Dr. Farrokh Jazizadeh of Virginia Tech visited the School of Civil Engineering
On November
9, 2018, Dr. Farrokh Jazizadeh of Virginia Tech visited the School of Civil
Engineering, Tsinghua University, and gave a presentation titled "Human-Centered
Adaptive Energy Management in Built Environment". The session was attended
by Prof. Dongping Fang, Prof. Nan Li, Prof. Xiaomei Deng, and postgraduates
from School of Civil Engineering of Tsinghua University, as well as Prof. Hongqin
Fan, Prof. Geoffrey Shen, and their post-graduates from Hongkong Polytechnic
University.
Throughout
the construction lifecycle, Dr. Jazizadeh pointed out that the operation of
building contributes to a comparatively higher energy consumption and carbon
emission. Therefore, energy management in building operation plays an important
role in energy sustainability efforts. With the goal of meeting occupant
comfort and reduced building energy consumption, Dr. Jazizadeh first introduced
multi-agent comfort and energy system (MACES) to model alternative management
and control of building systems and occupants by using multi-objective Markov
Decision Problems (MDP). MACES allows to model the actual input including
thermal zones, temperature, occupant preferences, and occupant schedules, enable
an improvement in occupant comfort and energy consumption reduction.
In the
second part of the lecture, Dr. Jazizadeh proposed an intermediary
communication plat which enables human-buildings two-way communication. He
introduced an evaluation framework that integrates occupants’ personalized
thermal (comfort) profiles, using a fuzzy predictive model, and controls the
HVAC system using a complementary control strategy, which enables the framework
to be implemented in existing centrally controlled HVAC system with minimum
intrusion. In addition, Dr. Jazizadeh used a series of different sensors,
combined with subjective evaluation and objective physiological indicators, to
determine occupant’s comfort level. He presented a vision-based approach that
employs RGB video images through webcams or smartphones to capture
thermoregulation states in the human body in response to indoor thermal
condition. By using photoplethysmography (PPG), the study leveraged the
mechanism of blood flow control to the skin surface (blood vessels’ dilation
and constriction) for heat dissipation regulations, reflected in PPG signal’s
amplitude. Then, a non-linear model is established and an algorithm is
developed to make efficient thermal comfort quantification for HVAC control.