Assignment no:5

1] Explain Big data Analytics and Software Defined

Networks?
Big data analytics is the often complex process of
examining big data to uncover information -- such as
hidden patterns, correlations, market trends and
customer preferences -- that can help organizations
make informed business decisions.
> Big data is different from conventional Data Warehouse
(DW) approaches.
> Big data apps cannot be fit in traditional DW
architectures (e.g Exadata ,Teradata)
> Distributed nothing, mighty parallel performing, scale
out frameworks are convenient for big data apps
>lloT can be recognized as a big benefactor of Big DataIt
needs new technologies to manage vast data.
>Cloud services are accessible to handle Big Data with
no-limit of storage on demand.
>In IloT, Hadoop (open source cloud based distributed
data storage) is also available for managing the data
Software Defined Network

Software-Defined Networking (SDN) is

a networking paradigm that allows the centralized control and
programmability of network infrastructure using software. It
provides a flexible and dynamic approach to network
management, enabling the automation and optimization of
network resources. When applied to the Industrial Internet of
Things (IIoT) domain, SDN brings several benefits and
considerations.

6TiSCH (IPv6 over the TSCH mode of IEEE 802.15.4e) is a

communication protocol stack specifically designed for low-power
and time-sensitive Industrial Internet of Things (IIoT) applications.
It combines the IPv6 networking protocol with the Time-Slotted
Channel Hopping (TSCH) media access control mechanism
defined in the IEEE 802.15.4e standard.
1. Low-Power and Energy Efficiency: 6TiSCH is optimized for
energy-constrained devices in IIoT deployments. By utilizing the
TSCH mode, which divides time into slots and assigns specific
channels to each slot, 6TiSCH enables devices to operate in a
synchronized manner, allowing them to sleep during idle periods
and conserve energy.

2. Deterministic Communication: In IIoT applications, deterministic

communication is crucial, especially in scenarios where real-time
control and coordination are required. 6TiSCH, with its time-
slotted operation, provides deterministic scheduling, ensuring
predictable and reliable communication between devices. It allows
for strict control over latency, packet delivery, and network
synchronization.

3. IPv6 Connectivity: 6TiSCH employs IPv6 as the network layer

protocol, enabling seamless integration of IIoT devices with the
existing Internet infrastructure. By utilizing IPv6, 6TiSCH provides
each device in the network with a unique IP address, enabling
end-to-end connectivity, scalability, and interoperability.

4. Time-Slotted Channel Hopping: The TSCH mode in 6TiSCH

divides time into slots, and each slot is associated with a specific
channel. This time and frequency hopping mechanism ensures
interference-free communication and improves reliability in IIoT
environments, where interference and congestion are common
challenges. Devices synchronize their schedules, allowing them to
communicate efficiently and avoid collisions.
5. Robustness and Resilience: 6TiSCH is designed to operate in
harsh and dynamic industrial environments. The use of TSCH
provides resilience to interference and ensures reliable
communication by hopping channels to avoid congested or noisy
channels. The protocol also supports link-layer retransmissions,
further enhancing robustness and reliability.

6. Scalability and Flexibility: 6TiSCH allows for the flexible

deployment of IIoT networks. It supports both centralized and
distributed network topologies, enabling scalability and
adaptability to various IIoT deployment scenarios. The protocol
accommodates various device types, ranging from resource-
constrained sensors to more powerful gateways and edge devices.

By combining low-power and energy-efficient communication,

deterministic scheduling, IPv6 connectivity, and TSCH's time and
frequency hopping mechanism, 6TiSCH provides a reliable and
robust communication solution for IIoT applications. It addresses
the specific requirements of industrial environments, such as
latency, reliability, scalability, and energy efficiency, making it
suitable for time-critical and mission-critical IIoT deployments.

2] Write note on Machine learning and also write applications

of lot with Machine Learning
Machine Learning is a subset of artificial intelligence (AI) that
focuses on the development of algorithms and models that
enable computer systems to learn and make predictions or
decisions without explicit programming. It involves the use of
statistical techniques to enable machines to improve their
performance on a given task through experience and data.
Machine Learning is widely used in various domains and has the
potential to revolutionize industries by enabling intelligent
systems to automate processes, extract insights from large
datasets, and make informed decisions.

>Machine Learning finds applications in a wide range of industries

and domains

1. Healthcare: Machine Learning is used for disease diagnosis,

medical imaging analysis, drug discovery, personalized
medicine, and patient monitoring. It helps in predicting
disease outcomes, identifying high-risk patients, and
optimizing treatment plans.

2. Finance: Machine Learning is employed in fraud detection,

credit scoring, algorithmic trading, portfolio management,
and risk assessment. It assists in detecting suspicious
patterns, assessing creditworthiness, predicting market
trends, and optimizing investment strategies.

3. E-commerce and Marketing: Machine Learning enables

personalized recommendations, customer segmentation,
demand forecasting, sentiment analysis, and churn
prediction. It helps in improving customer experience,
 targeting relevant advertisements, optimizing pricing, and
enhancing sales and marketing strategies.

4. Manufacturing and Industry: Machine Learning is used for

predictive maintenance, quality control, supply chain
optimization, anomaly detection, and process optimization. It
aids in identifying potential equipment failures, minimizing
downtime, improving product quality, and optimizing
production efficiency.

5. Natural Language Processing (NLP): Machine Learning

techniques are employed in NLP applications such as speech
recognition, sentiment analysis, language translation,
chatbots, and information retrieval. It enables machines to
understand and generate human language, facilitating
communication and interaction between humans and
computers.

6. Autonomous Vehicles: Machine Learning plays a crucial role

in developing self-driving cars and autonomous vehicles. It
enables perception systems to recognize objects, make real-
time decisions, and navigate safely in complex environments.

7. Image and Video Processing: Machine Learning is utilized for

object recognition, image classification, image generation,
video analysis, and computer vision tasks. It helps in tasks
like facial recognition, object detection, image restoration,
and video surveillance.
 8. Recommender Systems: Machine Learning powers
recommender systems used by platforms like Netflix,
Amazon, and Spotify to suggest personalized content,
products, and recommendations based on user preferences
and behavior.

3]
Machine learning Deep learning

A subset of AI A subset of machine learning

Can train on smaller data sets Requires large amounts of data

Requires more human

Learns on its own from
intervention to correct and
environment and past mistakes
learn
Shorter training and lower Longer training and higher
accuracy accuracy
Makes simple, linear Makes non-linear, complex
correlations correlations
Can train on a CPU (central Needs a specialized GPU
processing unit) (graphics processing unit) to
train

Machine learning Deep Learning

Requires less hardware capacity Requires high end hardware
than deep learning capabilities such as GPUs to
perform at its best
Training time is less Training time is high
Data points are hundreds to few Data points can be into millions
thousands
Uses automated algorithms that Interprets features in data and
learn to predict future decisions the relationships using neural
and model functions using the networks which pass the data
data which is provided. through several layers of the
algorithm.

4]Cloud computing in IIOT

Cloud computing in the context of Industrial Internet of Things

(IIoT) refers to the utilization of cloud-based services and
infrastructure to store, process, and analyze data generated by
IIoT devices and applications. It involves leveraging the power of
remote servers, networks, and services provided by cloud service
providers to enable scalable, on-demand, and cost-effective
computing resources for IIoT deployments. Here's an explanation
of cloud computing in IIoT:

1. Data Storage and Scalability: IIoT generates a vast amount of

data from sensors, devices, and machinery. Cloud computing
provides scalable and flexible storage solutions to handle this
massive volume of data. IIoT data can be securely stored in cloud-
based storage systems, such as object storage or databases,
allowing easy access, retrieval, and management of data as per
business requirements.

2. Data Processing and Analytics: Cloud computing enables

powerful data processing and analytics capabilities for IIoT
applications. IIoT data stored in the cloud can be processed and
analyzed using cloud-based services, such as serverless
computing, big data frameworks, or machine learning platforms.
This allows businesses to derive valuable insights, detect patterns,
and make data-driven decisions to optimize operations, predict
failures, and improve efficiency in industrial processes.

3. Edge-to-Cloud Connectivity: In IIoT deployments, there is often

a need for real-time or near-real-time processing and decision-
making. Cloud computing facilitates edge-to-cloud connectivity,
where edge devices or gateways at the network edge perform
local processing and send selected data to the cloud for further
analysis and storage. This hybrid approach balances the need for
low-latency processing at the edge and the computational power
and storage capabilities of the cloud.

4. Scalable and Flexible Infrastructure: Cloud computing provides

a highly scalable and flexible infrastructure for IIoT applications.
With cloud services, businesses can scale their computing
resources up or down based on demand, avoiding the need for
upfront investments in hardware and infrastructure. This flexibility
enables organizations to adapt to changing workloads and
accommodate the growth of IIoT deployments without the
constraints of physical infrastructure limitations.

5. Security and Reliability: Cloud service providers often have

robust security measures in place to protect IIoT data stored in
the cloud. These measures include encryption, access control, data
backups, and disaster recovery capabilities. Leveraging cloud
services can provide IIoT deployments with enhanced data
security, reliability, and business continuity.

6. Collaboration and Integration: Cloud computing enables

seamless collaboration and integration of IIoT data and
applications with other cloud-based services, third-party
applications, or existing enterprise systems. By integrating IIoT
data with cloud-based platforms, businesses can derive deeper
insights, enable cross-domain analytics, and connect IIoT
applications with other enterprise systems for enhanced
automation and decision-making.

7. Cost Efficiency: Cloud computing offers cost-efficient solutions

for IIoT deployments. It eliminates the need for upfront
investments in hardware, infrastructure, and maintenance costs.
Organizations pay for cloud services on a pay-as-you-go basis,
allowing them to optimize costs based on actual usage and scale
resources as needed.

Cloud computing plays a vital role in enabling the scalability, data

processing capabilities, security, and cost efficiency required for
successful IIoT implementations. It empowers businesses to
leverage the power of cloud-based services and infrastructure to
unlock the full potential of IIoT data and drive digital
transformation in industrial processes.