SlideShare a Scribd company logo
1 of 17
Download to read offline
The Changing Face of Telcos in a Digital
World
Optimisation of Fog computing for Industrial
IoT applications
Sabelo Dlamini
University of Cape Town
Cape Town, South Africa
dlmsab003@myuct.ac.za
Neco Ventura
University of Cape Town
Cape Town, South Africa
neco@crg.ee.uct.ac.za
H. Anthony Chan
Huawei Technologies
1700 Alma Dr. Plano, USA
h.anthony.chan@huawei.com
2019 Southern Africa Telecommunication Networks and Applications Conference (SATNAC)
SATNAC 2019 (September 1-4, 2019)
Fairmont Zimbali, Ballito, Durban, South Africa
Contents
• Introduction
• Background
• Related Work
• Proposed Scheme
• Evaluation
• Conclusion and Future Work
Introduction
• The application of IoT in the manufacturing industry is normally
referred to as the Industrial Internet of Things (IIoT).
• Manufacturing companies that have adopted smart manufacturing in
their operations are already seeing improved results with 82%
increased operational efficiency and improved product quality with
49% fewer product defects, according to Microsoft research .
• American Society for Quality states that connecting devices and
analyzing the data collected enables manufacturers to reduce
overhead, conserve resources, increase profits and optimize
operational efficiencies
Internet of Things (IoT) is expected to provide a quantum leap for the manufacturing industry with the market
potential for industrial applications projected to be $913 billion by 2018. Industry analysts are projecting that
there will be up to 50 billion connected devices with a market potential of between $10.6 to 14.2 trillion by
2030
Fog Computing
• As more factory processes adopt smart manufacturing, the data velocity and volume
increases, moving the big data from factory sensor/actuators to the cloud might not
be efficient, or even feasible due to bandwidth and network connection constraints.
• While on the other hand, smart manufacturing is required to support time-sensitive
and location-aware applications, such as real-time manufacturing applications,
making the distant cloud not be able to satisfy the low latency requirements of these
applications.
• Fog computing bridges the gap between the cloud and things to address the latency,
network bandwidth and availability and privacy/security issues in Internet of Things
(IoT).
• Fog architectures selectively move compute, storage, communication, control, and
decision making closer to the network edge where data is being generated in order
solve the limitations in current infrastructure to enable mission-critical, data-dense
use cases.
Current “cloud-only” architectures cannot keep up with the volume and velocity of this data across the
network, thereby reducing the value that can be created and captured from these investments.
Fog Computing – Autonomy
• As a technological paradigm, edge computing may be
architecturally organized as an autonomic (self-healing) computing
network.
• Autonomy should enable decision making to be made at all levels of
a deployment’s hierarchy including near the device or higher order
layers.
• Autonomy at the network edge means intelligence from local
devices and peer data can be used to fulfil the business’ mission at
the point where it makes the most business sense.
• In this study we focus on enhancing Fog Computing’s autonomy to
reduce delays in decision-making.
The autonomy pillar requires fog nodes to continue to deliver the designed functionality in the
face of the external service failures.
Related Work
• Aazam et al. In [11] :
– highlights the fast processing of the sensed data to generate instructions for the actuators and robots within
some acceptable latency as one of the challenges.
– other challenge noted was data structuring and filtering to avoid sending unnecessary data to the core and
the cloud.
• Li et al. In [12] :
– proposed a service popularity-based smart resources partitioning scheme for Fog computing-enabled IIoT to
improve delay time and fault tolerance.
– Their proposed scheme demonstrated improved performance. It was tested simulated using iFogSim a similar
simulator that has been adopted in this paper.
• de Brito et al. In [15] :
– highlights the challenge of orchestration in fog-enabled infrastructure environment and proposes an
infrastructure management and orchestration architecture for an fog computing.
– proposed architecture switches between centralized and distributed model. de Brito et al. not explore much
on the implementation of automatic event triggers.
Recently, there has been a number of promising research initiatives focused on solving issues related
to IoT and Fog computing.
Related Work…
• Checkired et al. In [17] :
– stated that the collected and sensed data from IIoT need to be scheduled in real-time, especially for big
factories, and proposed a hierarchical Fog servers’ deployment at the network service layer across different
tiers
– this study proved that processing data closer to the edge does improve performance in IIoT applications.
• Fui et al. In [18] :
– highlighted the challenges of data processing, secure storage, efficient retrieval and dynamic data collection
in IIoT.
– argued that storing all the IIoT data raw is unwise considering that the end devices energy and storage space
is limited in these devices.
– Proposed a scheme that selectively processes data based on latency requirements, where the raw data is
pre-processed in the Fog and then the time-sensitive data are used and stored locally, while the rest is sent to
the cloud
• de Brito et al. In [20] :
– addressed the problem of distributed decision making, but this work focused on the challenge of service
hosting where Fog nodes are required to be adaptively configured to host services for sensor nodes.
– proposed the use of an online distributed algorithm, called adaptive Fog configuration (AFC), to optimize
service hosting and task admission decisions.
Recently, there has been a number of promising research initiatives focused on solving issues related
to IoT and Fog computing.
Fog Computing – Machine Learning
• Robustness of machine learning algorithms is a key challenge for applications (e.g., self-driving cars and network operation) in
real-world environments where learning errors could lead to high costs.
• Most machine learning implementations require training process which is often time consuming and involves high cost for
small to medium manufactures
• One big challenge faced by cloud-based ML-solutions in manufacturing is delay. Most applications are delay-sensitive, it is not
easy to design a real-time system with heavy computation loads.
• Challenges with cloud-based Machine Learning solutions:
– implementations require training process which is often time consuming and involves high cost.
– require data collection and data analysis for the performance of the network
Machine Learning is in the forefront of research today that requires computation for both training models,
and inference or scoring those models for close to real time response at the edge.
Fog Computing – Hidden Markov Model (ML)
• Finite State Machines are efficient implementations of artificial intelligence with less
storage and processing requirements
• Finite State Machines are considered at the design phase and have been successfully
implemented in:
– Border Gateway Protocols (BGP)
– Controller Area Network (CAN)
– IEEE 802.11 (Wi-Fi)
• Edge Intelligence:
– Propose an option to provide decent intelligence to a network without going through the
different stages required to setup a machine learning function to support network
decision making.
• OpenFog, ETSI NFV MANO and FSM
• Requires detailed design and analysis of the proposed operation environment
Proposed scheme uses Hidden Markov Models, a machine learning algorithm that has been widely used in
autonomous robotics to enhance decision-making.
ETSI MANO
Architecture
OpenFog
Architecture
Hidden Markov
Model
Io
T
Fog
Manageme
nt
State
Proposed Scheme
Integration and the use of Hidden Markov Model to automatically optimise the Fog computing based
systems.
• Propose a scheme to enable fog-based systems to self-manage, including
self-configuration, self-optimization, and self-healing. This can be achieved
by an autonomic function having minimal dependencies on human
administrators or centralized management systems
• Proposed scheme will be sitting in the edge node of the autonomous edge
network
• If the network performance indicators are not satisfying the network user
requirements as defined, the proposed scheme will automatically change
the state of the network
• Proposed scheme will use reduce latency (average loop latency), and network
usage.
Backhaul
Edge Node
Central Cloud
Autonomous
Management
and
Orchestration
Centralised ManagementDistributed Management
Fog Nodes
ETSI
MANO
HM
M
Proposed Scheme
As mentioned in the proposed scheme, we will adopt the Hidden Markov Model as a Machine Learning algorithm
which has widely adopted in resource management in cloud computing applications .
• Distributed Mode: In this state, the Fog computing is fully autonomous and
is able to independently make decisions and function on its own, with
sufficient resources available. In this state, the computing functions are
locally implemented, the main aim is to have the system spending most of
its time in this mode or state.
• Hybrid Mode: This is the state where Fog computing has unreliable
connectivity to the cloud. Fog computing is integrated with the cloud over
the unguaranteed network connecting, necessitating switching between the
previous state and the centralized state. In this state, Fog computing
performs storage and computation are locally implemented while
networking is remote.
• Centralized Mode: In this state, the Fog is integrated with the cloud well.
Computation, storage, and networking are centrally provided by the Cloud.
Cloud provides more sturdy computation and storage facilities with the
drawback of high backhaul link consumption and cost related to the use of
cloud computing facilities.
Experimental Setup
• In order to compare the performance of both the resource management
scheme for the study, we used iFogSim was used for simulation of resource
management, specifically scheduling policies between Fog computing and
cloud computing with varying network configurations .
• We used a basic Fog node to sensor setup, each sensor/actuator is
connected to a Wi-Fi gateway, the gateway is then connected to an ISP
gateway, which connects the Fog computing to the Cloud datacenter. .
Source Destination Latency (ms)
Sensor/Actuator Fog Node 61ms
Fog Node Fog Node 22ms
Fog Node Fog Node 70ms
Edge Node Edge Node 30ms
Edge Node Cloud 200ms
• Distributed management provide very low latencies for Fog
computing with a limited number of sensor/actuators connected to
the Fog node.
• distributed management provides lower latency when compared to
centralized management in nodes below 16.
• Network usage from 16 sensors/actuators in both centralized and
distributed mode performance is the same, this is caused by limited
resources in the Fog nodes and transferred processing to the cloud.
• This results in similar performance between the two-management
mode. Therefore, it may be better to switch to centralized mode as
soon as the network usage is similar.
Results and Discussion
Conclusion
• Distributed management mode performed better than centralized with a low number of sensor/actuators connected to the
Fog node.
• Both management modes demonstrated similar performance from 32 sensors/actuators, highlighting the need for both
modes.
• One big challenge faced by cloud-based ML-solutions in manufacturing is delay. Most applications are delay-sensitive, it is not
easy to design a real-time system with heavy computation loads.
• The results highlight that there is a need for both orchestration (centralized management) and choreography (distributed
management) in a Fog computing environment.
• In addition to this we believe that there is a need for an intelligent switching between the centralized and distributed mode in order to
enhance performance and reduce latency.
As future work to develop an intelligent machine learning based scheme that can enhance switching
between the two modes. The scheme will sense the change conditions and switch management mode
accordingly.
References
[1] IDC, Internet of Things Spending Guide by Vertical Market, 2014.
[2] Luxiu Yin, Juan Luo, Haibo Luo. “Tasks Scheduling and Resource Allocation in Fog Computing Based on Containers for Smart Manufacturing,” IEEE
Transactions on Industrial Informatics, vol. 14, no. 10, October, 2018
[3] Microsoft, Competing in the digital age of manufacturing, 2018.
[4] Sebastian Trinks, Carsten Felden. “Edge Computing architecture to support Real Time Analytic applications: A State-of-the-art within the application area
of Smart Factory and Industry 4.0,” IEEE International Conference on Big Data (Big Data), 2018
[5] Flavio Bonomi, Rodolfo Milito, Jiang Zhu, Sateesh Addepalli. “Fog Computing and Its Role in the Internet of Things,” ACM SIGCOMM Mobile Cloud
Computing (MCC), 2012
[6] P1934/D2.0, Apr 2018 - IEEE Approved Draft Standard for Adoption of OpenFog Reference Architecture for Fog Computing, 2018
[7] Yuxuan Jiang, Zhe Huang, Danny H. K. Tsang. “Challenges and Solutions in Fog Computing Orchestration,” IEEE Network, volume: 32, issue: 3, May/June,
2018
[8] Mithun Mukherjee, Lei Shu, Di Wang. “Survey of Fog Computing: Fundamental, Network Applications, and Research Challenges,” IEEE Communications
Surveys & Tutorials, vol. 20, no. 3, 2018
[9] B. Zhang, N. Mor , J. Kolb , D.S. Chan , K. Lutz , E. Allman , J. Wawrzynek , E.A. Lee , J. Kubiatowicz , The cloud is not enough: saving IoT from the cloud.,
HotStorage, 2015
[10] Saad Khan, Simon Parkinson, Yongrui Qin. “Fog computing security: a review of current applications and security solutions,” Springer Journal of Cloud
Computing, December 2017
[11] Mohammad Aazam, Sherali Zeadally, and Khaled A. Harras. “Deploying Fog Computing in Industrial Internet of Things and Industry 4.0,” IEEE
Transactions on Industrial Informatics, vol. 14, no. 10, October 2018
[12] Gaolei Li, Jun Wu, Jianhua Li, Kuan Wang, and Tianpeng Ye. “Service Popularity-Based Smart Resources Partitioning for Fog Computing-Enabled Industrial
Internet of Things,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018
[13] Sabelo Dlamini, Neco Ventura. “Enhancement of Fog Computing based Autonomous Management Systems,” Southern Africa Telecommunication
Networks and Applications Conference (SATNAC), 2018
[14] Sabelo Dlamini, Joyce Mwangama, Neco Ventura and Thomas Magedanz. “Design of an Autonomous Management and Orchestration for Fog
Computing,” International Conference on Intelligent and Innovative Computing Applications (ICONIC), 2018
[15] M.S. de Brito, S. Hoque, R. Steinke, A. Willner and T. Magedanz. “Application of the Fog computing paradigm to Smart Factories and cyber-physical
systems,” Trans Emerging Tel Tech. 2018;
References…
[16] Harshit Gupta, Amir Vahid Dastjerdi, Soumya K. Ghosh, Rajkumar Buyya. " iFogSim: A Toolkit for Modeling and Simulation of Resource Management
Techniques in Internet of Things, Edge and Fog Computing Environments"
[17] Djabir Abdeldjalil Chekired, Lyes Khoukhi and Hussein T. Mouftah. “Industrial IoT Data Scheduling Based on Hierarchical Fog Computing: A Key for
Enabling Smart Factory,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018
[18] Jun-Song Fu, Yun Liu, Han-Chieh Chao, Bharat K. Bhargava and Zhen-Jiang Zhang. “Secure Data Storage and Searching for Industrial IoT by Integrating Fog
Computing and Cloud Computing,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018
[19] Mohammad Ashjaei and Marcus Bengtsson “Enhancing Smart Maintenance Management Using Fog Computing Technology,” IEEE IEEM, 2017
[20] Lixing Chen, Pan Zhou, Liang Gao and Jie Xu. “Adaptive Fog Configuration for the Industrial Internet of Things,” IEEE Transactions on Industrial
Informatics, vol. 14, no. 10, October 2018
[21] Chenhua Shi, Zhiyuan Ren, Kun Yangy, Chen Chen, Hailin Zhang, Yao Xiao and Xiangwang Hou. “Ultra-Low Latency Cloud-Fog Computing for Industrial
Internet of Things,” IEEE Wireless Communications and Networking Conference (WCNC), 2018
[22] Gabriele Castellano, Fulvio Risso, and Riccardo Loti. “Fog Computing over Challenged Networks: a Real Case Evaluation,” IEEE 7th International
Conference on Cloud Networking (CloudNet), October, 2018
[23] Olena Skarlat, Vasileios Karagiannis, Thomas Rausch, Kevin Bachmann and Stefan Schulte. “A Framework for Optimization, Service Placement, and
Runtime Operation in the Fog,” IEEE/ACM 11th International Conference on Utility and Cloud Computing (UCC), 2018.
[24] F. Bonomi, R. Milito, P. Natarajan, J. Zhu, "Fog Computing: A Platform for Internet of Things and Analytics", Big Data and Internet of Things: A Roadmap
for Smart Environments ser. Studies in Computational Intelligence, vol. 546, pp. 169-186, 2014.
[25] A.V. Dastjerdi, H. Gupta, R.N. Calheiros, S.K. Ghosh, R. Buyya, "Fog Computing: Principles Architectures and Applications", Internet of Things: Principles
and Paradigms, 2016.
[26] Sergej Svorobej, Patricia Takako Endo, Malika Bendechache, Christos Filelis-Papadopoulos, Konstantinos M. Giannoutakis, George A. Gravvanis, Dimitrios
Tzovaras, James Byrne and Theo Lynn. “Simulating Fog and Edge Computing Scenarios: An Overview and Research Challenges,” MDPI Future Internet, 2018
[27] Qayyum, T.; Malik, A.W.; Khattak, M.A.K.; Khalid, O.; Khan, S.U. FogNetSim++: A Toolkit for Modeling and Simulation of Distributed Fog Environment. IEEE
Access 2018
[28] Saiful Hoque, Mathias Santos de Brito, Alexander Willner. “Towards Container Orchestration in Fog Computing Infrastructures,” International Workshop
on Fog Computing and Networking (FCN), July, 2017
[29] Zhenyu Wen, Renyu Yang, Peter Garraghan, Tao Lin, Jie Xu, and Michael Rovatsos. Fog orchestration for internet of things services. IEEE Internet
Computing, 21(2):16–24, 2017.
DANKIE

More Related Content

What's hot

Fog Computing: Issues, Challenges and Future Directions
Fog Computing: Issues, Challenges and Future Directions Fog Computing: Issues, Challenges and Future Directions
Fog Computing: Issues, Challenges and Future Directions IJECEIAES
 
Internet of Things (IoT) in the Fog
Internet of Things (IoT) in the FogInternet of Things (IoT) in the Fog
Internet of Things (IoT) in the FogTom Donoghue
 
Computer Architecture
Computer ArchitectureComputer Architecture
Computer ArchitectureHaris456
 
A review on orchestration distributed systems for IoT smart services in fog c...
A review on orchestration distributed systems for IoT smart services in fog c...A review on orchestration distributed systems for IoT smart services in fog c...
A review on orchestration distributed systems for IoT smart services in fog c...IJECEIAES
 
Role of Cloud Computing Technology in Agriculture Fields
Role of Cloud Computing Technology in Agriculture FieldsRole of Cloud Computing Technology in Agriculture Fields
Role of Cloud Computing Technology in Agriculture Fieldssushil Choudhary
 
Information Technology for the success of Infrastructure Projects
Information Technology for the success of Infrastructure ProjectsInformation Technology for the success of Infrastructure Projects
Information Technology for the success of Infrastructure ProjectsVSR *
 
Disambiguating Advanced Computing for Humanities Researchers
Disambiguating Advanced Computing for Humanities ResearchersDisambiguating Advanced Computing for Humanities Researchers
Disambiguating Advanced Computing for Humanities ResearchersBaden Hughes
 
Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...
Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...
Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...Jiang Zhu
 
Loughtec cloud computing
Loughtec cloud computing Loughtec cloud computing
Loughtec cloud computing Loughtec
 
A Comparative Study: Taxonomy of High Performance Computing (HPC)
A Comparative Study: Taxonomy of High Performance Computing (HPC) A Comparative Study: Taxonomy of High Performance Computing (HPC)
A Comparative Study: Taxonomy of High Performance Computing (HPC) IJECEIAES
 
Ebook Guide To Data Centers
Ebook Guide To Data CentersEbook Guide To Data Centers
Ebook Guide To Data Centersrobgross144
 
How Cyber-Physical Systems Are Reshaping the Robotics Landscape
How Cyber-Physical Systems Are Reshaping the Robotics LandscapeHow Cyber-Physical Systems Are Reshaping the Robotics Landscape
How Cyber-Physical Systems Are Reshaping the Robotics LandscapeCognizant
 
Technology organization environment framework in cloud computing
Technology organization environment framework in cloud computingTechnology organization environment framework in cloud computing
Technology organization environment framework in cloud computingTELKOMNIKA JOURNAL
 
2011 infra challanges for oracle v1
2011 infra challanges for oracle v12011 infra challanges for oracle v1
2011 infra challanges for oracle v1Pini Cohen
 
VET4SBO Level 3 module 1 - unit 4 - 0.009 en
VET4SBO Level 3   module 1 - unit 4 - 0.009 enVET4SBO Level 3   module 1 - unit 4 - 0.009 en
VET4SBO Level 3 module 1 - unit 4 - 0.009 enKarel Van Isacker
 
Beyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud TechniquesBeyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud TechniquesDejan Kovachev
 
IRJET- Cost Effective Scheme for Delay Tolerant Data Transmission
IRJET- Cost Effective Scheme for Delay Tolerant Data TransmissionIRJET- Cost Effective Scheme for Delay Tolerant Data Transmission
IRJET- Cost Effective Scheme for Delay Tolerant Data TransmissionIRJET Journal
 
Security & privacy issues of cloud & grid computing networks
Security & privacy issues of cloud & grid computing networksSecurity & privacy issues of cloud & grid computing networks
Security & privacy issues of cloud & grid computing networksijcsa
 
Security and Privacy Issues of Fog Computing: A Survey
Security and Privacy Issues of Fog Computing: A SurveySecurity and Privacy Issues of Fog Computing: A Survey
Security and Privacy Issues of Fog Computing: A SurveyHarshitParkar6677
 

What's hot (20)

Fog Computing: Issues, Challenges and Future Directions
Fog Computing: Issues, Challenges and Future Directions Fog Computing: Issues, Challenges and Future Directions
Fog Computing: Issues, Challenges and Future Directions
 
Internet of Things (IoT) in the Fog
Internet of Things (IoT) in the FogInternet of Things (IoT) in the Fog
Internet of Things (IoT) in the Fog
 
Computer Architecture
Computer ArchitectureComputer Architecture
Computer Architecture
 
A review on orchestration distributed systems for IoT smart services in fog c...
A review on orchestration distributed systems for IoT smart services in fog c...A review on orchestration distributed systems for IoT smart services in fog c...
A review on orchestration distributed systems for IoT smart services in fog c...
 
Role of Cloud Computing Technology in Agriculture Fields
Role of Cloud Computing Technology in Agriculture FieldsRole of Cloud Computing Technology in Agriculture Fields
Role of Cloud Computing Technology in Agriculture Fields
 
Information Technology for the success of Infrastructure Projects
Information Technology for the success of Infrastructure ProjectsInformation Technology for the success of Infrastructure Projects
Information Technology for the success of Infrastructure Projects
 
Disambiguating Advanced Computing for Humanities Researchers
Disambiguating Advanced Computing for Humanities ResearchersDisambiguating Advanced Computing for Humanities Researchers
Disambiguating Advanced Computing for Humanities Researchers
 
Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...
Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...
Big Data and Internet of Things: A Roadmap For Smart Environments, Fog Comput...
 
Loughtec cloud computing
Loughtec cloud computing Loughtec cloud computing
Loughtec cloud computing
 
A Comparative Study: Taxonomy of High Performance Computing (HPC)
A Comparative Study: Taxonomy of High Performance Computing (HPC) A Comparative Study: Taxonomy of High Performance Computing (HPC)
A Comparative Study: Taxonomy of High Performance Computing (HPC)
 
Ebook Guide To Data Centers
Ebook Guide To Data CentersEbook Guide To Data Centers
Ebook Guide To Data Centers
 
How Cyber-Physical Systems Are Reshaping the Robotics Landscape
How Cyber-Physical Systems Are Reshaping the Robotics LandscapeHow Cyber-Physical Systems Are Reshaping the Robotics Landscape
How Cyber-Physical Systems Are Reshaping the Robotics Landscape
 
Green it
Green itGreen it
Green it
 
Technology organization environment framework in cloud computing
Technology organization environment framework in cloud computingTechnology organization environment framework in cloud computing
Technology organization environment framework in cloud computing
 
2011 infra challanges for oracle v1
2011 infra challanges for oracle v12011 infra challanges for oracle v1
2011 infra challanges for oracle v1
 
VET4SBO Level 3 module 1 - unit 4 - 0.009 en
VET4SBO Level 3   module 1 - unit 4 - 0.009 enVET4SBO Level 3   module 1 - unit 4 - 0.009 en
VET4SBO Level 3 module 1 - unit 4 - 0.009 en
 
Beyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud TechniquesBeyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
Beyond the Client-Server Architectures: A Survey of Mobile Cloud Techniques
 
IRJET- Cost Effective Scheme for Delay Tolerant Data Transmission
IRJET- Cost Effective Scheme for Delay Tolerant Data TransmissionIRJET- Cost Effective Scheme for Delay Tolerant Data Transmission
IRJET- Cost Effective Scheme for Delay Tolerant Data Transmission
 
Security & privacy issues of cloud & grid computing networks
Security & privacy issues of cloud & grid computing networksSecurity & privacy issues of cloud & grid computing networks
Security & privacy issues of cloud & grid computing networks
 
Security and Privacy Issues of Fog Computing: A Survey
Security and Privacy Issues of Fog Computing: A SurveySecurity and Privacy Issues of Fog Computing: A Survey
Security and Privacy Issues of Fog Computing: A Survey
 

Similar to Optimising Fog Computing for IoT with Hidden Markov Models

Design of an Autonomous Management and Orchestration for Fog Computing
Design of an Autonomous Management and Orchestration for Fog ComputingDesign of an Autonomous Management and Orchestration for Fog Computing
Design of an Autonomous Management and Orchestration for Fog ComputingSabelo Dlamini
 
Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.
Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.
Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.IRJET Journal
 
FOG COMPUTING, what and why a fog computing
FOG COMPUTING, what and why a fog computingFOG COMPUTING, what and why a fog computing
FOG COMPUTING, what and why a fog computingShivangi Bali
 
IRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational LeapIRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational LeapIRJET Journal
 
IRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational LeapIRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational LeapIRJET Journal
 
The Future of Fog Computing and IoT: Revolutionizing Data Processing
The Future of Fog Computing and IoT: Revolutionizing Data ProcessingThe Future of Fog Computing and IoT: Revolutionizing Data Processing
The Future of Fog Computing and IoT: Revolutionizing Data ProcessingFredReynolds2
 
Walking through the fog (computing) - Keynote talk at Italian Networking Work...
Walking through the fog (computing) - Keynote talk at Italian Networking Work...Walking through the fog (computing) - Keynote talk at Italian Networking Work...
Walking through the fog (computing) - Keynote talk at Italian Networking Work...FBK CREATE-NET
 
Internet of things - Introduction and Variations (Architecture)
Internet of things - Introduction and Variations (Architecture)Internet of things - Introduction and Variations (Architecture)
Internet of things - Introduction and Variations (Architecture)Mayank Vijh
 
A Case Study On Implementation Of Grid Computing To Academic Institution
A Case Study On Implementation Of Grid Computing To Academic InstitutionA Case Study On Implementation Of Grid Computing To Academic Institution
A Case Study On Implementation Of Grid Computing To Academic InstitutionArlene Smith
 
Data processing in Cyber-Physical Systems
Data processing in Cyber-Physical SystemsData processing in Cyber-Physical Systems
Data processing in Cyber-Physical SystemsBob Marcus
 
What is Edge Computing and Why does it matter in IoT?
What is Edge Computing and Why does it matter in IoT?What is Edge Computing and Why does it matter in IoT?
What is Edge Computing and Why does it matter in IoT?Sameer Ahmed
 
Get Cloud Resources to the IoT Edge with Fog Computing
Get Cloud Resources to the IoT Edge with Fog ComputingGet Cloud Resources to the IoT Edge with Fog Computing
Get Cloud Resources to the IoT Edge with Fog ComputingBiren Gandhi
 
Fog computing technology
Fog computing technologyFog computing technology
Fog computing technologyNikhil Sabu
 
Grid computing Seminar PPT
Grid computing Seminar PPTGrid computing Seminar PPT
Grid computing Seminar PPTUpender Upr
 
IRJET - Importance of Edge Computing and Cloud Computing in IoT Technolog...
IRJET -  	  Importance of Edge Computing and Cloud Computing in IoT Technolog...IRJET -  	  Importance of Edge Computing and Cloud Computing in IoT Technolog...
IRJET - Importance of Edge Computing and Cloud Computing in IoT Technolog...IRJET Journal
 

Similar to Optimising Fog Computing for IoT with Hidden Markov Models (20)

Design of an Autonomous Management and Orchestration for Fog Computing
Design of an Autonomous Management and Orchestration for Fog ComputingDesign of an Autonomous Management and Orchestration for Fog Computing
Design of an Autonomous Management and Orchestration for Fog Computing
 
Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.
Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.
Job Scheduling Mechanisms in Fog Computing Using Soft Computing Techniques.
 
FOG COMPUTING, what and why a fog computing
FOG COMPUTING, what and why a fog computingFOG COMPUTING, what and why a fog computing
FOG COMPUTING, what and why a fog computing
 
Fog Computing
Fog ComputingFog Computing
Fog Computing
 
IRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational LeapIRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational Leap
 
IRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational LeapIRJET- Edge Computing the Next Computational Leap
IRJET- Edge Computing the Next Computational Leap
 
The Future of Fog Computing and IoT: Revolutionizing Data Processing
The Future of Fog Computing and IoT: Revolutionizing Data ProcessingThe Future of Fog Computing and IoT: Revolutionizing Data Processing
The Future of Fog Computing and IoT: Revolutionizing Data Processing
 
Walking through the fog (computing) - Keynote talk at Italian Networking Work...
Walking through the fog (computing) - Keynote talk at Italian Networking Work...Walking through the fog (computing) - Keynote talk at Italian Networking Work...
Walking through the fog (computing) - Keynote talk at Italian Networking Work...
 
Internet of things - Introduction and Variations (Architecture)
Internet of things - Introduction and Variations (Architecture)Internet of things - Introduction and Variations (Architecture)
Internet of things - Introduction and Variations (Architecture)
 
A Case Study On Implementation Of Grid Computing To Academic Institution
A Case Study On Implementation Of Grid Computing To Academic InstitutionA Case Study On Implementation Of Grid Computing To Academic Institution
A Case Study On Implementation Of Grid Computing To Academic Institution
 
Data processing in Cyber-Physical Systems
Data processing in Cyber-Physical SystemsData processing in Cyber-Physical Systems
Data processing in Cyber-Physical Systems
 
FG2.pptx
FG2.pptxFG2.pptx
FG2.pptx
 
What is Edge Computing and Why does it matter in IoT?
What is Edge Computing and Why does it matter in IoT?What is Edge Computing and Why does it matter in IoT?
What is Edge Computing and Why does it matter in IoT?
 
Cloud computing managing
Cloud computing managingCloud computing managing
Cloud computing managing
 
Fog computing
Fog computing Fog computing
Fog computing
 
Fog Computing
Fog ComputingFog Computing
Fog Computing
 
Get Cloud Resources to the IoT Edge with Fog Computing
Get Cloud Resources to the IoT Edge with Fog ComputingGet Cloud Resources to the IoT Edge with Fog Computing
Get Cloud Resources to the IoT Edge with Fog Computing
 
Fog computing technology
Fog computing technologyFog computing technology
Fog computing technology
 
Grid computing Seminar PPT
Grid computing Seminar PPTGrid computing Seminar PPT
Grid computing Seminar PPT
 
IRJET - Importance of Edge Computing and Cloud Computing in IoT Technolog...
IRJET -  	  Importance of Edge Computing and Cloud Computing in IoT Technolog...IRJET -  	  Importance of Edge Computing and Cloud Computing in IoT Technolog...
IRJET - Importance of Edge Computing and Cloud Computing in IoT Technolog...
 

Recently uploaded

SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your BudgetHyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your BudgetEnjoy Anytime
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Hyundai Motor Group
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 

Recently uploaded (20)

SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your BudgetHyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 

Optimising Fog Computing for IoT with Hidden Markov Models

  • 1. The Changing Face of Telcos in a Digital World Optimisation of Fog computing for Industrial IoT applications Sabelo Dlamini University of Cape Town Cape Town, South Africa dlmsab003@myuct.ac.za Neco Ventura University of Cape Town Cape Town, South Africa neco@crg.ee.uct.ac.za H. Anthony Chan Huawei Technologies 1700 Alma Dr. Plano, USA h.anthony.chan@huawei.com 2019 Southern Africa Telecommunication Networks and Applications Conference (SATNAC) SATNAC 2019 (September 1-4, 2019) Fairmont Zimbali, Ballito, Durban, South Africa
  • 2. Contents • Introduction • Background • Related Work • Proposed Scheme • Evaluation • Conclusion and Future Work
  • 3. Introduction • The application of IoT in the manufacturing industry is normally referred to as the Industrial Internet of Things (IIoT). • Manufacturing companies that have adopted smart manufacturing in their operations are already seeing improved results with 82% increased operational efficiency and improved product quality with 49% fewer product defects, according to Microsoft research . • American Society for Quality states that connecting devices and analyzing the data collected enables manufacturers to reduce overhead, conserve resources, increase profits and optimize operational efficiencies Internet of Things (IoT) is expected to provide a quantum leap for the manufacturing industry with the market potential for industrial applications projected to be $913 billion by 2018. Industry analysts are projecting that there will be up to 50 billion connected devices with a market potential of between $10.6 to 14.2 trillion by 2030
  • 4. Fog Computing • As more factory processes adopt smart manufacturing, the data velocity and volume increases, moving the big data from factory sensor/actuators to the cloud might not be efficient, or even feasible due to bandwidth and network connection constraints. • While on the other hand, smart manufacturing is required to support time-sensitive and location-aware applications, such as real-time manufacturing applications, making the distant cloud not be able to satisfy the low latency requirements of these applications. • Fog computing bridges the gap between the cloud and things to address the latency, network bandwidth and availability and privacy/security issues in Internet of Things (IoT). • Fog architectures selectively move compute, storage, communication, control, and decision making closer to the network edge where data is being generated in order solve the limitations in current infrastructure to enable mission-critical, data-dense use cases. Current “cloud-only” architectures cannot keep up with the volume and velocity of this data across the network, thereby reducing the value that can be created and captured from these investments.
  • 5. Fog Computing – Autonomy • As a technological paradigm, edge computing may be architecturally organized as an autonomic (self-healing) computing network. • Autonomy should enable decision making to be made at all levels of a deployment’s hierarchy including near the device or higher order layers. • Autonomy at the network edge means intelligence from local devices and peer data can be used to fulfil the business’ mission at the point where it makes the most business sense. • In this study we focus on enhancing Fog Computing’s autonomy to reduce delays in decision-making. The autonomy pillar requires fog nodes to continue to deliver the designed functionality in the face of the external service failures.
  • 6. Related Work • Aazam et al. In [11] : – highlights the fast processing of the sensed data to generate instructions for the actuators and robots within some acceptable latency as one of the challenges. – other challenge noted was data structuring and filtering to avoid sending unnecessary data to the core and the cloud. • Li et al. In [12] : – proposed a service popularity-based smart resources partitioning scheme for Fog computing-enabled IIoT to improve delay time and fault tolerance. – Their proposed scheme demonstrated improved performance. It was tested simulated using iFogSim a similar simulator that has been adopted in this paper. • de Brito et al. In [15] : – highlights the challenge of orchestration in fog-enabled infrastructure environment and proposes an infrastructure management and orchestration architecture for an fog computing. – proposed architecture switches between centralized and distributed model. de Brito et al. not explore much on the implementation of automatic event triggers. Recently, there has been a number of promising research initiatives focused on solving issues related to IoT and Fog computing.
  • 7. Related Work… • Checkired et al. In [17] : – stated that the collected and sensed data from IIoT need to be scheduled in real-time, especially for big factories, and proposed a hierarchical Fog servers’ deployment at the network service layer across different tiers – this study proved that processing data closer to the edge does improve performance in IIoT applications. • Fui et al. In [18] : – highlighted the challenges of data processing, secure storage, efficient retrieval and dynamic data collection in IIoT. – argued that storing all the IIoT data raw is unwise considering that the end devices energy and storage space is limited in these devices. – Proposed a scheme that selectively processes data based on latency requirements, where the raw data is pre-processed in the Fog and then the time-sensitive data are used and stored locally, while the rest is sent to the cloud • de Brito et al. In [20] : – addressed the problem of distributed decision making, but this work focused on the challenge of service hosting where Fog nodes are required to be adaptively configured to host services for sensor nodes. – proposed the use of an online distributed algorithm, called adaptive Fog configuration (AFC), to optimize service hosting and task admission decisions. Recently, there has been a number of promising research initiatives focused on solving issues related to IoT and Fog computing.
  • 8. Fog Computing – Machine Learning • Robustness of machine learning algorithms is a key challenge for applications (e.g., self-driving cars and network operation) in real-world environments where learning errors could lead to high costs. • Most machine learning implementations require training process which is often time consuming and involves high cost for small to medium manufactures • One big challenge faced by cloud-based ML-solutions in manufacturing is delay. Most applications are delay-sensitive, it is not easy to design a real-time system with heavy computation loads. • Challenges with cloud-based Machine Learning solutions: – implementations require training process which is often time consuming and involves high cost. – require data collection and data analysis for the performance of the network Machine Learning is in the forefront of research today that requires computation for both training models, and inference or scoring those models for close to real time response at the edge.
  • 9. Fog Computing – Hidden Markov Model (ML) • Finite State Machines are efficient implementations of artificial intelligence with less storage and processing requirements • Finite State Machines are considered at the design phase and have been successfully implemented in: – Border Gateway Protocols (BGP) – Controller Area Network (CAN) – IEEE 802.11 (Wi-Fi) • Edge Intelligence: – Propose an option to provide decent intelligence to a network without going through the different stages required to setup a machine learning function to support network decision making. • OpenFog, ETSI NFV MANO and FSM • Requires detailed design and analysis of the proposed operation environment Proposed scheme uses Hidden Markov Models, a machine learning algorithm that has been widely used in autonomous robotics to enhance decision-making. ETSI MANO Architecture OpenFog Architecture Hidden Markov Model Io T Fog Manageme nt State
  • 10. Proposed Scheme Integration and the use of Hidden Markov Model to automatically optimise the Fog computing based systems. • Propose a scheme to enable fog-based systems to self-manage, including self-configuration, self-optimization, and self-healing. This can be achieved by an autonomic function having minimal dependencies on human administrators or centralized management systems • Proposed scheme will be sitting in the edge node of the autonomous edge network • If the network performance indicators are not satisfying the network user requirements as defined, the proposed scheme will automatically change the state of the network • Proposed scheme will use reduce latency (average loop latency), and network usage. Backhaul Edge Node Central Cloud Autonomous Management and Orchestration Centralised ManagementDistributed Management Fog Nodes ETSI MANO HM M
  • 11. Proposed Scheme As mentioned in the proposed scheme, we will adopt the Hidden Markov Model as a Machine Learning algorithm which has widely adopted in resource management in cloud computing applications . • Distributed Mode: In this state, the Fog computing is fully autonomous and is able to independently make decisions and function on its own, with sufficient resources available. In this state, the computing functions are locally implemented, the main aim is to have the system spending most of its time in this mode or state. • Hybrid Mode: This is the state where Fog computing has unreliable connectivity to the cloud. Fog computing is integrated with the cloud over the unguaranteed network connecting, necessitating switching between the previous state and the centralized state. In this state, Fog computing performs storage and computation are locally implemented while networking is remote. • Centralized Mode: In this state, the Fog is integrated with the cloud well. Computation, storage, and networking are centrally provided by the Cloud. Cloud provides more sturdy computation and storage facilities with the drawback of high backhaul link consumption and cost related to the use of cloud computing facilities.
  • 12. Experimental Setup • In order to compare the performance of both the resource management scheme for the study, we used iFogSim was used for simulation of resource management, specifically scheduling policies between Fog computing and cloud computing with varying network configurations . • We used a basic Fog node to sensor setup, each sensor/actuator is connected to a Wi-Fi gateway, the gateway is then connected to an ISP gateway, which connects the Fog computing to the Cloud datacenter. . Source Destination Latency (ms) Sensor/Actuator Fog Node 61ms Fog Node Fog Node 22ms Fog Node Fog Node 70ms Edge Node Edge Node 30ms Edge Node Cloud 200ms
  • 13. • Distributed management provide very low latencies for Fog computing with a limited number of sensor/actuators connected to the Fog node. • distributed management provides lower latency when compared to centralized management in nodes below 16. • Network usage from 16 sensors/actuators in both centralized and distributed mode performance is the same, this is caused by limited resources in the Fog nodes and transferred processing to the cloud. • This results in similar performance between the two-management mode. Therefore, it may be better to switch to centralized mode as soon as the network usage is similar. Results and Discussion
  • 14. Conclusion • Distributed management mode performed better than centralized with a low number of sensor/actuators connected to the Fog node. • Both management modes demonstrated similar performance from 32 sensors/actuators, highlighting the need for both modes. • One big challenge faced by cloud-based ML-solutions in manufacturing is delay. Most applications are delay-sensitive, it is not easy to design a real-time system with heavy computation loads. • The results highlight that there is a need for both orchestration (centralized management) and choreography (distributed management) in a Fog computing environment. • In addition to this we believe that there is a need for an intelligent switching between the centralized and distributed mode in order to enhance performance and reduce latency. As future work to develop an intelligent machine learning based scheme that can enhance switching between the two modes. The scheme will sense the change conditions and switch management mode accordingly.
  • 15. References [1] IDC, Internet of Things Spending Guide by Vertical Market, 2014. [2] Luxiu Yin, Juan Luo, Haibo Luo. “Tasks Scheduling and Resource Allocation in Fog Computing Based on Containers for Smart Manufacturing,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October, 2018 [3] Microsoft, Competing in the digital age of manufacturing, 2018. [4] Sebastian Trinks, Carsten Felden. “Edge Computing architecture to support Real Time Analytic applications: A State-of-the-art within the application area of Smart Factory and Industry 4.0,” IEEE International Conference on Big Data (Big Data), 2018 [5] Flavio Bonomi, Rodolfo Milito, Jiang Zhu, Sateesh Addepalli. “Fog Computing and Its Role in the Internet of Things,” ACM SIGCOMM Mobile Cloud Computing (MCC), 2012 [6] P1934/D2.0, Apr 2018 - IEEE Approved Draft Standard for Adoption of OpenFog Reference Architecture for Fog Computing, 2018 [7] Yuxuan Jiang, Zhe Huang, Danny H. K. Tsang. “Challenges and Solutions in Fog Computing Orchestration,” IEEE Network, volume: 32, issue: 3, May/June, 2018 [8] Mithun Mukherjee, Lei Shu, Di Wang. “Survey of Fog Computing: Fundamental, Network Applications, and Research Challenges,” IEEE Communications Surveys & Tutorials, vol. 20, no. 3, 2018 [9] B. Zhang, N. Mor , J. Kolb , D.S. Chan , K. Lutz , E. Allman , J. Wawrzynek , E.A. Lee , J. Kubiatowicz , The cloud is not enough: saving IoT from the cloud., HotStorage, 2015 [10] Saad Khan, Simon Parkinson, Yongrui Qin. “Fog computing security: a review of current applications and security solutions,” Springer Journal of Cloud Computing, December 2017 [11] Mohammad Aazam, Sherali Zeadally, and Khaled A. Harras. “Deploying Fog Computing in Industrial Internet of Things and Industry 4.0,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018 [12] Gaolei Li, Jun Wu, Jianhua Li, Kuan Wang, and Tianpeng Ye. “Service Popularity-Based Smart Resources Partitioning for Fog Computing-Enabled Industrial Internet of Things,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018 [13] Sabelo Dlamini, Neco Ventura. “Enhancement of Fog Computing based Autonomous Management Systems,” Southern Africa Telecommunication Networks and Applications Conference (SATNAC), 2018 [14] Sabelo Dlamini, Joyce Mwangama, Neco Ventura and Thomas Magedanz. “Design of an Autonomous Management and Orchestration for Fog Computing,” International Conference on Intelligent and Innovative Computing Applications (ICONIC), 2018 [15] M.S. de Brito, S. Hoque, R. Steinke, A. Willner and T. Magedanz. “Application of the Fog computing paradigm to Smart Factories and cyber-physical systems,” Trans Emerging Tel Tech. 2018;
  • 16. References… [16] Harshit Gupta, Amir Vahid Dastjerdi, Soumya K. Ghosh, Rajkumar Buyya. " iFogSim: A Toolkit for Modeling and Simulation of Resource Management Techniques in Internet of Things, Edge and Fog Computing Environments" [17] Djabir Abdeldjalil Chekired, Lyes Khoukhi and Hussein T. Mouftah. “Industrial IoT Data Scheduling Based on Hierarchical Fog Computing: A Key for Enabling Smart Factory,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018 [18] Jun-Song Fu, Yun Liu, Han-Chieh Chao, Bharat K. Bhargava and Zhen-Jiang Zhang. “Secure Data Storage and Searching for Industrial IoT by Integrating Fog Computing and Cloud Computing,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018 [19] Mohammad Ashjaei and Marcus Bengtsson “Enhancing Smart Maintenance Management Using Fog Computing Technology,” IEEE IEEM, 2017 [20] Lixing Chen, Pan Zhou, Liang Gao and Jie Xu. “Adaptive Fog Configuration for the Industrial Internet of Things,” IEEE Transactions on Industrial Informatics, vol. 14, no. 10, October 2018 [21] Chenhua Shi, Zhiyuan Ren, Kun Yangy, Chen Chen, Hailin Zhang, Yao Xiao and Xiangwang Hou. “Ultra-Low Latency Cloud-Fog Computing for Industrial Internet of Things,” IEEE Wireless Communications and Networking Conference (WCNC), 2018 [22] Gabriele Castellano, Fulvio Risso, and Riccardo Loti. “Fog Computing over Challenged Networks: a Real Case Evaluation,” IEEE 7th International Conference on Cloud Networking (CloudNet), October, 2018 [23] Olena Skarlat, Vasileios Karagiannis, Thomas Rausch, Kevin Bachmann and Stefan Schulte. “A Framework for Optimization, Service Placement, and Runtime Operation in the Fog,” IEEE/ACM 11th International Conference on Utility and Cloud Computing (UCC), 2018. [24] F. Bonomi, R. Milito, P. Natarajan, J. Zhu, "Fog Computing: A Platform for Internet of Things and Analytics", Big Data and Internet of Things: A Roadmap for Smart Environments ser. Studies in Computational Intelligence, vol. 546, pp. 169-186, 2014. [25] A.V. Dastjerdi, H. Gupta, R.N. Calheiros, S.K. Ghosh, R. Buyya, "Fog Computing: Principles Architectures and Applications", Internet of Things: Principles and Paradigms, 2016. [26] Sergej Svorobej, Patricia Takako Endo, Malika Bendechache, Christos Filelis-Papadopoulos, Konstantinos M. Giannoutakis, George A. Gravvanis, Dimitrios Tzovaras, James Byrne and Theo Lynn. “Simulating Fog and Edge Computing Scenarios: An Overview and Research Challenges,” MDPI Future Internet, 2018 [27] Qayyum, T.; Malik, A.W.; Khattak, M.A.K.; Khalid, O.; Khan, S.U. FogNetSim++: A Toolkit for Modeling and Simulation of Distributed Fog Environment. IEEE Access 2018 [28] Saiful Hoque, Mathias Santos de Brito, Alexander Willner. “Towards Container Orchestration in Fog Computing Infrastructures,” International Workshop on Fog Computing and Networking (FCN), July, 2017 [29] Zhenyu Wen, Renyu Yang, Peter Garraghan, Tao Lin, Jie Xu, and Michael Rovatsos. Fog orchestration for internet of things services. IEEE Internet Computing, 21(2):16–24, 2017.