Network researchers and professionals from government, education, research, and industry were invited to submit proposals for demonstrations and experiments that display innovation in emerging network hardware, protocols, and advanced network-intensive scientific applications.
Toward 1.2 Tbps Services WAN Services: Architecture, Technology and Control Systems
StarLight International National Communications Exchange Facility, Booth 1281
Large scale data production within and among science research collaborations and sites continues to increase,a long term trend that continues to accelerate, especially because of the deployment of new science instrumentation, including planned high luminosity research infrastructure. Consequently, the science networking community has begun to prepare for service paths beyond 100Gbps, with a thematic focus on 400 Gbps LANs and WANs (represented in other NRE demonstrations by this consortium). However, this consortium is also investigating capabilities for WAN services beyond 400 Gbps, including those approaching 800 Gbps, 1 Tbps, and multi-Tbps WAN and LANservices.
400 Gbps E2E WAN Services: Architecture, Technology and Control Systems
These demonstrations will showcase 400 Gbps E2E WAN services from the StarLight International/National Communications Exchange Facility in Chicago to the SC23 venue, between StarLight and the multi-agency Joint Big Data Testbed (JBDT) Facility in McLean, Virginia, and between the JBDT Facility and the SC23 venue.
AP-REX 2.0 Prototype Demonstration
the AP-REX consortium is designing an international infrastructure based on 400 Gbps end-to-end paths interconnecting major open exchange points. Other service components include open exchange Data Transfer Nodes (DTNs), and AutoGOLE/NSI dynamic provisioning.
Global Research Platform (GRP)
The Global Research Platform (GRP) is an international scientific collaboration that is creating innovative advanced ubiquitous services that integrate resources around the globe at speeds of gigabits and terabits per second, especially for data-intensive science research.
LHC Networking And NOTED
This NRE abstract describes an experimental technique, NOTED (Network Optimized for Transfer of Experimental Data), being developed by CERN for potential use by the Large Hadron Collider (LHC) networking community. This SC23 NRE will demonstrate the capabilities of NOTED using an international networking testbed.
Packet Marking and Flow Labeling for Networked Scientific Workflows
Scientific network tags (scitags), an initiative that is promoting identification of the science domains and their high-level activities at the network level. This open system initiative provides open source technologies to help R&E networks understand resource utilization while providing information to scientific communities on the behavior of their workflows network flows.
Software Defined Exchange (SDX) Multi-Services for Petascale Science
The StarLight SDX is based on a flexible, scalable, programmable platform. This SDX, which is managed by a multi-organizational consortium, has been proven able to integrate many different multi-domain services and to insure services isolation. Services include those based on 100 Gbps Data Transfer Nodes (DTNs) for Wide Area Networks (WANs), including trans-oceanic WANs. Currently, a key focus is scaling to 400 Gbps WAN and LAN E2E technologies that provide high performance transport services for petascale science, controlled using Software Defined Networking (SDN) techniques.
FABRIC-Chameleon Testbed Integration
Two large scale National ScienceFoundation computer science testbed projects have been planning to provide integrated resources for their communities: Chameleon, a large-scale, deeply reconfigurable experimental platform for Computer Sciences systems research, and FABRIC, which enables cutting-edge and exploratory research at-scale in networking, cybersecurity, distributed computing andstorage systems, machine learning, and science applications.
Toward Fully-Automated Network Configuration Management for Large-Scale Science Networks
California Institute of Technology/CACR, Booth 1255
Over the past few years, we have developed a series of tools that can automatically and efficiently verify, diagnose and repair network configuration errors. These tools include (1) Coral, a distributed, on-device dataplane verification framework (ACM HotNets’23, ACM SIGCOMM’23), (2) Scalpel, a network configuration diagnosis system using symbolic program analysis (ACM APNet’23), and (3) IVeri, a privacy-preserving, interdomain configuration verification system (IEEE INFOCOM’21, ACM APNet’23). During SC’23, we will demonstrate, through both a testbed reconstruction of the Internet2 WAN environment and large-scale simulations of WAN/LAN/ DC with real-world datasets, that these tools can efficiently automate the network configuration management for large-scale networks.
Multi-site data streaming orchestration with SciStream
SciStream is an embedded middlebox-based architecture with control protocols to enable efficient and secure memory-to-memory data streaming between producers and consumers without direct network connectivity. SciStream operates at the transport layer to be application agnostic, supporting well-known protocols such as TCP, UDP, and QUIC. This demonstration will emulate multi-site online data processing using ESnet testbed, StarLight, FABRIC and SC show floor. The mem-to-mem data streaming over the Wide-Area Network (WAN) between ESnet Testbed, StarLight, FABRIC and SC showfloor will be enabled by SciStream.
StarLight DTN-as-a-Service and SciTag Network Analytics Prototype for High-Performance Data Transport with Research Platforms
For SC23, iCAIR will build on previous SciTag and DTN-as-a- Service initiatives to prototype network analytic services for up to 400 Gbps WAN end to end infrastructure. DTN-as-a- Service focuses on transporting large data across WANs and LANs within cloud environments, including using orchestrators such as Kubernetes, to improve the performance of the data transport over the high- performance networks. We will demonstrate implementation of cloud-native services for data transport within and among Kubernetes clouds through the DTN-as-a- Service framework, which sets up, optimizes, and monitors the underlying system and network. DTN-as-a-Service streamlines big data movement workflow by providing a Jupyter controller, a popular data science tools, to identify,examine and tune the underlying DTNs for high-performance data movement in Kubernetes and enabling data transport over long-distance WAN.
High Performance Network Entropy Platform Prototype for The Research Platforms with International P4 Experimental Networks
To support different monitoring and anomalies detection approaches, we will prototype and demonstrate a Network Entropy Platform for the Global Research Platform (GRP) and related Research Platforms.
The Global Network Advancement Group: A Next Generation System for Data Intensive Sciences
This network research exhibition (NRE) will present and demonstrate, in partnership with several NREs covering specific areas, many aspects of the next generation system which the GNA-G is developing both for data intensive sciences and help set the course for future R&E network operations.
AutoGOLE/SENSE: End-to-End Network Services and Workflow Integration
The GNA-G AutoGOLE/SENSE WG demonstrations will present the latest features and status for AutoGOLE and SENSE infrastructure and services.
SENSE and Rucio/FTS/XRootD Interoperation
This demonstration will show new mechanisms enabling better integration of advanced networks services into domain science workflows. These workflows typically coordinate and orchestrate compute and storage resources, and initiate associated data management/movement activities.
FABRIC (FABRIC is Adaptive Programmable Research Infrastructure for Computer Science and Science Applications) is an International infrastructure that enables cutting-edge experimentation and research at-scale in the areas of networking, cybersecurity, distributed computing, storage, virtual reality, 5G, machine learning, and science applications.
Resilient Distributed Processing and Reconfigurable Networks
California Institute of TechnologyStarLight International National Communications Exchange Facility/CACR, Booth 1281
This demonstration will build on our previous NRE SC demonstrations. We aim to show dynamic arrangement and re-arrangement of widely distributed processing of large volumes of data across a set of compute and network resources organized in response to resource availability and changing application demands. We also aim to explore performance limitations and enablers for high volume bulk data transfers. A software controlled network will be assembled using a number of switches and multiple SCinet 400G/100G connections from DC and Chicago to Denver. We plan to show rapid automated deployment and redeployment, real-time monitoring and QOS management application data flows with very different network demands.Technologies we intend to leverage include SDN, RDMA, RoCE, NVMe, GPU acceleration and others.
Distributed Experimental Pipelines over WAN for Online Data Analysis
The high-level goal of this demonstration is to show that experimental pipelines of can be extended over wide area networks enabling the integration of experiments directly with HPC facilities.
AmLight 2.0: Flexible control, deep visibility, and programmability @ Tbps!
This demo aims to showcase the newest open SDN architecture built leveraging Edgecore Tofino 1 and Tofino 2 with a homemade SDN Controller built to support AmLight’s science drivers and community. Among the benefits of the new SDN fabric, AmLight will present its support for In-band Network Telemetry (INT) in a long-haul production network and a flexible pathfinding approach created to support fine-grained traffic engineering.
Global P4 Lab
GP4L (Global P4 Lab) is a global overlay network composed of 100G/400G programmable switches from the GNA-G AutoGOLE / SENSE Persistent Multi-Resource Testbed and the GÉANT P4 Lab. It uses SONiC and RARE/FreeRtr, which are full featured open source network operating systems (NOSes) that at the same time implement traditional networking protocols and can be extended to integrate next generation features as an opt-In strategy. GP4L provides the means to implement production oriented feature experimentations and protocols, without impacting the rest of the network.
ALTO-TCN: Application-Defined Network Control for Data Intensive Sciences Through Deep Network Visibility
The goals of this NRE are to demonstrate the feasibility and benefits of application layer network control for Data Distribution Networks (DDN).
5G on the Showfloor
Department of Energy, Booth 243
In this research proposal, we aim to build a self-driving 5G network using multiple research experiences – engineering, hardware and field scientists. Leveraging open source solutions for tackling the 5G stack, our solution monitors and manages fronthaul to backhaul for a complete edge-to-core solution
Quantum Networks a Reality
Quantum networks will play a crucial role in maximizing the benefits of quantum technology, especially when scaling quantum sensor systems and quantum computers. Our key goal is to establish fault-tolerant quantum communications between localized as well as geographically distributed quantum resources. As the quantum network ecosystem expands, it facilitates interconnection of smaller networks, thus setting the stage for the ultimate realization of the Quantum Internet .
Exploring FDT, QUIC, BBRv2 and HTTP/3 protocols in High Latency WAN paths for use on Data Transfer Nodes
King Abdullah University of Science and Technology, Booth 1625
In this project, we will evaluate the end-to-end performance of the traditional routed interdomain paths and compare with the results of layer 2 ciruit paths provided by RENs connecting KAUST to US research institutions in different regions. Our first objective is to transfer 1TB of data on a path with RTT of 200ms or above in up to 15min, which requires a sustained data transfer of 10Gbps.
StarLight, Booth 1281
Standard Packet Drop Monitoring In High Performance Networks
Ctrl IQ, Inc., Booth 981
Exhibitors Arista Networks and InMon Corp. will demonstrate this standard measurement mechanism running live on the SCinet network at SC23.
N-DISE: NDN for Data Intensive Science Experiments
The N-DISE project builds on recently developed high-throughput NDN caching and forwarding methods, containerization techniques, leverage the integration of NDN and SDN systems concepts and algorithms with the mainstream data distribution, processing, and management systems of CMS, as well as the integration with Field Programmable Gate Arrays (FPGA) acceleration subsystems, to produce a system capable of delivering LHC and genomic data over a wide area network at throughputs approaching 100 Gbits per second, while dramatically decreasing download times.
Uncompressed 8K video processing using SRv6-based service function chaining between Japan and the U.S.
NICT, Booth 781
This project aims to establish a video processing platform for uncompressed 8K ultra-high-definition videos that can freely link transmission, storage, and processing functions, and automatically configure the required video production workflow using computing resources distributed among data centers and edges in the cloud.
Performance Evaluation of DTNs Towards ResearchEnhanceD ONION (RED ONION)
The goal of this proposal is to obtain the measurement results of throughput performance of data transfer between Osaka University in Japan and NICT booth in SC2023 venue Denver, USA.
Distributed Machine Learning over Heterogeneous Edge Computing Resources
In this demonstration, we deploy edge computing resources at several sites in the U.S., Japan, and other Asian regions, and interconnect them by EdgeVPN.io, a P2P-based overlay network software creating scalable virtual Ethernet networks across distributed edge nodes. On top of this overlay network, we perform hierarchical federated learning with different levels of aggregation. We will demonstrate how hierarchical federated learning can achieve higher efficiency and accuracy in a distributed and heterogeneous environment.
Long-Distance Streaming for SBC MD System
In this demonstration, wide-area network is utilized to perform streaming transmission of application screens between SC23 Dever and Tokyo Otemachi. An overview diagram of the network environment is presented in Figure 2. Additionally, in the experiment, the screen rendering speed (FPS) is measured and compared with the local environment. The screen resolutions of WGX, Full-HD, and 4K are compared for the purpose of this demonstration.
PolKA routing approach to support traffic engineering for data-intensive science
This NRE proposes to demonstrate PolKA functionality to support the traffic engineering challenges for data-intensive science.PolKA is a novel source routing approach  that explores the Residue Number System (RNS) and Chinese Remainder Theorem (CRT) by performing the forwarding as an arithmetic operation: the remainder of division. PolKA encodes the path in a routeID using the RNS in contrast to the conventional list-based representation, which transports the path information “in clear” inside the packet header. Then, PolKA core nodes use this encoded route label to discover the output ports.