Keynote

Abstract: Cloud platforms’ rapid growth is raising significant concerns about their increasing energy consumption and carbon emissions. To address these concerns, future cloud platforms will need to be flexible enough to use power whenever and wherever it is available---including from renewable sources, such as solar and wind, which have zero carbon emissions but are highly unreliable. Unfortunately, today's energy systems mask this unreliability from software, preventing applications from optimizing their carbon-efficiency, or work per kilogram of carbon emitted. This talk presents the CarbonFirst project, which elevates carbon to a first-class metric for designing a sustainable and reliable cloud-edge software infrastructure. The foundation of CarbonFirst is the design of an "ecovisor," which virtualizes the energy system and exposes software-defined control of it to applications. Importantly, an ecovisor enables each application to handle energy's unreliability in software based on its own specific requirements. We highlight the benefits of this approach by showing how an ecovisor can support multiple applications that concurrently exercise their virtual energy system in different ways to better optimize carbon-efficiency based on their specific requirements compared to general system-wide policies.

Bio: David Irwin is a Professor in the Department of Electrical and Computer Engineering at the University of Massachusetts Amherst and Chair of ACM’s Special Interest Group on Energy Systems and Informatics (ACM SIGEnergy). His research focuses on designing distributed software systems with an emphasis on improving efficiency and sustainability.

Bio: Vishy (Viswanathan) Swaminathan is a Sr. Principal Scientist and a research org head within Adobe Research . He currently works on Agentic AI experiences for end users, creators, and marketers at the intersection of multimodal content, documents, and behavioral data. His research org, EPIC (Experiences, Platforms, Insights, and Content) focuses on Agentic AI research for Adobe's Experience, Document, and Creative Clouds. Research from Vishy’s organization powers several flagship innovations, including the award-winning Acrobat AI Assistant, Adobe Experience Platform AI Assistant, and the newly announced Adobe Express, Creative Assistants, and the Agent Orchestrator. Vishy's research contributions have significantly shaped Adobe’s video monetization technologies (delivery, rights management, advertising, recommendation), campaigns, and recommendation technologies. Earlier his work on HTTP Dynamic Streaming which won the ‘Best Streaming Innovation of 2011′ Streaming Media Readers’ Choice Award. Vishy has received several honors, including best paper awards, 2017 Distinguished alumnus from Utah State University ECE Department, and 3 ISO certificates of appreciation for outstanding contributions to MPEG Standards - most notably as editor of the Emmy-winning MPEG-DASH standard. Prior to Adobe, Vishy was a Senior Researcher at Sun Labs. He holds an MS and Ph.D. in Electrical Engineering from Utah State University and a B.E. in ECE from the College of Engineering, Guindy, Anna University, Chennai, India. Vishy has authored numerous papers, articles, RFCs, and book chapters, holds over 100 issued patents, and actively volunteers in organizing IEEE and ACM conferences.

Bio: Lei Zhong received the Ph.D. degree from the Graduate University for Advanced Studies, Japan, in 2011. He is currently a Principal Researcher and Project Manager in the InfoTech Division at Toyota Motor Corporation, where he leads research and standardization activities in intelligent connected vehicles. He serves as Toyota’s chief delegate to major standardization organizations, including 3GPP, IEEE, and the Wi-Fi Alliance, and chairs the PoC and Liaison Relationship Strategy committees within the Automotive Edge Computing Consortium (AECC).

His research interests include wireless networking, edge computing, machine learning, connected vehicles, and big data analytics. He has co-authored more than 100 technical publications and holds over 50 patents in these areas. Dr. Zhong also actively contributes to the academic community as Vice-Chair of the IEEE TCGCC Special Interest Group on Green Internet of Vehicles and serves on the editorial boards of Elsevier Vehicular Communications, IEEE Internet Computing, and the IEEE Open Journal of the Computer Society.

Abstract: AI has made great strides in NLP and knowledge-based tasks. AI is poised to enter the real physical world to perform tasks far beyond knowledge. Still some persistent problems need to be addressed. This presentation explores the challenges of physical AI at the Edge and proposes potential areas of solution.

Bio: Jeff serves as Chief Architect for Ernst & Young LLP Americas, leading product development for emerging technologies including AI, simulation, and advanced computation. He chairs the EY Enterprise Architecture Council and directs the emerging technology lab, driving innovation and research across the organization.

Previously at Dell Technologies, Jeff held executive roles including AI Factory and AI Edge Product Lead, overseeing business and technical roadmaps for enterprise AI infrastructure. As CTO for Dell’s Edge business, he pioneered edge application management, distributed platform control, and AI operations for connected vehicles and edge systems.

Jeff’s career spans leadership positions at HPE, Ericsson, Alcatel-Lucent, and early-stage AI/robotics ventures, including serving as CTO of Elefante Group’s stratospheric communications platform. His expertise encompasses distributed systems, edge computing, machine reasoning, and enterprise architecture.

With 26 granted patents and 40 applications spanning AI, distributed systems, cybersecurity, and edge technology, Jeff is recognized as an innovation leader. He formerly chaired the North Texas Technology Council (Tech Titans) and holds credentials as an IEEE Senior Member and Certified Agile Product Owner.