Abschlussarbeitstyp: Bachelor, Master
Betreuer: Heiner Teigeler
Forschungsgruppe: Critical Information Infrastructures
Beginn: 27. März 2020
One of the biggest challenges for future trends and digital innovations like Internet of Things (IoT), embedded artificial intelligent, ubiquitous computing or 5G wireless networks is the management, storage and processing of huge amounts of data (Madsen et al. 2013; Brogi and Forti 2017). Based on these innovations, millions of new devices, sensors and applications will be going online in the next decade. Measuring, monitoring, analyzing, processing and reacting are just a few examples of tasks that have to be done with the data flood that will be generated by them. The trend of consuming and producing large data amounts challenges existing technologies like cloud computing, because they struggle to handle this upcoming data flood (Bittencourt et al. 2015). Another challenge is the latency for providing the data. Nowadays cloud computing environments offer access to data at any time and from everywhere. In the case of conventional cloud applications like Dropbox, these latencies are not taken into account. In future application, where technology needs to support applications in the IoT environment the flow of data needs to changed. In application fields like autonomous driving it is essential to provide data in real-time. Another challenge is the inaccessibility of data. In many areas and use cases the devices are not able to use an internet connection with a high bandwidth or even there is no connection available, because the telco providers still have a lack of coverage in the field of mobile connections. Like already mentioned in IoT environments the devices need the data up on time and would have significant problems when the connection is bad. Rising costs and sensitive data concerns are also challenges of existing architectures like cloud computing. To cope these challenges fog computing presents a new distributed architecture that helps to reduce latency and supports the storage, management and processing of huge data amounts (Bittencourt et al. 2015). In simple words it spans the continuum between the cloud and each device that measures, monitors, analyzes, processes or reacts based on data from the cloud ecosystem. The fog computing architecture allows the distribution of core functions closer to the point where the data is originated or consumed. These core functions are computing, storage, communication, controlling and decision making. But in addition to move these core functions closer to the devices that use them, these devices also can be integrated in serving these core functions. By using fog computing the consumer receives advantages like lower latency, improved location awareness, higher business agility, better support for mobility, lower transportation costs (Mahmood 2018).
Possible topics include but are not limited to:
- Cloud and Fog: What are the mechnisms and actors in this consolidated architecture?
- Pricing models of fog computing
- Security opportunites and challanges of fog computing infrastructures
- State of the art: Comparison between implemented and upcoming fog computing use cases
This is an umbrella topic since topics of interest change rapidly. A specific topic will be selected during a first meeting.
Bittencourt LF, Lopes MM, Petri I, Rana OF Towards Virtual Machine Migration in Fog Computing. In: 2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC), 4-6 Nov. 2015 2015. pp 1-8. doi:10.1109/3PGCIC.2015.85
Brogi A, Forti S (2017) QoS-Aware Deployment of IoT Applications Through the Fog. IEEE Internet of Things Journal 4 (5):1185-1192. doi:10.1109/JIOT.2017.2701408
Chen N, Yang Y, Zhang T, Zhou M, Luo X, Zao JK (2018) Fog as a Service Technology. IEEE Communications Magazine 56 (11):95-101. doi:10.1109/MCOM.2017.1700465
Madsen H, Burtschy B, Albeanu G, Popentiu-Vladicescu F Reliability in the utility computing era: Towards reliable Fog computing. In: 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP), 7-9 July 2013 2013. pp 43-46. doi:10.1109/IWSSIP.2013.6623445