Document Type
Thesis
Date of Award
Spring 5-31-2019
Degree Name
Master of Science in Telecommunications - (M.S.)
Department
Electrical and Computer Engineering
First Advisor
Joerg Kliewer
Second Advisor
Ali Abdi
Third Advisor
Alexander Haimovich
Abstract
The latest 5G technology in wireless communication has led to an increasing demand for higher data rates and low latencies. The overall latency of the system in a cloud radio access network is greatly affected by the decoding latency in the uplink channel. Various proposed solutions suggest using network function virtualization (NFV). NFV is the process of decoupling the network functions from hardware appliances. This provides the exibility to implement distributed computing and network coding to effectively reduce the decoding latency and improve the reliability of the system. To ensure the system is cost effective, commercial off the shelf (COTS) devices are used, which are susceptible to random runtimes and server failures. NFV coded computation has shown to provide a significant improvement in straggler mitigation in previous work. This work focuses on reducing the overall decoding time while improving the fault tolerance of the system. The overall latency of the system can be reduced by improving the computation efficiency and processing speed in a distributed communication network. To achieve this, multiframe NFV coded computation is implemented, which exploits the advantage of servers with different runtimes. In multiframe coded computation, each server continues to decode coded frames of the original message until the message is decoded. Individual servers can make up for straggling servers or server failures, increasing the fault tolerance and network recovery time of the system. As a consequence, the overall decoding latency of a message is significantly reduced. This is supported by simulation results, which show the improvement in system performance in comparison to a standard NFV coded system.
Recommended Citation
Monteiro, Brinell F., "Multiframe coded computation for distributed uplink channel decoding" (2019). Theses. 1658.
https://digitalcommons.njit.edu/theses/1658
