1. ECVET Training for Operatorsof IoT-enabledSmart Buildings (VET4SBO)
2018-1-RS01-KA202-000411
Level: 2 (two)
Module: 2 Optimization strategies to meet quality
of service criteria
Unit 2.3 Optimization examples for intelligent
buildings
2. L2-M2-U2.3 Optimization examples for intelligent
buildings
• UNIT CONTENTS
– Increased occupants’ comfort in buildings by means of metaheuristic
optimization.
– Increased energy efficiency in buildings by means of metaheuristic
optimization.
– Example: temperature controller optimizationby metaheuristics.
– Example: smart grid and smart building interoperation optimization
using particle swarm optimizationmetaheuristics
– Example: network coverage optimizationin smart homes using
optimizationmetaheuristics.
– Example: coordination among home
appliances using multi-objective energy optimization
– Other examples: optimal IoT sensor placement optimization, optimal
energy use, etc.
https://pixabay.com/illustrations/business-
search-seo-engine-2082639/
3. Optimization examples for intelligent buildings
• Optimization can be efficiently used in
intelligent buildings.
• It is used both in design and operation of
intelligent buildings.
• Various energy savings, equipment wear
reduction and comfort improvements can be
obtained by optimization, to name only few.
https://pixabay.com/photos/smart-home-
computer-internet-canvas-3148026/
4. 2.3 Optimization examples for intelligent buildings
• Especially efficient and suitable is
metaheuristic optimization, representing
derivative free approach that generally
demands less heavy mathematics and is
suitable for relatively easy applicationof
software tools. https://pixabay.com/photos/smart-home-house-
technology-3096219/
5. Optimization for intelligent buildings
• The following are some examples of
optimization for intelligent buildings.
• They aim at mentioned goals - various
energy savings, equipment wear reduction
and comfort improvements.
• Although computation behind these
scenarios requires sometimes significant
research, application remains fairly simple.
https://pixabay.com/illustrations/binary-
null-one-cyber-design-3441007/
6. Example #1 - Temperature Controller Optimization
by Computational Intelligence
• The aim in this example are exactly the mentioned goals -
various energy savings, equipment wear reduction and comfort
improvements.
• Although computation behind this scenarios requires
sometimes significant research, application remains fairly
simple [1].
» [1] Ćojbašić, Ž. M., et al.: Temperature Controller Optimization by Computational …
THERMAL SCIENCE, Year 2016, Vol. 20, Suppl. 5, pp. S1541-S1552.
7. Example #1 - Temperature Controller Optimization
by Computational Intelligence
• A temperature control system for an automated
educationalclassroom is optimized with several
advanced computationally intelligent methods.
• Controller development and optimization has
been based on developed and extensively
tested mathematical and simulation model of
the observed object.
https://pixabay.com/photos/tablet-heating-man-
pointing-manual-2471184/
8. Example #1 - Temperature Controller Optimization
by Computational Intelligence
• For the observed object cascade P-PI temperature
controller has been designed and conventionally
tuned.
• To improve performance and energy efficiency of
the system, several meta-heuristic optimizations of
the controller have been attempted, namely:
– genetic algorithm optimization,
– simulated annealing optimization,
– particle swarm optimization and
– ant colony optimization.
https://pixabay.com/photos/smart-
home-house-3317442/
9. Example #1 - Temperature Controller Optimization
by Computational Intelligence
• In order to have a rational energy consumption, one typical
classroom in higher edu-cation institution building has been
equipped in such manner to ensure high comfort for users by
controlling of heating, ventilation, and air conditioning (HVAC).
Ćojbašić,Ž.M., et al.: Temperature Controller Optimization by Computational … THERMAL SCIENCE, Year 2016,Vol. 20, Suppl. 5, pp. S1541-S1552.
10. Example #1 - Temperature Controller Optimization
by Computational Intelligence
• In contemporary HVAC systems various control techniques are used, from
classical to contemporary.
• However, in commercial applications cascade proportional-integral-
derivative (PID) controllers are largely dominant, where instead of a single
conventional PID controller two cascade PID controllers are interconnected
and used together in order to obtain superior dynamic performance.
Ćojbašić,Ž.M., et al.: Temperature Controller
Optimization by Computational … THERMAL
SCIENCE, Year 2016, Vol.20, Suppl. 5, pp.
S1541-S1552.
11. Example #1 - Temperature Controller Optimization
by Computational Intelligence
• Metaheuristic
control system
optimization
(optimal controller
tuning).
Ćojbašić,Ž.M., et al.: Temperature Controller
Optimization by Computational … THERMAL SCIENCE,
Year 2016, Vol. 20, Suppl.5, pp. S1541-S1552.
12. Example #1 - Temperature Controller Optimization
by Computational Intelligence
Ćojbašić,Ž.M., et al.: Temperature Controller Optimization by Computational … THERMAL SCIENCE, Year 2016,Vol. 20, Suppl. 5, pp. S1541-S1552.
13. Example #1 - Temperature Controller Optimization
by Computational Intelligence
Ćojbašić,Ž.M., et al.: Temperature Controller Optimization by Computational … THERMAL SCIENCE, Year 2016,Vol. 20, Suppl. 5, pp. S1541-S1552.
14. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• Transition towards a so-called smart grid (SG) electrical systems in cities
requires advanced building energy management systems (BEMS) to cope
with the highly complex interaction between two environments.
• Approach is need to optimize the inter-operation of the SG–BEMS
framework. Particle Swarm Optimization (PSO) can be used to maximize
both comfort and energy efficiency of the building [2].
– [2] L. Hurtado, P. Nguyen, W. Kling, Smart grid and smart building interoperation
using agent-based particle swarm optimization, Sustainable Energy, Grids and
Networks 2 (2015) 32–40. doi:10.1016/j.segan.2015.03.003.
15. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• Results show that the operation of the building can be dynamically
changed to support the voltage control of the local power grid,
without jeopardizing the building main function, i.e. comfort
provision.
• To cope with the complexity of Smart Grid – Building Eneregy
Management System integration, a shift is evident from a
centralized energy management systems to a decentralized
structure with the introduction of computational and distributed
intelligence.
16. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• The two main aspects of the building consumer
domain are comfort management and energy
consumption.
• In buildings, the central objective is to provide
the occupantswith a comfortable environment. https://pixabay.com/photos/relaxing-lounging-
saturday-cozy-1979674/
17. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• About 50% of the total electrical energy
consumed is used for comfort management.
• This strong correlation is crucial to reveal
flexibility from the built environment to offer
to the smart grid. https://pixabay.com/photos/agriculture-
sunflower-field-1853323/
18. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• Comfort is a complex and subjective human perception, which varies
according to each person and each particular environmental context.
• Traditionally, it is controlled by a combination of a centralized management
system and human interventions, e.g. lights in local zones.
• Different standards have been developed to guarantee comfort levels.
– For instance, ASHRAE55 and ISO7730, for thermal comfort;
– ISO8995−1, for visual comfort;
– and ASHRAE62.1, for indoor air quality.
19. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• Optimization problem formulation is complex, since the SG–BEMS
framework involves multiple objectives which might be conflicting,
i.e. comfort maximization and energy minimization, and a
consideration to enable grid support services.
• The maximization of comfort can be rewritten as the minimization
of discomfort. The second objective is the minimization of the
energy consumed in the building, i.e. the energy optimization
problem can be reduced to the minimization of the energy
consumed by the comfort systems.
20. Example #2: Smart grid and smart building
interoperation optimization using particle swarm
optimization metaheuristics
• An optimization strategy is needed for building
energy management systems, which optimizes
both energy and comfort in a zone.
• From the results obtained, it can be concluded
that the PSO algorithm offers great potential not
only for energy savings and comfort optimization,
but also for voltage grid support.
https://pixabay.com/photos/smart-
home-house-technology-3920905/
21. Example #3: network coverage optimization in
smart homes using optimization metaheuristics
• Smart devices in IoT intelligent buildings require Internet
access, but locations of intelligent devices are often
dispersed.
• Thus, ensuring that all devices are able to access the
network is an important issue for resolution.
• Another challenge encounteredin smart home networks is
the complex electromagnetic environment. A smart home is
a multi-network environment and many indoor short-
distance communication technologies are working in the 2.4
GHz industrial scientific medical (ISM) band.
https://pixabay.com/photos/network-
networking-rope-connection-1246209/
22. Example #3: network coverage optimization in
smart homes using optimization metaheuristics
• ISM band has been demonstrated that it has not
impact on human health. However, the hybrid
electromagnetic environment may cause serious
electromagnetic interference between devices
that reduces communication quality.
• The indoor wireless communication systems
usually include two kinds of channels that are the
line-of-sight channels and the multipath channels.
https://pixabay.com/illustrations/finger-touch-
hand-structure-769300/
23. Example #3: network coverage optimization in
smart homes using optimization metaheuristics
• Due to the increase in popularity of light
emitting diode (LED) as a lighting source, it
is convenient and easy to provide in-home
and in-building visible light communication
(VLC) using the already existing LED lamps.
• VLC is an effective method to solve
problems concerning network access and
coverage in smart homes.
https://pixabay.com/photos/light-lights-
led-beams-stage-812677/
24. Example #3: network coverage optimization in
smart homes using optimization metaheuristics
• For VLC power coverage problem in smart homes, metaheuristic
optimization of network coverage is a feasible approach.
• Such approach can avoid the interdimensional interference so that
reducing the repeated computation times. Therefore, it can
enhance the coverage rate and the accuracy of the solutions.
• Succesfull application of cuckoo search has been reported [3].
» [3] G. Sun, Y. Liu, M. Yang, A. Wang, S. Liang, Y. Zhang, Coverage optimization of VLC in
smart homes based on improved cuckoo search algorithm, Computer Networks 116
(2017) 63–78. doi:10.1016/j.comnet.2017.02.014.
25. Example #4: Coordination among home
appliances using multi-objective energy optimization
• A home energy management system can optimize the energy
consumption patterns of a smart home.
• It aims to manage the load demand in an efficient way to minimize
electricity cost and peak to average ratio while maintaining user
comfort through coordination among home appliances [4].
» [4] A. Khalid, N. Javaid, M. Guizani, M. Alhussein, K. Aurangzeb, M. Ilahi, Towards
Dynamic Coordination Among Home Appliances Using MultiObjective Energy
Optimization for Demand Side Management in Smart Buildings, IEEE Access 6 (2018)
19509–19529. doi:10.1109/ACCESS. 2018.2791546.
26. Example #4: Coordination among home
appliances using multi-objective energy optimization
• In order to meet the load demand of electricity
consumers, the load in day-ahead and real-time
basis is scheduled.
• A fitness criterion for that is formulated
(optimization function) which helps in balancing the
load during On-peak and Off-peak hours.
• For real-time rescheduling, the concept of
coordination among home appliances is used.
• This helps the scheduler to optimally decide the
ON/OFF status of appliances in order to reduce the
waiting time of appliance.
https://pixabay.com/photos/smart-home-
house-technology-3096224/
27. Example #4: Coordination among home
appliances using multi-objective energy optimization
• Realtime rescheduling problem is solved as
multi-objective optimization problem.
• Verification of good behavior of the proposed
technique includes behavior for three pricing
schemes including:
– time of use, real-time pricing and critical peak
pricing.
https://pixabay.com/photos/coins-currency-
investment-insurance-1523383/
28. Other examples: optimal IoT sensor placement
optimization, optimal energy use, etc.
• To design and develop reliable, efficient, flexible, economical,
real-time and realistic wellness sensor networks for smart
home systems, metaheuristics are also often used.
• The heterogeneous sensor and actuator nodes based on
wireless networking technologies are deployed into the
home environment. These nodes generate real-time data
related to the object usage and movement inside the home,
to forecast the wellness of an individual.
• Here, wellness stands for how efficiently someone stays fit in
the home environment and performs his or her daily routine
in order to live a long and healthy life. Monitor the activity of
an inhabitant for wellness detection.
https://pixabay.com/photos/wellness-health-
well-being-healing-3961684/
29. Other examples: optimal IoT sensor placement
optimization, optimal energy use, etc.
• In all previous examples, and with modern
smart buildings, optimal energy use is crucial
demand besides user comfort.
• Therefore all modern software based BMS
and/or BEM systems offer energy use
optimization, which is often based on AI and
metaheuristics.
https://pixabay.com/vectors/energy
-efficiency-energy-154006/
30. Thank you for your attention.
https://pixabay.com/illustrations/thank-you-polaroid-letters-2490552/
31. Disclaimer
For further information, relatedto the VET4SBO project, please visit the project’swebsite at https://smart-building-
operator.euor visit us at https://www.facebook.com/Vet4sbo.
Downloadour mobile app at https://play.google.com/store/apps/details?id=com.vet4sbo.mobile.
This project (2018-1-RS01-KA202-000411) has been funded with support from the European Commission (Erasmus+
Programme). Thispublicationreflects the views only of the author, and the Commission cannot be held responsible
for any use which may be made of the informationcontainedtherein.