New algorithms, high data volumes and the increasing use of artificial intelligence in machine control require a completely new performance class of embedded control systems as well as new methods for the design and testing of control software.
The Distributed Computing and Communication group is characterized by a broad spectrum of competencies - from the design of microelectronic integrated circuits and architectures to the development of hardware-related software, the integration of sensors and actuators, and the networking of electronic control systems.
Special competencies already exist in the subject areas:
- Energy efficiency
- real-time capability
- Safety and security
- sturdiness
- Hardware/Software Architectures
- System partitioning, modelling and simulation
In production plants, the products often go through many successive processing steps, which take place on different machines and positions in the shop floor. In order for these processing steps to be carried out in a coordinated manner, the control devices must be able to communicate reliably with each other. Therefore, secure communication procedures and architectures are a central object of research for the DCC Group.
The most diverse requirements, such as compatibility with industrial standards, reaction times and bandwidths, as well as safety and security, play an important role in the design. The group is therefore researching processes and methods for developing efficient solutions for the various communication requirements of production systems.
The FAVIA reference platform is being developed in the DCC group as a research platform and concept for future architectures of automation technology. It enables the testing of new approaches for control and automation tasks. At the same time, it allows a smooth transition from prototypes to productive systems.
Persons 
B
D
R
Behnam Razi Perjikolaei
E-Mail: behnam.razi.perjikolaei(at)offis.de, Phone: +49 441 9722-159, Room: O82
S
W
Projects
C
G
K
KI embedded
KI-Grundlagenentwicklung für Embedded-Systems mit Leitanwendungen in Virtueller Sensorik und Brennstoffzellenregelung
Duration: 2021 - 2024T
ThermoTwin
Duration: 2022 - 2025
V
VE-VIDES
Duration: 2021 - 2024
Z
Publications
2023
Teaching Cyber-Physical Systems in Student Project Groups: How Do Alumni Assess the Experience in Retrospective?
Henning Schlender, Ralf Stemmer, Kim Grüttner, Günter Ehmen, Friederike Bruns, Bernd Westphal; 2023
2022
A Comparison of Virtual Platform Simulation Solutions for Timing Prediction of Small RISC-V Based SoCs
Böseler, Felix and Walter, Jörg and Razi Perjikolaei, Behnam; Forum on specification & Design Languages (FDL) 2022; 09 / 2022
A Detailed Analysis of Timing Effects in an IEC 61499 Ethernet/TSN Communication Scenario
Bruns, Friederike and Walter, Jörg and Nebel, Wolfgang; 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA); 09 / 2022
Architectural Concepts for IEC 61499-based Machine Controls: Beyond Normal Operation Handling
Sonnleithner, Lisa and Walter, Jörg and Wiesmayr, Bianca and Ashiwal, Virendra and Sharma, Shubham and Zoitl, Alois; 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA); 09 / 2022
Model-aware Simulation of IEC 61499 Designs
Mehlhop, Sven and Walter, Jörg; 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA); 09 / 2022
2021
FPGA based low latency, low power stream processing AI
Domenik Helms, Mark Kettner, Behnam Razi Perjikolaei, Lukas Einhaus, Christopher Ringhofer, Gregor Schiele; European Workshop on On-Board Data Processing; June / 2021
2020
An Embedded CNN Implementation for On-Device ECG Analysis
Alwyn Burger, Chao Qian, Gregor Schiele, Domenik Helms; 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops); March / 2020
Modelling neural networks as SDFG representations for energy efficient hardware
Mark Kettner and Behnam Razi Perjikolaei and Wolfgang Nebel; 09 / 2020
Patent: LUTnet – Vorrichtung zur rechnergestützten Klassifikation von Sensordaten unter Verwendung einer trainierten neuronalen Netzstruktur (LUTnet - Device for computer-aided classification of sensor data using a trained neural network structure)
Domenik Helms, Gregor Schiele, Moritz Könnecke; 2020
