BACHELOR / MASTER THESIS - MAPPING CLOUD SCHEDULING AND OPTIMIZATION ALGORITHMS TO CUSTOMER ENERGY MANAGEMENT (CEM) SYSTEMS (M/F/D)
München, DEWer sind wir?
- Conduct an in-depth literature review on scheduling and optimization algorithms in cloud computing (and CEM systems).
- Categorize different scheduling approaches based on optimization objectives (e.g., cost, response time, flexibility or deterministic, metaheuristic, machine learning).
- Investigate the application of AI and ML techniques in scheduling for both cloud (and energy systems).
- Map at least two cloud scheduling schemes to CEM systems, identifying synergies and limitations.
- Develop a conceptual framework for adapting cloud-based scheduling to CEM.
- Implement and evaluate a selected scheduling approach in the CommonPower simulation framework.
Your tasks:
- Identify and compare relevant scheduling and optimization algorithms from both cloud computing and energy management domains.
- Categorize techniques by objectives such as latency, energy efficiency, cost, and adaptability.
- Analyze the contribution of AI and ML techniques in enhancing scheduling performance--especially in cloud computing contexts.
- Select a representative scheduling algorithm from the cloud domain.
- Map it to CEM requirements and constraints (e.g., household-level energy consumption, DER coordination).
- Define hierarchical scheduling structures where applicable (e.g., local vs. community-level coordination).
- Implement the adapted algorithm using the CommonPower simulation framework.
- Simulate different scenarios to evaluate effectiveness, scalability, and potential benefits for CEM systems.
Your profile:
Our offer:
- Get involved with novel and exciting solutions in the context of Energy Management System and Software Defined Solutions, and in alignment with industrial partners.
- An international and dynamic work environment with highly qualified and motivated colleagues.
