Master’s thesis “Cognitive network intelligence for energy-efficient and deterministic industrial communication”

Modern manufacturing environments increasingly integrate AI/ML-based inference workloads directly on the shop floor. The resulting communication loads traverse heterogeneous network infrastructures spanning 5G core, Industrial Wi-Fi (IEEE 802.11ax/be), and IEEE 802.1 TSN each with distinct determinism, reliability, and energy characteristics. Existing network management systems for industrial environments are designed primarily for determinism, resilience, and interoperability, in particular for seamless integration across Ethernet/TSN infrastructures. Energy efficiency and greenness metrics such as CO₂ footprint, energy cost models, or Power Usage Effectiveness at the network level are currently treated at best as secondary optimization objectives, not as functional requirements of the network architecture itself.

This prioritization is becoming increasingly untenable. Regulatory requirements (EU Energy Efficiency Directive, Corporate Sustainability Reporting Directive), rising energy costs in industrial production, and the growing energy demands of AI/ML inference workloads require that energy measurement and modeling be integrated into network management as a first-class functional requirement — not as an add-on. No integrated, architecture-spanning solution currently exists that simultaneously addresses determinism, Ethernet/TSN interoperability, and energy observability.

The thesis contributes to a cognitive network management layer, which dynamically and energy-efficiently distributes application workloads including compute-intensive applications such as large language models and AI inference across the three-layer industrial communication infrastructure. The central challenge is energy-aware traffic engineering that coordinates transmission paths and resources across domains so as to minimize energy consumption, CO₂ footprint, and network operating costs without violating deterministic latency and jitter guarantees, Ethernet/TSN interoperability, or resilience requirements.

Your tasks:

Survey and analyse energy modelling and greenness metric approaches for heterogeneous industrial network components that can be integrated into the ns-3 DetNetWiFi framework and design a consistent, domain-spanning energy measurement and modelling framework as the functional foundation of the cognitive management layer.
Design and implement a reinforcement learning or graph-based optimisation agent for energy-aware traffic engineering across the 5G/TSN/Wi-Fi DetnetWiFi continuum, jointly optimising energy consumption, CO₂ footprint, and QoS constraints including bounded latency, jitter, and fault tolerance.
Address, investigate, and implement selected domain-specific optimisation targets such as UPF placement and greenness reporting at the 5G core level; GCL schedule optimisation (IEEE 802.1Qbv) and energy-aware stream scheduling at the TSN backbone level; adaptive transmit power, sleep scheduling, and power-state management at the Wi-Fi edge level.
Evaluate the proposed framework with ns3-48 DetNetiWiFi, measuring energy savings, CO₂ reduction, latency compliance, and resilience under varying workload and topology conditions.

__________

Your profile:

Master student in Computer Science, Electrical Engineering, Communications Engineering, or a related field.
Background in wireless communications and/or industrial networking is a plus.
Practical programming experience in Python, C/C++, or similar.
Familiarity with network simulation or emulation tools, preferably ns-3.
Strong analytical skills and interest in real-time systems and network optimization.
Excellent communication skills in English; German is a plus.

Our offer:

An exciting and innovative open research environment within a nationally funded R&D project.
Direct collaboration with industrial partners (Deutsche Telekom, Siemens) and academic research groups.
International, dynamic work environment with highly qualified and motivated colleagues.
Opportunity to contribute to IEEE/3GPP standardization and publish research results.
Note: this master thesis position is not remunerated.

Have we piqued your interest?

If so, please submit your application, including a cover letter, a detailed resume, and a recent transcript.

Job ID: IIoT-MSC-01-2026
Contact: Prof. Dr. Rute Sofia personal@fortiss.org