2nd International Workshop on
Testing Distributed Internet of Things Systems
September 27, 2022, in Pacific Grove, California
Co-located with the
10th IEEE International Conference on Cloud Engineering (IC2E 2022)
The 2nd International Workshop on Testing Distributed Internet of Things Systems (TDIS) will again bring together researchers and practitioners who focus on simulations, models, hybrid testbeds, test frameworks, fault injection, monitoring tools, as well as IoT experiments and applications, providing a forum for ongoing work presentations and discussions.
Thank you!
The workshop has been held on September 27th with around 25
participants. We have been impressed by the inspiring invited
talks, the interesting paper presentations, and the lively
discussions.
We thank the authors and the program committee for the
contributions of papers and reviews. Another cordial Thank
you! to all participants.
Call for Papers
The Internet of Things (IoT), cloud computing, and machine learning
will allow for more adaptive cities, houses, and infrastructures. Yet,
this vision of intelligent cyber-physical systems will not be
implemented with centralized cloud resources alone. Such resources are
simply too far away from sensor-equipped IoT devices, leading to high
latencies, bandwidth bottlenecks, and unnecessary energy consumption.
Additionally there are often privacy and safety requirements mandating
distributed architectures. Therefore, new distributed computing
paradigms and system architectures are currently emerging for the IoT
that promise to provide computing and storage in proximity of edge
devices.
However, the resulting heterogeneous, distributed, and dynamic
environments pose significant challenges to the performance,
dependability, and efficiency of distributed systems. It is also far
less clear how to best create test environments and integrate
domain-specific simulations to be able to efficiently assess the
behavior IoT systems will exhibit in the field. Yet, continuous testing
in realistic test environments is essential for many IoT systems. For
instance, IoT systems might be deployed to continuously optimize the
operation of critical urban infrastructures, including public transport
systems, energy grids, water networks, and medical infrastructures. New
versions of such IoT systems must be tested thoroughly before they can
be deployed and relied on. Furthermore, the behavior of such IoT systems
has to be tested under the expected computing environment conditions,
including variations of such conditions, given the inherently unsteady
nature of IoT environments.
The TDIS workshop aims to provide a forum for current work by
researchers and practitioners in the different research areas and
application domains connected to testing IoT systems. We welcome
submissions that describe initial ideas and visions just as much as
reports on novel approaches, practical tools, and completed projects.
Topics of Interest
Topics of interest include but are not limited to:
- physical and hybrid IoT testbeds
- simulation and emulation of IoT environments
- co-simulation within IoT domains
- model-based and model-supported approaches
- simulation-based integration testing
- testing and benchmarking on heterogeneous IoT devices
- testing and benchmarking of network technologies and protocols
- testing and benchmarking of real-time behavior
- testing and benchmarking of fault tolerance mechanisms
(fault injection, chaos engineering, etc.)
- dependability modeling and assessments
(high availability, consistency, etc.)
- testing and modeling of resource usage and energy consumption
- resource management and scheduling in testbeds
- scalability and efficiency of test runs and testbeds
- testing frameworks for edge and fog computing
- testbed automation and orchestration
- distributed monitoring, tracing, and error detection
- usability of testbeds and testing frameworks
- representativeness, reproducibility, and repeatability of test results
Important Dates
- workshop paper submission:
June 21 July 19, 2022 (final)
- notification of acceptance: August 6, 2022
- camera-ready submission: August 13, 2022 (firm)
- workshop day: September 27, 2022
Workshop Program
The workshop will be held on September 27, starting from 09:00 PDT,
Pacific Grove, California, co-located with IC2E 2022.
The program is planned as follows:
09:00 – 10:00
Morning Coffee
10:00 – 10:15
Workshop Opening
10:15 – 11:00
Keynote #1
-
AI workloads at Meta and their Implication on System Design.
Dr. Ehsan K. Ardestani, Meta
Abstract: AI services are widespread across many services at Meta.
Organic demand for these workloads continues to grow, in addition
to scaling of the workload complexity in terms of compute, data,
memory, and communication requirements. This separates the design
of AI platforms from traditional compute platform, in that the
scaling of the complexity outpaces the rate at which the underlying
compute, memory, and networking technology improves generation over
generation, requiring end to end codesign and optimization of the
HW and SW. This talk overviews some of the most relevant AI
workloads at Meta, their compute requirements, and how it impacts
the design of the underlying system.
Speaker: Ehsan K. Ardestani is a Technical Lead Manager at Meta
working on codesign of AI platforms. Ehsan has been working in the
industry on architecture of several generations of General purpose
and Application specific Processors, with more recent focus on
computing Systems, for about a decade.
11:00 – 12:00
Paper Session #1
- Network Emulation in Large-Scale Virtual Edge Testbeds:
A Note of Caution and the Way Forward.
Sören Becker (Technische Universität Berlin),
Tobias Pfandzelter, Nils Japke, David Bermbach
(Technische Universität Berlin & Einstein Center Digital Future),
and Odej Kao (Technische Universität Berlin)
- IoTreeplay: Synchronous Distributed Traffic Replay in IoT
Environments.
Markus Toll, Ilja Behnke, and Odej Kao
(Technische Universität Berlin)
- Towards Energy Consumption and Carbon Footprint Testing for
AI-driven IoT Services. Demetris Trihinas (University of
Nicosia), Lauritz Thamsen (University of Glasgow), Jossekin
Beilharz (Hasso Plattner Institute, University of Potsdam), and
Moysis Symeonides (University of Cyprus)
12:00 – 13:00
Lunch
13:00 – 13:45
Keynote #2 (remote)
-
Experiences with cloud-based distributed training and edge support
for mobile AR. Dr. Tian Guo, Worcester Polytechnic Institute
Abstract: Deep learning (DL) has been utilized in many
user-facing applications, such as augmented reality (AR). Training
DL models often require access to multiple GPUs, which can be
expensive to set up on-premises. In this talk, I will describe our
recent work in speeding up cloud-based DL training by utilizing
cheap transient servers and devising policies to manage training
sessions effectively. Despite the advancement in VM-based
distributed training, it can still be daunting for DL practitioners
to select the proper amount of resources and configure the training
cluster. To alleviate the management complexity, I will talk about
a recent work for fast and cost-effective serverless-based DL
training. Lastly, I will end with a use case where we leverage an
edge-based DL model to support mobile AR and challenges in
conducting controlled experiments.
Speaker: Dr. Tian Guo is an Assistant Professor of Computer
Science at Worcester Polytechnic Institute (WPI). She earned her
Ph.D. degree from the University of Massachusetts Amherst. Her
research interests include designing systems mechanisms and
policies to handle trade-offs in cost, performance, and efficiency
for emerging applications. Specifically, she has worked on projects
at the intersection of systems and machine learning, secure machine
learning, cloud/edge resource management, big data frameworks, deep
learning inference, distributed training, neural architecture
search, and AR/VR. Her recent work focuses on improving system
support for deep learning and on the practical applications of deep
learning in AR/VR. She is the recipient of the National Science
Foundation CRII award, the MMSys 2020 best paper award, and the
2022 award for Outstanding Achievement by a Young Alum from The
Manning College of Information and Computer Sciences, UMass
Amherst.
13:45 – 14:25
Paper Session #2
- An End-to-End Framework for Benchmarking Edge-Cloud Cluster
Management Techniques. Philipp Raith, Thomas Rausch, Paul Prüller,
Alireza Furutanpey, and Schahram Dustdar (Vienna University of
Technology)
- Integration of C-V2X Into a Hybrid Testbed to Co-Simulate ITS
Applications and Scenarios.
Paul Geppert and Jossekin Beilharz (Hasso Plattner Institute, University of Potsdam)
14:25 – 14:30
Closing Remarks
14:30 – 15:00
Afternoon Coffee
Workshop Organizers
Workshop Chairs
- Lauritz Thamsen,
University of Glasgow, United Kingdom
- Jossekin Beilharz,
Hasso Plattner Institute, University of Potsdam, Germany
- Demetris Trihinas,
University of Nicosia, Cyprus
- Andreas Polze,
Hasso Plattner Institute, University of Potsdam, Germany
Publicity Chairs
Program Committee
- Fotis Nikolaidis, ICS-FORTH, Greece
- Shashikant Ilager, Technische Universität Wien, Austria
- Miguel Matos, Universidade de Lisboa, Portugal
- Steffen Zeuch, German Research Center for Artificial Intelligence (DFKI), Germany
- Vasileios Karakostas, University of Athens, Greece
- Lito Michala, University of Glasgow, United Kingdom
- Ang Li, Duke University, USA
- Peter Tröger, Beuth University of Applied Sciences Berlin, Germany
- Thomas Rausch, Vienna University of Technology, Austria
- Moysis Symeonides, University of Cyprus, Cyprus
- Eyhab Al-Masri, University of Washington Tacoma, USA
- Eleni Tzirita Zacharatou, IT University of Copenhagen, Denmark
- Dragi Kimovski, Alpen-Adria Universität Klagenfurt, Austria
Previous Workshop Editions
- Our 1st workshop edition, TDIS 2021, was held online with IEEE IC2E 2021, a program of eight talks, and up to 33 participants.