Change search
Link to record
Permanent link

Direct link
Publications (10 of 38) Show all publications
John, W., Balador, A., Taghia, J., Johnsson, A., Sjöberg, J., Marsh, I., . . . Dowling, J. (2023). ANIARA Project - Automation of Network Edge Infrastructure and Applications with Artificial Intelligence. ACM SIGAda Ada Letters, 42(2), 92-95
Open this publication in new window or tab >>ANIARA Project - Automation of Network Edge Infrastructure and Applications with Artificial Intelligence
Show others...
2023 (English)In: ACM SIGAda Ada Letters, Vol. 42, no 2, p. 92-95Article in journal (Refereed) Published
Abstract [en]

Emerging use-cases like smart manufacturing and smart cities pose challenges in terms of latency, which cannot be satisfied by traditional centralized infrastructure. Edge networks, which bring computational capacity closer to the users/clients, are a promising solution for supporting these critical low latency services. Different from traditional centralized networks, the edge is distributed by nature and is usually equipped with limited compute capacity. This creates a complex network to handle, subject to failures of different natures, that requires novel solutions to work in practice. To reduce complexity, edge application technology enablers, advanced infrastructure and application orchestration techniques need to be in place where AI and ML are key players.

National Category
Communication Systems
Identifiers
urn:nbn:se:ri:diva-66258 (URN)10.1145/3591335.3591347 (DOI)
Available from: 2023-09-11 Created: 2023-09-11 Last updated: 2023-09-11Bibliographically approved
Marsh, I., Hsu, P.-L. & Ghandeharioon, C. (2021). Data-driven traffic flow : A state-of-the-art report.
Open this publication in new window or tab >>Data-driven traffic flow : A state-of-the-art report
2021 (English)Report (Other academic)
Abstract [en]

This state-of-the-art report is the first of two reports. Both are the result of a Swedish project, the Swedish Energy Authority’s TENS project, which spanned from 2018-2021. This report lays out the background, related work, state of the art, related projects as well as mapping out the area for the newcomer to the area. Examples are from Sweden due to the available data, as well as the locally installed infrastructure. We dedicate some space to the data gathering process as well as basic traffic flow principles. It should be seen as introductory material to the topic, getting the laymen up to speed in data processing issues arising from using traffic sensors. A second (sister) report contains technical results from our work in the above named Swedish project.

Publisher
p. 35
Series
RISE Rapport ; 2021:93
Keywords
Transport ITS, data-driven, traffic flow
National Category
Infrastructure Engineering
Identifiers
urn:nbn:se:ri:diva-57512 (URN)978-91-89385-83-2 (ISBN)
Note

The second report in this serie of two: http://urn.kb.se/resolve?urn=urn:nbn:se:ri:diva-57513

Available from: 2022-01-03 Created: 2022-01-03 Last updated: 2023-05-19Bibliographically approved
Marsh, I., Abrahamsson, H. & Hsu, P.-L. (2021). Data-driven traffic flow : Summary of experiments.
Open this publication in new window or tab >>Data-driven traffic flow : Summary of experiments
2021 (English)Report (Other academic)
Abstract [en]

This final report is the second of two reports. Both are the result of a Swedish project, the Swedish Energy Authority’s TENS project, which spanned from 2018-2021. Other reports from the project provide results from estimating emissions from traffic measurements as well as simulation studies. Like any European capital, Stockholm suffers from many problems related to its road network. The main factor is traffic jams, which are aggravated with difficult weather conditions in winter but also due to accidents, popular events and holidays. Therefore, this report provides the results from a data-driven approach to estimating traffic flow. This work aims at predicting and understanding the behavior of this network based on data collected at several places. More specifically, the goal is to predict and model the traffic flow i.e macroscopic information, on ground measurements (MCS), using floating microscopic (INRIX) data. We focus on estimating the fundamental traffic law relationships, the flow using time series and future directions. Methods and results are in the related work section.

Series
RISE Rapport ; 2021:119
Keywords
Transport ITS, data-driven, traffic flow
National Category
Infrastructure Engineering
Identifiers
urn:nbn:se:ri:diva-57513 (URN)978-91-89561-10-6 (ISBN)
Note

The first report in this serie of two: http://urn.kb.se/resolve?urn=urn:nbn:se:ri:diva-57512

Available from: 2022-01-03 Created: 2022-01-03 Last updated: 2023-05-19Bibliographically approved
Marsh, I., Paladi, N., Abrahamsson, H., Gustafsson, J., Sjöberg, J., Johnsson, A., . . . Amiribesheli, M. (2021). Evolving 5G: ANIARA, an edge-cloud perspective. In: Proceedings of the 18th ACM International Conference on Computing Frontiers 2021, CF 2021: . Paper presented at 18th ACM International Conference on Computing Frontiers 2021, CF 2021, 11 May 2021 through 13 May 2021 (pp. 206-207). Association for Computing Machinery, Inc
Open this publication in new window or tab >>Evolving 5G: ANIARA, an edge-cloud perspective
Show others...
2021 (English)In: Proceedings of the 18th ACM International Conference on Computing Frontiers 2021, CF 2021, Association for Computing Machinery, Inc , 2021, p. 206-207Conference paper, Published paper (Refereed)
Abstract [en]

ANIARA (https://www.celticnext.eu/project-ai-net) attempts to enhance edge architectures for smart manufacturing and cities. AI automation, orchestrated lightweight containers, and efficient power usage are key components of this three-year project. Edge infrastructure, virtualization, and containerization in future telecom systems enable new and more demanding use cases for telecom operators and industrial verticals. Increased service flexibility adds complexity that must be addressed with novel management and orchestration systems. To address this, ANIARA will provide en-ablers and solutions for services in the domains of smart cities and manufacturing deployed and operated at the network edge(s). © 2021 Owner/Author.

Place, publisher, year, edition, pages
Association for Computing Machinery, Inc, 2021
Keywords
AI, container tech, edge comp, energy metering, orchestration, Containers, Manufacture, EDGE architectures, Edge clouds, Efficient power, Network edges, Service flexibility, Smart manufacturing, Telecom operators, Telecom systems, 5G mobile communication systems
National Category
Communication Systems
Identifiers
urn:nbn:se:ri:diva-53472 (URN)10.1145/3457388.3458622 (DOI)2-s2.0-85106011241 (Scopus ID)9781450384049 (ISBN)
Conference
18th ACM International Conference on Computing Frontiers 2021, CF 2021, 11 May 2021 through 13 May 2021
Available from: 2021-06-14 Created: 2021-06-14 Last updated: 2023-05-22Bibliographically approved
Marsh, I., Paladi, N., Abrahamsson, H., Gustafsson, J., Sjöberg, J., Johnsson, A., . . . Amiribesheli, M. (2021). Evolving 5G: ANIARA, an edge-cloud perspective. In: CF '21: Proceedings of the 18th ACM International Conference on Computing FrontiersMay 2021: . Paper presented at CF '21: 18th ACM International Conference on Computing FrontiersMay 2021 (pp. 206-207). Association for Computing Machinery
Open this publication in new window or tab >>Evolving 5G: ANIARA, an edge-cloud perspective
Show others...
2021 (English)In: CF '21: Proceedings of the 18th ACM International Conference on Computing FrontiersMay 2021, Association for Computing Machinery , 2021, p. 206-207Conference paper, Published paper (Refereed)
Abstract [en]

ANIARA (https://www.celticnext.eu/project-ai-net) attempts to enhance edge architectures for smart manufacturing and cities. AI automation, orchestrated lightweight containers, and efficient power usage are key components of this three-year project. Edge infrastructure, virtualization, and containerization in future telecom systems enable new and more demanding use cases for telecom operators and industrial verticals. Increased service flexibility adds complexity that must be addressed with novel management and orchestration systems. To address this, ANIARA will provide en-ablers and solutions for services in the domains of smart cities and manufacturing deployed and operated at the network edge(s).

Place, publisher, year, edition, pages
Association for Computing Machinery, 2021
National Category
Communication Systems
Identifiers
urn:nbn:se:ri:diva-58315 (URN)10.1145/3457388.3458622 (DOI)
Conference
CF '21: 18th ACM International Conference on Computing FrontiersMay 2021
Available from: 2022-01-24 Created: 2022-01-24 Last updated: 2023-05-22Bibliographically approved
Abrahamsson, H., Ben Abdesslem, F., Ahlgren, B., Brunstrom, A., Marsh, I. & Björkman, M. (2018). Connected Vehicles in Cellular Networks: Multi-access versus Single-access Performance. In: : . Paper presented at 2nd Workshop on Mobile Network Measurement (MNM’18). , Article ID 8506559.
Open this publication in new window or tab >>Connected Vehicles in Cellular Networks: Multi-access versus Single-access Performance
Show others...
2018 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Connected vehicles can make roads traffic safer andmore efficient, but require the mobile networks to handle timecriticalapplications. Using the MONROE mobile broadbandmeasurement testbed we conduct a multi-access measurementstudy on buses. The objective is to understand what networkperformance connected vehicles can expect in today’s mobilenetworks, in terms of transaction times and availability. The goalis also to understand to what extent access to several operatorsin parallel can improve communication performance.In our measurement experiments we repeatedly transfer warningmessages from moving buses to a stationary server. Wetriplicate the messages and always perform three transactionsin parallel over three different cellular operators. This creates adataset with which we can compare the operators in an objectiveway and with which we can study the potential for multi-access.In this paper we use the triple-access dataset to evaluate singleaccessselection strategies, where one operator is chosen for eachtransaction. We show that if we have access to three operatorsand for each transaction choose the operator with best accesstechnology and best signal quality then we can significantlyimprove availability and transaction times compared to theindividual operators. The median transaction time improves with6% compared to the best single operator and with 61% comparedto the worst single operator. The 90-percentile transaction timeimproves with 23% compared to the best single operator andwith 65% compared to the worst single operator.

National Category
Communication Systems
Identifiers
urn:nbn:se:ri:diva-34311 (URN)10.23919/TMA.2018.8506559 (DOI)2-s2.0-85057241219 (Scopus ID)
Conference
2nd Workshop on Mobile Network Measurement (MNM’18)
Available from: 2018-07-30 Created: 2018-07-30 Last updated: 2023-05-19Bibliographically approved
Abrahamsson, H., Ben Abdesslem, F., Ahlgren, B., Björkman, M., Brunstrom, A. & Marsh, I. (2018). Selecting Operator in 3G/4G Networks for Time-Critical C-ITS Applications. In: : . Paper presented at 14th Swedish National Computer Networking Workshop (SNCNW 2018).
Open this publication in new window or tab >>Selecting Operator in 3G/4G Networks for Time-Critical C-ITS Applications
Show others...
2018 (English)Conference paper, Published paper (Refereed)
National Category
Communication Systems
Identifiers
urn:nbn:se:ri:diva-34312 (URN)
Conference
14th Swedish National Computer Networking Workshop (SNCNW 2018)
Available from: 2018-07-30 Created: 2018-07-30 Last updated: 2023-05-19Bibliographically approved
Marsh, I. (2017). A lightweight measurement platform for home internet monitoring. In: 2017 IFIP Networking Conference, IFIP Networking 2017 and Workshops: . Paper presented at 2017 IFIP Networking Conference and Workshops, IFIP Networking 2017, 12 June 2017 through 16 June 2017.
Open this publication in new window or tab >>A lightweight measurement platform for home internet monitoring
2017 (English)In: 2017 IFIP Networking Conference, IFIP Networking 2017 and Workshops, 2017Conference paper, Published paper (Refereed)
Abstract [en]

CheesePi is a lightweight measurement platform with the goal of performing active measurements directly from within users' homes. As an always on device, it provides better context on the network state, than those available from browser interaction (Speedtest, etc.) In this demonstration, we will show the frontend of CheesePi and how we incorporate data from several sources around Sweden into a dashboard. A testbed of CheesePi nodes has been deployed, where we have conducted several tests. The presentation will highlight how to make unbiased and neutral measurements of the telecommunications infrastructure (Table III). Measurements are of sufficient quality to be useful by an operator, plus requirements mandated by academia [3], regulatory bodies [1] and the IETF [4]. © 2017 IFIP.

Keywords
Active measurement, Browser interaction, Internet monitoring, Measurements of, Network state, Regulatory bodies, Telecommunications infrastructures
National Category
Natural Sciences
Identifiers
urn:nbn:se:ri:diva-34466 (URN)10.23919/IFIPNetworking.2017.8264886 (DOI)2-s2.0-85050540208 (Scopus ID)9783901882944 (ISBN)
Conference
2017 IFIP Networking Conference and Workshops, IFIP Networking 2017, 12 June 2017 through 16 June 2017
Available from: 2018-08-13 Created: 2018-08-13 Last updated: 2023-05-19Bibliographically approved
Marsh, I. (2017). CheesePi: Research, results, and the regulator. In: ANRW 2017 - Proceedings of the Applied Networking Research Workshop, Part ofIETF-99 Meeting: . Paper presented at 2017 Applied Networking Research Workshop, ANRW 2017, 15 July 2017 (pp. 7-12).
Open this publication in new window or tab >>CheesePi: Research, results, and the regulator
2017 (English)In: ANRW 2017 - Proceedings of the Applied Networking Research Workshop, Part ofIETF-99 Meeting, 2017, p. 7-12Conference paper, Published paper (Refereed)
Abstract [en]

In October 2015 we presented CheesePi at the Research and Applications of Internet Measurements (RAIM) workshop in Yokohama, Japan. In this followup paper, 18 months on, we present our findings. These range from simple round trip delay measurements to entire quality campaigns over several weeks. A significant portion of the research has been done in conjunction with the Swedish regulator, which we bring to the fore. CheesePi is a lightweight platform with the goal of performing measurements from within users' homes. Since the goal is to measure Internet quality delivered by ISPs, measurement fairness is of prime concern. This paper covers the regulator's demands, ISPs feedback, our research interests, the users' needs of nearly two years work.

Keywords
Home networking, Network measurements, Regulation, Internet measurement, Network measurement, Research and application, Research interests, Round trip delay, Yokohama, Japan, Internet service providers
National Category
Natural Sciences
Identifiers
urn:nbn:se:ri:diva-33206 (URN)10.1145/3106328.3106337 (DOI)2-s2.0-85027716193 (Scopus ID)9781450351089 (ISBN)
Conference
2017 Applied Networking Research Workshop, ANRW 2017, 15 July 2017
Available from: 2018-01-31 Created: 2018-01-31 Last updated: 2023-05-19Bibliographically approved
Bjurling, B., Kreuger, P. & Marsh, I. (2017). Data Readiness for BADA: BADA main study 1, FFI/Vinnova grant 2015-00677.
Open this publication in new window or tab >>Data Readiness for BADA: BADA main study 1, FFI/Vinnova grant 2015-00677
2017 (English)Report (Other academic)
Series
SICS Technical Report, ISSN 1100-3154 ; T2017:08
National Category
Computer Sciences
Identifiers
urn:nbn:se:ri:diva-32974 (URN)
Funder
VINNOVA
Available from: 2018-01-03 Created: 2018-01-03 Last updated: 2023-05-19Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-8338-5513

Search in DiVA

Show all publications