NSF Platforms for Advanced Wireless Research�Research Testbeds enabling Artificial Intelligence for Wireless Networks

https://www.advancedwireless.org/

June 30, 2020

Platforms For Advanced Wireless Research (PAWR)

Kick-Off: April 2017

​

PAWR and AI

2

6/30/2020

Industry Consortium

<$ + In-Kind>

$50M

NSF

<$>

$50M

The PAWR vision

PAWR and AI

3

6/30/2020

Drivers for

success

Interoperability

• Prevent silos within research ecosystem
• Well-defined interfaces
• Interconnection with other PAWR platforms

Open Access

• Accessible by the research community
• Fairness in access

Diversity

• Broad range of topics
• Spectrum, mmWave, Internet of Things, wide-area wireless backhaul, measurements etc.

Programmability

• Programmable at multiple levels (e.g., radio, resource allocation, backbone)
• Clearly defined interfaces and APIs.

Usability

• Low learning curve, even if “open”
• Operable by BS technical level
• Reprogrammed by Advanced Users

Reproducibility

• Platforms setup, maintained, documented
• High scientific standards
• Accuracy and repeatability

PAWR industry consortium

PAWR and AI

4

6/30/2020

• 34 wireless organizations currently a part of the PAWR Industry Consortium
• Continual growth of PAWR partner ecosystem since launch
• New partnerships developing with federal agencies and the open source community

The PAWR approach

PAWR and AI

5

6/30/2020

Initial topic areas that PAWR enables

PAWR and AI

6

6/30/2020

mmWave R&D and systems testing at the millimeter-wave bands that are about 28GHz, 60GHz with a target of 100 Gbps in data rates for small-cell networks that cover a few city blocks.

​

Network Slicing to focus on the providing differential isolated Micro services to multiple users from RAN to Network slicing .

​

NFV MANO provide support for ETSI and other MANO implementations to orchestrate end-to-end VM,container, VNF deployment in a cloud native environment including radio resources that operate on the wireless edge.

​

Microservices Architecture assembling, controlling, and composing services. PAWR provides a service control plane that is layered on top of a diverse collection of back-end service implementations, including VM-hosted VNFs, container-based micro-services, and SDN-based control programs that embed functionality in white-box switches

Massive MIMO 2.5-2.7GHz and 3.5-3.7GHz 128 antenna element fully programmable radio to allow PHY/MAC/network FDD, full duplex research to design, build and demonstrate high bandwidth connectivity to multiple users simultaneously.

​

RAN CU-DU Split to advance capabilities of baseband-RRH and other functional splits being debated n different communities e.g.eCPRI, OTN backhaul, O-RAN.

​

Applications/Services in later years – Platforms will serve as examples of Smart and Connected Community networks that demonstrate potential applications/services including Cyber-Physical Systems, Cyber-Security, Internet of Things, Robotics, Smart and Connected Health, and Big Data.

Where is PAWR today?

Three platforms funded:

• Round I announced April 9, 2018
• POWDER/RENEW: University of Utah – Available for experimenter use since Nov 2019
• COSMOS: Columbia University – Available for experimenter use since May 2020
• Round II announced September 18, 2019
• AERPAW: NCSU – Available by January 2021
• Round III RFP on rural broadband technologies currently in review

Plus:

• Colosseum
• Belongs to the PAWR family, at Northeastern University – available from March 2020
• NSFCloud and FABRIC testbeds
• Provides Cloud Computing and internet-scale experimentation capabilities

PAWR and AI

7

6/30/2020

PAWR: The first (and only) FCC Innovation Zones

PAWR and AI

8

6/30/2020

• First-ever Innovation Zone designation for experimental research as designated by the FCC
• Established on 9/18/19 in NYC and SLC, expected in mid-2020 for Raleigh/Cary, NC
• Allows for experimental license operation across wider (city-scale) geography and with additional flexibility in frequency bands

Salt Lake City Technical and Band Information

West Harlem Technical and Band Information

POWDER/RENEW

PAWR and AI

9

6/30/2020

POWDER: Platform for Open Wireless Data-driven Experimental Research

RENEW: A Reconfigurable Eco-system for Next-generation End-to-end Wireless

• RENEW Massive MIMO base station
• End-to-End Programmable
• Diverse Spectrum Access 50 MHz-3.8GHz
• Hybrid Edge computer composed of FPGA and GPU/CPU-based processing,
• Hub Board aggregates/distributes streams of radio samples

• Next Generation Wireless Architecture
• Dynamic Spectrum Sharing
• Distinct environments: a dense urban downtown and a hilly campus environment.

Control Framework with Hardware + Software Building Blocks

IRIS software-defined radio modules

Architectural view of RENEW base station

Deployment Area: UofU Campus +Downtown SLC + Connected Corridor

POWDER/RENEW: Truly “city-scale”

PAWR and AI

10

6/30/2020

Campus Shuttle Routes

Base Station locations

POWDER/RENEW: Open for experimenters

PAWR and AI

11

6/30/2020

8 Rooftop Base station and Fixed End Point sites

• Available since Nov. 2019

​

Software Profiles Available:

- Open Air Interface

- Worked with ONF to provide basic XRAN functionality in OAI

- Open Network Automation Platform (ONAP) [LF]

- Converged Multi-Access and Core (COMAC)/Open Mobile Evolved Core (OMEC) [ONF]

- Akraino Edge Stack, Radio Edge Control (REC)

- RAN Intelligent Controller (RIC)

- O-RAN [O-RAN Alliance]

COSMOS: Cloud-Enhanced, Open, Software-Defined Mobile Testbed for City-Scale Deployment

PAWR and AI

12

6/30/2020

Deployment Area: West Manhattan/Harlem

• A multi-layered computing system with an RF thin client; flexible signal processing; network function virtualization (NFV) between a local SDR (with FPGA assist) and a remote cloud radio access network (CRAN) with massive CPU/GPU and FPGA assist
• Deployed in New York City, one of the country’s most populated urban centers
• Wideband radio signal processing (with bandwidths of ~500 MHz or more)
• Support for mmWave communication (28 and 60 GHz)
• Optical switching technology (~1µs) provides passive WDM switch fabrics and
• radio over fiber interfaces for ultra-low latency connections

​

28GHz phased-array ICs and phased-array antenna modules (PAAM)

COSMOS Radio Site Design All-Optical Network Design

COSMOS: Large and medium nodes

PAWR and AI

13

6/30/2020

COSMOS: Available today

Base Configuration

• 2 Large and 3 Medium Nodes
• 16 port Space Switch
• ROADMs: 1 fiber pair each, 2 total
• Direct CRF connections: 6 fiber pairs
• Ethernet switch: 2 fiber pairs

PAWR and AI

14

6/30/2020

AERPAW: Aerial Experimentation and �Research Platform for Advanced Wireless

PAWR and AI

15

6/30/2020

Goals

• Accelerate the integration of UAS into the national air-space
• Enable new advanced wireless features for UAS platforms, including flying base stations for hot spot wireless connectivity

​

Focus areas

• Advanced wireless communication technologies that enable beyond-VLOS and autonomous UAS operations and three-dimensional mobility for UAS
• New use cases for advanced wireless technologies that are emerging in the unmanned aerial systems (UAS) space

​

Tactics

• Create a one-of-a-kind aerial wireless experimentation platform and a proving ground and technological enabler for emerging innovations, including package delivery platforms and urban air mobility
• Accelerate development, verification, and testing of transformative advances and breakthroughs in telecommunications, transportation, infrastructure monitoring, agriculture, and public safety

AERPAW at a glance

​

• Led by North Carolina State University (NCSU) with three other universities
• Start date 9/01/2019
• NSF award of $9,094,403 over 5 years
• Estimated Industry Consortium cash and in-kind match of up to $10M, including major contributions from:
• National Instruments, Keysight, Ericsson, Commscope
• Private spectrum licensees
• Approximately 20 fixed nodes at 3 main sites in the RDU Triangle area
• 20+ unmanned autonomous vehicles (drones) with advanced wireless tech through the coverage area

​

AERPAW: Deployment plans

PAWR and AI

16

6/30/2020

Colosseum

PAWR and AI

17

6/30/2020

Colosseum is the world’s largest wireless network emulator with granularity at the RF signal level

• 256 x 256 100 MHz RF channel emulation
• 128 Programmable Radio Nodes
• Computing resources (CPU, GPU, FPGA)
• Access control and scheduling infrastructure
• Supports remote shared access
• Colosseum is a General Purpose Cooperative Radio Development and Testing Environment
• https://www.darpa.mil/program/spectrum-collaboration-challenge

Envisioned experiment lifecycle �for future wireless research

PAWR and AI

18

6/30/2020

Round III RFP on rural broadband

Full proposals due: December 13, 2019

Finalist selection in process

PAWR and AI

19

6/30/2020

• Open-ended for emerging and frontier ideas
• Focus on architectures – question assumptions and conventional wisdom
• Provide solutions and specifications as well as relevant trade-offs and implications
• Looking for various possible solutions to particular challenges in rural broadband
• Reduce cost/bit using a mix of technologies: fiber, FSO, microwave, mmWave, HAPS, satellite, etc.

https://advancedwireless.org/wp-content/uploads/2019/10/PAWR_Project_Office_LOI_Round_III-FINAL.pdf

Find out more

• PAWR Project Office: http://advancedwireless.org
• POWDER/RENEW:
• http://powderwireless.net
• http://renew.rice.edu
• COSMOS: http://cosmos-lab.org
• AERPAW: http://aerpaw.org
• Colosseum: https://www.northeastern.edu/colosseum

​

PAWR and AI

20

6/30/2020

Relevance to AI

• Networking research is largely stymied by lack of appropriate datasets
• Context, Scale, Timeliness, Relevance, Diversity
• Spectrum and Policy questions
• Best answered through use of unbiased datasets and collection methods
• AI (ML specifically) is touted as the solution to many network management/design woes
• Yet, the one thing AI/ML needs to work: data!!
• Reliable, extensive, reproducible, annotated, real-world, big data
• Industry has data
• Access, Intellectual Property, Reproducibility, Collection bias issues
• PAWR can fill the void
• A key motivator for the companies in the PAWR Industry Consortium

PAWR and AI

21

6/30/2020

Spectrum and AI

PAWR and AI

22

6/30/2020

Example: DARPA SC2 and SHARE

On the Salt Lake City POWDER testbed

​

• $2.7M PAWR Project Funded by DoD
• Test AI-Driven Spectrum Sharing Optimization In a 5G-NR Network
• Taking the emulator-tested SC2 solution to the real-world
• Extensive measurements driving practical solutions

​

• DARPA SHARE Program validation through PAWR
• Dissemination of information securely and at multiple levels of security
• Utilizes the NSF-funded Named Data Network (NDN) architecture
• Solution from Perspecta Labs to be deployed on POWDER platform
• Cybersecurity attack generation and defense using AI-based strategies

PAWR and AI

23

6/30/2020

Example: Smart Intersection and Channel Measurements

On the New York City COSMOS testbed

• Traffic cameras connected to a wireless SDN network
• AI-powered traffic management
• Wirelessly share in-vehicle sensor data with other vehicles and the edge cloud servers
• Data available for other researchers to verify and validate
• Wideband channel sounding
• Millimeter-wave (28 GHz) channel measurements over wideband
• Open sharing of data for any experimenter

​

​

PAWR and AI

24

6/30/2020

Summary

• PAWR platforms are a unique resource
• Can enable AI solutions for modern networks
• Wireless networks as well as wired
• Open, unbiased, reproducible data collection and datasets
• Train the AI for future networks
• Unleash them in the controlled ‘wild’ – enabled by PAWR
• Enable rapid advances in AI for network policy, design, operations and management

PAWR and AI

25

6/30/2020