2. Outlines
• What is Metaheuristic.
• What is Internet of Things.
• The is Internet of Things Needs Swarm Intelligence.
• Swarm Intelligence and its Applications.
• Applications of Swarm Intelligence in IoT Processes.
• Conclusion.
Metaheuristic applications in IoT 1/18Ibrahim Fares
3. What is Metaheuristic
• Metaheuristic can be seen as a general algorithmic
framework which can be applied to different
optimization problems with relatively few modifications
to make them adapted to a specific problem.
Metaheuristic applications in IoT 3Ibrahim Fares
6. Swarm Intelligence(SI)
• Swarm Intelligence (SI) is the
collective behavior of a self-organized
and decentralized system that may be
natural or artificial intelligence.
• SI can be found widely in Colonies of
ants, school of fishes, honey bees etc.
• Aim: the main aim of SI is to increase
the performance and robustness.
Metaheuristic applications in IoT 6Ibrahim Fares
7. Swarm Intelligence(SI)
• Features: Swarm algorithms are faster
and more robust solutions to solve
complex set of problems.
• Applications:
✓Swarm intelligence algorithms have
been widely applied to robotics,
DNA computing, vehicle routing
problem.
✓Recently, applied to data intensive
Internet of Things (IoT) operations
and services.
Metaheuristic applications in IoT 7Ibrahim Fares
8. Internet of Things(IoT)
• IoT is a system of interrelated computing devices,
mechanical and digital machines, objects, animals or
people that are provided with unique identifiers
(UIDs) and the ability to transfer data over a network
without requiring human-to-human or human-to-
computer interaction.
• The IoT is an umbrella of technologies.
• IoT services: like environmental monitoring, fitness
tracking, home appliance control, smart waste
management >> are already being deployed in Smart
Cities.
Metaheuristic applications in IoT 8Ibrahim Fares
9. Internet of Things(IoT)
• The smart device or Things
generate data in high volume,
velocity, variety and veracity >>>
Big Data.
• It is estimated that 20-25 Billion
Things will be connected to the
Internet by 2020, which would
generate around 1.2 zettabytes of
data.
Metaheuristic applications in IoT 9Ibrahim Fares
10. The IoT Needs Swarm Intelligence
• Optimization of data intensive
of IoT processes highly desirable.!
• Why using SI in IoT?
✓Because the utilization of SI algorithms in IoT can
make the IoT data processing much faster and
efficient.
✓This would give a boost to the emerging IoT
ecosystems, improve the consumer experience of
IoT applications and services.
✓SI with it’s optimization capabilities can ameliorate
IoT processes that are data intensive.
Metaheuristic applications in IoT 10Ibrahim Fares
11. Applications of Swarm Intelligence in IoT
Processes
• We have chosen three domains where SI could have a better
solution.
A. Vehicle routing problem (VRP) for connected cars with ACO [1].
B.Data routing from a wide spread sensor network with ACO[2].
C.Cloud Computing techniques for data optimization [3].
Metaheuristic applications in IoT 11Ibrahim Fares
12. SI in Connected Cars
• Vehicle Routing Problem (VRP) is
a well studied logistic problem in SI.
• The problem deals with the cost
minimization of running ”n” vehicles
that has to serve ”m” customers.
• Vehicle routing is an important service
for connected cars offered by IoT
platforms.
• Using the data the current platforms are
offering services like shortest path to a
fuel station, predictive analysis of car
health and more.
Metaheuristic applications in IoT 12Ibrahim Fares
13. SI in Connected Cars…Cont.
• They would generate Gigabytes of data
per second to:
✓Create Locally Dynamic Maps (LDM),
logistics
delivery, transporting people, vehicle
health
analytics, usage based insurance and
more.
• Using ACO, novel IoT services can be
developed to provide route construction,
trail update and route improvement
strategies.
Metaheuristic applications in IoT 13Ibrahim Fares
14. SI in Data Routing
• SI finds wide application in communication for its
application of routing in telecommunication
networks.
• It is estimated that 20-30 Billion sensors will be
connected to the Internet by 2020.
• So, intelligent routing, storage of the sensor data will
be required for the communication backbone.
• Use of SI would ensure systematic data routing and
storage which in turn prevent data loss.
Metaheuristic applications in IoT 14Ibrahim Fares
15. SI in Cloud computing for Data Optimization
• The value of IoT lies in processing, storage and
visualization of data.
• 1.2 zettabytes of IoT data are estimated to be generated by IoT devices which
would undoubtedly require Cloud for storage.
• With such a large volume of data, data processing algorithms might potentially
have a performance loss thereby increase in processing time.
• Utilizing ACO for data optimization to reduce the overall data processing time is
what suggest.
• ACO offers large scale optimization for fast data mining on large scale dataset.
Metaheuristic applications in IoT 15Ibrahim Fares
16. SI in Cloud computing for Data
Optimization…Cont.
• ACO can handle high dimensional data so that the performance of the
algorithm does not decay with large datasets, capacity of handling
dynamical data which provides almost real-time data processing, and
multi-objective optimization in ACO can manage data coming from
different sources.
• This is an efficient and robust solution for data optimization in IoT.
Metaheuristic applications in IoT 16Ibrahim Fares
17. Conclusion
• Metaheuristic algorithms have been widely studied and applied to many
well known problems.
• In this presentation we examine the intersection of SI with the IoT.
• IoT is an umbrella of several verticals which required data intensive IoT
processes to provide consumer services.
• We advocate for utilizing such ACO algorithm and other algorithms to
optimize the IoT processes and make them more efficient.
• As a current and future goal, we plan to implement the three scenarios
described in this presentation and evaluate their performances by recently
metaheuristic developed algorithms.
Metaheuristic applications in IoT 17Ibrahim Fares
18. References
• I. Kassabalidis, M.A. El-Sharkawi, R. J. Marks, P. Arabshahi, andA. A. Gray, “Swarm
intelligence for routing in communication networks,” in GlobalTelecommunications
Conference, 2001. GLOBECOM ’01. IEEE, vol. 6, pp. 3613–3617 vol.6, 2001.
• J. E. Bell and P. R. McMullen, “Ant colony optimization techniques for the vehicle routing
problem,” Advanced Engineering Informatics, vol. 18, no. 1, pp. 41 – 48, 2004.
• I. Kassabalidis, M.A. El-Sharkawi, R. J. Marks, P. Arabshahi, andA. A. Gray, “Swarm
intelligence for routing in communication networks,” in GlobalTelecommunications
Conference, 2001.GLOBECOM ’01. IEEE, vol. 6, pp. 3613–3617 vol.6, 2001.
• S. Cheng,Y. Shi, Q. Qin, and R. Bai, Swarm Intelligence in Big Data Analytics, pp. 417–426.
Metaheuristic applications in IoT 18Ibrahim Fares