arXiv subjects

Hicham Johra

Publications and source records attributed to Hicham Johra.

2 recordsLinked to original sources

arXiv2023

Outdoor micro-climate: Air temperature measurements around an office building in Denmark during summer

The outdoor micro-climate caused by the presence of buildings can significantly differ from that around weather stations located outside of urban areas. However, the latter is often used to design buildings and size building systems. This could lead to significant mistakes and performance gaps. To date, there is a certain lack of experimental studies assessing the micro-climate around buildings, especially in Scandinavian countries. The current paper presents the preliminary results and analysis of a measurement campaign of the temperature gradient in the two-meter air layer around the envelope of a multi-storey office building in Denmark in the summertime. Depending on the orientation of the external building surface (South/North façade or rooftop), the distance from the latter and the weather conditions, the temperature in this two-meter air layer can vary significantly and differ from the air temperature measured at nearby open fields or recorded by the reference weather station. During sunny days, a temperature gradient of up to 3.4 °C and 13.6 °C was measured in the air layer around the South façade and the rooftop, respectively. These results could help to validate urban climate models and bridge the gap between building design and real-condition performance. The curated dataset of this measurement campaign is available in open access.

physics.ao-ph↗

arXiv2023

Predicting the performance of hybrid ventilation in buildings using a multivariate attention-based biLSTM Encoder-Decoder neural network

Hybrid ventilation is an energy-efficient solution to provide fresh air for most climates, given that it has a reliable control system. To operate such systems optimally, a high-fidelity control-oriented modesl is required. It should enable near-real time forecast of the indoor air temperature based on operational conditions such as window opening and HVAC operating schedules. However, physics-based control-oriented models (i.e., white-box models) are labour-intensive and computationally expensive. Alternatively, black-box models based on artificial neural networks can be trained to be good estimators for building dynamics. This paper investigates the capabilities of a deep neural network (DNN), which is a multivariate multi-head attention-based long short-term memory (LSTM) encoder-decoder neural network, to predict indoor air temperature when windows are opened or closed. Training and test data are generated from a detailed multi-zone office building model (EnergyPlus). Pseudo-random signals are used for the indoor air temperature setpoints and window opening instances. The results indicate that the DNN is able to accurately predict the indoor air temperature of five zones whenever windows are opened or closed. The prediction error plateaus after the 24th step ahead prediction (6 hr ahead prediction).

cs.LG↗