Below is a list of 4080 projects proposed by faculty members for Summer 2020. More project descriptions may be added once they come in. Please contact the supervisor directly you are in interested in a project. You can also contact faculty members individually to discuss possible projects. Click here to see a list of faculty members, their research areas and their contact information.

Supervisor: Hamzeh Khazaei

Contact: hkh@eecs.yorku.ca

We are amid an evolutionary paradigm shift in cloud computing towards serverless platforms. This change is due to several improvements over traditional cloud computing, like handling all the system administration operations, improving resource utilization, potential operational cost savings, improved energy efficiency, and more straightforward application development. However, current implementations have not yet reached the full potentials of serverless computing. Global research and efforts are required for improving the efficiency and performance of the serverless computation far beyond the current state. In PACS Lab, we are deeply involved in this global effort to improve the status quo.

This project aims to address these shortcomings using analytical and datadriven methods to improve the performance, power efficiency, and adoption of serverless computing for all industries. The project will be conducted in two phases.

1. In the first phase, our goal is to build a serverless computing platform simulator which mimics the behaviour of public serverless computing offerings. The resulting simulator should produce a behavior similar to the trace of our experiments on Amazon AWS Lambda.
2. In the second phase, we will be modifying and optimizing the operational management layer policies in the simulator in order to improve the resource utilization of the system and the Quality of Service (QoS) indicators such as response time and system availability.

Required skills: General EECS408x prerequisites, interest and willingness to learn about Cloud Computing, serverless computing in particular.

Recommended skills: Good programming skills, good math skills, experience with Python

Supervisor: Hamzeh Khazaei

Contact: hkh@eecs.yorku.ca

As the latest paradigm in cloud computing, serverless computing or functionas-a-service (FaaS) has recently gained a lot of attention both in academia and industry. In serverless computing, the developer delegates the infrastructure management tasks to the provider. As a result, the developer can focus on designing and implementing the application instead of spending time on the management, operation, and maintenance of the infrastructure.

Our research in PACS Lab1 has shown that personal computers have great potential to be used as the underlying infrastructure for building green, economic, open and public serverless computing platforms. To do so, we leveraged blockchain systems to introduce transparency in the computation as well as the billing. This system has been proposed in a recently submitted paper in which we also designed and implemented a preliminary prototype to show the feasibility and validity.

In this project, the student will be involved in research and development of the prototype of the proposed platform so that it can be used by all targeted stakeholders in real world. The project includes some degree of research, and both backend and front-end development.

Required skills: General EECS408x prerequisites; Python programming; having interest in cloud computing and blockchain.

Recommended skills: Basic knowledge in Linux containers and microservice architecture, blockchain systems, Python and serverless computing.

Supervisor: Hamzeh Khazaei

Contact: hkh@eecs.yorku.ca

Coupled with the development of lightweight virtualization, specifically containers, is a growing trend in the paradigm of cloud computing shifting from Infrastructure-as-a-Service (IaaS) to Function-as-a-Service (FaaS). Many cloud service providers have launched their FaaS platforms where developers can host serverless functions with high-scalability, pay-as-you-go billing model, and reduced management overhead. However, such a new trend raises new important questions, including the predictability and optimization of the performance and cost of serverless applications.

In PACS Lab, researchers have been working on addressing these urgent needs in the serverless computing area not yet addressed by industries and academics. This project is based on our published and submitted papers in which we give practical solutions to performance modeling and optimization problems for the serverless computing paradigm.

This project will solve pain points for serverless application developers by providing an online ready-to-use platform for profiling, predicting, and optimizing serverless applications. The student will involve in developing a toolkit that integrates multiple APIs of major cloud service providers, automates the deployment, test, and performance profiling of serverless applications, and leverages analytical models to give developers informed performance and optimized application configurations. The project will involve studying the serverless architecture and developing a web application.

Required skills: General EECS408x prerequisites; experience with major cloud computing platforms and APIs, experience with any web framework.

Recommended skills: Experience with containers and serverless functions, solid programming skills.