Master Thesis: Model Predictive ControlBased Energy Management System (EMS) for an Office Building
With the increasing demand for residential comfort and the rising importance of energy cost optimization it is a major challenge to balance comfort economy and sustainable energy usage in residential buildings. Advanced energy management systems (EMS) provide a practical solution for achieving this goal.
This thesis will develop a Model Predictive Control (MPC)based EMS for a data-driven building model created using neural networks in MATLAB or Python. The building model will represent a modular office building including thermal zones a HVAC system a static heating system a cold water storage tank and an electric chiller for cooling. The MPC-based EMS will optimize pre-heating in winter and pre-cooling in summer taking into account electricity prices including the contribution of a photovoltaic (PV) system and the operation of thermal storage and cooling equipment.
Tasks:
- Development of a neural networkbased building model capable of predicting thermal dynamics for heating and cooling scenarios
- Design and implementation of a Model Predictive Controlbased EMS for Winter and Summer operations Considering:
- Pre-heating and pre-cooling strategies
- Cold water storage and electric chiller operation
- Static heating System
- HVAC System
- Dynamic electricity prices and PV generation
Qualification:
- Knowledge in energy system analysis building modeling and control
- Experience with MATLAB/Simulink or Python (essential for neural network modeling and MPC implementation)
- Knowledge in machine learning (neural networks) and predictive control concepts
- Mechanical Electrotechnical or Informatics background
Apply online via this platform or by email:
We offer individualized support from highly qualified and dedicated professionals within an innovative medium-sized company.
We look forward to receiving your application.
Master Thesis: Model Predictive ControlBased Energy Management System (EMS) for an Office BuildingWith the increasing demand for residential comfort and the rising importance of energy cost optimization it is a major challenge to balance comfort economy and sustainable energy usage in residential bu...
Master Thesis: Model Predictive ControlBased Energy Management System (EMS) for an Office Building
With the increasing demand for residential comfort and the rising importance of energy cost optimization it is a major challenge to balance comfort economy and sustainable energy usage in residential buildings. Advanced energy management systems (EMS) provide a practical solution for achieving this goal.
This thesis will develop a Model Predictive Control (MPC)based EMS for a data-driven building model created using neural networks in MATLAB or Python. The building model will represent a modular office building including thermal zones a HVAC system a static heating system a cold water storage tank and an electric chiller for cooling. The MPC-based EMS will optimize pre-heating in winter and pre-cooling in summer taking into account electricity prices including the contribution of a photovoltaic (PV) system and the operation of thermal storage and cooling equipment.
Tasks:
- Development of a neural networkbased building model capable of predicting thermal dynamics for heating and cooling scenarios
- Design and implementation of a Model Predictive Controlbased EMS for Winter and Summer operations Considering:
- Pre-heating and pre-cooling strategies
- Cold water storage and electric chiller operation
- Static heating System
- HVAC System
- Dynamic electricity prices and PV generation
Qualification:
- Knowledge in energy system analysis building modeling and control
- Experience with MATLAB/Simulink or Python (essential for neural network modeling and MPC implementation)
- Knowledge in machine learning (neural networks) and predictive control concepts
- Mechanical Electrotechnical or Informatics background
Apply online via this platform or by email:
We offer individualized support from highly qualified and dedicated professionals within an innovative medium-sized company.
We look forward to receiving your application.
View more
View less