PhD Researcher
Peter Sossalla received his Diplom (Dipl.-Ing.) in electrical engineering in 2019 and started working in the 5G Campus project shortly afterwards. During his studies, he worked over 2 years in the software development and additionally as a student assistant. He also completed an internship at Airbus DS. His current research focus is on Industrial Networks, TSN, Robotics, Highly Deterministic Networks and uRLLC.
Phone: +49 151 27736594 Email: peter.sossalla@tu-dresden.de
We are currently looking for students for a diploma thesis or as student assistants (SHKs) for the following projects: Indoor Localization with 5G Industrial Environments Development of a Mobile Robotic system
Feel free to contact me (peter.sossalla@tu-dresden.de) if you are interested.
Sossalla, Peter; Rischke, Justus; Nguyen, Giang T.; Fitzek, Frank H. P.
Offloading Robot Control with 5G Inproceedings
In: 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC) (CCNC 2022), Las Vegas, USA, 2022.
Abstract | BibTeX
@inproceedings{Sossalla2201:Offloading, title = {Offloading Robot Control with 5G}, author = {Peter {Sossalla} and Justus {Rischke} and Giang T. {Nguyen} and Frank H. P. {Fitzek}}, year = {2022}, date = {2022-01-08}, urldate = {2022-01-01}, booktitle = {2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC) (CCNC 2022)}, address = {Las Vegas, USA}, abstract = {Simultaneous Localization and Mapping (SLAM), among other critical functions of mobile robots, such as navigation, are computationally expensive. When deployed at the robot, those functions demand high energy consumption and result in shorter operation time. Offloading SLAM to an Edge Cloud (EC) can significantly reduce the robot's computing demand and resources, subsequently reducing energy consumption. We offload intelligence of mobile robot control functionality, i.e., navigation, localization, and control to an EC. The EC processes sensor data and sends the robot the directional velocities. Meanwhile, a 5G wireless connection ensures the necessary low latencies and high throughputs. We demonstrate the feasibility of offloading SLAM and navigation in an EC based on a use case in automotive production. Additionally, we developed a digital twin of the robot and visualized its current sensor data.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} }
Close
Sossalla, Peter; Rischke, Justus; Hofer, Johannes; Fitzek, Frank H. P.
Evaluating the Advantages of Remote SLAM on an Edge Cloud Inproceedings
In: 2021 IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2021), 2021.
BibTeX
@inproceedings{Sossalla21:EdgeSLAM, title = {Evaluating the Advantages of Remote SLAM on an Edge Cloud}, author = {Peter {Sossalla} and Justus {Rischke} and Johannes {Hofer} and Frank H. P. {Fitzek}}, year = {2021}, date = {2021-09-07}, booktitle = {2021 IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2021)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} }
Rischke, Justus; Sossalla, Peter; Itting, Sebastian A. W.; Fitzek, Frank H. P.; Reisslein, Martin
5G Campus Networks: A First Measurement Study Journal Article
In: IEEE Access, 9 , pp. 121786-121803, 2021.
Links | BibTeX
@article{9524600, title = {5G Campus Networks: A First Measurement Study}, author = {Justus {Rischke} and Peter {Sossalla} and Sebastian A. W. {Itting} and Frank H. P. {Fitzek} and Martin {Reisslein}}, doi = {10.1109/ACCESS.2021.3108423}, year = {2021}, date = {2021-01-01}, urldate = {2021-01-01}, journal = {IEEE Access}, volume = {9}, pages = {121786-121803}, keywords = {}, pubstate = {published}, tppubtype = {article} }
Rischke, Justus; Sossalla, Peter; Salah, Hani; Fitzek, Frank H. P.; Reisslein, Martin
QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks Journal Article
In: IEEE Access, 2020, ISSN: 2169-3536.
Abstract | Links | BibTeX
@article{9201294, title = {QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks}, author = {Justus {Rischke} and Peter {Sossalla} and Hani {Salah} and Frank H. P. {Fitzek} and Martin {Reisslein}}, doi = {10.1109/ACCESS.2020.3025432}, issn = {2169-3536}, year = {2020}, date = {2020-01-01}, journal = {IEEE Access}, abstract = {Flow routing can achieve fine-grained network performance optimizations by routing distinct packet traffic flows over different network paths. While the centralized control of Software-Defined Networking (SDN) provides a control framework for implementing centralized network optimizations, e.g., optimized flow routing, the implementation of flow routing that is adaptive to varying traffic loads requires complex models. The goal of this study is to pursue a model-free approach that is based on reinforcement learning. We design and evaluate QR-SDN, a classical tabular reinforcement learning approach that directly represents the routing paths of individual flows in its state-action space. Due to the direct representation of flow routes in the QR-SDN state-action space, QR-SDN is the first reinforcement learning SDN routing approach to enable multiple routing paths between a given source (ingress) switch\textendashdestination (egress) switch pair while preserving the flow integrity. That is, in QR-SDN, packets of a given flow take the same routing path, while different flows with the same source-destination switch pair may take different routes (in contrast, the recent DRL-TE approach splits a given flow on a per-packet basis incurring high complexity and out-of-order packets). We implemented QR-SDN in a Software-Defined Network (SDN) emulation testbed. Our evaluations demonstrate that the flow-preserving multi-path routing of QR-SDN achieves substantially lower flow latencies than prior routing approaches that determine only a single source-destination route. A limitation of QR-SDN is that the state-action space grows exponentially with the number of network nodes. Addressing the scalability of direct flow routing, e.g., through routing only high-rate flows, is an important direction for future research. The QR-SDN code is made publicly available to support this future research.}, keywords = {}, pubstate = {published}, tppubtype = {article} }
Rischke, Justus; Sossalla, Peter
Machine Learning for Routing Book Chapter
In: Fitzek, Frank H. P.; Granelli, Fabrizio; Seeling, Patrick (Ed.): Computing in Communication Networks – From Theory to Practice, 1 , Chapter 16, pp. 303-311, Elsevier, 1, 2020, (https://cn.ifn.et.tu-dresden.de/compcombook/).
@inbook{CompBookChap16, title = {Machine Learning for Routing}, author = {Justus {Rischke} and Peter {Sossalla}}, editor = {Frank H. P. {Fitzek} and Fabrizio {Granelli} and Patrick {Seeling}}, year = {2020}, date = {2020-01-01}, booktitle = {Computing in Communication Networks \textendash From Theory to Practice}, volume = {1}, pages = {303-311}, publisher = {Elsevier}, edition = {1}, chapter = {16}, series = {1}, note = {https://cn.ifn.et.tu-dresden.de/compcombook/}, keywords = {}, pubstate = {published}, tppubtype = {inbook} }