Projects / Programmes
Autonomic edge computing for air quality monitoring
| Code |
Science |
Field |
Subfield |
| 2.07.05 |
Engineering sciences and technologies |
Computer science and informatics |
Information systems - software |
| Code |
Science |
Field |
| 1.02 |
Natural Sciences |
Computer and information sciences |
smart building, blockchain, edge computing, semantic Web services, graph optimization, network modeling, machine learning
Researchers (13)
| no. |
Code |
Name and surname |
Research area |
Role |
Period |
No. of publicationsNo. of publications |
| 1. |
04967 |
PhD Andrej Brodnik |
Computer intensive methods and applications |
Researcher |
2020 - 2023 |
453 |
| 2. |
36182 |
PhD Michael David Burnard |
Forestry, wood and paper technology |
Researcher |
2020 - 2023 |
156 |
| 3. |
51616 |
PhD Balazs David |
Computer science and informatics |
Researcher |
2020 - 2023 |
72 |
| 4. |
51617 |
PhD Laszlo Hajdu |
Computer science and informatics |
Researcher |
2020 - 2023 |
40 |
| 5. |
20243 |
PhD Branko Kavšek |
Computer intensive methods and applications |
Researcher |
2020 - 2023 |
136 |
| 6. |
37937 |
PhD Tilen Knaflič |
Physics |
Researcher |
2021 - 2022 |
24 |
| 7. |
50985 |
PhD Miklos Kresz |
Computer science and informatics |
Researcher |
2020 - 2023 |
117 |
| 8. |
35055 |
Lea Legan |
Chemistry |
Researcher |
2022 - 2023 |
182 |
| 9. |
51811 |
PhD Michael Mrissa |
Computer science and informatics |
Head |
2020 - 2023 |
74 |
| 10. |
57047 |
Marina Paldauf |
Computer science and informatics |
Researcher |
2023 |
1 |
| 11. |
35834 |
PhD Klara Retko |
Chemistry |
Researcher |
2022 |
165 |
| 12. |
28079 |
PhD Polonca Ropret |
Chemistry |
Researcher |
2020 - 2023 |
302 |
| 13. |
36213 |
PhD Aleksandar Tošić |
Computer science and informatics |
Researcher |
2020 - 2023 |
68 |
Organisations (3)
Abstract
Reducing the environmental impact of buildings is a top European priority and is highlighted in the sustainable development goals of the United Nations. To do so, we typically equip buildings with Wireless Sensor Networks (WSNs) to report the performance of building elements, optimise energy consumption and maintenance, improve the well-being of building occupants and inform future building design. Equipped buildings are then called smart buildings because they are able to self-assess and optimize their performance. Typical approaches to smart buildings rely on cloud facilities for data storage and processing and on autonomic computing to manage buildings along their life cycle (conception, construction, use, and end of life). However, these approaches present several drawbacks: dependency to cloud providers, heavy network use, high network latency, privacy and security concerns. Recently, we have witnessed a drastic increase of sensor integration into embedded devices. This evolution has driven researchers to reconsider typical cloud-based approaches and to distribute data and processes over the network, a concept called edge or fog computing. Edge computing solutions present multiple advantages. They optimize network usage, provide dynamic network configuration and low latency response to network changes, they facilitate data management, offer possibility for distributed on-site data processing and preserve independence from cloud providers. In this project, we look to edge computing to take advantage of the new generation of WSN devices and reduce the environmental cost of building monitoring solutions. More specifically, we integrate graph and infection models and distributed data mining into a decentralized service-oriented framework to implement dynamic self-configuring networks. We demonstrate the applicability of our work with a set of pilot buildings of diverse types (public and private), geographical areas (north, west, central and eastern Europe), living conditions and usages (residential and non-residential).
