Zurück zur Hauptseite / Back to main page

Cloud Computing (SS2026)

This seminar applies the fundamentals of distributed systems and cloud computing in practice. Groups of students combine various hardware and software components into a complex system to enable the practical application of artificial intelligence.

The goal of the semester project is to develop an edge computing monitoring solution to identify people and detect threats. Each group of students will develop, build, test, document, and present a complex hardware and software system that automatically detects people and identifies threat situations or events such as theft, fire, or vandalism. The semester project includes these tasks:

• Task 1: Develop and set up an infrastructure consisting of one or more sensor nodes with single-board computers (Raspberry Pi 5) and a Raspberry Pi AI Camera module, one or more Raspberry Pi Camera Module(s) plus a Raspberry Pi AI HAT+.
• Deployment of the operating system (for example Raspberry Pi OS or Ubuntu) and the object detection software (for example YOLO [1], [2] or TensorFlow)
• Investigate how the operating system images of the Raspberry Pi 3 nodes can be consolidated on a Raspberry Pi 4 or Raspberry Pi 5. The goal is to boot the Raspberry Pi 3 nodes via PXE over the LAN and simplify the administration of the cluster. Try it out and investigate the benefits and drawbacks of such a deployment scenario.
• Task 2: Investigate the performance (GFLOPS) of your infrastructure or cluster system by using the industry standard solution HPL (High Performance LINPACK).
• Task 3: Deploy the Message Passing Interface (MPI) on the cluster to make it a high-performance cluster The Raspberry Pi 3 nodes can act as worker nodes, while the Raspberry Pi 4 or Raspberry Pi 5 acts as the master node. Demonstrate the scalability of the cluster using MPI applications and analyze the potential performance as well as the bottlenecks. Also demonstrate Amdahl's Law and Gustafson's Law using at least two MPI examples.
• Task 4: Demonstrate Amdahl's Law and Gustafson's Law by using a non-MPI tool such as Task Distributor.
• Task 5: Deploy a monitoring solution that observes the health status of the hardware, relevant operating system parameters, service parameters, and network services with an open source tool such as Prometheus, Grafana, or CheckMK.
• Task 6: Collect a sufficient number of images for the training and testing of your object detection model (for example TensorFlow, OpenCV, YOLO) using your own hardware (in this case you need a supported GPU) or a cloud service (for example Roboflow or V7).
• You are expected to train your own model. Using a pre existing model is not sufficient.
• Task 7: Develop a backend to manage the sensor nodes and the collected data.
• The backend can be deployed as Docker container(s) on a Raspberry Pi Kubernetes cluster with k3s or a similar solution. The backend infrastructure will be a robust and scalable high availability cluster of Raspberry Pi 3 nodes. The cluster includes a distributed file system (for example Ceph with the Ceph Object Gateway S3 API) or a storage service (for example SeaweedFS or MinIO).
• Task 8: Develop a frontend to present, for example, log information, event messages, and a map of events with supporting evidence such as images and timestamps.
• The frontend will also be deployed as a Docker container on a Raspberry Pi Kubernetes cluster with k3s or a similar solution and should be implemented with a modern framework such as Vue.js or React.
• Use protocol(s) such as REST or MQTT for communication between the components (frontend, backend, services, etc.).
• Task 9: Implement a Telegram notification feature with a Telegram Bot.
• The Telegram Bot informs the team members about health related events of the infrastructure and threats or other events detected by the sensor node(s).
• Task 10: Documentation and presentation of the results from Tasks 1 to 9.
• Create documentation and guides that enable students, researchers, and lecturers to reproduce the edge computing scenarios and use them for their own modules and research projects.
• No slide presentations or traditional PDF project reports will be created. Instead, each team develops complete and understandable online documentation (for example via GitHub Pages) and presents the results in the form of a poster as well as a live demonstration.

This course has no written exam. Instead, your individual grade will depend entirely on your work and the results of the semester project.

• On April 16th, each team will receive one aluminum case (460 x 340 x 160 mm) with hardware that should be sufficient for the semester project. The aluminum case contains:
• Smart Gigabit Ethernet switch with power cable or power supply unit
• RJ45 twisted pair network cables
• Raspberry Pi 5 single-board computer (8 GB RAM)
• Raspberry Pi 27W USB C Power Supply (for the Raspberry Pi 5)
• Raspberry Pi 4 single-board computer
• Raspberry Pi 15W USB C Power Supply (for the Raspberry Pi 4)
• Micro HDMI to HDMI cable (for the Raspberry Pi 4)
• 8 Raspberry Pi 3 single-board computers
• One or two Anker USB power supplies (6 or 10 ports, 60 W or 5 ports, 40 W) (for the Raspberry Pi 3)
• Micro USB power cables (for the Raspberry Pi 3)
• HDMI to HDMI cable (for the Raspberry Pi 3)
• Micro-HDMI to HDMI adapter cable (for the Raspberry Pi 4/5)
• Raspberry Pi AI Camera module
• One or more Raspberry Pi Camera Module(s)
• Raspberry Pi AI HAT+ (for the Raspberry Pi 5)
• Some teams also got a Google Coral USB Accelerator, but this device is End-of-Life and is pretty hard to get running with modern operating system versions. Using it is only recommended for curious souls.
• Raspberry Pi Flash Drive USB 3.0 128 GB
• 500 GB PCIe GEN4 NVMe SSD M.2 2280 Flash Drive in external case
• MicroSD cards (32 GB each)
• USB 3.0 card reader for SD and MicroSD cards
• SD/MicroSD card adapter
• Spacer bolts M2.5
• Power strip

Zeitplan für das Semester / Schedule of the Course

Date	Time	Room	Target Audience	Topics
16.04.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Einführungsveranstaltung, Gruppenfindung, Anforderungsanalyse, Projektplanung
16.04.2026	14:15-17:15	1-234	(High-Integrity Systems)	Semester project introduction, team building, requirements analysis, task identification, time planning
23.04.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
23.04.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
30.04.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
30.04.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
07.05.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
07.05.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
14.05.2026	-----	-----	-----	Christi Himmelfahrt, Feiertag
14.05.2026	-----	-----	-----	Ascension Day, public holiday
21.05.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
21.05.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
28.05.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
28.05.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
04.06.2026	-----	-----	-----	Fronleichnam, Feiertag
04.06.2026	-----	-----	-----	Corpus Christi, public holiday
11.06.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
11.06.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
18.06.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
18.06.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
25.06.2026	-----	-----	(Allgemeine Informatik)	Dienstreise
25.06.2026	-----	-----	(High-Integrity Systems)	Business trip
02.07.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
02.07.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
09.07.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Gruppenarbeit
09.07.2026	14:15-17:15	1-234	(High-Integrity Systems)	Teamwork
16.07.2026	10:00-13:00	1-234	(Allgemeine Informatik)	Demonstration und Präsentation der Projektergebnisse aller Teams, Abschlussveranstaltung
16.07.2026	14:15-17:15	1-234	(High-Integrity Systems)	Semester project presentations and demonstrations, closing event

Course Materials

Teams / Results

Contact

The best way to reach me is by email: christianbaun@fb2.fra-uas.de