Model predictive control of non-domestic heating using genetic programming dynamic models

• Published in: Applied soft computing Vol. 97; p. 106695
• Main Authors: Dou, Tiantian, Kaszubowski Lopes, Yuri, Rockett, Peter, Hathway, Elizabeth A., Saber, Esmail
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2020
• Subjects: Building energy management; Dynamic non-linear system identification; Genetic programming; Model predictive control; Model predictive control; Dynamic non-linear system identification; Building energy management; Genetic programming
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2020.106695

We present a novel approach to obtaining dynamic nonlinear models using genetic programming (GP) for the model predictive control (MPC) of the indoor temperatures of buildings. Currently, the large-scale adoption of MPC in buildings is economically unviable due to the time and cost involved in the design and tuning of predictive models by expert control engineers. We show that GP is able to automate this process, and have performed open-loop system identification over the data produced by an industry grade building simulator. The simulated building was subject to an amplitude modulated pseudo-random binary sequence (APRBS), which allows the collected data to be sufficiently informative to capture the underlying system dynamics under relevant operating conditions. In this initial report, we detail how we employed GP to construct the predictive model for MPC for heating a single-zone building in simulation, and report results of using this model for controlling the internal environmental conditions of the simulated single-zone building. We conclude that GP shows great promise for producing models that allow the MPC of building to achieve the desired temperature band in a single zone space. •Model Predictive Control (MPC) of the internal temperature in a simulated building.•MPC employs a dynamical model obtained using Genetic Programming (GP).•Dynamical model trained automatically using simulated building data.•Automatic training of dynamical models enhances economic viability and adoption.