When Video Streaming Meets Named Data Networking: A Case Study

Generative AI (GenAI), exemplified by Large Language Models (LLMs), such as OpenAI’s ChatGPT, is revolutionizing various fields. Central to this transformation is Data Center Networking (DCN), which not only provides the infrastructure support for GenAI operation, but also provisions GenAI services to users. Hence, this article explores the interplay between GenAI and DCNs, analyzing their symbiotic relationship and mutual advances. We begin by reviewing the current challenges of DCNs and GenAI-based solutions, such as data augmentation, process automation, and domain transfer. We then discuss the distinctive characteristics of GenAI workloads on DCNs, gaining insights that catalyze the evolution of DCNs to more effectively support GenAI. Moreover, to illustrate the seamless integration of GenAI with DCNs, we present a case study on GenAI-empowered DCN digital twins. Specifically, we employ an LLM equipped with retrieval augmented generation to formulate optimization problems for DCNs (e.g., resource allocation and routing) and adopt diffusion-deep reinforcement learning to solve optimization. The experimental results on a representative DCN optimization problem, i.e., knowledge placement, demonstrate the validity and efficiency of our proposals. We anticipate that this article can promote further research to enhance the virtuous interaction between GenAI and DCNs.

360-degree video streaming is an important component of virtual reality. A video streaming server stores video streams with various quality levels. These streams are fragmented into several video segments. In 360-degree video streaming, these segments are tiled into video tiles. In general, the client changes the viewport quality level based on predictions of the user’s viewport and network throughput. In named data networking (NDN), the throughput measured at the client is not always stable due to network-inherent caching. Therefore, the viewport video quality changes (referred to as quality switching) frequently in 360-degree video streaming over NDN. In this paper, we propose buffer-based adaptation using scalable video coding for 360-degree video streaming over NDN. In the proposed method, a buffer-based adaptation algorithm and the prefetching of video tiles are used to avoid video quality switching. A simple performance evaluation using computer simulations shows that the proposed method reduces the quality switching compared with that for a rate-based adaptation algorithm.

Named data networking (NDN) is a new Internet architecture that replaces today’s focus on where – addresses and hosts with what – the content that users and applications care about. One of NDN’s prominent advantages is scalable and efficient content distribution due to its native support of caching and multicast in the network. However, at the last hop to wireless users, often the WiFi link, current NDN implementation still treats the communication as multiple unicast sessions, which will cause duplicate packets and waste of bandwidth when multiple users request for the same popular content. WiFi’s built-in broadcast mechanism can alleviate this problem, but it suffers from packet loss since there is no MAC-layer acknowledgement as in unicast. In this paper, we develop a new NDN-based cross-layer approach called NLB for efficient and scalable live video streaming over wireless LAN. The core ideas are: using WiFi’s broadcast channel to deliver content from the access point to the users, a leader-based mechanism to suppress duplicate requests from users, and receiver-driven rate control and loss recovery. The design is implemented and evaluated in a physical testbed comprised of one software AP and 20 Raspberry Pi-based WiFi clients. While NDN with multiple unicast sessions or plain broadcast can support no more than ten concurrent viewers of a 1Mbps streaming video, NDN plus NLB supports all 20 viewers, and Received December 29, 2015; accepted April 28, 2016 E-mail: zhxp@tsinghua.edu.cn can likely support much more when present.

Data centers consume significant amounts of energy, contributing indirectly to environmental pollution through greenhouse gas emissions during electricity generation. According to the Natural Resources Defense Council, information and communication technologies and networks account for roughly 10% of global energy consumption. Reducing power consumption in Data Center Networks (DCNs) is crucial, especially given that many data center components operate at full capacity even under low traffic conditions, resulting in high costs for both service providers and consumers. Current solutions often prioritize power optimization without considering Quality of Service (QoS). Services such as video streaming and Voice over IP (VoIP) are particularly sensitive to loss or delay and require QoS to be maintained below certain thresholds. This paper introduces a novel framework called QoS-Aware Power-Optimized Path Selection (Q-PoPS) for software-defined DCNs. The objective of Q-PoPS is to minimize DCN power consumption while ensuring that an acceptable QoS is provided, meeting the requirements of DCN services. This paper describes the implementation of a prototype for the Q-PoPS framework that leverages the POX Software-Defined Networking (SDN) controller. The performance of the prototype is evaluated using the Mininet emulator. Our findings demonstrate the performance of the proposed Q-PoPS algorithm in three scenarios. Best-case: Enhancing real-time traffic protocol quality without increasing power consumption. midrange-case: Replacing bottleneck links while preserving real-time traffic quality. Worst-case: Identifying new paths that may increase power consumption but maintain real-time traffic quality. This paper underscores the need for a holistic approach to DCN management, optimizing both power consumption and QoS for critical real-time applications. We present the Q-PoPS framework as evidence that such an approach is achievable.

Research in Information-Centric Networking (ICN) and Named Data Networking (NDN) has produced many protocol designs and software prototypes, but they need to be validated and evaluated by real usage on the Internet, which is also critical to the realization of the ICN/NDN vision in the long run. This article presents the first Internet-scale adaptive video streaming service over NDN, which allows regular users to watch videos using NDN technology with no software installation or manual configuration. Since mid-2019, the official NDN website [1] has started using our service to deliver its videos to Internet users over the global NDN testbed, showcasing the feasibility of NDN. We conduct real-world experiments on the NDN testbed to validate the proper implementation of the client, network, and server sides of the proposed system and also evaluate the performance of our video streaming service.

In this paper, we describe a new telepresence system which enables a user to look around a virtualized real world easily in network environments. The proposed system includes omni-directional video viewers on web browsers and allows the user to look around the omni-directional video contents on the web browsers. The omni-directional video viewer is implemented as an Active-X program so that the user can install the viewer automatically only by opening the web site which contains the omni-directional video contents. The system allows many users at different sites to look around the scene just like an interactive TV using a multi-cast protocol without increasing the network traffic. This paper describes the implemented system and the experiments using live and stored video streams. In the experiment with stored video streams, the system uses an omni-directional multi-camera system for video capturing. We can look around high resolution and high quality video contents. In the experiment with live video streams, a car-mounted omni-directional camera acquires omni-directional video streams surrounding the car, running in an outdoor environment. The acquired video streams are transferred to the remote site through the wireless and wired network using multi-cast protocol. We can see the live video contents freely in arbitrary direction. In the both experiments, we have implemented a view-dependent presentation with a head-mounted display (HMD) and a gyro sensor for realizing more rich presence.

Software-Defined Networking (SDN) is a networking design approach, which separates the data plane from the control plane, providing the network with certain benefits due to centralized programmatic control. SDN provides a centralized view and enables management of the entire network. It offers flexibility in configuration, reduces time to deploy, provides automation and facilitates building a network without requiring the knowledge of any vendor-specific software/hardware. SDN offers the datacenter network benefits such as improving traffic and security management as well as providing a scalable infrastructure. Load balancing enhances the performance of the network by distributing traffic among servers and therefore preventing congestion and server underutilization. This paper aims to explore SDN and test its implementation and demonstrate how to implement its concepts within a datacenter network. The experiment considers the datacenter network implemented in Sudan University of Science and Technology as a case study. The edited network topology is made up of a Demilitarize Zone (DMZ) having three servers, a Local Area Network (LAN) and a main switch. The Hub, Switch and Load balancer scenarios are implemented using Mininet emulator. In addition, the three scenarios are tested using external devices and analyzed using Wireshark. Moreover, the connectivity of HTTP and FTP is verified.

Within today's large-scale data centers, the inter-node communication is often the major bottleneck. This fact recently blooms the data center network (DCN) research. Since building a real data center is cost prohibitive, most of DCN studies rely on simulations. Unfortunately, state-of-the-art network simulators have limited support for real world applications, which prevents researchers from first-hand investigation. To address this issue, we developed a unified and cross-layer simulation framework, namely the DCNSim. By leveraging the two widely deployed simulators, DCNSim introduces computer architecture solutions into DCN research. With DCNSim, one could run packet-level network simulation driven by commercial applications while varying computer and network parameters, such as CPU frequency, memory access latency, network topology and protocols. With extensive validations, we show that DCNSim could accurately capture performance trends caused by changing computer and network parameters. Finally, we argue that future DCN researches should consider computer architecture factors via several case studies.

Fault tolerance, performance, and throughput have been major areas of research and development since the evolution of large-scale networks. Internet-based applications are rapidly growing, including large-scale computations, search engines, high-definition video streaming, e-commerce, and video on demand. In recent years, energy efficiency and fault tolerance have gained significant importance in data center networks and various studies directed the attention towards green computing. Data centers consume a huge amount of energy and various architectures and techniques have been proposed to improve the energy efficiency of data centers. However, there is a tradeoff between energy efficiency and fault tolerance. The objective of this study is to highlight a better tradeoff between the two extremes: (a) high energy efficiency and (b) ensuring high availability through fault tolerance and redundancy. The main objective of the proposed Energy-Aware Fault-Tolerant (EAFT) approach is to keep one level of redundancy for fault tolerance while scheduling resources for energy efficiency. The resultant energy-efficient data center network provides availability as well as fault tolerance at reduced operating cost. The main contributions of this article are: (a) we propose an Energy-Aware Fault-Tolerant (EAFT) data center network scheduler; (b) we compare EAFT with energy efficient resource scheduling techniques to provide analysis of parameters such as, workload distribution, average task per servers, and energy consumption; and (c) we highlight effects of energy efficiency techniques on the network performance of the data center.

Named Data Networking (NDN), an information-centric Internet architecture, introduces a new forwarding model, in which the forwarding plane can choose between multiple interfaces when forwarding a packet. While the forwarding module brings new opportunities it also introduces challenges when the application's performance or correctness is affected by a conflict between the application design and the assigned forwarding strategy. In this paper we demonstrate the impact of the forwarding strategy decision on the performance and correctness of NDN applications.

Information sharing among a group of friends or colleagues in real life is usually a distributed process: we tell each other interesting or important news without any mandatory assistance or approval from a third party. Surprisingly, this is not what happens when sharing files among a group of friends over the Internet. While the goal of file sharing is to disseminate files among multiple parties, due to the constraints imposed by IP's point-to-point communication model, most of today's file sharing applications, such as Drop box, Google Drive, etc., resort to a centralized design paradigm: a user first uploads files to the server (cloud), and the server (cloud) re-distributes these files to other users, resulting in unnecessary tussles and inefficient data distribution paths. To bring the truly distributed file sharing back into the cyberspace, this paper presents Chrono Share, a distributed file sharing application built on top of the Named Data Networking (NDN) architecture. By walking through Chrono Share design details, we show how file sharing, as well as many other similar applications, can be effectively implemented over NDN in a truly distributed and secure manner.

Data center networks (DCNs) require a low-cost, low-power optical transceiver to handle increased traffic from generative artificial intelligence, video streaming services, and more. Improving the required signal-to-noise ratio (RSNR) by digital signal processing such as forward error correction (FEC) mitigates the requirements for electrical and optical components. The optical transceivers in DCNs exploit a low-complexity soft-decision (SD) FEC, consisting of short block-length linear error-correcting codes and a low-complexity SD decoder (SDD), such as Chase decoding and ordered statistics decoding. The low-complexity SDD efficiently approaches a maximum likelihood decoding (MLD). However, the decoding performance of MLD is limited by its finite block length. In this paper, we describe the details of our proposed channel-polarized multilevel coding with iterative decoding (CP-MLC-ID). The proposed CP-MLC-ID improves the decoding performance by extending the codeword length to weakly and indirectly connect codewords via bypassed bits. The 19.5% –OH CP-MLC-ID using 128-bit extended Bose–Chaudhuri–Hocquenghem (eBCH) and KP4 codes outperforms the concatenated eBCH and KP4 codes with a net coding gain of 0.25 and 0.40dB for the same and double the number of SDDs, respectively. We also investigate the dependency of the decoding performance on the size of a bit interleaver. The performance degradation of CP-MLC-ID using an 8-bit interleaver is about 0.1dB compared to using the large-bit interleaver. Our results indicate that even a weak connection by exclusive-OR between codewords improves the decoding performance, compared to simple concatenated codes in the DCNs.

Data centers constitute the foundations of cloud computing. Increased adoption of cloud computing in various sectors of life necessitates the data center growth. Cloud providers are facing numerous challenges in data centers design and operation. This chapter presents the modeling and simulation of the major data center network architectures using ns-3. The chapter details the three major DCN architectures and their implementation details.

In this contemporary world, technology is advancing at a rapid pace. In the recent decades, information technology has grown exponentially. Improving data center energy efficiency is an urgent issue with remarkable economic and environmental impacts. Enormous heat generation is fuelled by the data centers. Distribution of heat is a crucial parameter that affects data center cooling and energy consumption. Heat reduction is the crux of environmentally sustainable computing. Typically, data centres lack in effective sensing systems to monitor heat distribution at a large scale. In this chapter, I aim at using sensor networks as a dense instrumentation technology to comprehend and control cooling in data centers. This chapter presents the Aquasar project as the case study and explores the environmental challenges in developing sensor networks in data centers. I also explore the effective way of dealing with the excess heat from multiple servers in the data centers and the upper hand of water cooling over air cooling.

Optical circuit switching may be instrumental in meeting the cost, energy, and aggregate bandwidth requirements of future data center networks. However, conventional MEMS beam-steering cross-connects cannot provide submillisecond switching with the port count necessary for data centers. Here, we investigate a novel noncrossbar selector switch architecture and pupil-division switching layout to improve optical switching performance by relaxing the requirement of arbitrary switch configurability. This architecture and switch design enable MEMS beam-steering micromirrors to scale to microsecond response speeds while supporting high port count and low loss switching, and can realize a number of useful interconnection topologies. We present the design, fabrication, and experimental characterization of a proof-of-principle prototype using a single comb-driven MEMS mirror to achieve 150 μs switching of 61 ports between four preprogrammed interconnection mappings. We demonstrate the scalability of this switch architecture with a detailed optical design of a 2048-port selector switch with 20 μs switching time.