News and Announcements
- August 16, 2026

Our article Efficient and Green Service Function Chain Deployment and Scheduling for Mobile Edge Computing has been accepted for publication in IEEE Transactions on Mobile Computing.
Service Function Chain (SFC) decomposes a user's overall service into multiple service components and links them in an orderly manner, providing more flexible, efficient, and responsive services for compute-intensive applications in mobile edge computing. Existing research primarily focuses on optimizing the deployment cost and system efficiency of SFC. However, the dynamic nature of user trajectories, along with the absence of adaptive scheduling and service component sharing in complex and heterogeneous environments, hinders existing approaches from achieving optimal resource efficiency. To achieve adaptive optimization of SFC deployment and efficient component sharing across multiple SFCs, we propose an SFC Deployment and Scheduling strategy based on the Soft Actor-Critic (SAC) algorithm, named SAC-DS. The proposed SAC-DS strategy first employs a Long Short-Term Memory (LSTM) model to predict user trajectories, thereby accurately forecasting future service demands. Based on these predictions, an SAC-based agent is trained to dynamically optimize SFC deployment and scheduling policies in real time. SAC-DS integrates SFC deployment, component sharing, and scheduling into a unified framework, effectively improving system throughput while minimizing overall deployment costs, thereby enhancing user experience. Compared with existing baseline methods, SAC-DS improves network throughput by 3.1%–18.1% and reduces average cost by 1.8%-10.0%.
(link to more information)
- August 04, 2026
Our team member Jorge Torres Gómez is leading a special issue for the IEEE Trans. On Molecular, Biological, and Multi-Scale Communications. As lead guest editor he is teaming with life science partners at Charité Universitätsmedizin and Michigan State University. The special issue is planned to publish contributions that demonstrate the creation of datasets for molecular communication scenarios.
- July 31, 2026

Our article Edge-assisted Video Object Detection with Adaptive Resource Allocation and Model Selection has been accepted for publication in IEEE Transactions on Mobile Computing.
With the rise of applications such as facial recognition and intelligent monitoring, demand for video object detection has surged. To optimize detection performance, existing works primarily focus on either video transmission or processing independently, often overlooking small object detection, which is particularly difficult for resource-limited terminals. To address these limitations, we propose a solution that leverages edge servers to assist video object detection, enabling real-time and high-precision performance under resource constraints. We introduce Adaptive-EVOD, the first edge-assisted video detection system that optimizes communication and computation simultaneously through adaptive resolution and frame rate adjustment, resource allocation, and model selection strategies, with a particular emphasis on small object detection. Specifically, Adaptive-EVOD introduces three core innovations: (1) proposing a detection strategy for small objects to enhance precision; (2) employing deep reinforcement learning to dynamically determine detection location, resolution, and frame rate based on heterogeneous environments; and (3) applying Bayesian optimization to dynamically allocate GPU resources and select Low-Rank Adaptation (LoRA) ranks for detection models adaptively.
(link to more information)
- July 30, 2026

On July 30 - 31, 2026, our TKNano group together with the Institute of Telematics of the Universität zu Lübeck organized an interdisciplinary workshop on Precision Medicine in the Era of the Internet of Bio-Nano Things.
At the MediaDocks in Lübeck, we discussed future in-body applications of molecular communication together with many colleagues from biomedical engineering, biology, and medicine. Saswati Pal and Jorge Torres Gomez presented our current research on ML-based cancer localization, smart drug-delivery systems, and future goals in our DFG project NaboCom III.
- July 27, 2026
Our proposal Machine Learning-based Wi-Fi Optimization 2 (ML4WiFi2) has been accepted for funding by the German research foundation DFG. In this project, we will explore learning-based approaches to optimize resource allocation in WiFi networks as well as the coexistence with legacy accesss points.
(link to more information)
- July 19, 2026

Our article Wi-Lo++: WiFi-to-LoRa Cross-Technology Communication with Multi-Packet Emulation has been accepted for publication in IEEE Internet of Things Journal.
This work presents Wi-Lo++, a WiFi-to-LoRa CTC mechanism. In contrast to existing WiFi-to-LoRa CTC approaches, it removes the constraint of the maximum packet length of WiFi and therefore can emulate LoRa transmissions with higher spreading factors (SFs). This is achieved by emulating a single LoRa frame through a train of consecutive IEEE 802.11b frames, each emulating only a part of the overall LoRa waveform while preserving symbol-level continuity across packet boundaries. In order to mitigate waveform distortions caused by the variety of immutable WiFi preambles and headers, we shift these distortions into less critical regions of the LoRa waveform. Using a second WiFi interface, these distortions can be further reduced further using overlapping WiFi frames.
(link to more information)
- July 03, 2026

Our member Doğanalp Ergenç presented a tutorial lecture on "IEEE 802.1 Time-Sensitive Networking Beyond Theory: Convergence, Resilience, and Practical Insights" at the 12th IEEE International Conference on Network Softwarization (NetSoft 2026), which was held in Berlin, Germany.
- July 03, 2026

Falko Dressler gave a keynote titled 6G Edge Computing: Improving Coverage and Resilience at the 5th IEEE International Workshop on Green and Sustainable Networking (GreenNet 2026), which was held in Berlin, Germany.
(link to more information)
- July 02, 2026

Elena Tonini received a Best Poster Award for our paper Delay-Doppler Domain Feature Extraction for Explainable Activity Recognition via SVM: Extending to IEEE 802.11be and mmWave Experimental Testbeds at the Mediterranean Artificial Intelligence and Networking (MAIN 2026), which was held in Palermo, Italy.
- June 29, 2026

Our team member Youming Tao received a Best Paper Award for our paper Distributed PAC Learning from Quantum Data with Efficient Communication at the 20th International Conference on Wireless Artificial Intelligent Computing Systems and Applications (WASA 2026), which was held in Xi’an, China.