Kerim Gökarslan | Searcharxiv

arXiv2023

Achieving Ultra-Reliable Low-Latency Communication (URLLC) in Next-Generation Cellular Networks with Programmable Data Planes

Recent advancements in wireless technologies towards the next-generation cellular networks have brought a new era that made it possible to apply cellular technology on traditionally-wired networks with tighter requirements, such as industrial networks. The next-generation cellular technologies (e.g., 5G and Beyond) introduce the concept of ultra-reliable low-latency communications (URLLC). This thesis presents a Software-Defined Networking (SDN) architecture with programmable data planes for the next-generation cellular networks to achieve URLLC. Our design deploys programmable switches between the cellular core and Radio Access Networks (RAN) to monitor and modify data traffic at the line speed. We introduce the concept of \textit{intra-cellular optimization}, a relaxation in cellular networks to allow pre-authorized in-network devices to communicate without being required to signal the core network. We also present a control structure, Unified Control Plane (UCP), containing a novel Ethernet Layer control protocol and an adapted version of link-state routing information distribution among the programmable switches. Our implementation uses P4 with an 5G implementation (Open5Gs) and a UE/RAN simulator. We implement a Python simulator to evaluate the performance of our system on multi-switch topologies by simulating the switch behavior. Our evaluation indicates latency reduction up to 2x with \textit{intra-cellular optimization} compared to the conventional architecture. We show that our design has a ten-millisecond level of control latency, and achieves fine-grained network security and monitoring.

cs.NI↗

arXiv2020

Menes: Towards a Generic, Fully-Automated Test and Validation Platform for Wireless Networks

A major step in developing robust wireless systems is to test and validate the design under a variety of circumstances. As wireless networks become more complex, it is impractical to perform testing on a real deployment. As a result, the network administrators rely on network simulators or network emulators to validate their configurations and design. Unfortunately, network simulation falls short per it requires users to model the network behavior analytically. On the other hand, network emulation allows users to employ real network applications on virtualized network devices. Despite their complex design, the existing network emulation solutions miss full-scale automation rather they rely on experienced users to write complex configuration scripts making testing. Therefore, the validation process is prone to human operator errors. Furthermore, they require a significant amount of computational resources that might not be feasible for many users. Moreover, most network emulators focus on lower layers of the network thus requiring users to employ their own network applications to control and measure network performance. To overcome these challenges, we propose a novel wireless network emulation platform, the system, that provides users a unified, high-level configuration interface for different layers of wireless networks to reduce management complexities of network emulators while having a generic, fully-automated platform. Menes is a generic, full-stack, fully-automated test and validation platform that empowers existing state-of-the-art emulation, virtualization, and network applications including performance measurement tools. We then provide an implementation of Menes based on the EMANE with Docker. Our extensive evaluations show that the system requires much less computing resources, significantly decreases CAPEX and OPEX, and greatly extensible for different use cases.

cs.NI↗