IEEE Emerging Technologies Reliability Roundtable 2024

IEEE Communications Society (ComSoc)
Technical Committee on Communications Quality & Reliability (CQR)
Emerging Technologies Reliability Roundtable 2024 (ETR-RT24)
May 21-22 (Tuesday-Wednesday), 2024
Lisbon, Portugal
Hotel Altis Belem

Scope of the Roundtable

  • Discuss and identify the RAS (Reliability, Availability and Serviceability) challenges,
    requirements, and methodologies in the emerging technology areas like the Cloud
    Computing, Wireless/Mobility (with focus on 5G technologies), NFV (Network Functions Virtualization), SDN (Software Defined Networking), or similar large-scale distributed and virtualization systems.
  • Discuss the RAS requirements and technologies for mission-critical industries (e.g., airborne systems, railway communication systems, the banking and financial communication systems, etc.), health care systems, and intelligent vehicles with the goal to promote the interindustry sharing of related ideas and experiences.
  • Investigate the use of large language models (LLMs) to find new/increase coverage of failure models – both security and other failures.
  • Identify Serviceability and Reliability-impacted Security Aspects under Resilience, which is considered as an “umbrella” topic.
  • Discuss the huge impact of Artificial Intelligence (AI), with an emphasis to the
    reliability/trustworthiness of AI solutions (Generative AI, Responsible AI, Sustainable AI and AI for Sustainability).
  • Identify potential directions for resolving identified issues and propose possible solutions.

The focus will be on:

  • IoT Reliability
    •  Reliability and serviceability for IoT applications, and massively scaled infrastructure 
    • Reliability and serviceability for Digital Energy
    • Intelligent Vehicles Safety
  •  AI Reliability and Responsibility
    • Reliability and serviceability of massively scaled infrastructure for AI Foundation Models 
    • Responsible and trustworthy AI for mission critical applications
    • Emerging regulations.

Participants at the ETR-RT 2024 in Lisbon, Portugal

Speakers/Participants and Talk Titles


This Roundtable was held on May 21-22, 2024 in Lisbon, Portugal. It was well balanced with
speakers/participants from Telecom Service Providers (AT&T, Telefónica), Telecom Suppliers
(Huawei, NOS Comunicações S.A.), IT companies (Google Research, Palindrome Technologies, Brighten AI, RoadToAmherst, LocalAI, INESC INOV-Lab), and universities (Czech Tech University in Prague, University. of Lisbon, University of Delaware, University of Illinois at Urbana-Champaign – UIUC, and University of Oulu).

The speakers addressed various issues and challenges of the 5G deployment and 6G research, the telecom regulatory environment, and the AI landscape providing further insight and impact on reliability, serviceability, and security. The talks provided “food for thought” questions in the common discussion held after each presentation and summarized in the closing discussion for highlighting major issues to address. Following are the titles of the presentations:

IEEE Emerging Technology Reliability Roundtable 2024: Summary of Findings

[#01] Spilios Makris – Introduction to ETR-RT2024
[#02] David Lu – ETR-RT2024 Opening Remarks
[#03] Lynette Webb – Update on AI Regulation
[#04] Kathy Meier-Hellstern – Scaling Responsible AI
[#05] John Burkey – Unleashing Potential Scaling AI for Impact (Talk 1)
[#06] Kostas Vlahodimitropoulos – AI for Energy Sustainability (Presentation)
[#06A] Kostas Vlahodimitropoulos – AI for Sustainable Energy (Paper)
[#07] Antonio Grilo – AI for Communications Networks
[#08] Pavel Kordik – Latest AI Developments Explained
[#09] David Guillen AI – Empowered Cloud Continuum for Mobile Networks
[#10] David Lu – Disruptive Impact 6G Future (Talk 1)
[#11] Matti Latva-aho – 6G Key Enabler for Metaverse
[#12] Lily Prasad – Data Driven Planning for Telecom under Climate Change
[#13] Luis Santo Green – Networks Minimizing Energy Consumption
[#14] Chengqiang Huang – Design for Dependability and its Challenges
[#15] David Lu – Risk and Opportunity of Large-Scale Network Outage (Talk 2)
[#16] Jun Xu – Understanding Battery Safety and Durability Issues
[#17] Tianyin Xu – Kubernetes Reliability and Reliable Cloud Infrastructures
[#18] Peter Thermos – Security and Reliability in Heterogeneous Networks
[#19] John Burkey – Harmonizing Realms (Talk 2)
[#20] David Lu – Hosting ETR-RT2025 in Prague Czech Republic

David H. Lu, Vice President (Retired), Network Systems AT&T, Board of Director for several Non-Profit organizations, USA

Talk Title 1: Risk and Opportunity of Large-scale Network Outages and Data Breach
 
Abstract 1: As industry leading communication networks going through major transformations to next generation ultra-fast fiber network, 5G terrestrial wireless networks, and disaggregated software defined networks, the reliance of these network infrastructure by business and consumer customers is increasing exponentially. This talk will focus on recent industry incidents with huge user and business impact to understand the reliability risks and opportunities. This talk will analyze the possible root causes triggered such incidents and operations implications that further complicates the incidents’ impact. The talk will also provide AI driven solution recommendations to better predict/protect networks as well as possible network design considerations that can further network resiliency.
 
Talk Title 2: Disruptive Impact of 6G to Global Technology, Humanity, and Reliability
 
Abstract 2: The proliferation of technology advancements in semiconductors, sensors, generative AI, cloud computing, blockchain, ultra-fast communication network, LEO satellite communication integration, and quantum computing is rapidly changing the landscape of the world including social interactions, economical models, industrial operations, political systems, and everything that touches mankind. As the 5G and 5G Advance deployment and applications gaining ground quickly, 6G is becoming the hot topic of the day. What, when and how about 6G is raising eyebrows of scientist and engineers around the world. This talk will focus on what is expected of 6G and how 6G might overcome the current technological and economical challenges to unleash its power, especially its impact on humanity and social fabrics. This talk will also explore network resilience design and reliability considerations as well as research areas to ensure the success of 6G.

John Burkey, Founder, CEO/CTO Brighten AI, USA

John Burkey, an AI expert, blends conversational AI, Ai hardware, and generative AI tools.
Featured in national and international TV and written journalism, he holds patents in operating systems, computing languages, development tools, and artificial intelligence. Burkey has had significant roles at Apple, including contributing to MacOS, iOS and Siri, and at Microsoft as Chief Architect for Office on iPhone, iPad, and Mac. He also served as Chief Architect for Java at Sun Microsystems. His journey is heavily influenced by his cherished mentor Leland Wilkinson, who wrote “the grammar of graphics”. John abides by Steve Jobs’ quote: “great artists ship” and worked with Jobs and when absolutely necessary, counseled him on Apple and industry futures.

Talk Title: Unleashing Potential: Scaling AI for Impact, Safety, and Global Change

Abstract: Embarking on the journey to harness the full potential of AI requires navigating a complex landscape of scalability, reliability, and ethical considerations. In this talk, we delve into the intricate interplay between model temperature, TopN selection, and the balance between goal directness and creativity within the context of building truly massive AI systems. We explore how the scalability of these systems enables them to transcend mere novelty, becoming truly valuable and transformative tools for humanity. Moreover, we emphasize the critical importance of safety in this pursuit, highlighting how the responsible harnessing of scale leads to AI systems that are not only useful and valuable but also inherently safe and trustworthy. By dissecting these themes, we aim to inspire a deeper understanding of how scaling AI can catalyze real-world change, driving progress towards a safer, more equitable future for all.

Talk Title 1: Unleashing Potential: Scaling AI for Impact, Safety, and Global Change

Abstract 1: Embarking on the journey to harness the full potential of AI requires navigating a complex landscape of scalability, reliability, and ethical considerations. In this talk, we delve into the intricate interplay between model temperature, TopN selection, and the balance between goal directness and creativity within the context of building truly massive AI systems. We explore how the scalability of these systems enables them to transcend mere novelty, becoming truly valuable and transformative tools for humanity. Moreover, we emphasize the critical importance of safety in this pursuit, highlighting how the responsible harnessing of scale leads to AI systems that are not only useful and valuable but also inherently safe and trustworthy. By dissecting these themes, we aim to inspire a deeper understanding of how scaling AI can catalyze real-world change, driving progress towards a safer, more equitable future for all.

Talk Title 2: Harmonizing Realms: Embracing Ethical Multi-Modal AI’s Awakening

Abstract 2: As we embrace the fusion of multi-modal inputs and outputs in AI, we embark on a journey akin to conducting a symphony of senses. Nvidia’s hardware advancements propel us towards unprecedented performance gains, reminiscent of Larry Niven’s Dreampark, where the boundaries between reality and imagination blur, reminding us that “the only way of discovering the limits of the possible is to venture a little way past them into the impossible.”
In this odyssey, we explore how orchestrating visual, auditory, and textual modalities not only amplifies AI’s capacity for understanding and creativity but also instantaneously customizes content. However, we recognize that with this power comes great responsibility. Thus, we argue that ethics and safety must be interwoven into the fabric of generative AI.
By harmonizing these elements, we’re poised to realize dreams that once resided solely in the realm of fiction while ensuring that the creations of AI uphold ethical standards and prioritize user safety. Through this awakening, we invite you to join us in a journey where the convergence of modalities heralds a new era of possibility and innovation, resonating across the landscape of human imagination.

 

Lily Prasad, Assistant Vice President, AT&T Labs, USA

Lily began her career in AT&T Bell Labs doing VLSI design, development, and testing. For most of her career she has led multiple systems engineering, program/project management, development, and test teams in a variety of areas spanning services, network, operations, and automation solutions. Lily has worked on the SS7 network, designed overlay networks for the switched network, defined operational automation for supporting AT&Ts network infrastructure and the global network. She also drove solutions for Business VoIP services and Cloud-based services.  She was a member of the original task force that defined AT&Ts SDN strategy and since then has worked to design SDN services and define capabilities needed to realize operational efficiencies through SDN concepts.  Currently, she leads the Analytics and Automation for Core and Transport organization within the Network CTO organization.   She has the lead for program management of Network Resiliency projects in the Network Analytics and Automation Organization working in close collaboration with Network Operations and Engineering. 

Lily has a Masters’ Degree in Electrical Engineering from Lehigh University.  Lily enjoys time with her family, especially traveling.  She is very involved in music as a member of a chorus and quartet.  In addition, she enjoys mentoring in both her private and professional world.   She volunteers her time in the community as well as with Women of AT&T, OASIS, and other employee resource groups in AT&T. 

Talk Title: Building a Climate-Change Resilient Network

Abstract: Telecommunications networks are without question foundational infrastructure for today’s society. Given such criticality, it is imperative that we address impending threats to our infrastructure – including climate change. Through scientific advancements in climate modeling and spatial intelligence, the threat of a changing climate to our networks can be identified and addressed.

In this presentation, we will discuss how AT&T is facing climate change head on by collaborating with climate experts at the US Department of Energy’s Argonne National Laboratory to integrate forward-looking climate projection data with advanced network planning analytics. Specifically, we will focus on AT&T activities to identify and then remediate climate related risks with existing key infrastructure, and the integration of climate models into the daily planning activities for new site deployments.

Chengqiang Huang, Principal Engineer, Huawei, China

Dr. Chengqiang Huang is a principal engineer in Huawei Technologies Co., Ltd. His primary research interests lie in reliability modeling and analysis of complex systems, especially complex network systems that require ultra-reliability, e.g., 5G core network. For the past years working in Huawei, Chengqiang had also participated in reliability analysis of public cloud systems, distributed data storage systems, AI cluster systems, etc. He holds a Ph.D. degree in network management from the University of Exeter and is now responsible for network reliability in the Reliability Technology Lab in Huawei.

Talk Title: Design for Dependability and its Challenges

Abstract: Considering the stringent reliability demands on commercial systems, it is imperative that considerations regarding reliability risk factors are incorporated into the design from its inception, necessitating adjustments to the design as needed. Also, throughout the testing and validation phase, the system’s vulnerabilities should be thoroughly exposed, and the design refined accordingly. During the operational phase, risks must be vigilantly monitored, ensuring swift restoration of services should any issues arise.

We have observed that across all these phases, the identification of reliability risk elements and the implementation of mitigation measures hinge upon meticulous system modeling. This is particularly crucial in understanding the origins and triggers of system failures, grasping how failures propagate, and assessing the effectiveness of remedial actions. Viewing the system through the lens of reliability and applying quantitative analysis is vital. Models serve as pivotal tools here, especially when augmented by experimental data from prototype or similar systems, enhancing engineers’ understanding of underlying risks and thereby facilitating improvements in reliability.

In this presentation, we will share our company’s recent experiences in reliability modeling, encompassing methodologies, tools, and prototype demonstrations. We will also delve into the challenges and obstacles we’ve encountered in our reliability modeling endeavors, discussing current situations and outlining our reflections. Furthermore, with the advent of the era of LLM, we explore whether and how they can further contribute to advancing the field of system and reliability modeling.

Peter Thermos, President & CTO, Palindrome Technologies, USA

Peter has over 25 plus years of experience in Cyber Security providing consulting to leading commercial organizations and conducting security research for US government organizations (i.e., DARPA, DHS, NIST). As founder of Palindrome Technologies, he is working as a subject matter expert with customers in several industry sectors, including Government, Telecommunication, Financial and Healthcare, in securing Enterprise Networks, Carrier-grade Networks and helping organizations secure emerging technologies including 5G, MEC, IoT, and V2X. Peter is the primary author of the book “Securing VoIP Networks” by Addison-Wesley and has been a speaker at various conferences (i.e., IEEE, ICIW, VoN, SANS, Blackhat, MIS InfoSec, ISSE) and has published research papers in academic and industry journals (i.e., IEEE, ACM, ISSA, IEC) and articles in trade magazines such as Information Security, ZDNET, Forbes, TechTarget and Wired. Furthermore, he has been the Co-Chair for IEEE CQR Workshop, IEEE World Forum IoT and committee member of ICCWS. Furthermore, Peter is a contributor to the FCC CSRIC VII Report on Risk to 5G from Legacy Vulnerabilities and Best Practices for Mitigation (June 10, 2020). Peter holds a Master’s degree in Computer Science from Columbia University, NY, is a senior member of IEEE and ISSA and a member of IETF and ACM.

Talk Title: Security and Reliability in Heterogeneous Networks

Abstract: The coexistence of disparate wireless network technologies such as 5G, 4G Long Term Evolution (LTE), CBRS, and Wi-Fi (which use different architectures and interworking configurations) introduce several challenges for users in selecting the right access and end-to-end networking technologies to meet their use case requirements. This presentation will discuss the security and reliability challenges in Heterogeneous networks along with possible solutions to provide device-agnostic, unified network access for HetNets and intelligent policy-based device orchestration.

Matti Latva-aho, Director for 6G Flagship, University of Oulu, Finland

Matti Latva-aho (IEEE Fellow) is one of the world’s top researchers in wireless communications. Wireless data communications systems and networks are already central to the effective functioning of society, and their significance is continuing to increase. The capacity of wireless communications networks is ultimately constrained by limited spectrum availability. Under current plans, new spectrum allocations for mobile data communications will only be made at much higher frequency bands than those used at present. This will bring major changes to how future wireless radio systems should be planned and optimized. Latva-aho’s research will help to improve understanding of how the design criteria for future wireless systems will change and what kind of transmission technologies and transmitter/receiver architectures they should use. Matti Latva-aho was Academy Professor in 2017 – 2021 and Director for National 6G Flagship in 2018 – 2026 with a total budget of 251 M€. Matti Latva-aho has worked on wireless communications research at the University of Oulu since the early 1990s. He was appointed professor of communications engineering in 2000. In 1998 – 2006, he served as the director of the Centre for Wireless Communications (CWC).

Talk Title: 6G Metaverse and Resilience – Friends or Foes?

Abstract: The development of 5G and 6G has been strongly driven by ever-faster network technologies. We often discuss the 6G-enabled metaverse, where real-world data collected is combined with virtual models to create super-realistic end-user applications. These offer new opportunities in the future, but the focus of the discussion should be strongly shifted towards real societal needs. One viewpoint on this is resilience, i.e., how society’s critical ICT-dependent infrastructures withstand intentional and unintentional attacks and remain functional, for example, during extensive power outages. Resilience is also related to the ability to serve all citizens with basic digital service needs, regardless of their location. This requires completely new types of solutions, in which, for instance, the network neutrality requirement set by the EU may have to be challenged so that basic service needs for critical services, such as health services or distance education, can be delivered in a cost-efficient way. Different authorities’ needs should also be considered by allowing customization of the baseline 6G system to consider tighter requirements for security, different frequency allocations, or the operation of the network.

Kathy Meier-Hellstern, Principal Engineer and Director, Google Research, USA

Meier-Hellstern is a Principal Engineer and Director in Google Research, serving as the Responsible AI Tech Lead for Google’s large language and multimodal models. Her research mission is to create scalable tools, data and processes for evaluating and improving Responsible AI in ML Models and Products. Kathy was previously a Principal Site Reliability Engineer at Google, focused on improving the end-to-end client experience in YouTube and Ads. Before joining Google, Kathy was Assistant Vice President of Optimization, Reliability & Customer Analytics (ORCA) in AT&T Labs, responsible for delivering enhanced analytic tools and software for AT&T’s Next Generation networks. Kathy is an AT&T Fellow, and holds a Ph.D. and Master’s degree in Operations Research from University of Delaware. 

Talk Title: Scaling Responsible AI for Generative Models

Abstract: As generative AI models become more popular, new applications are emerging and we find that not all users and use cases have the same responsible AI considerations. In this talk we discuss possible approaches to scaling Responsible AI to applications with different needs.

David Artuñedo Guillén, Head of Future Networks Lab, Telefónica, Spain

David Artuñedo Guillén is the Head of Future Networks Lab inside Chief Digital Office in Telefónica exploring how apply new network technologies to Products and Solutions to deliver best user experience to TEF customers. Future Networks Lab team has developed the first Open-Source version of Common API Framework specified by 3GPP Technical Specifications 23.222, 29.222 and 33.122.

Prior to joining Future Networks Lab, he worked in Telefónica at several business units, including CTO for TU Go Communications Product (launched in O2 UK, Movistar Argentina, Perú, Colombia and Mexico, and VIVO Brazil), Technology Liaison Manager at Jajah in Israel, and Senior Manager on Communication Services at Telefónica Research and Development.

David Artuñedo received Computer Science Engineer of the Year in Castilla y León (Spain) from Computer Science Engineering Professional Association in 2010 and has been associate professor in Computer Science Engineering at Universidad de Valladolid.

Talk Title: AI-empowered Cloud Continuum for Mobile Networks

Abstract: Mobile Networks and Cloud Computing are going hand by hand in concepts like Edge Computing. To provide the biggest Customer experience to customers, there are many aspects to consider like business relationships between Telcos and cloud providers, the connectivity model defined by 3GPP, Edge Computing API frameworks, Application Service providers. AI can play a significant role in orchestrating all these aspects to enable an optimized user experience.

Pavel Kordík, Associate Professor, Czech Technical University in Prague, Czech Republic

Extensive experience in areas related to AI-based solutions. Pavel has been working for 10 years as Vice-Dean and he was responsible for setting up the system of collaboration with industry. Pavel coordinates small research teams and supervises several doctoral students in various machine learning fields such as recommender systems, predictive modeling, meta-learning, optimization. He can secure both public and private research funding. He has over 8 years of experience with entrepreneurship and is the co-founder of two startups (i) Recombee, which bootstrapped to hundreds of customers worldwide and over $350K in MRR, and (ii) UNICO.AI, which is changing the way how universities cooperate with industry (experts.ai platform). Also, he co-founded and supported local non-profit organizations prg.ai and aidetem.cz, helping to structure visions, teams, and got recent $500K support from google.org for the informatika.gg project. Pavel has international experience from international projects, workshops delivered for international audiences (tech transfer in North Macedonia, Poland, Georgia), as well as public lectures on recent progress in AI and other activities.

Talk Title: Latest AI Developments Explained (OpenAI SORA, World Models, Q*)

Abstract: This presentation will describe how SORA works, how it is connected to world models, and will refer to the Q* algorithm. Also, it will address how to make AI systems affordable for end users. Finally, it will give a path towards personal LLM assistants, autonomous driving, etc.

Luis Miguel Santo, Head of Radio, NOS Comunicações S.A., Portugal

Luis is the Head of Radio at NOS SGPS, the largest communication and entertainment group in Portugal, with over 20 years of experience in the telecommunications and IT industry. He has a Master of Business Administration from AESE/IESE Business School and a Master in Electrical and Computer Engineering from Instituto Superior Técnico, specializing in Telecommunications Engineering. He also owns several post-graduations in management, big data, and analytics.

Luis core competencies includes defining and implementing mobile technology evolution and architecture, from 2G to 5G, Wi-Fi, IoT, and small cells, as well as supporting and developing new mobile-based products and services, supported by a team of more than 25 people. Most recent projects include 5G spectrum auction, 5G vendor negotiations, network sharing agreements with Vodafone, 5G rollout and optimization. 

Prior to NOS Luis worked at Vodafone, Jazztel, and Optimus in the radio engineering and project management space. Luis works closely with regulation and business units, as well as external stakeholders in analytics and I&D. 

Luis’ mission is to deliver the best mobile network performance and customer experience in the market, while driving innovation and growth for NOS SGPS. NOS has been awarded by OOKLA, OpenSignal, Deco, and other institutions with “Best Coverage”, “Fastest Network” and more recently as “Fastest Operator in Europe” by OOKLA.

Talk Title: Green Networks – Maximizing Performance while Minimizing Energy Consumption with AI/ML in 4G/5G Mobile Networks

Abstract: Radio networks, namely 4G & 5G are responsible for approximately 80% of total energy consumption in a mobile network. The launch of 5G services lead to very high consumption, especially in massive MIMO antenna rollouts typically recurring to 32T type antennas, more than doubling the energy consumption of an average 4G site. This predictive analytics project explored the maximization of power savings by using vendor radio resource
management features dynamically configured by a predictive analytics algorithm in close loop, guaranteeing minimum service levels (e.g. downlink throughput) depending on the period of the day. The project was developed under a PT2020 I&D national framework and funding.

The algorithm acted in the middle frequency 4G spectrum layers (1800/2100/2600 MHz) and at 5G 3500 MHz cells, defining an optimized configuration, per hour. A per sector algorithm was developed guaranteeing a minimum average service for 5G NSA and 4G devices. The data product interacts automatically with the RAN vendors OSS system predicting the next day hourly optimal setting to maximize power saving while keeping downlink throughput above 50 Mbps per user during the day and 10 Mbps per user during the night as examples. The algorithm allowed to capture additional daylight savings of around 4% to 7% on the daily consumption.

Jun Xu, Associate Professor, University of Delaware, USA

Dr. Jun Xu is an Associate Professor in the Department of Mechanical Engineering at the University of Delaware. Before he joined the University of Delaware, he was the founding Director of NC Battery Complexity, Autonomous Vehicle and Electrification Research Center, and an Associate Professor at UNC Charlotte. Dr. Xu’s research mainly focuses on multiphysics modeling and characterization of batteries and impact dynamics. He now serves as an executive committee member of the Advanced Energy System Division, ASME. He is an Associate Editor of ASME Journal of Electrochemical Energy Conversion and Storage, Scientific Reports and Batteries. He has published over 140 peer-reviewed journal papers with citations of 7,000+, H-index 48. Dr. Xu earned his Ph.D. degree from Columbia University in 2014. https://sites.google.com/view/vesl2014

Title: Understanding Battery Safety and Durability Issues from a Physics-Informed Data-Driven Modeling

Abstract: Lithium-ion batteries are one of the critical momentums of our current mobile society. With the further development and application of increasingly high energy density batteries and large capacity battery packs in electric vehicles, cellphones, laptops, and large-scale energy storage systems, the consequences of battery safety issues now become significant threats. Battery degradation, internal short circuits (ISCs) and thermal runaways (TRs) are typical battery safety and durability issues where mechanics, electrochemistry, and thermal are strongly coupled. Interdisciplinary endeavors are in pressing need to address these safety issues. In this talk, a machine-learning combined with physics-based modeling will be introduced to achieve faster computation of the multiphysics system/phenomenon with higher accuracy. Results provide new insights into multiphysics behaviors in battery safety and durability issues and offer engineering-ready modeling methodologies for the next-generation battery design, evaluation, and monitoring.

Kostas G. Vlahodimitropoulos, COO, Local AI, Greece

Kostas is the COO of Local AI, a tech startup that he founded together with a team of AI experts. Local AI is focused on AI solutions for sustainability projects around Europe. Through AI, it empowers Green Transition initiatives of private and public organizations and has received funding by EU Horizon projects framework.

Kostas has extensive experience in network planning and optimization, having worked for 27 years at Cosmote. He was Deputy Director of Service Quality & Customer Experience Management for Fixed & Mobile. He was involved with several R&D projects including  radio resource management, location-based optimization, efficient algorithms for radio propagation, and fleet management. His research interests were in the design and implementation of network-wide big data like for the on-line analytics of network performance vs. customer experience, and interactive presentation techniques using powerful visualization tools.

He received the Computer Engineering Diploma from the Technical University of Patra, Greece, the Master of Science degree in Computer Science from Rutgers University, New Jersey, USA, and Ph.D. in Mobile Telecommunications from the National Technical University of Athens, Greece.

Talk Title: AI for Sustainability – Promoting Green Energy Through AI

Abstract: The continuation of the substitution of fossil fuel generated electricity to renewable sources generated electricity is now at a critical point. Since these sources have a varying and uncontrollable pattern, they cannot be aligned to that of the consumption. Besides the expensive storage, the new trend is to influence the consumption side with flexible use of electricity pushing its pattern to match the green production one. There is also a European Framework promoting Smart Energy Appliances, appliances that communicate with the Grid regarding the usage patterns.

This introduces the need of modeling and forecasting the end-user’s consumption and the operation of intelligent agents on the consumption side making hundreds of decisions throughout the day that affect the usage of energy coming from the Grid. AI is the key enabler of these operations, and in our work, which is funded by the EU Horizon 2020 program, we use Reinforcement Learning, LSTM, RCNN, etc. for precision forecasting usage in EV Charging Stations, Households, Radio Base Stations, etc.

We developed an AI-based intelligent agent to make on-the-fly decisions for energy consumption for prosumer households. We train the agent to minimize the energy cost of a household by controlling the battery given the energy market prices, the energy production by the PV, and the user preferences. We do that using state-of-the-art Reinforcement Learning algorithms such as Deep Inventory Management, Deep Q Networks, and others. The agent learns by making actions in an environment, receiving rewards/penalties for those actions, and modifying its action pattern (policy) accordingly. We use the Gym framework, which is offered by OpenAI, to create a simulation environment for our agent and for that we will need to model the states, the possible actions, and their outcomes.

The result is a win-win case, with Financial Savings for the household and positive impact on Electricity Production Carbon Emissions.

Tianyin Xu, Assistant Professor, University of Illinois at Urbana-Champaign (UIUC), USA

Tianyin Xu is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC). His research focuses on building reliable computer systems that empower next-generation cloud and datacenter computing. He has been in the UIUC List of Teachers Ranked as Excellent seven times since he joined the CS department in 2018. He is the recipient of a Jay Lepreau Best Paper Award at OSDI 2016, a Best Paper Award at ASPLOS 2020, a Best Student Paper Award at SIGCOMM 2021, two SIGSOFT Distinguished Paper Awards at ISSTA 2021 and FSE 2021, a Gilles Muller Best Artifact Award at EuroSys 2023, and a CACM Research Highlight. He is a recipient of the NSF CAREER Award, an Intel Rising Star Faculty Award, a Facebook Distributed Systems Research award, and a Dean’s Award for Excellence in Research at UIUC. He was also selected as a Facebook Academic of the Month. He is an editor of the SIGOPS Blog and is an area chair of the Journal of Systems Research. More details can be found at his webpage: https://tianyin.github.io.

Talk Title: Kubernetes Reliability and an Avenue to Reliable Cloud Infrastructures

Abstract: Today, nearly all large-scale computing, no matter whether for supporting people’s daily life or for enabling science and discovery, relies on massive, highly distributed, and rapidly evolving cloud infrastructure systems. Given prevalent hardware faults, software bugs, and human mistakes, together with inherent system complexity at scale (e.g., concurrency and asynchrony), cloud reliability has been a grand challenge of the past decade. In this talk, I will present our research on improving cloud infrastructure reliability via software testing and formal verification. Taking Kubernetes as an open infrastructure, I will present novel push-button testing techniques for comprehensively checking safety and liveness of existing Kubernetes controllers, as well as practical formal verification techniques for building new controllers with guaranteed safety and liveness. Our vision is to gradually build a truly reliable cloud infrastructure.

António Grilo, Researcher, INESC INOV-Lab, Portugal

Prof. António Grilo holds the Ph.D. degree in Electrical and Computer Engineering from IST, where he is currently Associate Professor. Since 1996, he has been working in European Commission (EC) projects related with communication networks. He is currently a Researcher with the Intelligent Communication Networks group of INESC INOV-Lab, in Lisbon. He is the author or the co-author of more than eighty scientific articles on subjects related with communication networks. His current research interests include UAV networks, Internet of Things, edge computing optimization, and applications of Artificial Intelligence in communication systems and networks.

Talk Title: AI for Communication Networks, Communication Networks for AI

Abstract: The last decade has witnessed a huge development of Artificial Intelligence (AI) techniques, supporting classification, regression, clustering, Natural Language Processing (NLP), computer vision, system optimization, anomaly detection, generative applications, etc. AI is thus becoming pervasive and applied in all areas of human activity. Communication Networks (CNs) are no exception to this trend, as AI techniques are increasingly used to optimize network designs, operation and maintenance. However, in 5GB, CNs are also being designed and implement to incorporate computing and storage capabilities, besides the traditional communication role. The latter are paramount to support future services and applications with stringent requirements, some of them relying of advanced processing and AI (e.g., assisted driving and autonomous cars, Cyber-Physical Systems (CPS), the Internet of Things (IoT), etc.), leading to a binomial CNs for AI, and AI for CNs. This talk will delve into this question, presenting the main trends regarding the relationship between CNs and AI. These will them be illustrated with recent and current activities at the Intelligent Communication Networks group of INESC INOV-Lab, focusing some problems of interest for telecom operators, relevant results, lessons learned, and future perspectives.

Lynette Webb, Co-founder, RoadToAmherst Consulting (former European Lead for AI Policy at Google), UK

Lynette is co-founder of RoadToAmherst, a consultancy providing independent advice to help businesses understand how to responsibly harness the power of AI for competitive advantage. Previously Lynette worked at Google for 16 years, including 6 years focused on AI policy issues and a stint as a product manager in the responsible AI team. Earlier, Lynette spent 6 years working within Aegis Media, advising agency teams on emerging digital media and communications trends. Prior roles included business development for News Corp’s European arm and 4 years consulting for McKinsey. She has an MBA from New York University and a B.Sc. (Hons) majoring in Mathematics from the University of Melbourne. More information on her website is: https://www.roadtoamherst.com/

Talk Title: Update on AI Regulation

Abstract: The past 6 months have been a watershed for AI regulation, with finalized legislation in Europe and the US, and intensified collaboration between governments globally on AI safety. This talk will provide an overview of recent progress in the US, Europe, and UK, with a deeper dive look at the now-final AI Act in the EU and The White House’s Executive Order on Safe, Secure, and Trustworthy AI.

Technical Program Chair: Spilios Makris, Ph.D., Director, Palindrome Technologies, USA

Spilios Makris is currently the Director of Network Resilience and Business Continuity Management (BCM) in Palindrome Technologies. Spilios has extensive experience in BCM and network resilience serving as Director and Senior Consultant at Telcordia Technologies (formerly Bellcore) for over 28 years, conducting studies and developing methodologies along with industry Best Practices for over 50 Tier 1&2 telecom companies, telecom vendors, and Telecom Regulatory Authorities (TRAs) worldwide. Spilios has served as Chair, Vice-Chair, Lead Contributor of the Standards T1A1.2 WG on “Network Survivability Performance” (was renamed PRQC Reliability Task Force) for 20 years. He successfully managed the development and regular update of Telcordia Generic Reliability Requirements documents establishing them as the “de facto” industry standards (e.g., SR-332 on Reliability Prediction Procedure for Electronic Equipment). Spilios has served as the Chair of the IEEE Study Group for Security, Reliability, and Performance for Software Defined and Virtualized Ecosystems (e.g., SDN, NFV, etc.). 

Spilios received his PhD in Industrial Engineering & Operations Research from the University of Massachusetts at Amherst, Mass., MS in Engineering Management from Northeastern University, Boston, Mass., and Diploma (equiv. to MS) in Electrical & Mechanical Engineering from the National Technical University of Athens, Greece. He is a Certified Business Continuity Professional (CBCP) by the Disaster Recovery Institute International (DRII) and a Senior Member of IEEE.

General Chair: Chi-Ming Chen, Ph.D., AT&T Labs (Retired), USA

Chi-Ming Chen joined AT&T in 1995. He was with the AT&T Labs architecture organization which designs the Enhanced Control Orchestration Management Platform (ECOMP) and Open Network Automation Platform (ONAP). Prior to joining AT&T, Chi-Ming was with the Quality Assurance Center of Bell Communications Research (Bellcore) from 1985 to 1995 and was a faculty member at Tsing Hua University, Hsinchu, Taiwan from 1975 to 1979.
He received his Ph.D. in Computer and Information Science from the University of Pennsylvania in 1985; M.S. in Computer Science from the Pennsylvania State University in 1981; M.S. and B.S. in Physics from Tsing Hua University, Taiwan, in 1973 and 1971 respectively.

Chi-Ming Chen is a Life Senior Member of IEEE and Senior Member of the ACM. He is an Advisory Board Member of IEEE Communications Society (ComSoc) Technical Committee on Communications Quality & Reliability (CQR). He was a member of the IEEE GLOBECOM & ICC Management & Strategy (GIMS) Standing Committee and served as the GLOBECOM and ICC Site Selection Chair from 2012 to 2017. He has chaired the Industry Forums of several GLOBECOMs and ICCs and has served as the Executive Chair of ICC 2019, Shanghai, China. Currently, he is serving as the Keynote Chair of ICC 2024, Denver, Colorado, USA and Operations Co-Chair of GLOBECOM 2024, Cape Town, South Africa and Executive Chair of GLOBECOM 2026, Macau, China.

From 2015 to 2017, Chi-Ming was a Steering Committee member of the IEEE SDN Initiative and IEEE Big Data Initiative. Currently, he is co-chairing the 5G Roadmap Working Group of IEEE 5G Initiative. He has been a key Organizing Committee member of CyberC conference since it’s started in 2009. In addition, he also organizes the annual IEEE Emerging Technology Reliability Roundtable (ETR-RT) since 2014.

Operations Program Chair: Luis M. Correia, Professor, University of Lisbon, Portugal

Luis M. Correia was born in Portugal, in 1958. He received the Ph.D. in Electrical and Computer Engineering from IST (Univ. Lisbon) in 1991, where he is currently a Professor in Telecommunications, with his work focused on Wireless & Mobile Communications, with the research activities developed in the INESC-ID institute. He has acted as a consultant for the Portuguese telecommunications operators and regulator, besides other public and private entities, and has been in the Board of Directors of a telecommunications company. He has participated in 33 projects within European frameworks, having coordinated 6 and taken leadership responsibilities at various levels in many others, besides national ones. He has lectured 76 advanced training courses for industry and academia at the national and international levels. He has supervised over 230 M.Sc./Ph.D. students, having edited 6 books, contribute to European strategic documents, and authored over 550 papers in international and national journals and conferences, for which served also as a reviewer, editor and board member. Internationally, he was part of 40 Ph.D. juries, and 80 research projects and institutions evaluation committees for funding agencies in 12 countries, and the European Commission and COST. He has been the Chairman of Conference, of the Technical Program Committee and of the Steering Committee of 25 major conferences, besides other several duties. He was a National Delegate to the COST Domain Committee on ICT. He has launched and served as Chairman of the IEEE Communications Society Portugal Chapter, besides being involved in several other duties in this society at the global level. He is an Honorary Professor of the Gdańsk University of Technology (Poland) and a recipient of the 2021 EurAAP Propagation Award “for leadership in the field of propagation for wireless and mobile communications”.

Resource Links:

ETR-RT 2024 presentations and summary of findings
ETR-RT 2023 presentations and summary of findings
Due to COVID-19, this event was canceled for the period 2020-2022
ETR-RT 2019 presentations and summary of findings
ETR-RT 2018 presentations and summary of findings
ETR-RT 2017 presentations and summary of findings 
ETR-RT 2016 presentations 
ETR-RT 2015 presentations 
ETR-RT 2014 presentations 
IEEE SDN Initiative 
ETSI NFV 
ETSI NFV Portal TB (Technical Body)