Skip to main content
Thesis defences

PhD Oral Exam - Mohammad Altahat, Electrical and Computer Engineering

Dynamic Management of Virtual Machine and Container Scheduling in Multi-Cloud Data Centers

Date & time
Monday, June 17, 2024
10 a.m. – 1 p.m.

This event is free


School of Graduate Studies


Nadeem Butt


Engineering, Computer Science and Visual Arts Integrated Complex
1515 St. Catherine W.
Room 002.301

Wheel chair accessible


When studying for a doctoral degree (PhD), candidates submit a thesis that provides a critical review of the current state of knowledge of the thesis subject as well as the student’s own contributions to the subject. The distinguishing criterion of doctoral graduate research is a significant and original contribution to knowledge.

Once accepted, the candidate presents the thesis orally. This oral exam is open to the public.


Efficiently managing virtual resources is a critical component of server virtualization technology. The scheduler is crucial in strategically distributing VMs and containers across diverse computing nodes, responsible for the allocation and the placement of VMs and containers on different computing nodes, and the migration of deployed ones between different nodes. In this thesis, we propose novel solutions in scheduling virtual resources, particularly in the management of VMs and containers deployed across multi-data center cloud environments. The proposed solutions leverage mathematical models, machine learning techniques, and blockchain technology to optimize scheduling decisions, enhance server consolidation, minimize energy consumption, and secure container scheduling. We introduce mathematical models for live VM migration techniques used in simulating and studying live VM migration in cloud systems environments. We present a novel distributed scheduling model that leverages blockchain technology to facilitate efficient sharing of VM status across multiple data centers. This enables prompt local and WAN scheduling decisions for VMs. Additionally, we employ machine and deep learning techniques in a VM migration prediction service to identify the most suitable live migration method for each VM based on its unique characteristics. The proposed distributed model reduces the number of communication messages by 97.9\% and total delay by 49.4\% to 91.7\% compared to a centralized model. The SLA compliance rate of the proposed VM migration prediction service ranges from 18\% to 94.9\% for different machine learning algorithms and SLA policies. Furthermore, we present a novel two-stage container scheduling solution that addresses node imbalances and efficiently deploys containers as an optimization problem, integrating various objective functions and constraints to enhance server consolidation and minimize energy consumption. The confidentiality of migrated containers is ensured through encryption, and the associated costs of the proposed attributes-based encryption model are incorporated into the optimization constraints. The proposed solution's efficacy is demonstrated in its ability to efficiently deploy containers in multi-data center cloud environments and seamlessly migrate them between hosts within the same data center or across different data centers. The results show optimal consolidation, balanced server loads, and minimal total power consumption, highlighting the effectiveness of the proposed container scheduling approach.

Back to top

© Concordia University