Distributed and Parallel Systems

Authors: Clemens SAUERWEIN1 (Innsbruck), Ruth BREU (Innsbruck), Stefan OPPL (Krems), Iris GROHER (Linz), Tobias ANTENSTEINER (Innsbruck), Stefan PODLIPNIG (Wien) & Radu PRODAN (Klagenfurt)

Abstact: High-quality programming education at universities is a significant challenge due to rapidly increasing student numbers, tight teaching budgets and a shortage of instructors. The “CodeAbility Austria” project aims to meet this challenge by establishing suitable programming learning platforms. In this paper, we introduce the project in more detail, present the results of our empirical research on the experiences and challenges of using programming learning platforms, and provide an outlook for future work.

Link: Zeitschrift für Hochschulentwicklung

 

 

As part of our collaboration with the Department of Computer Architecture and Technology at the University of Granada, Spain two research papers were accepted for publishing at the 17th International Work-Conference on Artificial Neural Networks.

Paper title:  An Efficient Parallel Multi-population Wrapper for Solving Feature Selection Problems in High-dimensional Space

Authors: Juan Carlos Gómez López, Daniel Castillo Secilla, Dragi Kimoviski and Jesús González Peñalver

Abstract: One of the most widely accepted approaches to address feature selection problems are wrappers based on evolutionary algorithms. Over the years, these approaches have evolved from single-population models to multi-population models to achieve better-quality solutions. Moreover, they are highly parallelizable as each subpopulation evolves independently. This paper proposes two parallel strategies for a multi-population wrapper to take advantage of a multicore CPU. The first one, based on the Fork/Join model, focuses on parallelizing only the evaluation method since it is the main bottleneck of the procedure. Although this strategy speeds up the execution of the wrapper, it is far from optimal. In this context, the second strategy implements an Island-based model, where each subpopulation evolves independently in each CPU core, exchanging information via asynchronous migrations. The results show that the wrapper achieves a speedup of almost 35 with the Island-based model when individuals are distributed into 24 subpopulations.

 

Paper title: Energy-aware KNN for EEG Classification: A Case Study in Heterogeneous Platforms

Authors: Juan José Escobar Pérez, Francisco Rodríguez, Rukiye Savran Kızıltepe, Beatriz Prieto, Dragi Kimovski, Andrés Ortiz, Alberto Prieto and Miguel Damas

Abstract: The growing energy consumption caused by IT is forcing application developers to consider energy efficiency as one of the fundamental design parameters. This parameter acquires great relevance in HPC systems when running artificial neural networks and Machine Learning applications. Thus, this article shows an example of how to estimate and consider energy consumption in a real case of EEG classification. An efficient and distributed implementation of the KNN algorithm that uses mRMR as a feature selection technique to reduce the dimensionality of the dataset is proposed. The performance of three different workload distributions is analyzed to identify which one is more suitable according to the experimental conditions. The proposed approach outperforms the classification results obtained by previous works. It achieves an accuracy rate of 88.8% and a speedup of 74.53 when running on a multi-node heterogeneous cluster, consuming only 13.38% of the energy of the sequential version.

Zahra Najafabadi Samani, has been awarded travel grant to attend IPDPS 2023 in St. Petersburg, Florida, USA. Congratulations!

Radu Prodan participated in the panel:

“Computing in the Cloud Continuum: Technological challenges, killer applications and future trends”

jointly organized by the Fast Continuum and HotCloudPerf workshops at the 2023 ACM/SPEC International Conference on Performance Engineering (ICPE ’23).

6th Workshop on Hot Topics in Cloud Computing Performance (HotCloudPerf 2023)

Radu ProdanFour Hot Topics in Cloud Computing Performance in Klagenfurt 

Description: The presentation discusses four hot Cloud computing topics researched at the University of Klagenfurt:
– Social media as today’s largest and most popular front-end application worldwide;
– Fine-grained simulation of backend serverless functions workflows on commercial clouds;
– Scheduling of workflow applications on the computing continuum assuring service level agreements;
– Sustainable processing of the massive graph representation of extreme data generated on the Internet. 

On Saturday, during the #ICPE2023, the Graph-Massivizer Project organized the #GraphSys first #workshop on #Serverless, #ExtremeScale, and #Sustainable #GraphProcessing #Systems

It was great to see so many passionate #attendees eager to share and learn about the latest #advancements in #graphsystems ?️ We had some amazing speakers who shared their #insights and #expertise on the topic with a lot of engaging and thought-provoking discussions ⚡ ??Thanks to everyone who participated and made it such a memorable event!

Title: Performance Improvement Strategies of Edge-Enabled Social Impact Applications

Authors: Shajulin Benedict, S. Vivek Reddy, Bhagyalakshmi M., Jiby Mariya Jose, Radu Prodan

International Conference on Inventive Computation Technologies (ICICT 2023)

Abstract: In recent years, social relationships have been rooted in a blend with technological advancements to eradicate emerging challenges, such as loneliness, poverty, pollution, climate change, health issues, and so forth. IoT-enabled social good applications, accordingly, have emerged in various dimensions. In fact, those developing IoT-enabled social good applications have to diligently consider the efficiency of underlying computational infrastructures. This article explores the performance improvement (PI) aspects of edge intelligence techniques that apply to social good applications. It highlights the most commonly practiced PI methods in the literature. Additionally, the article lists the near-future research perspectives of edge-enabled solutions. The article
will be beneficial to several researchers/practitioners who prefer to address social causes using edge-enabled efficient intelligent techniques.

Authors: Zahra Najafabadi Samani, Narges Mehran, Dragi Kimovski, Shajulin Benedikt, Nishant Saurabh, Radu Prodan

IEEE Transactions on Parallel and Distributed Systems

Abstract: Fog computing platforms became essential for deploying low-latency applications at the network’s edge. However, placing and managing time-critical applications over a Fog infrastructure with many heterogeneous and resource-constrained devices over a dynamic network is challenging. This paper proposes an incremental multilayer resource-aware partitioning (M-RAP) method that minimizes resource wastage and maximizes service placement and deadline satisfaction in a dynamic Fog with many application requests. M-RAP represents the heterogeneous Fog resources as a multilayer graph, partitions it based on the network structure and resource types, and constantly updates it upon dynamic changes in the underlying Fog infrastructure. Finally, it identifies the device partitions for placing the application services according to their resource requirements, which must overlap in the same low-latency network partition. We evaluated M-RAP through extensive simulation and two applications executed on a real testbed. The results show that M-RAP can place 1.6 times as many services, satisfy deadlines for 43% more applications, lower their response time by up to 58%, and reduce resource wastage by up to 54% compared to three state-of-the-art methods.

On 03.02.2023 , Dragi Kimovski defended his habilitation thesis “The Computing Continuum in the Internet-of-Things Era: Beyond the Cloud Data Centers”. In the meantime, the procedure has been completed and we were happy to hand out the certificate. Congratulations!

Dragi Kimovski is a tenure track researcher at the Institute of Information Technology (ITEC), University of Klagenfurt. He earned his doctoral degree in 2013 from the Technical University in Sofia. He was an assistant professor at the University of Information Science and Technology in Ohrid and a senior researcher and lecturer at the University of Innsbruck. Kimovski conducted multiple research stays at renowned universities, including the University of Michigan, the University of Utrecht, the University of Bologna, and the University of Granada. He co-authored more than 60 articles in international conferences and journals. His research interests include parallel and distributed computing and multi-objective optimization for energy efficiency and sustainability. He acted as a scientific coordinator and work-package leader in dozen Horizon 2020 projects (DataCloud, ENTICE, and ASPIDE).

Fog and edge computing have been introduced as an extension of the cloud services towards the data sources, thus forming the computing continuum. The computing continuum enables the creation of a new type of services, spanning across distributed infrastructures, supporting various Internet of Things (IoT) applications. However, the introduction of the computing continuum raises multiple challenges for the management, deployment and orchestration of complex distributed applications, such as increased network heterogeneity, limited resource capacity of edge devices, fragmented storage management, high mobility of edge devices and limited support of native monolithic applications. Therefore, the habilitation thesis explores novel algorithms for low latency, scalable, and sustainable computing over heterogeneous resources for information processing and reasoning, thus enabling transparent integration of IoT applications. It tackles the heterogeneity challenge of dynamically changing computing infrastructure topologies and presents a novel concept for sustainable processing at scale.

Presentation of Radu Prodan on “Massive Graphs on the Computing Continuum” in the seminar on “AI meets complex knowledge structures: Neuro-Symbolic AI and Graph Technologies” at the Oslo Metropolitan University.