Valentin Mihai Radu

Dr. Valentin Mihai Radu

avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 November 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
VVVasilica Vasile
Vasilica Vasile
VIVlad IORDACHE
Vlad IORDACHE
VRValentin Mihai Radu
Valentin Mihai Radu
Cristian PetcuCristian Petcu
Cristian Petcu
CDClaudiu-Sorin Dragomir
Claudiu-Sorin Dragomir
Indoor air quality (IAQ) and energy consumption (Q) are well-known building estimators, but they are used separately. Energy consumption is used during the design stage, while IAQ is used during operation. The novelty of our approach is that we propose using both estimators simultaneously during building operations. The purpose of this study was to find an adaptive ventilation strategy that maintained good indoor air quality with minimal energy consumption. The second novelty of our approach consists of IAQ estimation. While the operation of ventilation systems depends only on the indoor carbon dioxide (CO2) concentration at present, our novel approach uses a more global IAQ index that includes four different air pollutants. Physical models are used for the hourly prediction of the two indices: global IAQ and Q. This study presents a comparative analysis of several ventilation operations strategies: fixed versus adaptive. The main findings show that a decrease in the ventilation rate, na, from 3.5 h−1 to 2.0 h−1 leads to a diminishment in energy consumption of 42.9%, maintaining the global IAQ index under the limited health risk value (VRL). Moreover, an adaptive ventilation strategy of na, maintaining the global IAQ index value under VRL, achieves a further reduction in energy consumption of 72.9%, highlighting its efficiency.
3 April 2024 in Atmosphere
Verified
Journal Article
Open access
PDF file
VVVasilica Vasile
Vasilica Vasile
VIVlad IORDACHE
Vlad IORDACHE
VRValentin Mihai Radu
Valentin Mihai Radu
CDClaudiu-Sorin Dragomir
Claudiu-Sorin Dragomir
Nowadays, indoor air quality (IAQ) and the energy performance of buildings are two main scientific and technical challenges because they are in direct connection with human health and the depletion of energy resources. In this study, we analyzed the influence of an outdoor air flow introduced through a mechanical ventilation system, focusing on the two aforementioned topics. A standardized ventilation rate (25 m3/h/person) led to an increase in the indoor O3 concentration (from 5 μg/m3 to 50 μg/m3) and, simultaneously, to a decrease in the indoor CO2 concentration (from 2000 mg/m3 to 800 mg/m3), a decrease in the PM2.5 concentration (from 300 μg/m3 to 150 μg/m3), and the maintenance of a constant indoor HCHO concentration. In our study, a new, single indoor air quality index, IIAQ, is proposed. This new index presents different implications: on the one hand, it has the ability to simultaneously take into account several pollutant species, and on the other hand, it can prioritize the ventilation strategy that responds to the extreme values of a certain pollutant. Moreover, indoor air quality classes were elaborated, similar to energy classes. The possibility of using this new index simultaneously with energy consumption may lead to ventilation strategies that are adaptative to dynamic outdoor pollutant concentrations.
1 September 2026 in Modelling in Civil Environmental Engineering
Verified
Journal Article
Open access
PDF file
VRValentin Mihai Radu
Valentin Mihai Radu
In the contemporary built environment, ensuring optimal Indoor Air Quality (IAQ) while maintaining energy efficiency represents a multifaceted challenge for building management systems (BMS). Traditional ventilation strategies are predominantly reactive, adjusting air exchange rates only after pollutant concentrations exceed established safety thresholds. This reactive latency, or “phase lag,” often results in temporary exposure to high pollutant levels and suboptimal energy utilization. This study proposes a proactive “feed-forward” control framework based on pollutant forecasting. We conduct a rigorous comparative analysis of three distinct modeling paradigms: Long Short-Term Memory (LSTM) neural networks, Random Forest (RF) ensembles, and Autoregressive Integrated Moving Average (ARIMA) models. The models were trained and validated using a comprehensive 1-year office environmental dataset from Kaggle, encompassing CO 2 , PM 2.5 temperature, and humidity. Our findings demonstrate that for CO 2 forecasting, both LSTM and RF architectures achieve high predictive accuracy (R 2 > 0.97) and successfully eliminate the reactive phase lag. For PM 2.5 , the stochastic nature of indoor particulate events presents a significant challenge, with the LSTM exhibiting a “conservative smoothing” effect and occasional mathematical artifacts such as negative values.