This article proposes a self-managing architecture for multi-HVAC systems in buildings, based on the ''Autonomous Cycle of Data Analysis Tasks'' concept. A multi-HVAC system can be plainly seen as a set of HVAC subsystems, made up of heat pumps, chillers, cooling towers or boilers, among others. Our approach is used for improving the energy consumption, as well as to maintain the indoor comfort, and maximize the equipment performance, by means of identifying and selecting of a possible multi-HVAC system operational mode. The multi-HVAC system operational modes are the different combinations of the HVAC subsystems. The proposed architecture relies on a set of data analysis tasks that exploit the data gathered from the system and the environment to autonomously manage the multi-HVAC system. Some of these tasks analyze the data to obtain the optimal operational mode in a given moment, while others control the active HVAC subsystems. The proposed model is based on standard standard HVAC mathematical models, that are adapted on the fly to the contextual data sensed from the environment. Finally, two case studies, one with heterogeneous and another with homogeneous HVAC equipment, show the generality of the proposed autonomous management architecture for multi-HVAC systems.

Most of the studies about control, automation, optimization and supervision of building HVAC systems are about the steady-state regime, i.e. when the equipment is already working on their setpoints. In this work, it is defined an approach for multi-HVAC systems to reach the setpoint at the startup, so that other steady statebased strategies can smoothly come into operation to control and supervise their operations. The proposed approach for the management of the transient regime for multi-HVAC systems is based on the "Autonomic Cycle of Data Analysis Tasks" concept. In this case, it is composed of two data analysis tasks: one for determining if the system is going towards the defined operational setpoint, and if it was not the case, another for reconfiguring the operational mode of the multi-HVAC system to redirect it. The proposal is proved in a real context that characterizes one multi-HVAC system and its operational setpoints. The performance obtained from the experiments in diverse situations is encouraging, since they show how this approach leads the multi-HVAC system to reach the setpoint optimizing contradictory objectives, such as to attain the desired comfort, or reduce the energy costs, among others.

Buildings consume a considerable amount of electrical energy, the Heating, Ventilation, and Air Conditioning (HVAC) system being the most demanding. Saving energy and maintaining comfort still challenge scientists as they conflict. The control of HVAC systems can be improved by modeling their behavior, which is nonlinear, complex, and dynamic and works in uncertain contexts. Scientific literature shows that Soft Computing techniques require fewer computing resources but at the expense of some controlled accuracy loss. Metaheuristics-search-based algorithms show positive results, although further research will be necessary to resolve new challenging multi-objective optimization problems. This article compares the performance of selected genetic and swarm-intelligence-based algorithms with the aim of discerning their capabilities in the field of smart buildings. MOGA, NSGA-II/III, OMOPSO, SMPSO, and Random Search, as benchmarking, are compared in hypervolume, generational distance, ε-indicator, and execution time. Real data from the Building Management System of Teatro Real de Madrid have been used to train a data model used for the multiple objective calculations. The novelty brought by the analysis of the different proposed dynamic optimization algorithms in the transient time of an HVAC system also includes the addition, to the conventional optimization objectives of comfort and energy efficiency, of the coefficient of performance, and of the rate of change in ambient temperature, aiming to extend the equipment lifecycle and minimize the overshooting effect when passing to the steady state. The optimization works impressively well in energy savings, although the results must be balanced with other real considerations, such as realistic constraints on chillers’ operational capacity. The intuitive visualization of the performance of the two families of algorithms in a real multi-HVAC system increases the novelty of this proposal.