Open RAN is a new mobile network technology concept replacing the current Radio Access
Network architecture based on vendor-specific implementations with an approach based
on standard specifications, using disaggregated functions working on general-purpose
hardware and supporting equipment interoperability from multiple vendors. Open RAN
helps mobile operators open their networks and allow rapid innovation and deployment of
new research and ideas in service automation, network visibility, data insight, intelligent
control, AI/ML, security, etc.
Poster/Demo Submission: Same as paper submission deadlines
CALL FOR PAPERS
Open RAN is a new mobile network technology concept replacing the current Radio Access
Network architecture based on vendor-specific implementations with an approach based
on standard specifications, using disaggregated functions working on general-purpose
hardware and supporting equipment interoperability from multiple vendors. Open RAN
helps mobile operators open their networks and allow rapid innovation and deployment of
new research and ideas in service automation, network visibility, data insight, intelligent
control, AI/ML, security, etc.
Open RAN and AI are set to revolutionize the future of wireless technology in the
commercial sector. By capitalizing on the advancements within existing 5G networks,
businesses are preparing to transition to 6G and beyond. This evolution requires a swift and
innovative approach to ensure that enterprises are equipped with cutting-edge data
management, transmission, and processing capabilities, meeting the demands of ultra-low
latency and high reliability.
Open RAN has been an area of industry prioritization in many countries. Over $1B in
government funding is dedicated to Open RAN R&D in the US alone. AT&T has set the goal of
70% of its RAN traffic being on an open platform by 2026. The UK government has set the
goal of 35% of network traffic being over Open RAN by 2030. Vodafone also has a goal of
30% of its European networks being Open RAN by 2030. Many technical issues need to be
addressed before Open RAN can deliver its promises.
ACM MobiCom is a premier international forum addressing mobile wireless networks. Open
RAN is one of the most important technological trends in industry. We need to have a
dedicated forum at the MobiCom conference to energize academic involvement and foster
exchanges and collaborations.
This workshop will explore the latest research activities in Open RAN networks, leveraging
open architecture, open interface, open-source technologies, and accessible software
APIs. This workshop will also explore AI technologies in RAN to enable new capabilities for
next-generation networks. The workshop will act as a forum for researchers and developers
across academia and industry to exchange ideas and share results on the design of future
mobile wireless networks. Topics of interest include but are not limited to the following:
RAN design, architecture, and implementation
Open-source approaches, open-source components for RAN
Analytical modeling and simulations
RAN disaggregation, programmability, API design and standardization.
Standard RAN components (RU, DU, CU, RIC/xApps/rApps, etc.)
System design, cloud-native, AI-native
Testbed and experimental networks
AI, ML, LLMs for RAN
RAN design for AI applications and workloads
AI user cases for mobile wireless networks
Security and privacy for the RAN
Advances in software-defined radio
Evolutions from 5G to 6G
Non-terrestrial and unconventional RAN networks
Please email TPC co-chairs if you would like to participate or have any questions.
All paper submissions will be handled electronically at the submission website (details at the end of this page). All submitted papers will be evaluated through a double-blind reviewing process, with the identities of the authors withheld from the reviewers.
Before final submission, you are expected to make sure that your paper complies with the following requirements. Please do not violate these requirements with the aim of including additional material: submissions that violate the formatting requirements may not be reviewed.
Any papers that do not adhere to the following guidelines may be immediately rejected:
Page limit: 6 pages, including all references.
Font size no smaller than 10 points. The camera-ready papers can have font size of 9 points
Double column format with each column having dimensions 9.25 inches x 3.33 inches, a space of 0.33 inches between the two columns, and with no more than 55 lines of text per column.
Fit properly on US letter-sized paper (8.5 inches by 11 inches).
Submissions must be in PDF (Portable Document Format) authors should ensure that they are compatible with Adobe Acrobat (English version). Any other formats, including Postscript and MS-Word, will not be accepted.
Authors' names must not appear anywhere in the paper or in the PDF file. The PDF file must also not contain any embedded hyperlinks, as these may compromise reviewer anonymity.
Limit the file size to less than 15 MB: contact the PC chairs if you have a file larger than this limit.
You may find these templates useful in complying with the above requirements. For Latex users, please use\documentclass[sigconf,10pt]{acmart}. But as an author, you bear the final responsibility to verify (manually or through the above online paper checker) that your submission is format-compliant.
Poster/Demo
You can also present a poster or demo of your work. Demos and poster submissions should consist of a three-page abstract in the same format describing the demonstration plan or the outline of the poster content.
The title of these papers must bear a "Poster:"/"Demo:" prefix.
Page limit: 3 pages including references, with 10 points font
Important Dates
Paper Registration: Aug 23, 2024
Paper Submission: Aug 30, 2024
Paper Acceptance Notification: September 30, 2024
Paper Camera Ready: Oct 13, 2024
Workshop Date: Nov 18, 2024
Poster/Demo Submission: Same as paper submission deadlines
All paper submissions will be handled electronically at the S3 2023 submission website. Authors should prepare a PDF version of their papers. You may use these templates helpful in complying with the requirements.
Paper submissions should be no longer than 3 pages in font size no smaller than 10 points, including figures and references, in standard ACM conference format. Demos and poster submissions should consist of a one-page abstract in the same format describing the demonstration plan or the outline of the poster content. We encourage students with a paper, poster, or demo at ACM MobiCom main conference to present their work at this workshop as well.
Important Dates
Paper Registration: Aug 23, 2024
Paper Submission: Aug 30, 2024
Paper Acceptance Notification: September 30, 2024
Paper Camera Ready: Oct 13, 2024
Workshop Date: Nov 18, 2024
Poster/Demo Submission: Same as paper submission deadlines
CALL FOR SPONSORS
Workshop Objectives
The S3 Workshop provides a unique venue for graduate students around the world to plan, manage, and experience a vibrant workshop focused on research in all aspects of mobile wireless networks. It encompasses both theory and systems research, exposing participants to the full breadth of research in networking. As its name suggests, the workshop is organized by students, and the technical sessions are given by student presenters. It aims to foster early career development among students and expose them to the workings of an academic life. It encourages students to actively participate in the networking research community and offers unique networking opportunities.
Why sponsor the S3 workshop
Sponsoring S3 will give your organization increased visibility within the computer networking and mobile computing community, especially among talented PhD students. Supporting this student-organized workshop will benefit the community of student researchers. This focused venue will be a great opportunity for companies to attract the future researchers to them. We will acknowledge all supporters during the conference opening remarks and prominently display company names
and logos on the S3 website. You can also direct your funds to name specific awards such as Travel Grants (which will encourage huge participations), Best Papers, Best Posters, Best Presentation, Best Questions, Best Demos etc. With your sponsorship, S3 will give financial awards to the student attendees and TPC members, who otherwise may not be able to attend due to financial constraints.
Previous Workshops
S3 has been held in conjunction with ACM MobiCom, one of the most prestigious conferences in mobile networking, for the past 13 out of 14 years. Previous workshops have attracted over 60 participants, including several ACM MobiCom attendees. Traditionally, the workshop has been sponsored by ACM SIGMOBILE and industry partners.
Links to workshop homepages can be found below:
ACM S3 2022 in Sydney, Australia, with ACM MobiCom 2022. ACM S3 2021 in New Orleans, USA with ACM MobiCom 2021. ACM S3 2019 in Los Cabos, Mexico with ACM MobiCom 2019. ACM S3 2018 in New Delhi, India with ACM MobiCom 2018. ACM S3 2017 in Snowbird, Utah, USA with ACM MobiCom 2017 ACM S3 2016 in New York, USA with ACM MobiCom 2016 ACM S3 2015 in Paris, France with ACM MobiCom 2015 ACM S3 2014 in Maui, Hawaii with ACM MobiCom 2014 ACM S3 2013 in Miami, Florida with ACM MobiCom 2013 ACM S3 2012 in Istanbul, Turkey with ACM MobiCom 2012 ACM S3 2011 in Las Vegas, Nevada with ACM MobiCom 2011 ACM S3 2010 in Chicago, Illinois with ACM MobiCom/MobiHoc 2010 ACM S3 2009 in New Orleans, Louisiana with ACM MobiHoc 2009.
Qingtian Wang China Telecom Research InstituteAbstract: In this talk, we will provide an overview of the next Generation Research Group (nGRG) at the O-RAN ALLIANCE. Bio: Qingtian Wang is a Senior Research Engineer with the Wireless AI System Research Team (Wistar) at China Telecom Research Institute in Beijing, China. He received his Ph.D. from the Beijing University of Posts and Telecommunications (BUPT). He currently serves as the co-chair of the next Generation Research Group (nGRG) at O-RAN.
Tracy Van Brakle AT&TAbstract: The INDIGO (Intelligent “All G” Networks Designed and Integrated for Globalized Operations) project, part of NSF’s Convergence Accelerator Track G program, seeks to enhance the adaptability, security, and resilience of 5G/xG networks for public safety and peacekeeping missions. This effort integrates Human-Centered AI for multi-operator network orchestration, particularly in scenarios requiring rapid deployment, such as natural disasters or defense situations. INDIGO leverages open standards, including O-RAN, 3GPP, and TMF, along with interoperable platforms, to enable adaptive network management and service restoration across diverse operator networks. The INDIGO prototyping effort relies upon COSMOS, an indoor/outdoor city-scale testbed established as part of the NSF PAWR initiative that is now being augmented via the NTIA PWSCIF ACCoRD project. Bio: Tracy van Brakle is a Member of Technical Staff within AT&T Labs Wireless Technologies / Network Automation and Analytics group, and is also a co-chair and/or contributor within several open source projects and standards development organizations. Her current area of interest is integrating Open RAN technologies with open platforms, e.g., LFN 5G SBP, ETSI NFV MANO, using model-driven interface specifications from O-RAN and 3GPP. Before joining AT&T, Tracy was a Senior Technologist with Goldman Sachs. She holds 17 active US patents in Wireless Technologies.
Focus area: Meeting functional and security requirements of military missions and civilian first responder teams in near real-time through a system-of-systems/network-of-networks (JADC2) approach across (1) Planning and Composition, (2) Interoperability, and (3) Execution. This integrates a novel Artificial Intelligence Planner with an open-source Service Management & Orchestration Framework and RAN Intelligent Controllers.
Mahesh Marina The University of EdinburghAbstract: The architecture and deployment of mobile networks, including the Radio Access Network (RAN), has undergone a dramatic transformation over the past decade, driven by the adoption of “disaggregation” at multiple levels. This shift has fostered a more diverse and open telecom ecosystem. Today, we are entering a new era for the RAN, where another major opportunity awaits: the transition to data-driven, AI-powered RAN operations with even greater disaggregation and openness. However, this evolution also brings new challenges, much like the earlier phase of disaggregation. In this talk, I will focus on two key challenges — the efficient acquisition of RAN data and troubleshooting in a disaggregated RAN — and outline our GenAI-based solutions to address them. Bio: Mahesh Marina is a Professor in the School of Informatics at the University of Edinburgh, where he leads the Networked Systems Research Group, and a Visiting Professor in the Department of Computer Science at Johns Hopkins University. Previously, he was a Turing Fellow at the Alan Turing Institute (the UK’s national institute for data science and AI) for five years (2018-23) and has served as the Director of the Institute for Computing Systems Architecture within Informatics@Edinburgh for four years (2018-22). Earlier, he has held visiting roles at ETH Zurich and at Ofcom (the UK’s telecoms regulator). Prior to joining Edinburgh, he had a two-year postdoctoral stint at the UCLA Computer Science Department after earning his PhD in Computer Science from the State University of New York at Stony Brook. He is an ACM Distinguished Member and an IEEE Senior Member.
Dinesh Bharadia UC San DiegoAbstract: In the rapidly evolving landscape of robotics, AR/VR/XR, automotive perception, and machine learning applications, it has become evident that traditional approaches to network optimization focused solely on throughput and latency are insufficient. To deliver an enhanced user experience, it is crucial to consider additional network metrics such as jitter and application state awareness. Such requirements are not traditional considered during the standardization and nor are easy to optimize.
In this talk, I would first present the limitations of existing RAN intelligent controllers (RICs) in adapting to highly mobile wireless channels, which restricts their ability to meet the on-demand needs of applications. While these controllers may offer macro level network optimizations, I will next introduce EdgeRIC—a realtime RAN intelligent controller that leverages the power of AI, specifically Reinforcement Learning, to elevate the performance of ORAN (Open RAN) stacks and address the diverse requirements of various applications in realtime. Decoupled from the RAN stack, EdgeRIC functions as an intelligent controller that employs AI-powered optimization techniques to provide control decisions to the RAN across multiple-layers. Next, to train these AI models, we have developed a digital twin that ensures spatial and temporal consistency of the wireless channel. Our deployment showcases the integration of EdgeRIC with an open-source ORAN stack, highlighting the remarkable over-the-air performance improvements achieved. Notably, we present compelling results, demonstrating a substantial 75% reduction in video streaming stalls with an application aware intelligent scheduling policy. Bio: Prof. Dinesh Bharadia has been an associate professor in the ECE department at the University of California San Diego since July 2022, where he directs the WCSNG group. He received early promotion to a tenured professorship and held Assistant Professorship for four brief years from 2018 – 2022. He received his Ph.D. from Stanford University in 2016 and was a Postdoctoral Associate at MIT. Specifically, he built a prototype of a radio that invalidated a long-held assumption in wireless that radios cannot transmit and receive simultaneously on the same frequency, which inspired research on this topic from different communities (communication theory to RFIC). From 2013 to 2015, he worked to commercialize his research on full-duplex radios, building a product that underwent successful field trials at Tier 1 network providers worldwide like Deutsche Telekom and SK Telecom. This product is currently under deployment. He serves as a technical advisor for multiple startups. Dinesh was named to Forbes 30 under 30 for the science category worldwide list in recognition of his work. Dinesh was named a Marconi Young Scholar for outstanding wireless research and was awarded the Michael Dukakis Leadership Award. MIT Technology Review also named him one of the top 35 Innovators under 35 worldwide in 2016.
Hao Chen Samsung Research AmericaAbstract: AI has greatly changed almost every industry. AI for cellular radio access network (RAN) has also achieved its momentum. Following state-of-the-art research results, which revealed the potential for large performance gains by applying AI/ML techniques in RAN, the wireless industry is now broadly pushing for the adoption of AI in 5G and future 6G technology. However, despite this enthusiasm, there are a lot of challenges when deploying AI in RAN and AI-based wireless systems still remain largely untested in the field. Common simulation methods for generating datasets for AI model training suffer from “reality gap,” in that they fall short of accurately representing real-world networks. As a result, the performance of these simulation-trained models may not carry over to practical cellular systems. In this talk, we will introduce some details of the challenges and some existing efforts to solve these issues. Bio: Hao Chen is a senior staff engineer at Samsung Research America, where he is working on algorithm design and proof-of-concept development of AI for wireless communication, wireless sensing, and localization. He received his B.S. and M.S. degrees in Information Engineering from Xi'an Jiaotong University, Shaanxi, in 2010 and 2013. He received the Ph.D. degree in Electrical Engineering from University of Kansas, Lawrence, KS, in 2017.
10:50 - 11:30
Technical Session 1- Inspiration for O-RAN: Testbed and Architectures
10:50 - 11:10
ORANSlice: An Open Source 5G Network Slicing Platform for O-RAN
Hai Cheng (Northeastern University),
Salvatore D'Oro (Northeastern University),
Rajeev Gangula (Northeastern University),
Sakthivel Velumani (Northeastern University),
Davide Villa (Northeastern University),
Leonardo Bonati (Northeastern University),
Michele Polese (Northeastern University),
Tommaso Melodia (Northeastern University),
Gabriel Arrobo (Intel),
Christian Maciocco (Intel)
Technical Session 2- Applications of O-RAN: AI and App Development
11:40 - 12:00
Evaluation of the Latency of Machine Learning Random Access DDoS Detection in
Open RAN
Paulo Ricardo Branco da Silva (CPQD), João Paulo Henriques Sales de Lima (CPQD), Erika Costa Alves (CPQD), William Sanchez Farfan (CPQD), Victor Aguiar Coutinho (CPQD), Thomas William do Prado Paiva (CPQD), Daniel Lazkani Feferman (CPQD), Francisco Hugo Costa Neto (CPQD)
Yongdae Kim KAISTAbstract: Despite known vulnerabilities in cellular networks, standardization
bodies like GSMA and 3GPP have been reluctant to implement
comprehensive security fixes. While intelligence agencies continue to
develop sophisticated tools like IMSI catchers, their solutions remain
hidden from the academic community. When questioned about security
gaps, these organizations often claim 'no one exploits these
vulnerabilities' - even as they leave core vulnerabilities unpatched.
To bridge this gap between known vulnerabilities and practical
exploitation, we propose 'Cellular Metasploit', a comprehensive
toolkit for testing cellular network security. In this talk, I will
discuss its design, implementation, and how it can drive more
transparent discussions about cellular security. Bio: Yongdae Kim is a professor in the Department of Electrical Engineering at KAIST.
He received PhD degree from the computer science department at the University of Southern California under the guidance of Gene Tsudik.
He received my MS and BS degrees in Mathematics from Yonsei University in 1993 and 1991.
Between 2002 and 2012, He was an associate/assistant professor in the Department of Computer Science and Engineering at the University of Minnesota - Twin Cities.
14:20 - 14:40
Invited Talk
O-RAN Intelligence: Use cases, research challenges and experimental testbeds
Salvatore D'Oro Northeastern UniversityAbstract: In this talk, we will provide an overview of recent advances in the O-RAN domain, with specific focus on how network intelligence and data-driven approaches can address operator pain points and enable new services and use cases. We will cover topics related to intelligent resource management, security aspects of O-RAN intelligence and interfaces, orchestration and conflict mitigation. We will discuss how access to experimental platforms (e.g., the X5G private 5G network at Northeastern University) can facilitate O-RAN research, and help in generating datasets, prototype intelligent solutions and demonstrate advanced use cases. Bio: Salvatore D'Oro is a Research Associate Professor at Northeastern University. He received his Ph.D. degree from the University of Catania in 2015. Salvatore is an area editor of Elsevier Computer Communications journal and serves on the Technical Program Committee (TPC) of multiple conferences and workshops such as IEEE INFOCOM, IEEE CCNC, IEEE ICC and IFIP Networking. Dr. D'Oro's research interests include optimization, artificial intelligence, security, network slicing and their applications to 5G networks and beyond. Prof. D’Oro is the co-chair of the ACM WiNTECH workshop at ACM MOBICOM 2024. Prof. D’Oro has given tutorials on Open RAN at IEEE MILCOM 2024, Dyspan 2024, ACM MobiCom 2023 and IEEE Globecom 2022. Contributed to O-RAN specifications and the establishment of the Open6G Open Testing and Integration Center (OTIC) at Northeastern University.
14:40 - 15:00
Invited Talk
Project Janus: Paving the way to AI-RAN with a programmable RAN and platform
Xenofon Foukas Microsoft ResearchAbstract: Virtualization of telco networks is beginning to happen in Radio Access Networks (RAN), especially regarding Open Radio Access Networks (O-RAN). However, there are some obstacles to this trend. The current O-RAN architecture limits programmability to predefined telemetry and control that an xApp can access through existing, standardized service models which may limit the pace of innovation.
To address this limitation and unleash O-RAN's full potential, Microsoft has developed Project Janus, programmable RAN platform technology that introduces flexible, dynamically loadable service models. The proposed architecture is primarily based on the existing O-RAN architecture. The main difference is the dynamic service model, whose functionality can be implemented by the application designer and deployed at run-time without affecting RAN operations. All this flexibility does not come at the cost of reliability, safety, or security.
New applications of analytics and automation are possible with the flexibility of dynamic service models and low latency, including RAN energy efficiency and anomaly detection. New applications are able to access almost all information available at different layers of RAN and exercise control at many different levels of RAN. As a result, Open RAN has the potential to significantly accelerate the pace of RAN transformation, making it possible to achieve the full benefits of 5G sooner. Bio: Xenofon Foukas is a Principal Researcher at the Intelligent Networked Systems group of Microsoft Research. He received his PhD in Computer Science in 2018 from the University of Edinburgh and his MSc in Advanced Computing in 2013 from Imperial College London. His research interests are at the intersection of programmable edge architectures, systems for mobile connectivity, applications of machine learning to mobile networks and large scale testbeds and experimentation.
15:00 - 16:00
Demo Session
15:00 - 15:10
Synthetic Data for Data-Driven Wireless
Qiancheng Li (University of Washington), Xinghua Sun (University of Washington), Akshay Gadre (University of Washington)
For detailed MobiCom registration information, click here
For general MobiCom travel grant information, click here
AWARDS
Coming Soon!
Best Paper Award: TBD
Best Demo Award: TBD
PAST EVENTS
This is the first iteration of Open-AI RAN workshop with Mobicom 2024. If you wish to organize any future workshops, please contact the organizing committee.
