The extensive growth in adoption of mobile devices pushes global Internet protocol (IP) traffic to grow and content delivery network (CDN) will carry 72 percent of total Internet traffic by 2022, up from 56 percent in 2017. In this praxis, Interconnected Cache Edge (ICE) based on different public cloud infrastructures with multiple edge computing sites is considered to help CDN service providers (SPs) to maximize their operational profit. The problem of resource allocation and performance optimization is studied in order to maximize the cache hit ratio with available CDN capacity.

The considered problem is formulated as a multi-stage stochastic linear programming model that involves jointly optimizing the resource allocation and network performance. The problem is challenged in reality since the multi-cloud SPs have dynamic price strategies in different regions, tasks could be time sensitive, and busy-hour traffic model is hard to simulate. To overcome these challenges, the praxis proposes a method to decompose the problem into (i) a resource-allocation problem with fixed task-offloading decisions and (ii) a performance optimization problem that optimizes the cache hit ratio, round-trip time (RTT) and edge processing time corresponding to the resource allocation.

The praxis addresses the problem using optimization solvers of the General Algebraic Modeling System (GAMS) and proposes a broker scheme (ICE: Interconnected Cache Edge) using cloud-based CDN with edge computing architecture to maximize expected profit. Experimental design shows that ICE performs closely to the optimal solution and that it significantly improves the CDN profitability and network performance over traditional approaches.

Degree Date

Fall 12-2019

Document Type


Degree Name



Engineering Management, Information, and Systems


Richard Barr

Second Advisor

Eli Olinick

Third Advisor

Jeff Tian

Fourth Advisor

Harsha Gangammanavar

Fifth Advisor

John Medellin

Subject Area

Communication, Computer Engineering

Number of Pages




Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License