MECC 2017
The 2nd Workshop on Middleware for Edge Clouds & Cloudlets
Colocated with ACM/IFIP/USENIX Middleware 2017, 11th-15th December 2017, Las Vegas, Nevada, USA

Call For Papers

The Middleware for Edge Clouds & Cloudlets (MECC) workshop aims to address the increasing need for closer integration between the different tiers on modern cloud computing platforms.

There is a growing trend of interactive and resource-intensive (e.g., compute, storage, need for big data) applications on mobile devices today, and currently many such applications are provided using resources on infrastructural clouds. However, it is challenging to provide such applications using cloud resources when there is limited connectivity. Harvesting the resources present on nearby mobile devices and/or cloudlets is a viable solution to this problem.

Today, there is also increasing demand for middleware that offers higher level abstractions without hampering expressiveness and performance. However, many distributed systems today are designed for the datacenter, and their assumptions, such as that nodes use fast wired interconnects, no longer hold in edge environments. In particular, edge clouds, such as those made up of only mobile devices at the edge, use unreliable wireless links. These unreliable links directly translate into unavailability and churn. Simultaneously, since mobile devices have limited energy resources, heavyweight distributed algorithms, such as coordination using a leader-based consensus protocol, are impractical.

As an effort to offload computation from mobile devices, cloudlets were originally envisioned as server-class hardware deployed in a neighborhood, office building or more generally, in close physical proximity to any scenario with a high density of users, such as at large public events. It is now transitioning to a more lightweight approach where the offloading is done through multiple techniques besides the use of virtual machines, as originally proposed, and where cloudlets can also offer connectivity support to crowd-sourced mobile devices, i.e., edge clouds.

With this new trend in sight, there is a need to define the services that should be offered at each tier. For example, cloudlets can provide well-defined APIs to support multiple computation offloading methods. Furthermore, new modular and reconfigurable architectures have to be proposed in order to support a variety of deployment scenarios, such as edge clouds without cloudlet support, and scenarios with very limited access to infrastructural clouds.

Topics

Topics of interest include but are not limited to:

  • Design and performance of middleware platforms for edge clouds and cloudlets
  • Mechanisms for the integration of edge clouds with cloudlets
  • Security mechanisms  for edge clouds including, including but not limited to, storage and computation
  • Context-aware services by cloudlets
  • Connectivity-as-a-service provided by cloudlets
  • Novel theoretical approaches for churn tolerance
  • Lightweight replication and fault-tolerance algorithms
  • Distributed coordination and cooperation for edge clouds
  • Lightweight computation sandboxing for edge clouds
  • Novel storage systems for edge clouds, with special focus on geo-aware storage engines
  • Tools for testing and benchmarking MECC
  • Experimental deployments
  • Novel applications for MECC
  • Networking coding approaches for MECC
  • P2P overlays and systems for edge clouds
  • Gossip based protocols for edge clouds
  • Computational frameworks for MECC
  • Programming models and abstractions to manage edge to infrastructure cloud interactions
  • Middleware platforms for cloud-of-clouds
  • Privacy enforcing algorithms for leveraging MECC
  • Trust for edge clouds and/or cloudlets
  • Interoperability between mobile OSes
  • Sensor fusion for MECC
  • Infrastructure cloud based services for supporting MECC


Publication of Accepted Papers

All accepted papers will appear in a Middleware 2017 companion proceedings, which will be available in the ACM Digital Library prior to the workshop.

At least one of the authors will have to register for the workshop and present the paper.

Authors should also acknowledge the following disclaimer by the ACM: The official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of your conference. The official publication date affects the deadline for any patent filings related to published work. (For those rare conferences whose proceedings are published in the ACM Digital Library after the conference is over, the official publication date remains the first day of the conference.)


Important Dates (Extended)

  • September 15, 2017 September 8, 2017 - Paper submission
  • October 5, 2017 September 28, 2017 - Notification of Acceptance
  • October 20, 2017 - Final version
Note that all deadlines are 23:59 in the GMT/UTC-12 timezone.


Submission Guidelines

MECC 2017 will receive proposals for communication in the form of full research papers of at most 6 pages, and short research papers of at most 3 pages, including references. Short papers should either describe work-in-progress, or should describe visions of challenges, problems, and potential research directions in MECC. Content should be work that is not previously published or concurrently submitted elsewhere.

All submissions should be in PDF and must follow the ACM template. Submissions must have authors information, text, figures, references and appendices (if applicable). Submissions that do not respect the formatting requirement may be rejected without review.

Reviewing is single-blind. This means that the names and affiliations of the authors must appear in the submitted papers. Each paper will receive at least three reviews from members of the program committee.

Submissions should be done through EasyChair at the following URL: https://easychair.org/conferences/?conf=mecc2017

Organization

General and Technical Program Co-Chairs

The program co-chairs can be contacted through the workshop Easychair email.

Technical Program Committee Publicity Chairs

Program of the IoT Federated Workshops: MECC & M4IoT

MECC 2017 will be part of the IoT Federated Workshops, which also include the Workshop on Middleware and Applications for the Internet of Things (M4IoT). This is the overall program:

Monday, December 11th 2017

  • 8:30 - Introduction M4IoT and keynote by Dr. Douglas C. Schmidt (Vanderbilt University)
    Topic: The Blockchain: What It is and Why It Matters for Us
    Abstract: Since the inception of Bitcoin technology, its underlying data structure--the blockchain--has garnered much attention due its key properties, such as decentralization, transparency, and immutability. These properties make blockchains suitable for decentralized apps (DApps) that require trustless exchange, consistent and incorruptible transaction records, as well as enables operational use cases beyond cryptocurrencies. For example, blockchain has the potential to address interoperability challenges in a number of domains--including IoT domains--such as delivering patient data securely to healthcare organizations and devices, improving the overall efficiency of energy transactions in electrical power distribution systems, and enabling effective interactions between commuters and transit apps in smart cities. Despite the interest in using blockchain technology for interoperability, however, little information is available on the concrete architectural styles and recommendations for designing middleware in support of blockchain-based DApps for IoT systems. This talk discusses key concepts in blockchains and important design, privacy, and security considerations when considering using their use in practice.
  • 10:00 - Coffee Break
  • 10:30 - Session: Middleware and Applications for the Internet of Things
    • PlaTIBART: a Platform for Transactive IoT Blockchain Applications with Repeatable Testing (Michael A. Walker, Abhishek Dubey, Aron Laszka, Douglas C. Schmidt (Vanderbilt University))
    • A dynamic decision fusion middleware for trustworthy context-aware IoT applications (Tim Van hamme, Davy Preuveneers, Wouter Joosen (imec - DistriNet - KU Leuven))
    • IoTVar to transparently handle interactions between applications and IoT platforms (Courtais, Taconet, Conan, Chabridon (Télécom SudParis); Gomes, Cavalcante, Batista (Federal University of Rio Grande do Norte))
    • ThingsJS: Towards a Flexible and Self-Adaptable Middleware for Dynamic and Heterogeneous IoT Environments (Julien Gascon-Samson, Mohammad Rafiuzzaman, Karthik Pattabiraman (University of British Columbia))
  • 12:00 - Lunch break
  • 13:30 - Introduction MECC and Keynote by Prof. Paulo Ferreira (INESC-ID, IST)
    Abstract:The need to process large amounts of data, Big Data, is a reality, and ranges from scientific experiments to social networks. Big Data means processing and storing massive amounts of data in a efficient way, possibly on the cloud or on cloudlets. With easy and fast development cycles, managed object-oriented programming languages (such as Java) are now preferred languages to implement most Big Data platforms. With the increasing importance of Big Data, we identify two main requirements that are common to most platforms running on any tier of modern cloud computing platforms: i) the ability to tolerate faults and to adapt to the number of nodes to satisfy new workload requirements, and ii) the ability to scale with the amount of local resources. In this talk, we address two solutions to deal with the above requirements: i) JLM, live migration of running Java applications, and ii) NG2C, an N-generational Garbage Collection (GC) algorithm. Both solutions improve Big Data platforms performance by decreasing the number of objects to copy between physical nodes (for migration) and heap generations (for GC). With JLM and NG2C, both latency and throughput is improved for Big Data applications when a migration or a GC takes place, thus increasing applications performance.
  • 15:00 - Coffee break
  • 15:30 - Session: Middleware for Edge Clouds & Cloudlets
    • Towards a Middleware for Mobile Edge-Cloud Applications (João Rodrigues, Eduardo R. B. Marques, Luís M. B. Lopes, Fernando Silva (University of Porto))
    • Towards a Persistent Publish/Subscribe System for Networks of Mobile Devices (Filipe Cerqueira, João A. Silva, João M. Lourenço, Hervé Paulino (Universidade NOVA de Lisboa))
    • Towards Decentralised Resilient Community Cloud Infrastructures (Arjuna Sathiaseelan, Mennan Selimi, Carlos Molina, Adisorn Lertsinsrubtavee (University of Cambridge), Leandro Navarro, Felix Freitag (Universitat Politécnica de Catalunya), Fernando Ramos (University of Lisbon), Roger Baig (Guifi.net Foundation))
    • A Bandwidth Allocation Scheme Based on Residual Bandwidth Information in Mobile Edge Computing (Yusuke Ito, Hiroyuki Koga (University of Kitakyushu), Katsuyoshi Iida (Hokkaido University))
  • 17:00 - Wrap up

About

The Middleware for Edge Clouds & Cloudlets (MECC) workshop aims to address the ever-increasing need for a closer integration between the different tiers on modern cloud computing platforms. Several opportunities can arise from a better integration/leverage of these different tiers.

The increasing concerns about privacy and data security might be an enabler for MECC, as computation can be done locally, the need for central rendezvous (normally provided by an infrastructure cloud) can be avoided or at least minimized. We also envision new applications that make use of this local computation and data locality, such as VR.

Research on edge clouds and cloudlets has been progressively generating more interest in the systems research community. As an indicator of this interest, since 2014 there have been 1750 papers on cloudlets and 296 on edge clouds.