Off-campus UNL users: To download campus access dissertations, please use the following link to log into our proxy server with your NU ID and password. When you are done browsing please remember to return to this page and log out.
Non-UNL users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Using Contextual Bandits to Improve Traffic Performance in Edge Network
Edge computing network is a great candidate to reduce latency and enhance performance of the Internet. The flexibility afforded by Edge computing to handle data creates exciting range of possibilities. However, Edge servers have some limitations since Edge computing process and analyze partial sets of information. It is challenging to allocate computing and network resources rationally to satisfy the requirement of mobile devices under uncertain wireless network, and meet the constraints of datacenter servers too. To combat these issues, this dissertation proposes smart multi armed bandit algorithms that decide the appropriate connection setup for multiple network access technologies on the Edge access layer, and the adaptive placement of Edge core layer traffic in datacenter servers to reduce the service time and balance the use of resources under fluctuating traffic environment in a heterogeneous mobile network. For the access layer traffic management, we developed a system that adopts an emerged transport layer protocol, Multi-path TCP (MPTCP), that can run on mobile devices to enable multipath data transmission. A centralized controller is designed to manage the MPTCP connections and regulate their bandwidth usage from each connected network. The proposed online MPTCP path manager is based on the contextual bandit algorithm to choose the primary path connection that maximizes throughput and minimizes delay and packet loss. The output introduces an adaptive policy to the path manager whenever the MPTCP connection is attempted based on the last hop wireless signals characteristics. For the core layer traffic management, we want to utilize links more effectively to map virtual control resources to the underlying infrastructure. We propose OctoMap, an efficient supervised placement of traffic in large virtualized multi-path data centers. OctoMap system is designed to use learning theory to solve the problem of mapping chains embedding of Virtual Network Functions (VNF). OctoMap utilizes a Convolution Neural Network for traffic prediction and provisioning, and a contextual multi-armed bandit algorithm to solve the online VNF chain embedding problem.
Al Zadjali, Aziza Najeeb, "Using Contextual Bandits to Improve Traffic Performance in Edge Network" (2021). ETD collection for University of Nebraska - Lincoln. AAI28652629.