The NITRD technical coordination efforts are focused in its Interagency Working Groups (IWGs) where member- and participating-agency representatives exchange information and collaborate on research plans and activities such as testbeds, workshops, and cooperative solicitations.
Artificial Intelligence & Wireless Spectrum:
Opportunities and Challenges
August 28-29, 2019
Griffiss Institute, Rome, NY
Agencies of the NITRD Wireless Spectrum Research & Development (WSRD) Interagency Working Group (IWG) are conducting a workshop focused on the application of existing and new AI techniques in the wireless spectrum context.
Wireless spectrum has been managed and utilized over many decades through a complex regulatory framework and a patchwork of policies. The current manual process of assessing spectrum needs is a growing problem due to the high-level of interdependencies in the spectrum domain. Existing and emerging methods for allocating spectrum are often driven by small studies that suffer from inherent biases. As a result, spectrum policies and usage are often sub-optimal and rigid, preventing efficient use of wireless spectrum. As the U.S. moves forward as a leader in 5G technologies and deployment, it critically needs fast and efficient wireless spectrum policy creation, adoption, and management of wireless spectrum.
Artificial Intelligence techniques have been successfully applied in many other domains, such as image classification or autonomous navigation, which previously relied on either a model-based approaches or a vital human-in-the-loop element. Despite the differences between multimedia and RF signals, researchers have shown that the judicious integration of Artificial Intelligence techniques can provide similar gains in the wireless spectrum domain.
Potential areas to be explored in this workshop include, but are not limited to:
Experts from government, private industry, and academia will discuss current use cases, effective technology, tools, and practices, while identifying gaps and issues that will require additional research to resolve.
Identify areas where artificial intelligence techniques can help increase efficiency of wireless spectrum use; and discuss ongoing efforts in federal, industrial and academic domains to utilize AI techniques in the wireless spectrum domain.
Today's artificial intelligence (AI), specifically machine learning (ML), has the potential to touch every area of our global digital society (i.e., our lives), and wireless spectrum is no exception. In this talk, Mr. Garris will describe what AI is, and how it can mean different things to different people. He will describe today’s AI versus what Hollywood portrays it to be. He will tie desired capabilities of wireless spectrum (framed by the agenda of this workshop) to AI’s capabilities, and he will emphasize the role of data to drive AI-powered innovation. In the second portion of this talk, Mr. Garris will provide an overview of AI policy and R&D coordination taking place at the highest levels of Government – within the White House’s National Science and Technology Council as well as within the newly formed independent National Security Commission on Artificial Intelligence.
This presentation will give an overview of DARPA's Spectrum Collaboration Challenge (SC2), as well as emerging lessons learned from this Grand Challenge to use collaborative AI and autonomy to optimize spectrum without human intervention. Perspectives will be shared from both Program Manager Paul Tilghman and the lead of one of the finalist teams, Brent Josefiak.
Opening Panel: The Current State of Artificial Intelligence
While the new wave of artificial intelligence (AI) and machine learning (ML) technologies has captured our attention, it is important to consider the broad landscape of AI. AI is not limited to one type, but rather is a concept covering a wide variety of approaches with differing capabilities and limitations. This panel will explore the AI landscape, shedding light on how types of data and different functional capabilities guide the selection of AI/ML techniques, mapping these insights to applications, and then drawing connections to the opportunities and challenges facing next generation wireless spectrum management.
Discussion Theme 1: Artificial Intelligence for Future Communications Networks
Communication networks and their associated architectures are evolving to be complex, heterogenous, interconnected entities that are becoming increasingly difficult to manage using traditional, model-based approaches. This discussion theme will focus on how AI can be used as a tool for (a) dynamic network planning and resource allocation (b) network monitoring, diagnosis and self-healing and (c) integrating heterogeneous networks end-to-end. The goal is to address the overall potential for AI to assist in operating and securing large complex networks more efficiently, addressing emerging use cases and applications, in addition to achieving target end-to-end objectives.
Discussion Theme 2: Artificial Intelligence for Dynamic Spectrum Allocation and Policy Management
The spectrum sharing paradigm has necessitated a shift in the way spectrum is managed and utilized. Artificial Intelligence (AI) will undoubtedly play an important role in facilitating the shift away from static frequency assignment and toward automated dynamic spectrum management. This discussion theme will focus on the utilization of Artificial Intelligence for Dynamic Spectrum Allocation and Policy Management. Specifically, this discussion theme will explore (a) AI and ML Tools and Datasets for RF Spectrum Sensing. Processing & Readout (b) Automated Learning over large data-sets and time-horizons (c) Role of AI predictions in spectrum allocations. The objective is to foster compelling and productive discussion regarding the potential for AI to enhance the way spectrum is managed and utilized in shared electromagnetic spectrum environments.
Discussion Theme 3: Artificial Intelligence for Spectrum Sharing
Spectrum sharing among independent users presents challenging decision-making problems, whether for the users themselves (peer-to-peer sharing) or for a control system seeking to arbitrate among them (spectrum access system). The data available to the decision engine is often incomplete, out-of-date, and noisy. The payoff of a decision depends in part on the actions of others and on details of the environment that are difficult to predict at design time. Assessing the effects of decisions is difficult given rapid changes in the environment. Because of these complexities, AI-enabled decision engines have the potential to outperform legacy software designs. Realizing this potential will require research on multiple interlinked topics. The second day starts off with lessons learned from the DARPA spectrum collaboration challenge (SC2) program on AI-enabled peer-to-peer sharing. Following this, workshop participants will divide into groups to identify opportunities and prioritize critical research topics in three areas: AI-enabled peer-to-peer sharing, AI-enabled spectrum access systems, and verification/validation of AI-enabled spectrum access mechanisms.