Pekka Pääkkönen

Mr. Pekka Pääkkönen


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 April 2020 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
PPPekka Pääkkönen
Pekka Pääkkönen
DPD. Pakkala
D. Pakkala
Background: Augmented reality, computer vision and other (e.g. network functions, Internet-of-Things (IoT)) use cases can be realised in edge computing environments with machine learning (ML) techniques. For realisation of the use cases, it has to be understood how data is collected, stored, processed, analysed, and visualised in big data systems. In order to provide services with low latency for end users, often utilisation of ML techniques has to be optimized. Also, software/service developers have to understand, how to develop and deploy ML models in edge computing environments. Therefore, architecture design of big data systems to edge computing environments may be challenging.Findings: The contribution of this paper is reference architecture (RA) design of a big data system utilising ML techniques in edge computing environments. An earlier version of the RA has been extended based on 16 realised implementation architectures, which have been developed to edge/distributed computing environments. Also, deployment of architectural elements in different environments is described. Finally, a system view is provided of the software engineering aspects of ML model development and deployment.Conclusions: The presented RA may facilitate concrete architecture design of use cases in edge computing environments. The value of RAs is reduction of development and maintenance costs of systems, reduction of risks, and facilitation of communication between different stakeholders.

8 April 2016 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
PPPekka Pääkkönen
Pekka Pääkkönen
For getting up-to-date insight into online services, extracted data has to be processed in near real time. For example, major big data companies (Facebook, LinkedIn, Twitter) analyse streaming data for development of new services. Several technologies have been developed, which could be selected for implementation of stream processing functionalities. The contribution of this paper is feasibility analysis of technologies for stream-based processing of semi-structured data. Particularly, feasibility of a Big Data management system for semi-structured data (AsterixDB) will be compared to Spark streaming, which has been integrated with Cassandra NoSQL database for persistence. The study focuses on stream processing in a simulated social media use case (tweet analysis), which has been implemented to Eucalyptus cloud computing environment on a distributed shared memory multiprocessor platform. The results indicate that AsterixDB is able to provide significantly better performance both in terms of throughput and latency, when data feed functionality of AsterixDB is used, and stream processing has been implemented with Java. AsterixDB also scaled on the same level or better, when the amount of nodes on the cloud platform was increased. However, stream processing in AsterixDB was delayed by batching of data, when tweets were streamed into the database with data feeds.

23 March 2017 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
PPPekka Pääkkönen
Pekka Pääkkönen
JJJuha Jokitulppo
Juha Jokitulppo
Social media data has provided various insights into the behaviour of consumers and businesses. However, extracted data may be erroneous, or could have originated from a malicious source. Thus, quality of social media should be managed. Also, it should be understood how data quality can be managed across a big data pipeline, which may consist of several processing and analysis phases. The contribution of this paper is evaluation of data quality management architecture for social media data. The theoretical concepts based on previous work have been implemented for data quality evaluation of Twitter-based data sets. Particularly, reference architecture for quality management in social media data has been extended and evaluated based on the implementation architecture. Experiments indicate that 150–800 tweets/s can be evaluated with two cloud nodes depending on the configuration.

29 December 2020 in Future Internet
Verified
Journal Article
Open access
PDF file
PPPekka Pääkkönen
Pekka Pääkkönen
DPDaniel Pakkala
Daniel Pakkala
JKJussi Kiljander
Jussi Kiljander
RSRoope Sarala
Roope Sarala
The current approaches for energy consumption optimisation in buildings are mainly reactive or focus on scheduling of daily/weekly operation modes in heating. Machine Learning (ML)-based advanced control methods have been demonstrated to improve energy efficiency when compared to these traditional methods. However, placing of ML-based models close to the buildings is not straightforward. Firstly, edge-devices typically have lower capabilities in terms of processing power, memory, and storage, which may limit execution of ML-based inference at the edge. Secondly, associated building information should be kept private. Thirdly, network access may be limited for serving a large number of edge devices. The contribution of this paper is an architecture, which enables training of ML-based models for energy consumption prediction in private cloud domain, and transfer of the models to edge nodes for prediction in Kubernetes environment. Additionally, predictors at the edge nodes can be automatically updated without interrupting operation. Performance results with sensor-based devices (Raspberry Pi 4 and Jetson Nano) indicated that a satisfactory prediction latency (~7–9 s) can be achieved within the research context. However, model switching led to an increase in prediction latency (~9–13 s). Partial evaluation of a Reference Architecture for edge computing systems, which was used as a starting point for architecture design, may be considered as an additional contribution of the paper.

9 July 2019 in Journal of Cloud Computing
Verified
Journal Article
Open access
PDF file
PPPekka Pääkkönen
Pekka Pääkkönen
AHAntti Heikkinen
Antti Heikkinen
TATommi Aihkisalo
Tommi Aihkisalo
End users stream video increasingly from live broadcasters (via YouTube Live, Twitch etc.). Adaptive live video streaming is realised by transcoding different representations of the original video content. Management of transcoding resources creates costs for the service provider, because transcoding is a CPU-intensive task. Additionally, the content must be transcoded within real time with the transcoding resources in order to provide satisfying Quality of Service. The contribution of this paper is validation of an online architecture for enabling live video transcoding with Docker in a Kubernetes-based cloud environment. Particularly, online cloud resource allocation has been focused on by executing experiments in several configurations. The results indicate that Random Forest regressor provided the best overall performance in terms of precision regarding transcoding speed and CPU consumption on resources, and the amount of realised transcoding tasks. Reinforcement Learning provided lower performance, and required more effort in terms of training.

1 September 2006
Verified
Conference Paper
Open access
NANadeem Akhtar
Nadeem Akhtar
RCRui Campos
Rui Campos
CKCornelia Kappler
Cornelia Kappler
PPPekka Pääkkönen
Pekka Pääkkönen
PPPetteri Poyhonen
Petteri Poyhonen
Di ZhouDi Zhou
Di Zhou
There is a growing trend towards convergence of telecommunication and data networks in order to support a richer set of services and applications. At the same time, increasing diversity and density of network access technologies has made the goal of providing connectivity anytime and anywhere a real possibility. Another important development is the emergence of small, low-complexity user owned networks, such as personal area networks and body area networks. Dynamic interworking, also known as network composition, between networks of different types and sizes is essential in the push towards convergence, as well as to realize truly seamless connectivity between heterogeneous access networks. Dynamic interworking requires signalling between different elements of the control planes of the different networks in order to coordinate the control functions and resources of the networks concerned. In this paper, we present the generic ambient network signalling protocol suite to address the diverse signalling requirements for dynamic interworking of networks.