Cloud Computer and Computing Fundamentals.pptx

Advanced Computer Networking refers to the study and application of complex networking concepts that go beyond the basics of connecting devices and systems. It involves in-depth knowledge of networking protocols, advanced routing and switching techniques, network security, wireless networking, network virtualization, and cloud networking. Advanced topics often include:

Routing and Switching: Advanced techniques such as BGP, OSPF, MPLS, and VLAN configurations for large-scale networks.

Network Security: Implementation of firewalls, VPNs, intrusion detection/prevention systems (IDS/IPS), and security policies to protect data integrity and privacy.

Wireless Networking: Management of large-scale wireless networks (Wi-Fi 6, mesh networks), and RF spectrum analysis for optimizing wireless coverage.

Virtualization and Cloud Networking: Use of software-defined networking (SDN), network function virtualization (NFV), and cloud-based services to enhance scalability and efficiency.

High Availability and Disaster Recovery: Techniques like network redundancy, load balancing, failover systems, and backup solutions to ensure uninterrupted network operations.

This field is crucial for designing, maintaining, and securing modern, high-performance enterprise networks.






You said:
more
ChatGPT said:
ChatGPT
Here’s a more detailed description of Advanced Computer Networking with additional key topics:

Advanced IP Addressing & Subnetting: Delving into complex subnetting schemes, variable length subnet masking (VLSM), classless inter-domain routing (CIDR), and IPv6 configuration for efficient IP management in large-scale networks.

Quality of Service (QoS): Techniques to manage network traffic and ensure the reliable transmission of critical applications like VoIP and streaming media. This includes traffic prioritization, bandwidth management, and reducing latency for real-time services.

Network Automation: Automating repetitive network tasks using scripts and tools like Python, Ansible, or Cisco’s DevNet. Automation helps streamline configuration, deployment, and management of networks.

Network Monitoring & Management: Tools like SNMP, NetFlow, Wireshark, and cloud-based network monitoring services to continuously track network performance, identify bottlenecks, and troubleshoot issues in real-time.

Software-Defined Networking (SDN): A cutting-edge approach where network control is decoupled from hardware, allowing centralized and programmatic control over the network. This is pivotal in creating flexible, scalable, and easier-to-manage networks.

Data Center Networking: Focuses on the unique needs of data centers, involving the use of technologies such as FabricPath, Virtual Extensible LAN (VXLAN), and data center bridging (DCB) to provide low-latency, high-bandwidth interconnectivity for virtualized environments.

1. CM5108 – CLOUD COMPUTING Department of Computer Engineering Government Polytechnic Pune CLOUD COMPUTING

2. CLOUD COMPUTING CLOUD COMPUTING

3. UNIT – I (OVERVIEW) CLOUD COMPUTING 1. Cloud Computing in a Nutshell 2. Roots of Cloud Computing: A. From Mainframes to Clouds, B. SOA, Web Services, Web 2.0, and Mashups, C. Grid Computing, D. Utility Computing, E. Hardware Virtualization - Virtual Appliances and the Open Virtualization Format F. Autonomic Computing 3 . La y ers and Types o f Cloud s : I n frastruc t ur e a s a Service, Platform a s a Service, Software as a Service, Deployment Models 4. Properties and Characteristics of a Cloud computing 5. Challenges and Risks: Security, Privacy, and Trust, Data Lock-In and Standardization, Availability, Fault-Tolerance, and Disaster Recovery, Resource Management and Energy- Efficiency

4. 1. Cloud Computing in a Nutshell CLOUD COMPUTING COMPUTING Computing refers to “any goal oriented activity”. From digital word’s point of view it encompasses – configuration, processing, maintenance related activities Trends in Computing Distributed computing Grid Computing Cluster Computing Utility Computing CLOUD COMPUTING

5. Distributed Computing - This is advancement over the tradition “centralized computing” Make use od distributed systems to solve a problem Distributed System: Network of several autonomous computational entities, each of which has its own local memory. Computational entities = workstations, server computers, Personal assistance devices The entities communicate with each other by message passing. The processors communicate with one another through various communication lines, such as high-speed buses or telephone lines. Each processor has its own local memory. Examples of Distributed Computing: - ATM Machines, Intranet workgroups, CLOUD COMPUTING

6. Distributed Computing - Key properties of Distributed Computing: Fault tolerance •When one or some nodes fails, the whole system can still work fine except performance. •Need to check the status of each node Each node play partial role •Each computer has only a limited, incomplete view of the system. •Each computer may know only one part of the input. Resource sharing •Each user can share the computing power and storage resource in the system with other users Load Sharing •Dispatching several tasks to each nodes can help share loading to the whole system. Easy to expand •We expect to use few time when adding nodes. Hope to spend no time if possible. Performance •Parallel computing can be considered a subset of distributed computing CLOUD COMPUTING

7. Need of Distributed computing CLOUD COMPUTING Nature of Application (As per requirements) Robustness – No Single point of failure, tasks get distributed over remaining nodes Performance – Computing intensive, data intensive

8. Grid Computing - Grid •Users (or client applications) gain access to computing resources (processors, storage, data, applications, and so on) as needed with little or no knowledge of where those resources are located or what the underlying technologies, hardware, operating system, and so on are “The Grid" links together computing resources (PCs, workstations, servers, storage elements) and provides the mechanism needed to access them. When to use Grid Computing -> Share more than information: Data, computing power, applications in dynamic environment, multi- institutional, virtual organizations Efficient use of resources at many institutes. People from many institutions working to solve a common problem (virtual organization). Join local communities. Interactions with the underneath layers must be transparent and seamless to the user. CLOUD COMPUTING

9. Sample of Grid Computing CLOUD COMPUTING

10. Type of Grids: Computational Grid: These grids provide secure access to huge pool of shared processing power suitable for high throughput applications and computation intensive computing. Data Grid: Data grids provide an infrastructure to support data storage, data discovery, data handling, data publication, and data manipulation of large volumes of data actually stored in various heterogeneous databases and file systems. Collaboration Grid: With the advent of Internet, there has been an increased demand for better collaboration. Such advanced collaboration is possible using the grid. For instance, persons from different companies in a virtual enterprise can work on different components of a CAD project without even disclosing their proprietary technologies. * Network Grid: A Network Grid provides fault-tolerant and high-performance communication services. Each grid node works as a data router between two communication points, providing data- caching and other facilities to speed up the communications between such points. Utility Grid: This is the ultimate form of the Grid, in which not only data and computation cycles are shared but software or just about any resource is shared. The main services provided through utility grids are software and special equipment. For instance, the applications can be run on one machine and all the users can send their data to be processed to that machine and receive the result back. CLOUD COMPUTING

11. CLUSTER COPMUTING CLOUD COMPUTING A cluster is a type of parallel or distributed computer system, which consists of a collection of inter-connected stand- alone computers working together as a single integrated computing resource . Key components of a cluster include multiple standalone computers (PCs, Workstations, or SMPs), operating systems, high-performance interconnects, middleware, parallel programming environments, and applications. Clusters are usually deployed to improve speed and/or reliability over that provided by a single computer, while typically being much more cost effective than single computer the of comparable speed or reliability In a typical cluster: – Network: Faster, closer connection than a typical network (LAN) – Low latency communication protocols – Loosely coupled than SMP Types of Cluster High Availability or Failover Clusters Load Balancing Cluster Parallel/Distributed Processing Clusters

12. Basic building blocks of clusters are broken down into multiple categories: Cluster Nodes Cluster Network Network Characterization CLOUD COMPUTING

13. Features of Cluster Computing CLOUD COMPUTING System availability: offer inherent high system availability due to the redundancy of hardware, operating systems, and applications. •Hardware fault tolerance: redundancy for most system components (eg. disk-RAID), including both hardware and software. •OS and application reliability: run multiple copies of the OS and applications, and through this redundancy •Scalability. adding servers to the cluster or by adding more clusters to the network as the need arises or CPU to SMP. •High performance: (running cluster enabled programs)

14. “Utility” Computing ? Utility Computing is purely a concept which cloud computing practically implements. Utility computing is a service provisioning model in which a service provider makes computing resources and infrastructure management available to the customer as needed, and charges them for specific usage rather than a flat rate. This model has the advantage of a low or no initial cost to acquire computer resources; instead, computational resources are essentially rented. The word utility is used to make an analogy to other services, such as electrical power, that seek to meet fluctuating customer needs, and charge for the resources based on usage rather than on a flat-rate basis. This approach, sometimes known as pay-per-use "Utility computing" has usually envisioned some form of virtualization so that the amount of storage or computing power available is considerably larger than that of a single time-sharing computer. CLOUD COMPUTING

15. Features of Utility Computing CLOUD COMPUTING Pay-for-use Pricing Business Model Data Center Virtualization and Provisioning Solves Resource Utilization Problem Outsourcing Web Services Delivery Automation

16. Example of Utility Computing CLOUD COMPUTING

17. Cloud Computing US National Institute of Standards and Technology defines Computing as “ Cloud computing is a model for enabling ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources (e.g networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal management effort or service provider interaction. ” CLOUD COMPUTING

18. Cloud Computing Characteristics: CLOUD COMPUTING ESSENTIAL CHARACTERISTICS On- demand self service – consumer can use or release resources as per requirement (auto) Broad network access – broad access capabilities to heterogenous platforms Re s ou r ce different p o olin g – m u l t i- t enant mo d e l w i t h p h ysi c a l an d vir t ual r eso u rces dynamically assigned to consumer as per demand Measured service – pay as per usage, monitored, controlled, and reported, providing transparency for both the provider and consumer of the utilized service. Rapid Elasticity - Capabilities can be elastically pr o v i s i o ned an d r e l eas e d , i n som e cas e s automatically COMMON CHARACTERISTICS Massive scale Resilient computing Homogeneity Geographic distribution Virtualization Service orientation Low cost software Advanced security

19. SOA (Service oriented architecture) SOA is an architectural approach in which applications make use of services available in the network. In this architecture, services are provided to form applications, through a network call over the internet. It uses common communication standards to speed up and streamline the service integrations in applications. Each service in SOA is a complete business function in itself. These services are published in such a way that it makes it easy for the developers to assemble their apps using those services. CLOUD COMPUTING

20. SOA Components: There are two major roles within Service-oriented Architecture: 1.Service provider: The service provider is the maintainer of the service and the organization that makes available one or more services for others to use. To advertise services, the provider can publish them in a registry, together with a service contract that specifies the nature of the service, how to use it, the requirements for the service, and the fees charged. 2.Service consumer: The s ervi c e consumer can locate the serv i ce metadata in the registry and develop the required client components to bind and use the service. CLOUD COMPUTING

21. Web Services Web service ( WS ) is either: a service offered by an electronic device to another electronic device, communicating with each other via the World Wide Web OR a server running on a computer device, listening for requests at a particular port over a network, serving web documents (HTML, JSON, XML, images). CLOUD COMPUTING

22. Web 2.0 CLOUD COMPUTING

23. Hardware Virtualization It is logical abstraction of either components of hardware or functionalities provided by that specific hardware in a system. It hides physical characteristics of computing platform This term is also know as “Pseudo Machine” or “Virtual machine” CLOUD COMPUTING

24. Need of Hardware Virtualization CLOUD COMPUTING COST – many small components / nodes can be replaced by one larger physical entity, which could be more cost effective way To reduce maintenance over head and its related costs Virtual hardware can be easily managed and controlled from remote than physical hardware Scalable structure Ease of relocation – can be used in disaster recovery scenario

25. Types of Clouds Cloud Service Models Software as a service (SaaS) Infrastructure as a service (IaaS) Platform as a service (PaaS) Cloud Deployment Models Private Public Community Hybrid CLOUD COMPUTING

26. Cloud Service Models 1. Software as a Service (SaaS) - The capability provided to the consumer is to use the provider’s applications running on a cloud infrastructure. The applications are accessible from various client devices through either a thin client interface, such as a web browser (e.g., web-based email), or a program interface. The consumer does not manage or control the underlying cloud infrastructure including network, servers, operating systems, storage, or even individual application capabilities, with the possible exception of limited user-specific application configuration settings. e.g.: Google Spread Sheet CLOUD COMPUTING

27. Cloud Service Models CLOUD COMPUTING 2. Infrastructure as a Service (IaaS) - The capability provided to provision processing, storage, networks, and other fundamental computing resources Consumer can deploy and run arbitrary software e.g.: Amazon Web Services and Flexi scale .

28. Cloud Service Models 3. Platform as a Service (PaaS) - The ca p ab i l i t y pr o vid e d t o t he c o ns u m er i s to dep l oy onto the c l o ud i n f ras t r uc t ure c on s u m e r - creat e d o r a cqu i r e d a p pl i ca t i o ns cr e a t e d pr og ra m m ing l a ngu a ge s , l i b ra r i e s, s e r v i ce s , us i ng a n d tools supported by the provider. The consumer does not manage or control the underlying cloud infrastructure including network, servers, operating systems, or storage, but has control over the deployed applications and possibly configuration settings for the application-hosting environment. CLOUD COMPUTING

29. Cloud Service Models CLOUD COMPUTING

30. Cloud Service Models CLOUD COMPUTING

31. Cloud Deployment Models facilitate the open use to general public e.g. Google App Engine, EC2, Azure Workload locations are hidden from users/ public Public Cloud Facilitate exclusive use by single organization or business units e.g. Eucalyptus, Amazon VPC, ECI data center Can be -> on-site OR outsourced Private Cloud Composition of two or more distinct cloud e.g. windows Azure, VMWare vCloud Hybrid Cloud exclusive use by a specific community of consumers from organizations that have shared concerns e.g. Google Apps for Government Com m unity Cloud CLOUD COMPUTING

32. Challenges and Risks in Cloud Computing CLOUD COMPUTING Security – Data security, Application Security, Data Privacy, Trust, lock-in Performance monitoring – Availability, Fault tolerance, resource management, disaster recovery Consistent and robust service abstraction – Data standardization Meta scheduling - Availability, Fault tolerance Energy efficient load balancing – resource management Scale management - Availability, Fault tolerance, resource management SLA and QoS architecture Interoperability and portability Green computing/ environment efficient IT – Energy efficiency