print page

Florian Meyer

Picture of Florian Meyer
Florian Meyer
Room 4.085, building E
Am Schwarzenberg-Campus 3
21073 Hamburg
phone+49 40 42878 - 3746
fax+49 40 427 - 3 - 10456
e-mail

Teaching

Projects

Publications

Florian Meyer and Volker Turau. Towards Delay-Minimal Scheduling through Reinforcement Learning in IEEE 802.15.4 DSME. Technical Report, February 2020.
@TechReport{Telematik_meyer_FGMLVS, author = {Florian Meyer and Volker Turau}, title = {Towards Delay-Minimal Scheduling through Reinforcement Learning in IEEE 802.15.4 DSME}, booktitle = {Proceedings of the 1st GI/ITG KuVS Fachgespr{\"a}che Machine Learning and Networking}, pages = , publisher = {}, day = {20-21}, month = feb, year = 2020, location = {M{\"u}nchen, Germany}, }
Abstract: The rise of wireless sensor networks (WSNs) in industrial applications imposes novel demands on existing wire- less protocols. The deterministic and synchronous multi-channel extension (DSME) is a recent amendment to the IEEE 802.15.4 standard, which aims for highly reliable, deterministic traffic in these industrial environments. It offers TDMA-based channel access, where slots are allocated in a distributed manner. In this work, we propose a novel scheduling algorithm for DSME which minimizes the delay in time-critical applications by employing reinforcement learning (RL) on deep neural networks (DNN).
Florian Meyer, Ivonne Andrea Mantilla-Gonzales, Florian Kauer and Volker Turau. Performance Analysis of the Slot Allocation Handshake in IEEE 802.15.4 DSME. In Proceedings of 18th International Conference on Ad Hoc Networks and Wireless (AdHoc-Now 2019), Springer, October 2019, pp. 102–117. Luxembourg.
@InProceedings{Telematik_adhocnow_2019, author = {Florian Meyer and Ivonne Andrea Mantilla-Gonzales and Florian Kauer and Volker Turau}, title = {Performance Analysis of the Slot Allocation Handshake in IEEE 802.15.4 DSME}, booktitle = {Proceedings of 18th International Conference on Ad Hoc Networks and Wireless (AdHoc-Now 2019)}, pages = {102-117}, publisher = {Springer}, day = {1-3}, month = oct, year = 2019, location = {Luxembourg}, }
Abstract: Wireless mesh networks using IEEE 802.15.4 are getting increasingly popular for industrial applications because of low energy consumption and low maintenance costs. The IEEE 802.15.4 standard introduces DSME (Deterministic and Synchronous Multi-channel Extension). DSME uses time-slotted channel access to guarantee timely data delivery, multi-channel communication, and frequency hopping to mitigate the effects of external interferences. A distinguishing feature of DSME is its flexibility and adaptability to time-varying network traffic and to changes in the network topology. In this paper we evaluate the ability of DSME to adapt to time-varying network traffic. We examine the limits for slot allocation rates for different topologies. The evaluation is performed with openDSME, an open-source implementation of DSME.
Florian Meyer and Volker Turau. Delay-Bounded Scheduling in IEEE 802.15.4e DSME using Linear Programming. In Proceedings of 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), May 2019, pp. 659–666. Santorini, Greece.
@InProceedings{Telematik_ISIoT_2019, author = {Florian Meyer and Volker Turau}, title = {Delay-Bounded Scheduling in IEEE 802.15.4e DSME using Linear Programming}, booktitle = {Proceedings of 15th International Conference on Distributed Computing in Sensor Systems (DCOSS)}, pages = {659-666}, day = {29-31}, month = may, year = 2019, location = {Santorini, Greece}, }
Abstract: The Deterministic and Synchronous Multi-Channel Extension (DSME) protocol is a recent amendment to the IEEE 802.15.4 standard. It combines contention-based and time-division medium access, offers channel diversity, and is aimed to support IIoT applications with stringent requirements in terms of timeliness and reliability. In this paper, we show how to configure DSME for a given data collection task. This includes the definition of the slot and frame length and the slot and channel schedule. We formulate different scheduling strategies as linear programs minimizing latency and energy. We verify our results through theoretical analysis and simulations and compare them with state-of-the-art scheduling algorithms. The results indicate a reduced delay of up to 80% for deep networks while also increasing reliability. Additionally, the proposed scheduling strategies significantly reduce the required buffer size.

The complete list of publications is available separately.

Supervised Theses

Ongoing Theses

Completed Theses