Control in HVAC (heating, ventilation and air-conditioning) systems of buildings is not trivial, and its design is considered challenging due to the complexity in the analysis of the dynamics of its nonlinear characteristics for the identification of its mathematical model. HVAC systems are complex since they consist of several elements, such as heat pumps, chillers, valves, heating/cooling coils, boilers, air-handling units, fans, liquid/air distribution systems, and thermal storage systems. This article proposes the application of LAMDA (learning algorithm for multivariable data analysis) for advanced control in HVAC systems for buildings. LAMDA addresses the control problem using a fuzzy classification approach without requiring a mathematical model of the plant/system. The method determines the degree of adequacy of a system for every class and subsequently determines its similarity degree, and it is used to identify the functional state or class of the system. Then, based on a novel inference method that has been added to LAMDA, a control action is computed that brings the system to a zero-error state. The LAMDA controller performance is analyzed via evaluation on a regulation problem of an HVAC system of a building, and it is compared with other similar approaches. According to the results, our method performs impressively in these systems, thereby leading to a trustable model for the implementation of improved building management systems. The LAMDA control performs very well for disturbances by proposing control actions that are not abrupt, and it outperforms the compared approaches.

This article proposes a self-management architecture for multi-HVAC systems in buildings, based on the Autonomous Cycle of Data Analysis Tasks. A multi-HVAC system can be plainly seen as a set of HVAC systems, with elements such as heat pumps, chillers, cooling towers or boilers. Our approach is used for improving the energy consumption and some other objectives in a given context, like indoor comfort or equipment performance, which requires the determination or selection of the current functional mode of the multi-HVAC system, i.e. possible combinations of the HVAC subsystems, for a given context. In the proposed architecture, a set of analysis tasks exploits the data obtained from the environment to an autonomously manage the multi-HVAC system. Some of these tasks compute the optimal operational mode in a given moment, while others control the multi-HVAC system activating in in a given moment accordingly. The proposed model is based on a classical HVAC mathematical formulation, adapting in real time its behavior with contextual data sensed from the environment. Finally, to show the generality of our approach, this article applies the multi-HVAC system autonomous management architecture in two case studies, one with heterogeneous and another with homogeneous HVAC installations.

Currently, population growth is global and tends to concentrate in large cities, which increases the demand for illuminating public spaces for safety, visual orientation, aesthetic considerations, and quality of life. The undesirable side effects are increase in energy consumption and light pollution. The current tools used for designing public lighting systems are not suitable for optimizing multiple objectives in addition to energy savings, and these solutions could provide for a more sustainable environment. The application of evolutionary optimization techniques seems to be growing rapidly because of the nonlinearity of the model behavior and the nonproprietary nature of the algorithms, which are considered as black box systems . This paper develops a data model for these types of optimizers, analyzing the ability of different artificial neural network (ANN) architectures to simulate a simple public lighting design by measuring the performance with respect to the fitness function, training speed, and goodness of fit with a dataset generated with different conditions. The architectures selected in this paper are those with multilayer perceptrons (MLPs) with different hidden layer configurations using different numbers of neurons in each layer, which have been analyzed to determine the configuration that best fits the purpose of this work. The data for training the ANNs were generated with a recognized open-software platform, DIALux. The experiments were repeated and analyzed to determine the variance of the results obtained. In this way, it was possible to identify the most appropriate number of iterations required. The results show that better precision is obtained when using the Levenberg–Marquardt training algorithm, especially when the ANN architecture has fewer neurons in the hidden layer.

Early fault detection and diagnosis in heating, ventilation and air conditioning (HVAC) systems may reduce the damage of equipment, improving the reliability and safety of smart buildings, generating social and economic benefits. Data models for fault detection and diagnosis are increasingly used for extracting knowledge in the supervisory tasks. This article proposes an autonomic cycle of data analysis tasks (ACODAT) for the supervision of the building’s HVAC systems. Data analysis tasks incorporate data mining models for extracting knowledge from the system monitoring, analyzing abnormal situations and automatically identifying and taking corrective actions. This article shows a case study of a real building’s HVAC system, for the supervision with our ACODAT, where the HVAC subsystems have been installed over the years, providing a good example of a heterogeneous facility. The proposed supervisory functionality of the HVAC system is capable of detecting deviations, such as faults or gradual increment of energy consumption in similar working conditions. The case study shows this capability of the supervisory autonomic cycle, usually a key objective for smart buildings.

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.

This research addresses the problem of detecting acute respiratory, urinary tract, and other infectious diseases in elderly nursing home residents using machine learning algorithms. The study analyzes data extracted from multiple vital signs and other contextual information for diagnostic purposes. The daily data collection process encounters sampling constraints due to weekends, holidays, shift changes, staff turnover, and equipment breakdowns, resulting in numerous nulls, repeated readings, outliers, and meaningless values. The short time series generated also pose a challenge to analysis, preventing the extraction of seasonal information or consistent trends. Blind data collection results in most of the data coming from periods when residents are healthy, resulting in excessively imbalanced data. This study proposes a data cleaning process and then builds a mechanism that reproduces the basal activity of the residents to improve the classification of the disease. The results show that the proposed basal module-assisted machine learning techniques allow anticipating diagnostics 2, 3 or 4 days before doctors decide to start treatment with antibiotics, achieving a performance measured by the area-under-the-curve metric of 0.857. The contributions of this work are: (1) a new data cleaning process; (2) the analysis of contextual information to improve data quality; (3) the generation of a baseline measure for relative comparison; and (4) the use of either binary (disease/no disease) or multiclass classification, differentiating among types of infections and showing the advantages of multiclass versus binary classification. From a medical point of view, the anticipated detection of infectious diseases in institutionalized individuals is brand new.