Projects

Grant, NSERC CRD grant (2014-2017)

Principal Investigator: Abdelouahed Gherbi

Abstract:

Cloud computing is a computing paradigm that enables an on-demand and scalable provision of computing resources. Cloud computing is increasingly gaining industrial acceptance due to its flexibility, efficiency and ability to reduce OPEX (operational expenses) and CAPEX (capital expenses) for Cloud users. Although Cloud computing provides an efficient solution for hosting non-critical IT services, it is still limited in terms of dependability, including high availability (HA), in hosting telecom and critical real-time applications. From the perspective of major Cloud providers, such as Amazon, the focus is to ensure the availability of the virtual resources that they offer as a service. From the perspective of Cloud tenants, the main concern is the HA of their applications deployed in the Cloud. The first objective of this research project is to define a HA solution that bridges the gap between the aspirations of Cloud users and the offerings of Cloud providers. In order to achieve this objective in the project, we define a novel agent-based software architecture, which allows for scaling up of the HA solution to meet the stringent requirements in Cloud computing. Moreover, within the context of Cloud computing, high availability imposes certain requirements that conflict with Green computing, which targets efficient resource utilization and reduction of the environmental footprint of the Cloud. In particular, HA favors redundancy and the use of standby entities to eliminate single failure points, whereas Green computing encourages the consolidation of resources to maximize utilization. This introduces a multi-dimensional optimization problem where we look for a trade-off between HA and the Green requirements. The second objective of this research project is to incorporate Green-awareness into the HA solutions that are defined in order to achieve the first objective. We will achieve this objective using a meta-heuristic approach that allows for optimal placement and live migration of VMs from the perspective of both HA and Green requirements. We expect the results of this project to have a significant impact on the development and management of HA software applications deployed in the Cloud and to meet Green requirements.

Mitacs Clusters (Ericsson Canada, 2019-2021)

Principal Investigator: Chamseddine Talhi

Abstract:

This project is part of the Ericsson’s GAIA (Global Artificial Intelligence Accelerator), focusing on managing the lifecycle of machine learning solutions for monitoring a virtualized infrastructure.

Mitacs Clusters (Ericsson Canada, 2019-2021)

Principal Investigator: Chamseddine Talhi

Abstract:

The goal of this project is to develop solutions for monitoring and orchestrating virtual network functions (VNF). It is part of a light virtualization development initiative identified today by Cloud native.

Prompt (Ericsson Canada, Rogers communication Inc., 2018-2020)

Principal investigator: Nadjia Kara

Abstract:

The main objective of this project is to develop a platform for dynamic resource management for virtualized network functions (VNF). This platform integrates a set of mechanisms, such as dynamic adaptation of resources and dynamic service chain placement, along with workload modeling and prediction. It allows for automated resource management under variable workload conditions and timescales while meeting the performance requirements of different VNF (e.g.: reliability and latency requirements).

NSERC CRD (Ericsson Canada, Rogers communication Inc., 2016-2020)

Principal investigator: Nadjia Kara

Abstract:

The main objective of this project is to define and validate new mechanisms (e.g.: models, algorithms and methodologies) to support dynamic resource management for virtualized network functions through efficient and fine-grained resource provisioning while satisfying Service Level Agreements (SLAs). These approaches will react to various dynamic virtualized network functions and enable efficient and flexible resource management. The proposed research activities will increase flexibility for network and service management, and will help to reduce physical infrastructure cost, energy consumption and time to market for the deployment of new applications.

NSERC Alliance project

Principal investigator: Nadjia Kara

Abstract:

This project will enable the development of new technologies for dynamic and joint optimization of performances and energy consumption in serverless edge computing platforms under time-varying workflows, workloads and resource consumption while meeting application deployment and management constraints (e.g.: configurations of resources, workflow structures). Moreover, these technologies will allow for resources and their configuration runtimes to be adapted to optimize resource and energy costs while meeting the performance requirements of running applications. The developed technologies will stimulate rapid Function as a Service (FaaS) edge infrastructure evolution and adoption, and will speed up the time to market for new serverless applications. They will help FaaS edge computing providers to reduce OPEX, because they will be able to minimize FaaS edge computing infrastructure deployment and operational costs (minimize resource and energy consumption, automatic resource deployment and adaptation). Moreover, they will provide green and reliable FaaS edge computing infrastructure and deliver new serverless applications to customers in a sustainable manner.

NSERC Discovery grant (2016-2023)

Principal investigator: Nadjia Kara

Abstract:

This research program addresses very challenging issues related to resource provisioning and management in distributed virtualized communication environments. New mechanisms and tools will be developed to enable the provisioning and management of flexible and efficient networks and services within these environments. New mathematical models and algorithms will be developed with a view to satisfying multiple objectives of virtualized communication environments. New mechanisms will also be developed to integrate configuration, provisioning and optimization of resources through the federation of virtualized communication environments. This research program will provide novel approaches that ease the migration toward open and interoperable communication environments while satisfying both providers and customers.

NSERC Discovery grant (May 2019 – April 2024)

Principal investigator: Aris Leivadeas 

Abstract:

In recent decades, the Internet has been a key factor in building the global information society and leading economic growth. The mix of technologies in the Internet, including Cloud Computing, Network Function Virtualization (NFV), Data Analytics and the Internet of Things (IoT), provides the necessary tools to build a service-centric Future Internet Architecture. Future Internet is expected to rely on virtualization technologies, moving away from dedicated and expensive hardware middleboxes, while IoT will be one of the main sources of data generation in this communication paradigm. In light of this, the long-term goal of this proposal is to establish a scalable softwarized end-to-end solution that will gracefully combine varied technologies to provide networking services with high Quality of Service (QoS) and low communication costs.

NSERC Discovery grant (May 2017 – April 2021)

Principal Investigator: Chamseddine Talhi

Abstract:

The goal of this project is to develop new mobile and IoT equipment authentication solutions in new-generation mobile networks.

NSERC CRD grant (ACME Engineering Prod. Ltd, 2019-2022)

Principal Investigator: Abdelouahed Gherbi

Abstract:

The Internet of Things (IoT) vision is now a firmly established reality, considering the variety of applications and provided services, including Smart cities, Smart grids and Healthcare. According to recent studies, the IoT sector is growing exponentially, which is motivating numerous industrial and business entities in Canada and worldwide, including the industrial partners of this project, to adopt IoT initiatives. IoT systems are often the backbone of various safety-critical applications, such as infrastructure monitoring, smart grid or smart healthcare, which rely on the performance, reliability and predictability of these systems. The failure of these types of IoT systems may have severe consequences. Therefore, the dependability of these systems is a critical and challenging issue. Moreover, major IoT solution providers, including the industrial partners of this project, need to support large-scale deployments of their IoT systems to a growing number of clients with a diversity of system-functional and quality-of-service requirements. The main objective of this research project is to investigate, develop and validate new engineering techniques to enable the automatic deployment and operation of smart large-scale dependable IoT systems.

NSERC discovery grant (2017-2022)

Principal Investigator: Abdelouahed Gherbi

Abstract:

Software systems are now the backbone of diverse activities within our modern society, including transportation, communication, health and entertainment. In addition to their inherent complexity, these systems are increasingly deployed on highly dynamic runtime platforms (e.g. Cloud Computing), and they interface with an uncertain environment (e.g. Cyber-Physical Systems). Within this context, software systems should be designed with an adaptation capacity and should continuously verify stringent dependability requirements. Model-driven software engineering (MDE) is now a well-established approach that focuses on design-time modeling to support coping with software system complexity. With the emergence of the models at runtime concept, MDE techniques can be extended to support the engineering of adaptive software systems. However, there are still a number of challenging issues related to using these runtime models to support and manage the dependability of adaptive software systems. First, we point to the lack of specific framework to support runtime dependability modeling, in contrast to the numerous standard frameworks for design-time modeling. Having the framework to build such models, there is a need for efficient analysis techniques that allow for using dependability runtime models to generate optimal adaptations. Third, the dependability requirement is a multidimensional concept that encompasses numerous dimensions, including availability, reliability, safety and performance, to mention just a few. These are inter-dependent, inter-related and potentially conflicting dimensions. As a consequence, keeping the dependability runtime model consistent on one hand and also continuously synchronized with the running system throughout the system adaptions on the other hand is challenging. In this research program, we propose leveraging the model-driven software engineering approach combined with the models at runtime concept in order to define, develop and validate modeling techniques to support the development and management of dependable adaptive software systems.