MMLite

Abstract

With increase in cellular-enabled IoT devices having diverse traffic characteristics and service level objectives (SLOs), handling the control traffic in a scalable and resource-efficient manner in the cellular packet core network is critical. The traditional monolithic design of the cellular core adopted by service-providers is inflexible with respect to the diverse requirements and bursty loads of IoT devices, specifically for properties such as elasticity, customizability, and scalability. To address this key challenge, we focus on the most critical control plane component of the cellular packet core network, the Mobility Management Entity (MME). We present MMLite, a functionally decomposed and stateless MME design wherein individual control procedures are implemented as microservices and states are decoupled from their processing, thus enabling elasticity and fault tolerance. For SLO compliance, we develop a multi-level load balancing approach based on skewed consistent hashing to efficiently distribute incoming connections. We evaluate the performance benefits of MMLite over existing approaches with respect to scaling, fault tolerance, SLO compliance and resource efficiency.

CoreKube: An Efficient, Autoscaling and Resilient Mobile Core System

“…Virtualized and cloud based mobile core systems need to meet several key requirements that are largely linked to the control plane. Scalability is chief among them, given the anchor role that the mobile core performs serving millions of users or devices differing in their access patterns, as also noted by prior work (e.g., [20,51,60]). Crucially, scaling with control plane workload needs to be achieved in a way that optimizes the operational costs.…”

“…Autoscaling. The scaling challenge presented by growing number of devices and control signaling traffic to virtualized mobile core systems is well recognized in the literature (e.g., [20,49,51,60]). Crucially, we would like a mobile core that efficiently scales such that resources used for control plane processing are proportional to the volume of signaling traffic being handled, as opposed to one that scales well but also has a high resource usage.…”

“…This is particularly the case for the mobile core as it is inherently less coupled with essential physical hardware like radio equipment in the RAN. This is reflected through the recent developments in the mobile networking industry (e.g., [22,25,69]), emergence of multiple open source projects (e.g., [28,36,45]) and from the focus of alternative core system designs in the research literature (e.g., [20,48,49,51,53]).…”

PP5GS—An Efficient Procedure-Based and Stateless Architecture for Next-Generation Core Networks

“…Stateless mobile core: MMLite [18] and dMME [19] implement and investigate the scalability of stateless MME entities. More specifically, MMLite presents a stateless and fully decomposed MME entity where each control procedure is implemented in its own microservice.…”

Investigating Inter-NF Dependencies in Cloud-Native 5G Core Networks

“…1) Cloud-Native Mobile Core: Following the design principles of cloud-native solutions, works [7] and [8] propose functionally decomposed architectures for the Mobility Management Entity (MME) in LTE networks. These microserviceoriented designs are superior to their monolithic counterparts with respect to resource efficiency, fault tolerance, scaling and throughput.…”