Data-Driven Predictive Control of Buildings; A Regression Based Approach

In this paper, we present a data-driven predictive control (DDPC) strategy suitable for (general bilinear) building energy systems, which only relies on historical measurements. The introduced control technique operates iteratively in a receding horizon scheme. During the operation of DDPC, using available historical building data which are collected during the normal operation of building, the dynamics of building are approximated and estimated. Therefore, the system dynamics are decomposed into two stable subsystems, one describing the thermal dynamics of the mass of building and the other one describing the dynamics of the temperature of rooms leading to a linear infinite-dimensional interconnected system. Linear regression is used to estimate a finite approximation thereof. Employing the approximate model, a cost is minimized in each iteration. The performance of the introduced data-driven control method is numerically verified for a validated building simulation environment.

[1]  António E. Ruano,et al.  Neural networks based predictive control for thermal comfort and energy savings in public buildings , 2012 .

[2]  Kaamran Raahemifar,et al.  Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system , 2017 .

[3]  Nuria Forcada,et al.  Implementation of predictive control in a commercial building energy management system using neural networks , 2017 .

[4]  Dario Ambrosini,et al.  Data-driven model predictive control using random forests for building energy optimization and climate control , 2018, Applied Energy.

[5]  Constantinos A. Balaras,et al.  Heating energy consumption and resulting environmental impact of European apartment buildings , 2005 .

[6]  Manfred Morari,et al.  Use of model predictive control and weather forecasts for energy efficient building climate control , 2012 .

[7]  Manfred Morari,et al.  Model Predictive Climate Control of a Swiss Office Building: Implementation, Results, and Cost–Benefit Analysis , 2016, IEEE Transactions on Control Systems Technology.

[8]  Paul T. Boggs,et al.  Sequential Quadratic Programming , 1995, Acta Numerica.

[9]  Eva Žáčeková,et al.  Towards the real-life implementation of MPC for an office building: Identification issues , 2014 .

[10]  Lennart Ljung,et al.  Kernel methods in system identification, machine learning and function estimation: A survey , 2014, Autom..

[11]  Roy S. Smith,et al.  Frequency-Domain Identification of a Ventilated Room for Model Based Control , 2014 .

[12]  David Sturzenegger,et al.  Model predictive building climate control - steps towards practice , 2014 .