Program Overview

Overview

Computing in the cloud has emerged as a leading paradigm for cost-effective, scalable, well-managed computing. Users pay for services provided in a broadly shared, power efficient datacenter, enabling dynamic computing needs to be met without paying for more than is needed. Actual machines may be virtualized into machine-like services, or more abstract programming platforms, or application-specific services, with the cloud computing infrastructure managing sharing, scheduling, reliability, availability, elasticity, privacy, provisioning and geographic replication.

Curriculum

• Motivations & risks
• Use cases
• Building blocks
• Encapsulating computation
• Scheduling
• Storage
• Programming models
• Elastic scaling & load balancing
• Multi-level scheduling
• Key-value stores
• Geo-replication
• Data center networking
• Security & privacy
• Mobile at the edge
• Power management
• Failure modes
• Reliability & fault tolerance
• Perf. isolation & lowering latency
• Monitoring & diagnosis

Course Details

• Lecture time : MW 16:00 - 17:50 (4:00 PM - 5:50 PM) ET, starting January 13
• Units : 12
• Prerequisites : 15-213, 18-213, 15-513, 18-613, 14-513 from CMU, or 15-319, 15-619 with a grade of at least a B.
• Location : DH 2315

Learning Goals

Students completing Advanced Cloud Computing will develop a broad based understanding of state-of-the-art technologies, underlying business and technological trends, key systems and artifacts and research directions in modern data center computing, scalable distributed systems, and programming frameworks enabling the widespread adoption of cloud computing. Many will go on to code, design and architect innovative new cloud computing services and offerings, and to develop business processes to exploit opportunities afforded by modern cloud computing.

Learning Objectives

Specific skills learned and outcomes achieved by graduates of this course include:

• Describe, explain, justify, and criticize differing perspectives on the definition, novelty, and essential features of state of the art cloud computing.
• Design and implement distributed systems for big data science applications to operate in and exploit advanced features of cloud computing systems.
• Design, criticize, implement and improve features of large scale cluster computing, with emphasis on scale elasticity, limitations on unusually long duration corner cases, high availability in the face of rare and dependent failure modes.
• Interpret and criticize cloud computing research papers, and anticipate and design strategies to avert structural or implementation problems identified.

Instructors and Staff

Instructors

Course Staff and Teaching Assistants

| Name
---|---
| Audrey Gao
| Xuye He
| Haoliang Cheng
| Sarvesh Tandon
| Dapeng Gao
| Yifan Guang
| Jim Shao

Course Structure

This course will survey the aspects of cloud computing by reading about 30 papers and articles, executing cloud computing tasks on a state of the art cloud computing service, and implementing a change or feature in a state of the art cloud computing framework. There will be no final exam, but there will be two in class exams. Grades will be calculated using approximately 50% project work, 15% quizzes, and 35% examination results. The class is supported in part by a AWS in Education Grant award.