, , , ,

The paper “MAPO: A Multi-Objective Model for IoT Application Placement in a Fog Environment” has been accepted

The paper “MAPO: A Multi-Objective Model for IoT Application Placement in a Fog Environment” has been accepted for publication at the 9th International Conference on the Internet of Things, IoT 2019 to be held at Bilbao, Spain (October 22-25, 2019).

Authors: Narges Mehran, Dragi Kimovski, Radu Prodan (Alpen-Adria Universität Klagenfurt).

Abstract: The emergence of the Fog computing paradigm that leverages in-network virtualized resources raises important challenges in terms of resource and IoT application management in a heterogeneous environment offering only limited computing resources. In this work, we propose a novel Pareto-based approach for application placement close to the data sources called Multi-objective IoT Application Placement in fOg (MAPO). MAPO models applications based on a finite state machine and uses three convicting optimization objectives, namely completion time, energy consumption, and economic cost, considering both the computation and communication aspects. In contrast to existing solutions that optimize a single objective value, MAPO enables multi-objective energy and cost-aware application placement. To evaluate the quality of the MAPO placements, we created both simulated and real-world testbeds tailored for a set of medical IoT application case studies. Compared to the state-of-the-art approaches, MAPO reduces the economic cost by up to 27%, while decreasing the energy requirements by 23-68%, and optimizes the completion time by up to 7.3 times.

Keywords: Fog computing, IoT application placement, multi-objective optimization, energy consumption
Acknowledgement: Austrian Research Promotion Agency (FFG), project 848448, Tiroler Cloud, funded this work.

, , , ,

Papers accepted at Europar Workshop 2019, Göttingen, August 26-27, 2019

The papers titled, ‘ARTICONF: Towards a Smart Social Media Ecosystem in a Blockchain Federated Environment’ , and ‘A Semantic Model with Self-Adaptive and Autonomous Relevant Technology for Social Media Applications’ are accepted at Seventh Workshop on Large Scale Distributed Virtual Environments, LSDVE 2019 collocated at Europar 2019. The papers descriptions are as follows:

1. ARTICONF: Towards a Smart Social Media Ecosystem in a Blockchain Federated Environment

Authors: Radu Prodan, Nishant Saurabh, Zhiming Zhao and Kate Orton-Johnson

2. A Semantic Model with Self-Adaptive and Autonomous Relevant Technology for Social Media Applications

Authors: Zahra Najafabadi Samani, Alexander Lercher, Nishant Saurabh, Radu Prodan

,

Philipp Moll and Sabrina Kletz presented their Demo on “Alternative inputs for games and AR/VR applications” @ MMSys 2019 in Amherst

Paper Title: Alternative inputs for games and AR/VR applications: deep headbanging on the web

Abstract: In multimedia research, scientific progress is often slowed downby high demands on hard- and software. However, hardware con-tinuously improves and today’s hardware got powerful enoughto meet the performance demands of complex 3D and deep learn-ing applications. With this demo, we demonstrate that utilizingdeep learning and 3D modeling is not a major barrier anymorewhen building prototypes for showcasing research projects. Ourweb-based game, called “HeadbangZ”, showcases a novel gesture-based input methodology realized through deeply learned poseestimation and user interaction in a 3D environment. Since gesture-based inputs increase the immersion in virtual environments, weassume this input methodology to be especially useful for AR/VRapplications and games. Furthermore, we demonstrate that rapidprototyping of applications using novel technologies, such as deeplearning, is even possible within 48 hours by developing a workingdemo within this time frame. Finally, we provide insights into whatwe learned during the development of HeadbangZ to encourageother researchers to make use of novel technologies. In referenceto Stephen Harper’s quote “Having hit a wall, the next logical stepis not to bang our heads against it.”, we hope that the presentationof HeadbangZ encourages researchers to bang their heads rhythmi-cally to rock music instead of angrily against a virtual wall createdby hard- and software limitations.

Authors: Philipp Moll, Andreas Leibetseder, Sabrina Kletz, Mathias Lux, Bernd Münzer (Institute of Information Technology, Alpen-Adria-Universität Klagenfurt)

More information on the paper can be found on: https://dl.acm.org/citation.cfm?id=3323832

, , , ,

A glimpse into ARTICONF meeting @Stavanger, Norway.

Prof. Radu Prodan coordinated EU H2020 Project ARTICONF team met at Stavanger and held technical cum plenary discussions between June 4th to June 7th 2019 with a goal to present some exciting development towards next generation social media.

Articonf meeting at Stavanger 2019

Articonf meeting at Stavanger 2019

Prof. Radu Prodan
, , ,

Prof. Radu Prodan is the Program Chair for ISPDC 2019

Prof. Radu Prodan is the Program Chair for ISPDC 2019, the 18th IEEE International Symposium on Parallel and Distributed Computing, to be held at Amsterdam (Netherlands).

, , ,

ITEC representation @IPDPS 2019, 33rd IEEE International Parallel and Distributed Processing Symposium

The prestigious 33rd IEEE International Parallel & Distributed Processing Symposium, IPDPS 2019 held at Rio de Janerio, Brazil (May 20-24 2019) found representation from ITEC department at UNI-KLU in a number of activities including paper and poster presentations, panel discussions etc. led by Prof. Radu Prodan, Josef Hammer, and Nishant Saurabh.

1. Panel discussion @PAISE 2019, the collocated workshop @IPDPS.

Prof. Radu Prodan led the panel discussion on emerging Blockchain, Parallel AI and Edge computing technology and paradigms at PAISE (Parallel AI and Systems for the Edge), collocated workshop at the prestigious 33rd IEEE International Parallel & Distributed Processing Symposium, IPDPS 2019 along with some renowned researchers including Pete Beckman (Argonne National Laboratory and the University of Chicago), Sandip Kundu (National Science Foundation), Tal Ben-Nun (ETH Zürich), and Ilkay Altintas (Chief Data Science Officer at the San Diego Supercomputer Center), moderated by Rajesh Sankaran (Argonne National Laboratory and the University of Chicago). Prof. Prodan highlighted disruptive scenarios, typically posed with the arrival of next generation technologies and introduced EU H2020 project ARTICONF coordinated by UNI-KLU to the audience in the light of the panel topics.

2. Workshop paper presentation @PAISE 2019, the collocated workshop @IPDPS to be published in IPDPSW proceedings.

Josef Hammer presented the workshop paper “Transparent Access to 5G Edge Computing Services” accepted for publication at 33rd IEEE International Parallel & Distributed Processing Symposium workshop, PAISE 2019.

Authors: Josef Hammer, Philipp Moll and Hermann Hellwagner

3. Conference paper presentation @IPDPS 2019 Cloud Computing session to be published in IPDPS proceedings.

Nishant Saurabh presented the conference paper “Semantics-aware Virtual Machine Image Management in IaaS Clouds” accepted for publication at 33rd IEEE International Parallel & Distributed Processing Symposium , IPDPS 2019.

Authors: Nishant Saurabh (Alpen-Adria Universität Klagenfurt), Julian Remmers (University of Innsbruck), Dragi Kimovski (Alpen-Adria Universität Klagenfurt), Radu Prodan (Alpen-Adria Universität Klagenfurt), Jorge G. Barbosa (LIACC, Faculdade de Engenharia da Universidade do Porto).

4. Poster presentation @IPDPS 2019 PhD Forum.

The ITEC representative members Josef Hammer and Nishant Saurabh presented respective posters amongst distinguished researchers. While, Josef’s poster titled “Transparent Access to 5G Edge Computing Services”, Nishant presented the poster on “Towards a semantic-centric VMI repository management”.

5. Session Chair @IPDPS 2019, Scheduling and Load balancing session.

Prof. Radu Prodan chaired the Scheduling and Load balancing session, which observed some interesting research works from all around the globe.

ipdps-2019

,

Matthias Janetscheck completed his PhD at the University of Innsbruck with a thesis on a “Worfkflow Compiler for Manycores” under the supervision of Prof. Radu Prodan

Pictures from the Rigorosum with Prof. Thomas Fahringer and Prof. Justus Piater.

Matthias Janetscheck Defense Pic 1

Prof. Radu Prodan
, , , ,

Univ.-Prof. DI Dr. Radu Prodan has been invited to be a part of panel discussion on emerging Blockchain and Edge computing technology and paradigms at PAISE (Parallel AI and Systems for the Edge)

Univ.-Prof. DI Dr. Radu Prodan has been invited to be a part of panel discussion on emerging Blockchain and Edge computing technology and paradigms at PAISE (Parallel AI and Systems for the Edge), collocated workshop at the prestigious 33rd IEEE International Parallel & Distributed Processing Symposium, IPDPS 2019 to be held at Rio de Janerio, Brazil (May 20-24 2019).

Nishant Saurabh
, ,

The paper “Semantics-aware Virtual Machine Image Management in IaaS Clouds” has been accepted

The paper “Semantics-aware Virtual Machine Image Management in IaaS Clouds” has been accepted for publication at 33rd IEEE International Parallel & Distributed Processing Symposium , IPDPS 2019 to be held at Rio de Janerio, Brazil (May 20-24 2019).

Authors: Nishant Saurabh (Alpen-Adria Universität Klagenfurt), Julian Remmers (University of Innsbruck), Dragi Kimovski (Alpen-Adria Universität Klagenfurt), Radu Prodan (Alpen-Adria Universität Klagenfurt), Jorge G. Barbosa (LIACC, Faculdade de Engenharia da Universidade do Porto).

Abstract: Infrastructure-as-a-service (IaaS) Clouds concurrently accommodate diverse sets of user requests, requiring an efficient strategy for storing and retrieving virtual machine images (VMIs) at a large scale. The VMI storage management require dealing with multiple VMIs, typically in the magnitude of gigabytes, which entails VMI sprawl issues hindering the elastic resource management and provisioning. Nevertheless, existing techniques to facilitate VMI management overlook VMI semantics (i.e at the level of base image and software packages) with either restricted possibility to identify and extract reusable functionalities or with higher VMI publish and retrieval overheads. In this paper, we design, implement and evaluate Expelliarmus, a novel VMI management system that helps to minimize storage, publish and retrieval overheads. To achieve this goal, Expelliarmus incorporates three complementary features. First, it makes use of VMIs modelled as semantic graphs to expedite the similarity computation between multiple VMIs. Second, Expelliarmus provides a semantic aware VMI decomposition and base image selection to extract and store non-redundant base image and software packages. Third, Expelliarmus can also assemble VMIs based on the required software packages upon user request. We evaluate Expelliarmus through a representative set of synthetic Cloud VMIs on the real test-bed. Experimental results show that our semantic-centric approach is able to optimize repository size by 2.2-16 times compared to state-of-the-art systems (e.g. IBM’s Mirage and Hemera) with significant VMI publish and retrieval performance improvement.

Keyword: Virtual machine image management, semantic similarity, storage optimization
Acknowledgement: The The Austrian Research Promotion Agency (FFG, grant agreement 848448, Tiroler Cloud) and the European Union (Horizon 2020 research and innovation program, grant agreement 644179, ARTICONF) funded this work.