The prevalence of extensive glazed areas in contemporary buildings contributes significantly to solar radiation infiltration, elevating energy demands and causing discomfort for occupants. Window shading devices play a pivotal role in addressing this challenge. This paper presents the development and optimization of an artificial neural network (ANN) predictive model, designed to enable real-time control of slat angles by predicting total energy loads, specifically during summer (for cooling and lighting purposes). The refined model demonstrates high precision, achieving a normalized root mean square error (nRMSE) of approximately 1.72% and a correlation coefficient (R) of around 0.999, despite utilizing limited meteorological data. Key inputs for the model include solar radiation, solar altitude, and external temperature, with a particular focus on slat reflectivity. The study assesses the efficiency of three slat types based on their reflectivity: high (80%), medium (50%), and low (20%). Additionally, the research explores the impact of window-to-wall ratio (WWR) values on the control system's efficacy, revealing a positive correlation between higher WWR values and improved energy savings through ANN slat angle control. Furthermore, the study extends the applicability of the ANN model to the six thermal zones in Morocco, affirming its generalization across diverse environmental conditions.
In this work, we present a parametric study of a new administrative building, located in El-Ksar El Kebir region (Morocco). In order to have a building that complies with the RTCM in a technically and economically sound manner, we have carried out a number of interventions to insulate the components of the building, namely external walls, exposed roofs and openings. In this perspective, we have modelled the building envelope as a multi-zone building in TRNSYS and we have adopted an occupation scenario for this type of building. After determining the optimal insulation solutions, we simulated the administrative building in the five other thermal zones, to determine its feasibility in the latter.