lighting aspects is carried out. The goal of this procedure is to provide reasonable starting
values for the parameters of the different adaptive models used by the controllers. It
concerns the RI model, the electric lighting model and the blinds controller. This
commissioning is only run when the global irradiance is higher than 50 W/m2.
The procedure is described more in details in the PhD thesis of Antoine Guillemin.
No commissioning is carried out regarding the heating, because a correct adjustment of
parameters needs data on several days (to deal with inertial aspects of room
characteristics) and these data are not always available.
3. Algorithm description Adaptation to user preferences with Genetic Algorithms
(to be completed !!!)
4. Experimental results
In a second phase, measurements have been done on the LESO experimental building,
involving 14 occupied office rooms (mostly with one or two persons in each room),
during 9 months. The monitoring results have proved the interest of the new user-
adaptive algorithms. These results can be summarized by the table below.
Controller type
Energy
savings
(base: manual)
Thermal
comfort
satisfaction
Visual
comfort
satisfaction
Rejection rate
after 4 weeks
Manual
-
84 %
86 %
-
automatic, without
adaptation to user's
preferences
-26 %
84 %
88 %
25 %
automatic, with adaptation to
user's preferences
-26 %
86 %
89 %
5 %
The table shows clearly that the significant energy savings due to the automatic controller
were not altered by the introduction of the adaptation to the user's preferences, and that at
the same time the rejection rate after 4 weeks was reduced considerably from 25 % to
only 5 %.
Summary :
Controller type Energy savings (base: manual) Thermal comfort satisfaction Visual comfort satisfaction Rejection rate after 4 weeks Manual - 84 % 86 % - automatic, without adaptation to user's preferences -26 % 84 % 88 % 25 % automatic, with adaptation to user's preferences -26 % 86 % 89 % 5 % The table shows clearly that the significant energy savings due to the automatic controller were not altered by the introduction of the adaptation to the user's preferences, and that at the same time the rejection rate after 4 weeks was reduced considerably from 25 % to only 5 %.
Tags :
adaptation,preferences,automatic,results,controller,users,out,room,manual,algorithms,user,saings,energy