Page 17 - 251119_BJ_ME-Journal_14_digital
P. 17
Technology
Precautionary maintenance and optimized It must also be ensured that a BMS can
servicing: analysis of failure probability, also control room and system automation.
timely maintenance and consequential In many cases, the specific behavior of, for
avoidance of technical failures. example, room-side bus systems and system-
Employee-oriented value-added services: side controllers is hard-coded and cannot be
mobile devices can – for instance – be used influenced by the BMS. This ability to influence
to generate space utilization forecasts, view must be guaranteed, which means that all
canteen usage intensity, request parking controllers and systems must be connected
space availability and preferred workspace to each other for communication purposes.
location or select individual meals. This requires a powerful and standardized
Compensation of skilled-staff shortages: TCP/IP-based protocol, with BACnet/IP and
making effective use of facility maintenance BACnet/SC being particularly suitable options.
staff in managing the building’s technical
systems. In addition, it must be taken into account that the
Focus on meaningful sensor data: generate AI platform requires as much data as possible
as much data as possible from as few from a wide variety of sensors for effective
sensors as possible – reducing redundancy, operation. Wiring the required number of sensors
cutting investment and operating costs. would be very complex and expensive, especially
in an existing building. Radio-based sensors are
Demands upon System Architecture a good solution here, ideally battery-free and
maintenance-free energy harvesting sensors
An AI platform is indispensable for the such as those with EnOcean technology.
introduction of intelligent learning processes
such as those described above. This can be All of this information can then be used to
either cloud-based or server-based. Cloud- create cloud-based digital twins and further
based server farms offer more processing improve the monitoring of activities, the working
power, and cloud-based AI frameworks offer environment, augmented reality, productivity,
a broader range of features, so this currently and the health and safety of building users.
represents common practice.
Conclusions
The AI platform is built on a Smart Building
infrastructure, and all technical systems AI-based processes enable a broad range of
should ideally be connected to a BMS (Building applications in the field of building automation.
Management System). The BMS must be able to The concrete benefits anticipated from AI-based
govern the building facility and room automation solutions should be clearly defined before
systems. implementation, since this plays a determining role
in the choice of learning process and its modelling,
Requirements for Building Infrastructure as well as in the choice of AI platform and the type,
number and location of the energy harvesting
AI-based processes require high computing sensors needed to supply the data inputs.
power and are therefore best run on a dedicated
AI platform. This can be cloud-based or run on
a server in the company’s own data center. Due
to the higher computing power of cloud-based
server farms and the currently greater scope of
services offered by cloud-based AI frameworks,
this option is shown in Fig. 2.
Prof. Dr. Michael Krödel
This figure also shows that a smart building must Professor of Building Automation and
be in place as a basis for the use of AI-based Building Technology at Rosenheim Technical University
processes. It is important that all building services michael.kroedel@th-rosenheim.de | www.th-rosenheim.de
in this smart building are connected to a building
management system (BMS) for communication
purposes. In many cases, building automation
is still implemented in such a way that room-
side and system-side automation are operated
separately from each other as respective Graham Martin
island systems. This must be converted into a Chairman & CEO | EnOcean Alliance
holistically networked installation. graham.martin@enocean.com | www.enocean-alliance.org
17
BACnet Middle East Journal 14 11/25 17
