2. OUTLINES
• Introduction
• Cloud computing applications
• Cloud management
• Multi-cloud management
• Multi-access edge computing
• Optimizing the cloud computing performance
• Optimization methods
• Literature review for the previous research work
• Adopting locust inspired algorithm into the cloud computing area
• Server consolidation based on locust inspired algorithm
• The obtained results
• Cloudlet scheduling based on locust inspired algorithm
• The obtained results
• Conclusion
• My PhD publications
• References
3. INTRODUCTION
• Cloud computing is a current computer technology for delivering
services to customers based on demand. This technology eases access
to information through various devices, for instance, Smart-phones,
PDAs, PCs, and tablets. Nowadays, cloud computing is considered a
worldwide trend, with many advantages.
• The cloud computing is required cloud management to handle it.
4. CLOUD COMPUTING APPLICATIONS
CLOUD COMPUTING EXAMPLES
• Software-as-a-Service (SaaS): Salesforce
• Infrastructure-as-a-Service (IaaS): DigitalOcean
• Platform-as-a-Service (PaaS): AWS
• File Sharing + Data Storage: Dropbox
• Big Data Analysis: Civis Analytics
• Data Governance: Carbonite
• Cybersecurity: Forcepoint
5.
6. CLOUD MANAGEMENT
• Cloud management is a suite of software tools that enterprises use to
manage and optimize their cloud resources. It is also a practice that allows
administrators to control and orchestrate all of the products and services that
run on a cloud, such as user accounts, access, data, applications, and
services.
• Cloud management solutions are built to reduce complexity and provide IT
teams with an easy-to-use platform with a rich UI to simplify the overall
management of the hybrid IT estate. It ensures that decision-making is
accelerated as information is available in real-time.
7. CLOUD MANAGEMENT PLATFORMS
• Cloud Management Platforms are highly sophisticated products
that provide administrators with the required tools to manage
cloud infrastructures. To this end, cloud management
platforms can manage a range of infrastructures including
private, public, and hybrid cloud environments.
8. CLOUD MANAGEMENT PLATFORM
FUNCTIONS
• To be considered as a Cloud Management Platform, it needs to
fulfill certain functions as follows:
1. A self-service user interface.
2. Provision system images.
3. Include metering and billing functionality.
4. Workload balancing and optimization.
9. LIST OF THE TOP 10 CLOUD MANAGEMENT
SOFTWARE
1.VMware
2. IBM Cloud Orchestrator
3. Flexera Rightscale
4. Apache CloudStack
5. BMC Cloud Lifecycle Management
6. Scalr
7. Embotics
8. OpenStack
9. RedHat CloudForms
10. CloudHealth
11. WHAT IS MULTI-CLOUD MANAGEMENT?
• Multi-cloud management is the set of tools and procedures
that allows a business to monitor and secure applications and
workloads across multiple public clouds. Ideally, a multi-cloud
management solution allows IT teams to manage multiple
clouds from a single interface, and supports multiple cloud
platforms (such as AWS and Azure) as well as new tools
like Kubernetes.
• Today, most organizations use more than one public
cloud service provider. This reduces dependency on any one
vendor.
12. WHAT ARE THE BENEFITS OF MULTI-CLOUD
MANAGEMENT?
• Reduced strain on IT teams: By offering simplified, centralized management.
• Visibility: Without multi-cloud management, it’s difficult to monitor workloads and know
what’s running where in a complex environment that spans multiple cloud providers.
• Security: It’s challenging to keep security policies consistent across cloud providers, and
the complexity of multi-cloud can contribute to security holes and an increased attack
surface. A managed approach allows IT teams to deal with potential security issues
proactively.
• Cost management: While many businesses adopt a multi-cloud strategy to take advantage
of discounts and cost savings offered by different cloud providers, it’s easy to lose track
of costs in the increased complexity of a multi-cloud environment. Multi-cloud
management helps your business keep track of costs and usage, and some platforms
even use intelligent data analysis to optimize cost management.
• Increased availability: Availability is just one of the many advantages that businesses seek
when they pursue a multi-cloud strategy. But to fully realize the benefits of multi-cloud,
IT teams need to be able to duplicate and seamlessly migrate workloads when one
14. WHAT IS MULTI-ACCESS EDGE COMPUTING
OR MULTI EDGE?
• Multi-Access Edge Computing (MEC) moves the computing of traffic
and services from a centralized cloud to the edge of the network and
closer to the customer. Instead of sending all data to a cloud for
processing, the network edge analyzes, processes, and stores the
data. Collecting and processing data closer to the customer reduces
latency and brings real-time performance to high-bandwidth
applications.
17. HOW IS MEC USED?
Some common MEC use cases are:
• Data and video analytics
• Location tracking services
• Internet-of-Things (IoT)
• Augmented reality
• Local hosting of content, such as videos
An IoT example is a connected car constantly sensing driving patterns, road
conditions and other vehicle movements to provide safety guidance to the driver.
18. OPTIMIZING THE CLOUD COMPUTING
PERFORMANCE
OPEN ISSUES FOR CLOUD COMPUTING DEVELOPERS
19. OPTIMIZATION METHODS
• Cloud computing is a worldwide trend and it is still in
consideration for evolving by cloud developers.
• Many challenges are facing cloud computing such as handling
the high number of users’ requests, the energy consumption of
the date centers, the system availability, the execution time for
the submitted tasks, the waiting time, the cost, the single point
of failure, and many more.
20. CLOUD COMPUTING SOLUTIONS
• One of the solutions to encounter the cloud computing
challenges is the nature-inspired algorithms to manage the
scheduling of the cloudlet and mapping the servers.
21. LITERATURE REVIEW OF BIO-INSPIRED
ALGORITHMS
• A human inspired method was proposed by (Bhatt et al, 2020) to solve the job shop scheduling
problem for scheduling in a multicloud environment.
• Energy-efficient scheduling was proposed by (Sharma and Garg, 2020) , where they came up with
a novel hybrid meta-heuristic scheme, namely, the harmony-inspired genetic algorithm (HIGA). A
capacity exploration of the harmony search and genetic algorithm has been combined in HIGA with
providing quick convergence in the local and global optimal regions.
• (Kumar et al, 2020) studied crows’ search habits in collecting food, attempting to adapt the
behavior for use in the cloud computing environment. Crows monitor their mates to discover better
food sources, which was the inspiration for the crow search algorithm (CSA) intended to find
suitable VMs for tasks while reducing the execution time of the algorithm.
• A problem-dependent resource scheduling algorithm inspired from locusts was proposed by (Kurdi
et al,2018). This can be considered a decentralized software optimization approach for ensuring
robustness, scalability, and cost-effectiveness. However, the research is still in the primary stage of
development. This letter offers a deep analysis that points out the limitations of the algorithm
developed by (Kurdi et al,2018) while discussing work in progress to address these limitations and
to optimize the overall algorithm.
25. AREA 2: CLOUDLET SCHEDULING
• This feeding behavior depends on a local search by locusts that are looking for food.
Additionally, the mating and gregarious phases are represented as the social
interactions of locusts, and the rate of change in the position of a locust can be
represented mathematically. We used the following mathematical model to simulate the
swarm behavior of locusts
There are N locusts in the group, which represents the cloudlets, and the ith locust has
position xi. xi as the locust position, the social interactions Si, gravity vg, and downwind
advection va are each represented in the three phases of the proposed algorithm. The
allocation problem of cloudlets can be solved while achieving significant improvements in
the makespan, waiting time, and utilization metrics.
28. CONCLUSION
• Cloud computing is a paradigm that contains sensitive data for
organizations and industries that required accurate work by researchers to
develop their systems, while, many users are migrating their works and data
to be online that giving them the ability to access the data easier and handle
massive data on devices with simple specs.
• Cloud computing has many areas that are still under development.
• Using bio-inspired algorithms can present an impressive optimization for
cloud computing.
• We have presented enhancements for the performance of cloud computing
that are inspired from locust.
• Our algorithm can be adopted in other areas of cloud computing such as
edge computing.
29. PHD PUBLICATIONS
International Refereed Journals
• Mohammed Ala’anzy and Mohamed Othman (2019). Load balancing and server consolidation in cloud computing
environments: A meta-study. IEEE Access, 7, 141868-141887. (Published 2019, JIF = 3.745, Q1, ISI, JCR)
• Mohammed Alaa Ala’anzy, Mohamed Othman, Zurina Mohd Hanapi, and Mohamed A Alrshah (2021). Locust Inspired
Algorithm for Cloudlet Scheduling in Cloud Computing Environments. Sensors, 21, 7308. (Published 2021, JIF = 3.576,
Q1, ISI, JCR)
• Mohammed Alaa Ala’anzy and Mohamed Othman (2021). Mapping and Consolidation of VMs Using Locust-Inspired
Algorithms for Green Cloud Computing. Neural Processing Letters, 54, 405–421. (Published 2021, JIF =2.908, Q2, ISI,
JCR)
International Refereed Conferences
• Mohammed Alanzy, Rohaya Latip, and Abdullah Muhammed (2018). Range wise busy checking 2-way imbalanced
algorithm for cloudlet allocation in cloud environment. In Journal of Physics: Conference Series, IOP Publishing, 1st
International Conference on Big Data and Cloud Computing (ICoBiC) 2017 25–27 November 2017, Kuching, Sarawak,
Malaysia, pp. 012018. (Published 2018)
• Mohammed Alaa Ala’anzy, Mohamed Othman, Sazlinah Hasan, Safwan Ghaleb, and Rohaya Latip (2021). Optimising
Cloud Servers Utilisation Based on Locust-Inspired Algorithm. In 2020 7th International Conference on Soft Computing &
Machine Intelligence (ISCMI),IEEE, pp. 23-27. (Published 2020)
30. PHD PUBLICATIONS (CONT.)
International Refereed Journals, As Co-author
• Anees Ur Rehman, Zulfiqar Ahmad, Ali Imran Jehangiri, Mohammed Alaa Ala’Anzy, Mohamed Othman, Arif
Iqbal Umar, and Jamil Ahmad (2020). Dynamic energy efficient resource allocation strategy for load balancing in
fog environment. IEEE Access, 8, 199829-199839. (Published 2020, JIF = 3.367, Q2, ISI, JCR)
• Zulfiqar Ahmad, Ali Imran Jehangiri, Mohammed Alaa Ala’anzy, Mohamed Othman, and Arif Iqbal Umar
(2021). Fault-Tolerant and Data-Intensive Resource Scheduling and Management for Scientific Applications in
Cloud Computing. Sensors, 21, 7238. (Published 2021, JIF = 3.576, Q1, ISI, JCR)
• Zulfiqar Ahmad, Ali Imran Jehangiri, Mohammed Alaa Ala’anzy, Mohamed Othman, Rohaya Latip, Sardar
Khaliq Uz Zaman, and Arif Iqbal Umar (2021). Scientific Workflows Management and Scheduling in Cloud
Computing: Taxonomy, Prospects, and Challenges. IEEE Access, 9, 53491-53508. (Published 2021, JIF =
3.367, Q2, ISI, JCR)
• Muhammad Khan, Ali Imran Jehangiri, Zulfiqar Ahmad, Mohammed Alaa Ala’anzy, and Asif Umer (2022). An
Exploration to Graphics Processing Unit Spot Price Prediction. Cluster Computing, x, PAGE XX. (Published
2022, JIF = 1.809, Q2, ISI, JCR)
31. REFERENCES
• Bhatt A, Dimri P, Aggarwal A (2020) Self-adaptive brainstorming for jobshop scheduling in
multicloud environment. Softw Pract Exp 50(8):1381–1398
• Kumar KP, Kousalya K (2020) Amelioration of task scheduling in cloud computing using crow
search algorithm. Neural Comput Appl 32(10):5901–5907
• Kurdi HA, Alismail SM, Hassan MM (2018) Lace: a locust-inspired scheduling algorithm to
reduce energy consumption in cloud datacenters. IEEE Access 6:35435–35448.
• Sharma M, Garg R (2020) Higa: Harmony-inspired genetic algorithm for rack-aware energy-
efficient task scheduling in cloud data centers. Eng Sci Technol Int J 23(1):211–224