Akos Kovacs

57158572800

Publications - 9

Network Optimization Aspects of Autonomous Vehicles: Challenges and Future Directions

Publication Name: IEEE Network

Publication Date: 2023-07-01

Volume: 37

Issue: 4

Page Range: 282-288

Description:

Global megatrends, such as urbanization, population growth, and emerging network solutions are accelerating the development of the Connected and Autonomous Vehicles (CAVs) industry. There are many truths, some misconceptions, and even some excitement about CAVs in the public's opinion. The main objective of the current article is to provide a comprehensive review, eliminate misconceptions, and outline the future of the network optimization aspects of autonomous vehicles by presenting various multidisciplinary methods, such as cooperative perception. Given our extensive experience with CAVs, we are aiming to share some of the insights and knowledge we have gained, along with relevant use-cases and experiment results.

Open Access: Yes

DOI: 10.1109/MNET.007.2300023

Evaluation of layer 3 multipath solutions using container technologies

Publication Name: 2019 42nd International Conference on Telecommunications and Signal Processing Tsp 2019

Publication Date: 2019-07-01

Volume: Unknown

Issue: Unknown

Page Range: 207-211

Description:

The MPT network layer multipath communication library is capable of using multiple communication channels by creating an UDP tunnel over them. The contemporary version of MPT uses the GRE tunnel protocol. MPTCP is another multipath solution, which uses TCP subflows on kernel level to ensure multipath communication. In this paper, we are using multiple container technologies to install these multipath communication solutions. Most common Docker container and a HPC specific Singularity container interconnected with twelve 100Mbit/s links were used to evaluate the aggregation capabilities of the combination of these technologies.

Open Access: Yes

DOI: 10.1109/TSP.2019.8768820

Evaluation of the aggregation capability of the mpt network layer multipath communication library and multipath TCP

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2019-01-01

Volume: 16

Issue: 6

Page Range: 129-147

Description:

Multipath communication techniques can bring in a new era for Cognitive Infocommunication, due to ensuring resilient and high-speed data transfer. In this paper, we evaluated the MPT network layer multipath communication library, which creates an UDP tunnel, based on the GRE in UDP tunnel protocol. We compared the aggregation capability of MPT to that of MPTCP, which stands for Multi-Path TCP and based on TCP sub-flows to aggregate the transmission capacities of different physical interfaces and their potentially disjoint paths to ensure high network throughput. In this article, we used 100 Mbps and 1 Gbps speed channels to compare the aggregation capabilities of these two different multipath communication solutions. We used several scenarios for the evaluation. We tested both IPv4 and IPv6 both as underlying and as encapsulation protocols. We used several channels up to 12 to evaluate the aggregation capabilities with the industry standard iperf tool, even with different numbers of iperf threads. Meanwhile we measured the CPU usage of the two examined multipath technologies to get further insight into their operation. On the basis of our measurement results, we also set up a mathematical model of their channel aggregation capabilities.

Open Access: Yes

DOI: 10.12700/APH.16.6.2019.6.9

Comparison of different linux containers

Publication Name: 2017 40th International Conference on Telecommunications and Signal Processing Tsp 2017

Publication Date: 2017-10-19

Volume: 2017-January

Issue: Unknown

Page Range: 47-51

Description:

The new generation of virtualization is containerization. In this paper we measured the most common container techniques to determinate the performance of these techniques regarding computing power and network performance with industry standard measurement applications. We used these measurement results to compare them with native performance without any container techniques and with the Linux standard virtualization KVM performance. For the first time, this paper also measures the performance of the Singularity container system, which is a new approach of HPC systems container usage.

Open Access: Yes

DOI: 10.1109/TSP.2017.8075934

Comparing the aggregation capability of the MPT communications library and multipath TCP

Publication Name: 7th IEEE International Conference on Cognitive Infocommunications Coginfocom 2016 Proceedings

Publication Date: 2017-01-03

Volume: Unknown

Issue: Unknown

Page Range: 157-161

Description:

The MPT network layer multipath communication library-which was proposed to be a possible new basis for the future cognitive info-communication-is capable to use multiple communication channels to create an UDP tunnel which uses GRE tunnel protocol. On the other hand, Multipath TCP uses a special kernel module which creates multiple TCP sub-flows to aggregate network throughput. In this paper we used twelve 100Mbps speed channels to compare the aggregation capabilities of these two multipath communication techniques. Different scenarios were used: we measured both IPv4 and IPv6 as underlying and encapsulation protocols. In all cases, we used one to twelve channels to measure the aggregation capabilities with the iperf network measurement tool and also with HTTP download.

Open Access: Yes

DOI: 10.1109/CogInfoCom.2016.7804542

Modelling of virtualized servers

Publication Name: 2015 38th International Conference on Telecommunications and Signal Processing Tsp 2015

Publication Date: 2015-10-09

Volume: Unknown

Issue: Unknown

Page Range: 421-425

Description:

The virtualized systems are one of the key elements of the next generation IT infrastructures. Modeling it will prevent mistakes, and oversized management. Opennebula is one of the most current open source cloud management solutions. Together with Haizea, they are a powerful tool to model and manage a virtualized infrastructure trough the API of Openebula. Haizea has multiple scheduler algorithms that are more effective than that of Opennebula. We performed several experiments to compare simulation and measurement capabilities of Haizea and we highlighted some difference between them which can be reduced if required.

Open Access: Yes

DOI: 10.1109/TSP.2015.7296296

Modelling of virtualized servers

Publication Name: 2015 38th International Conference on Telecommunications and Signal Processing Tsp 2015

Publication Date: 2015-10-09

Volume: Unknown

Issue: Unknown

Page Range: 241-245

Description:

The virtualized systems are one of the key elements of the next generation IT infrastructures. Modeling it will prevent mistakes, and oversized management. Opennebula is one of the most current open source cloud management solutions. Together with Haizea, they are a powerful tool to model and manage a virtualized infrastructure trough the API of Openebula. Haizea has multiple scheduler algorithms that are more effective than that of Opennebula. We performed several experiments to compare simulation and measurement capabilities of Haizea and we highlighted some difference between them which can be reduced if required.

Open Access: Yes

DOI: 10.1109/TSP.2015.7296260

Using dispersion models at microscale to assess long-term air pollution in urban hot spots: A FAIRMODE joint intercomparison exercise for a case study in Antwerp

Publication Name: Science of the Total Environment

Publication Date: 2024-05-15

Volume: 925

Issue: Unknown

Page Range: Unknown

Description:

In the framework of the Forum for Air Quality Modelling in Europe (FAIRMODE), a modelling intercomparison exercise for computing NO2 long-term average concentrations in urban districts with a very high spatial resolution was carried out. This exercise was undertaken for a district of Antwerp (Belgium). Air quality data includes data recorded in air quality monitoring stations and 73 passive samplers deployed during one-month period in 2016. The modelling domain was 800 × 800 m2. Nine modelling teams participated in this exercise providing results from fifteen different modelling applications based on different kinds of model approaches (CFD – Computational Fluid Dynamics-, Lagrangian, Gaussian, and Artificial Intelligence). Some approaches consisted of models running the complete one-month period on an hourly basis, but most others used a scenario approach, which relies on simulations of scenarios representative of wind conditions combined with post-processing to retrieve a one-month average of NO2 concentrations. The objective of this study is to evaluate what type of modelling system is better suited to get a good estimate of long-term averages in complex urban districts. This is very important for air quality assessment under the European ambient air quality directives. The time evolution of NO2 hourly concentrations during a day of relative high pollution was rather well estimated by all models. Relative to high resolution spatial distribution of one-month NO2 averaged concentrations, Gaussian models were not able to give detailed information, unless they include building data and street-canyon parameterizations. The models that account for complex urban geometries (i.e. CFD, Lagrangian, and AI models) appear to provide better estimates of the spatial distribution of one-month NO2 averages concentrations in the urban canopy. Approaches based on steady CFD-RANS (Reynolds Averaged Navier Stokes) model simulations of meteorological scenarios seem to provide good results with similar quality to those obtained with an unsteady one-month period CFD-RANS simulations.

Open Access: Yes

DOI: 10.1016/j.scitotenv.2024.171761

Complex-Geometry 3D Computational Fluid Dynamics with Automatic Load Balancing

Publication Name: Fluids

Publication Date: 2023-05-01

Volume: 8

Issue: 5

Page Range: Unknown

Description:

We present an open-source code, Xyst, intended for the simulation of complex-geometry 3D compressible flows. The software implementation facilitates the effective use of the largest distributed-memory machines, combining data-, and task-parallelism on top of the Charm++ runtime system. Charm++’s execution model is asynchronous by default, allowing arbitrary overlap of computation and communication. Built-in automatic load balancing enables redistribution of arbitrarily heterogeneous computational load based on real-time CPU load measurement at negligible cost. The runtime system also features automatic checkpointing, fault tolerance, resilience against hardware failure, and supports power- and energy-aware computation. We verify and validate the numerical method and demonstrate the benefits of automatic load balancing for irregular workloads.

Open Access: Yes

DOI: 10.3390/fluids8050147