Change search
Link to record
Permanent link

Direct link
BETA
Schelén, Olov
Publications (10 of 41) Show all publications
Synnes, K., Kranz, M., Rana, J. & Schelén, O. (2017). User-Centric Social Interaction for Digital Cities. In: Bin Guo; Daniele Riboni; Peizhao Hu (Ed.), The internet of things: breakthroughs in research and practice (pp. 41-70). Paper presented at . IGI Global.
Open this publication in new window or tab >>User-Centric Social Interaction for Digital Cities
2017 (English)In: The internet of things: breakthroughs in research and practice, IGI Global, 2017, 41-70 p.Chapter in book (Refereed)
Abstract [en]

Pervasive Computing was envisioned by pioneers like Mark Weiser, but has yet to become an everyday technology in our society. The recent advances regarding Internet of Things, social computing and mobile access technologies however converge to make pervasive computing truly ubiquitous. The key challenge is however to make simple and robust solutions for normal users, which shifts the focus from complex platforms involving machine learning and artificial intelligence to more hands on construction of services that are tailored or personalized for individual users.This chapter therefore discusses Internet of Things together with Social Computing as a basis for components that users in a ’digital city’ could utilize to make their daily life better, safer, etc. A novel environment for user-created services, such as social apps, is presented as a possible solution for this. The vision is that anyone could make simple service based on Internet-enabled devices (Internet of Things) and encapsulated digital resources such as Open Data, which also can have social aspects embedded.This chapter also aims to identify trends, challenges and recommendations in regard of Social Interaction for Digital Cities. This work will help expose future themes with high innovation and business potential based on a timeframe roughly 15 years ahead of now. The purpose is to create a common outlook on the future of information and communication technologies (ICT) based on the extrapolation of current trends and ongoing research efforts.

Place, publisher, year, edition, pages
IGI Global, 2017
National Category
Media and Communication Technology Computer Science
Research subject
Mobile and Pervasive Computing; Dependable Communication and Computation Systems
Identifiers
urn:nbn:se:ltu:diva-64828 (URN)10.4018/978-1-5225-1832-7.ch003 (DOI)2-s2.0-85021277900 (Scopus ID)9781522518334 (ISBN)
Available from: 2017-07-07 Created: 2017-07-07 Last updated: 2017-11-24Bibliographically approved
Idowu, S., Saguna, S., Åhlund, C. & Schelén, O. (2016). Applied Machine Learning: Forecasting Heat Load in District Heating System. Energy and Buildings, 133, 478-488.
Open this publication in new window or tab >>Applied Machine Learning: Forecasting Heat Load in District Heating System
2016 (English)In: Energy and Buildings, ISSN 0378-7788, E-ISSN 1872-6178, Vol. 133, 478-488 p.Article in journal (Refereed) Published
Abstract [en]

Forecasting energy consumption in buildings is a key step towards the realization of optimized energy production, distribution and consumption. This paper presents a data driven approach for analysis and forecast of aggregate space and water thermal load in buildings. The analysis and the forecast models are built using district heating data unobtrusively collected from ten residential and commercial buildings located in Skellefteå, Sweden. The load forecast models are generated using supervised machine learning techniques, namely, support vector machine, regression tree, feed forward neural network, and multiple linear regression. The model takes the outdoor temperature, historical values of heat load, time factor variables and physical parameters of district heating substations as its input. A performance comparison among the machine learning methods and identification of the importance of models input variables is carried out. The models are evaluated with varying forecast horizons of every hour from 1 up to 48 hours. Our results show that support vector machine, feed forward neural network and multiple linear regression are more suitable machine learning methods with lower performance errors than the regression tree. Support vector machine has the least normalized root mean square error of 0.07 for a forecast horizon of 24 hour.

National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-59596 (URN)10.1016/j.enbuild.2016.09.068 (DOI)000389087300045 ()2-s2.0-84992362157 (Scopus ID)
Note

Validerad; 2016; Nivå 2; 2016-11-08 (andbra)

Available from: 2016-10-10 Created: 2016-10-10 Last updated: 2017-11-30Bibliographically approved
Lindgren, A., Abdesslem, F. B., Ahlgren, B., Schelén, O. & Malik, A. M. (2016). Design choices for the IoT in Information-Centric Networks (ed.). In: (Ed.), 2016 13th IEEE Annual Consumer Communications & Networking Conference (CCNC): Las Vegas, 9-12 Jan. 2016. Paper presented at 13th IEEE Annual Consumer Communications & Networking Conference (CCNC,Las Vegas, 9-12 Jan. 2016 (pp. 882-888). Piscataway, NJ: IEEE Communications Society, Article ID 7444905.
Open this publication in new window or tab >>Design choices for the IoT in Information-Centric Networks
Show others...
2016 (English)In: 2016 13th IEEE Annual Consumer Communications & Networking Conference (CCNC): Las Vegas, 9-12 Jan. 2016, Piscataway, NJ: IEEE Communications Society, 2016, 882-888 p., 7444905Conference paper, Published paper (Refereed)
Abstract [en]

This paper outlines the tradeoffs involved in utilizing Information-Centric Networking (ICN) for Internet of Things (IoT) scenarios. It describes contexts and applications where the IoT would benefit from ICN, and where a host-centric approach would be better. Requirements imposed by the heterogeneous nature of IoT networks are discussed in terms of connectivity, power availability, computational and storage capacity. Design choices are then proposed for an IoT architecture to handle these requirements, while providing efficiency and scalability. An objective is to not require any IoT specific changes of the ICN architecture per se, but we do indicate some potential modifications of ICN that would improve efficiency and scalability for IoT and other applications

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2016
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-31711 (URN)10.1109/CCNC.2016.7444905 (DOI)000382042200184 ()5f7c22bb-4a6e-4fc9-adb5-101c18f24ca2 (Local ID)978-1-4673-9291-4 (ISBN)5f7c22bb-4a6e-4fc9-adb5-101c18f24ca2 (Archive number)5f7c22bb-4a6e-4fc9-adb5-101c18f24ca2 (OAI)
Conference
13th IEEE Annual Consumer Communications & Networking Conference (CCNC,Las Vegas, 9-12 Jan. 2016
Note

Validerad; 2016; Nivå 1; 2016-10-06 (andbra)

Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Rao, A., Schelén, O. & Lindgren, A. (2016). Performance implications for IoT over information centric networks. In: CHANTS '16: Proceedings of the Eleventh ACM Workshop on Challenged Networks. Paper presented at The Eleventh ACM Workshop on Challenged Networks : CHANTS '16, New York City, New York, October 03-07, 2016 (pp. 57-62). New York: ACM Digital Library.
Open this publication in new window or tab >>Performance implications for IoT over information centric networks
2016 (English)In: CHANTS '16: Proceedings of the Eleventh ACM Workshop on Challenged Networks, New York: ACM Digital Library, 2016, 57-62 p.Conference paper, Published paper (Refereed)
Abstract [en]

Information centric networking (ICN) is a proposal for a future in-ternetworking architecture that is more efficient and scalable. Whileseveral ICN architectures have been evaluated for networks carry-ing web and video traffic, the benefits and challenges it poses forInternet of Things (IoT) networks are relatively unexplored. In ourwork, we evaluate the performance implications for typical IoT net-work scenarios in the ICN paradigm. We study the behavior of in-network caching, introduce a way to make caching more efficientfor periodic sensor data, and evaluate the impact of presence andlocation of lossy wireless links in IoT networks. In this paper, wepresent and discuss the results of our evaluations on IoT networksperformed through emulations using a specific ICN architecture,namely, content centric networking (CCN). For example, we showthat the newly proposed UTS-LRU cache replacement strategy forimproved caching performance of time series content streams re-duces the number of messages transmitted by up to 16%. Our find-ings indicate that the performance of IoT networks using ICN areinfluenced by the content model and the nature of its links, and mo-tivates further studies to understand the performance implicationsin more varied IoT scenarios.

Place, publisher, year, edition, pages
New York: ACM Digital Library, 2016
National Category
Communication Systems Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-60896 (URN)10.1145/2979683.2979686 (DOI)978-1-4503-4256-8 (ISBN)
Conference
The Eleventh ACM Workshop on Challenged Networks : CHANTS '16, New York City, New York, October 03-07, 2016
Available from: 2016-12-03 Created: 2016-12-03 Last updated: 2017-11-24Bibliographically approved
Schelén, O., Elragal, A. & Haddara, M. (2015). A roadmap for big-data research and education (ed.). Paper presented at . Luleå: Luleå tekniska universitet.
Open this publication in new window or tab >>A roadmap for big-data research and education
2015 (English)Report (Other academic)
Abstract [en]

The research area known as big data is characterized by the 3 V’s, which are vol- ume; variety; and velocity. Recently, also veracity and value have been associated with big data and that adds up to the 5 V’s. Big data related information systems (IS) are typically highly distributed and scalable in order to handle the huge datasets in organizations. Data processing in such systems includes creation, retrieval, storage, analysis, presentation, visualization, and any other activity that is typical for IS sys- tems. Big data is often associated with business analytics, cloud services, or industrial systems.This document presents a brief overview of the state of the art in selected topics of big data research, with the purpose of providing input to a roadmap for research and education at Lule ̊a University of Technology (LTU). The selection of topics is based on assessments of where LTU can make an impact based on current and anticipated research strengths and position with industry (e.g., process industry, data centers and cloud application providers). Topics include distributed systems, mobility, Internet of Things, and advanced analytics.

Place, publisher, year, edition, pages
Luleå: Luleå tekniska universitet, 2015. 10 p.
Series
Technical report / Luleå University of Technology, ISSN 1402-1536
National Category
Media and Communication Technology Information Systems, Social aspects
Research subject
Mobile and Pervasive Computing; Information systems; Intelligent industrial processes (AERI); Enabling ICT (AERI)
Identifiers
urn:nbn:se:ltu:diva-24316 (URN)a77593be-a71c-4c7c-ae73-0cc30c31e50b (Local ID)978-91-7583-275-3 (ISBN)a77593be-a71c-4c7c-ae73-0cc30c31e50b (Archive number)a77593be-a71c-4c7c-ae73-0cc30c31e50b (OAI)
Note
Godkänd; 2015; 20150325 (olov)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2017-11-24Bibliographically approved
Jimenez, L. L., Simon, M. G., Schelén, O., Kristiansson, J., Synnes, K. & Åhlund, C. (2015). CoMA: Resource Monitoring of Docker Containers (ed.). In: (Ed.), (Ed.), Proceedings of the 5th International Conference on Cloud Computing and Services Science (CLOSER 2015): . Paper presented at International Conference on Cloud Computing and Services Science : 20/05/2015 - 22/05/2015 (pp. 145-154). : SCITEPRESS Digital Library, 1.
Open this publication in new window or tab >>CoMA: Resource Monitoring of Docker Containers
Show others...
2015 (English)In: Proceedings of the 5th International Conference on Cloud Computing and Services Science (CLOSER 2015), SCITEPRESS Digital Library , 2015, Vol. 1, 145-154 p.Conference paper, Published paper (Refereed)
Abstract [en]

This research paper presents CoMA, a Container Monitoring Agent, that oversees resource consumption of operating system level virtualization platforms, primarily targeting container-based platforms such as Docker. The core contribution is CoMA, together with a quantitative evaluation verifying the validity of the measurements reported by the agent for three metrics: CPU, memory and block I/O. The proof-of-concept is implemented for Docker-based systems and consists of CoMA, the Ganglia Monitoring System and the Host sFlow agent. This research is in line with the rising trend of container adoption which is due to the resource efficiency and ease of deployment. These characteristics have set containers in a position to topple virtual machines as the reigning virtualization technology in data centers.

Place, publisher, year, edition, pages
SCITEPRESS Digital Library, 2015
Keyword
Docker, Containers, OS-level virtualization, Cloud Computing, Information technology - Computer science, Informationsteknik - Datorvetenskap
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-31992 (URN)10.5220/0005448001450154 (DOI)65372d05-6cc9-4916-b19f-df00f4a146dc (Local ID)978-989-758-104-5 (ISBN)65372d05-6cc9-4916-b19f-df00f4a146dc (Archive number)65372d05-6cc9-4916-b19f-df00f4a146dc (OAI)
Conference
International Conference on Cloud Computing and Services Science : 20/05/2015 - 22/05/2015
Projects
Cloudberry Datacenters
Note
Godkänd; 2015; Bibliografisk uppgift: The full text of this paper is only available to INSTICC members. ; 20150821 (larjim)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Idowu, S., Saguna, S., Åhlund, C. & Schelén, O. (2014). Forecasting Heat Load for Smart District Heating Systems: A Machine Learning Approach (ed.). In: (Ed.), (Ed.), 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm 2014): Venice, 3-6 Nov. 2014. Paper presented at International Conference on Smart Grid Communications : 06/11/2014 - 06/11/2014 (pp. 554-559). Piscataway, NJ: IEEE Communications Society.
Open this publication in new window or tab >>Forecasting Heat Load for Smart District Heating Systems: A Machine Learning Approach
2014 (English)In: 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm 2014): Venice, 3-6 Nov. 2014, Piscataway, NJ: IEEE Communications Society, 2014, 554-559 p.Conference paper, Published paper (Refereed)
Abstract [en]

The rapid increase in energy demand requires effective measures to plan and optimize resources for efficient energy production within a smart grid environment. This paper presents a data driven approach to forecasting heat load for multi- family apartment buildings in a District Heating System (DHS). The forecasting model is built using six and eleven weeks of data from five building substations. The external factors and internal factors influencing the heat load in substations are parameters used as our model’s input. Short-term forecast models are generated using four supervised Machine Learning (ML) techniques: Support Vector Regression (SVR), Regression Tree, Feed Forwards Neural Network (FFNN) and Multiple Linear Regression (MLR). Performance comparison among these ML methods was carried out. The effects of combining the internal and external factors influencing heat load at substations was studied. The models are evaluated with varying horizon up to 24-hours ahead. The results show that SVR has the best accuracy of 5.6% MAPE for the best-case scenario.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2014
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing; Enabling ICT (AERI)
Identifiers
urn:nbn:se:ltu:diva-34352 (URN)10.1109/SmartGridComm.2014.7007705 (DOI)886feb09-67f9-4347-84a0-516e622f7f5c (Local ID)978-1-4799-4934-2 (ISBN)886feb09-67f9-4347-84a0-516e622f7f5c (Archive number)886feb09-67f9-4347-84a0-516e622f7f5c (OAI)
Conference
International Conference on Smart Grid Communications : 06/11/2014 - 06/11/2014
Note
Godkänd; 2014; 20140817 (samidu)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Idowu, S., Åhlund, C. & Schelén, O. (2014). Machine learning in district heating system energy optimization (ed.). In: (Ed.), (Ed.), 2014 IEEE International Conference on Pervasive Computing and Communications workshops: PERCOM WORKSHOPS 2014, Budapest, Hungary; 24-28 March 2014. Paper presented at IEEE International Conference on Pervasive Computing and Communication Workshops : 24/03/2014 - 28/03/2014 (pp. 224-227). Piscataway, NJ: IEEE Communications Society, Article ID 6815206.
Open this publication in new window or tab >>Machine learning in district heating system energy optimization
2014 (English)In: 2014 IEEE International Conference on Pervasive Computing and Communications workshops: PERCOM WORKSHOPS 2014, Budapest, Hungary; 24-28 March 2014, Piscataway, NJ: IEEE Communications Society, 2014, 224-227 p., 6815206Conference paper, Published paper (Refereed)
Abstract [en]

This paper introduces a work in progress, where we intend to investigate the application of Reinforcement Learning (RL) and online Supervised Learning (SL) to achieve energy optimization in District-Heating (DH) systems. We believe RL is an ideal approach since this task falls under the control-optimization problem where RL has yielded optimal results in previous work. The magnitude and scale of a DH system complexity incurs the curse of dimensionalities and model, hereby making RL a good choice since it provides a solution for the problem. To assist RL even further with the curse of dimensionalities, we intend to investigate the use of SL to reduce the state space. To achieve this, we shall use historical data to generate a heat load sub-model for each home. We believe using the output of these sub-models as feedback to the RL algorithm could significantly reduce the complexity of the learning task. Also, it could reduce convergence time for the RL algorithm. The desired goal is to achieve a realtime application, which takes operational actions when it receives new direct feedback. However, considering the dynamics of DH system such as large time delay and dissipation in DH network due to various factors, we hope to investigate things such as the appropriate data sampling rate and new parameters / sensors that could improve knowledge about the state of the system, especially on the consumer side of the DH network.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2014
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing; Enabling ICT (AERI)
Identifiers
urn:nbn:se:ltu:diva-32000 (URN)10.1109/PerComW.2014.6815206 (DOI)658e9b02-e0f4-418c-a2e3-7fe90e666b29 (Local ID)658e9b02-e0f4-418c-a2e3-7fe90e666b29 (Archive number)658e9b02-e0f4-418c-a2e3-7fe90e666b29 (OAI)
Conference
IEEE International Conference on Pervasive Computing and Communication Workshops : 24/03/2014 - 28/03/2014
Note
Godkänd; 2014; 20140605 (samidu)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Börjesson, M., Nilsson, M., Schelén, O., Andersson, K. & Nolin, M. (2014). Project: Cloudberry Datacenters. Paper presented at . .
Open this publication in new window or tab >>Project: Cloudberry Datacenters
Show others...
2014 (English)Other (Other (popular science, discussion, etc.))
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-36176 (URN)97ff2b32-abdb-4c4d-a298-f3e68bca89cd (Local ID)97ff2b32-abdb-4c4d-a298-f3e68bca89cd (Archive number)97ff2b32-abdb-4c4d-a298-f3e68bca89cd (OAI)
Note

Publikationer: CoMA: Resource Monitoring of Docker Containers; Status: Pågående; Period: 01/07/2013 → 30/06/2015

Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
Schelén, O., Brännström, R. & Åhlund, C. (2013). A sensor-data acquisition grid architecture (ed.). In: (Ed.), (Ed.), 2013 IEEE International Conference on Networking, Sensing and Control: . Paper presented at IEEE International Conference on Networking, Sensing and Control : 10/04/2013 - 12/04/2013 (pp. 361-366). Piscataway, NJ: IEEE Communications Society.
Open this publication in new window or tab >>A sensor-data acquisition grid architecture
2013 (English)In: 2013 IEEE International Conference on Networking, Sensing and Control, Piscataway, NJ: IEEE Communications Society, 2013, 361-366 p.Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents SAGA, a functional software architecture for distributing sensor data. The recursive architecture is dynamically instantiated for collecting, composing and storing data at multiple locations. Objectives are to support devices that are intermittently connected over different access-technologies, to save energy by avoiding repetitive transmission from sensors, and to scale out data compositions for different application services. When the architecture is instantiated the entities form a directed graph across organizational boundaries between sensors and applications. Data may be retrieved from sensors on-demand or be disseminated in real-time, for composition and delivery to the applications. The architecture is based on current sensor network principles such as client-server, representational state transfer and web services. The architecture is presented together with identified key requirements and design choices, and it has been instantiated in a prototype implementation for a smart city application. Some key issues for further research are presented.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2013
Series
I E E E International Conference on Networking, Sensing and Control. Conference Proceedings, ISSN 1810-7869
National Category
Computer Science Media and Communication Technology
Research subject
Dependable Communication and Computation Systems; Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-37599 (URN)10.1109/ICNSC.2013.6548764 (DOI)babed004-99c5-49d7-b08d-7a841c812ef0 (Local ID)978-1-4673-5199-7 (ISBN)978-1-4673-5199-7 (ISBN)babed004-99c5-49d7-b08d-7a841c812ef0 (Archive number)babed004-99c5-49d7-b08d-7a841c812ef0 (OAI)
Conference
IEEE International Conference on Networking, Sensing and Control : 10/04/2013 - 12/04/2013
Note
Godkänd; 2013; 20130508 (olov)Available from: 2016-10-03 Created: 2016-10-03 Last updated: 2017-11-25Bibliographically approved
Organisations

Search in DiVA

Show all publications