重点研究MEC系统中虚拟网络映射（VNE）的多维资源碎片问题，旨在最大化基础设施提供商（InP）的收益。将MEC系统中的VNE问题转化为双层优化问题，同时考虑虚拟节点映射（VNoE）与虚拟链路映射（VLiE）之间的相互依赖关系。为解决该问题，我们提出一种名为BiVNE的嵌套双层优化方法。上层采用蚁群系统（ACS）求解VNoE，下层则结合最短路径算法与精确匹配频谱分配方法求解VLiE。评估结果表明，BiVNE算法能够通过提高接受率并避免资源碎片，有效提升InP的收益。