This paper studies the problem of decentralized control design for thermal control in buildings, to achieve a satisfactory trade-off between underlying performance and robustness objectives. An output-feedback, model predictive framework is used for decentralized control which is based on a reduced order system representation. It entails the use of decentralized extended state observers to address the issue of unavailability of all states and disturbances. The decision on control architecture selection is based on an agglomerative clustering methodology developed previously [22]. The potential use of the proposed control design methodology is demonstrated in simulation on a multi-zone building, which quantifies the tradeoffs in performance and robustness with respect to the degree of decentralization. (C) 2014 Elsevier Ltd. All rights reserved.