All news


Posted in: News

Our partners Iago Cupeiro Figueroa, Damien Picard and Lieve Helsen from KU Leuven's recent Paper

Short-term modeling of hybrid geothermal systems for Model Predictive Control

Is available open source for download and reading...


• A simulation study assesses the impact of COP formulation and borefield controller model for model predictive control of a hybrid geothermal system.
• Using an accurate COP formulation presents a smoother and more efficient heat pump behaviour.
• Including a borefield controller model avoids hitting the heat pump safety freezing constraints, improving robustness.
• Despite reducing the number of iterations in the optimisation, the simulation time is increased, however still feasible.

Can download here

And also access it from our Publications page on this website




Model Predictive Control (MPC) has shown significant energy savings potential in the operation of building energy systems, yet it needs accurate and simple models for optimization. In hybrid geothermal systems the source-side temperatures affect the system efficiency and its operational feasibility. Since the ground dynamics are rather slow, simplifications such as considering a constant coefficient of performance (COP) are made. We evaluate the added value of including a short-term dynamic borefield model to the controller. Simulations are performed in a heating-dominated building equipped with a hybrid geothermal system for two winter weeks. We consider 4 different modeling strategies where the formulation of the COP and the return fluid temperature from the borefield is varied in complexity. Results show that using a constant COP results in a bang-bang behavior of the heat pump, while with an accurate prediction of the COP the operation is smoother, saving 0.46%, 1.86% and 2.71% for low, average and high electricity-to-gas price ratios respectively. Including a short-term borefield model avoids shutting down the heat pump due to safety constraints which saves up to 8.12% more money while the use of the ground-source is quintupled. Despite reducing the optimization iteration number by almost 18%, simulation time is increased.