Data-Driven Living Spaces’ Heating Dynamics Modeling in Smart Buildings using Machine Learning-Based Identification

Abstract

Modeling and control of the heating feature of living spaces remain challenging tasks because of the intrinsic nonlinear nature of the involved processes as well as the strong nonlinearity of the entailed dynamic parameters in those processes. Although nowadays, adaptive heating controllers represent a crucial need for smart building energy management systems (SBEMS) as well as an appealing perspective for their effectiveness in optimizing energy efficiency, unfortunately, the leakage of models competent in handling the complexity of real living spaces’ heating processes means the control strategies implemented in most SBEMSs are still conventional. Within this context and by considering that the living space’s occupation rate (i.e., by users or residents) may affect the model and the issued heating control strategy of the concerned living space, we have investigated the design and implementation of a data-driven machine learning-based identification of the building’s living space dynamic heating conduct, taking into account the occupancy (by the residents) of the heated space. In fact, the proposed modeling strategy takes advantage, on the one hand, of the forecasting capacity of the time-series of the nonlinear autoregressive exogenous (NARX) model, and on the other hand, from the multi-layer perceptron’s (MLP) learning and generalization skills. The proposed approach has been implemented and applied for modeling the dynamic heating conduct of a real five-floor building’s living spaces located at Senart Campus of University Paris-Est Créteil (UPEC), taking into account their occupancy (by users of this public building). The obtained results assessing the accuracy and addictiveness of the investigated hybrid machine learning-based approach are reported and discussed.

A Heating Controller Designing Based on Living Space Heating Dynamic’s Model Approach in a Smart Building

“…Before introducing the fuzzy controller architecture design for the dynamics of heating spaces, we will review the modeling of heating dynamics of living spaces, which was done in our last paper [6].…”

“…Within this context, and regarding our previous work about the identification of the heating dynamic model of living spaces by a data-driven machine learning approach, taking into account the thermodynamical influence of occupations (by users or residents) [6], we investigated the design, implementation, and validation of a heating controller by the fuzzy inference system.…”

“…In the second part of this article, the implementation of living spaces regarding the heating system in the Senart Campus of Université Paris Est Créteil is introduced. In the third part, the modeling of the heating dynamic of living spaces, which is completely discussed in our previous work [6], is highlighted. In the fourth, fifth, and sixth parts, respectively, the structure of the heating control chain, construction of the knowledge-based part of the Fuzzy controller, plus the simulation and evaluation of the proposed approach based on a neuro-fuzzy structure (modeling of living spaces and the heating controller) is presented.…”

“…In other words, the identified heating slope is a function of the occupants and valve position of the heating device (ℎ ( ) = ( ( ), )), and the indoor temperature can be estimated by the identified heating slope (the identified value of ℎ( )). With regards to the mentioned formulation, the approach for the modeling of a living space dynamic by considering the effect of occupants is presented in [6].…”

Privacy-Preserving Sensing and Two-Stage Building Occupancy Prediction using Random Forest Learning

“…Data-driven building models are described in [21] which can be suitable to incorporate occupancy models as constraints to [18] the optimization problem. A significant body of experimental data is provided by [22] allowing off-line training of quality occupancy models.…”