In order to fit the requirements of future enterprise management networks with multiple service providers, conventional mobile edge computing enabled small cells (MEC-SCs) peer-offloading requires research efforts towards fully-decentralized computation-efficient global-optimal quality of service (QoS) aware load balancing, while ensuring service providers’ privacy protection. In this article, we propose a new fully-decentralized on-demand MEC-SC peer-offloading NETwork (named DEEP-NET), targeting QoS-aware load balancing with enhanced latency and service providers’ privacy protection. Newly developed federated gradient descent based algorithm is fully decentralized to MEC-SCs, which only requires local data and privacy-free inter-MEC-SC data sharing to achieve global optimal QoS-/latency-aware fairness. Result analysis for convergence of the proposed DEEP-NET provides guidance to the future topology optimization of fully-decentralized on-demand MEC-SC deployment. Besides, DEEP-NET outperforms the benchmarks with dynamic user demand to achieve optimal load balancing, with enhanced QoS, latency, and service providers’ privacy.

中文翻译：

---

适用于企业管理网络的完全去中心化、公平感知的联合 MEC 小单元对等卸载


为了满足未来具有多个服务提供商的企业管理网络的要求，支持传统移动边缘计算的小型基站（MEC-SC）对等卸载需要研究完全分散的计算高效的全局最佳服务质量（QoS）感知负载均衡，同时确保服务提供商的隐私保护。在本文中，我们提出了一种新的完全去中心化的按需 MEC-SC 对等卸载网络（名为 DEEP-NET），其目标是具有增强的延迟和服务提供商隐私保护的 QoS 感知负载平衡。新开发的基于联邦梯度下降的算法完全去中心化到MEC-SC，只需要本地数据和无隐私的MEC-SC间数据共享即可实现全局最优的QoS/延迟感知公平性。对所提出的 DEEP-NET 收敛的结果分析为完全去中心化按需 MEC-SC 部署的未来拓扑优化提供了指导。此外，DEEP-NET 在动态用户需求方面优于基准，可实现最佳负载平衡，并具有增强的 QoS、延迟和服务提供商的隐私。