Multi-structural fast nonlinear model-based predictive control of a hydronic heating system

Buildings consume a significant amount of energy to maintain the indoor thermal comfort. One way to reduce the energy consumption in buildings is to improve the overall energy efficiency through integrated advanced controls. It is undoubted that incorporating a model and utilizing future information in real-time building operation offers great energy saving potentials. However, there are many barriers preventing this from happening. Building systems are nonlinear and multiple-input-multiple-output (MIMO) in nature. Conventional approach with a global search solver and a detailed model simulator or direct nonlinear model predictive control (MPC) incurs prohibitive computational cost. This paper proposes a multi-structural fast nonlinear model predictive control (MPC) for handling nonlinear building systems and applied it on a hydronic heating system. The methodology remains the advantages of linear classical MPC and solves the nonlinearity issues involved in thermal comfort and energy conservation oriented control. The simulation shows that the controllers can achieve the optimal solutions in less than five minutes for five days simulation in a full look-ahead scenario with a Duo T6400 2.0 GHz computer. The fastest scenario takes only thirty more seconds to accomplish, which makes the approach feasible for online implementation. The techniques of using MPC for achieving smooth day-night switch, band control, dynamic constraints, and dynamic weighting are discussed. The energy saving potential of applying the proposed MPCs is found to be between six to forty two percent. In addition, the techniques decouple the building system from the mechanical system and are applicable to other space conditioning systems as well. (C) 2013 Elsevier Ltd. All rights reserved.