School of Engineering

Staff Profile

Dr Mehdi Pazhoohesh

Research Associate

Background

He has a background in the field of building energy and human comfort science and currently works as research associate within the National Center for Energy System Integration (CESI) at Newcastle University. Most recent duties involved deploying machine learning and Artificial Intelligence techniques to deal with partial data sets and missing data imputation under big data analytics of building energy. 

Research

Current projects: 

Active Building Centre

http://www.activebuildingcentre.com

The £36m Active Building Centre project will investigate the potential for large scale role out of domestic active buildings for the new build sector. Researchers at Newcastle University shall investigate the impact of active buildings on the energy networks, smart control of building elements, and the role of electric vehicles. Overall, energy demand, generation, storage and transport combine to enable the active building to be controlled to offer services to local networks, as well as ensuring energy services to the building occupant. 

Building as a Power Plant

This project will investigate the feasibility of the Urban Sciences Building (Newcastle University) to offer services to the local network. The building is an interesting case study since it includes electricity generation, storage and demand, and thermal generation, storage and demand.


Previous projects:

Co-Investigator for occupancy-driven intelligent control of HVAC system for saving energy and enhancing thermal comfort 

Research Institute for Smart and Green Cities (RISGC)                               

This project aims to propose an intelligent control of the HVAC system to meet the requirements in terms of energy saving and thermal comfort at the same time. Algorithms will be proposed to analyse individual’s thermal preferences, behaviour patterns, and real-time locations and to predict the presence situation in the target room. Thermal preference of individuals will be investigated using computational fluid dynamics simulation and a survey corresponding to different scenarios. Historical behaviour data of the occupants will be collected, including daily schedule, arriving and leaving time, short-term and long-term leaves. Those data will be used to train the proposed algorithm and to predict the occupants’ absent/present status in the room in real time, which will decide the mode change of HVAC outlets based on the presented occupants' thermal preferences.