LTE KPI for data mining and machine learning

Published: 10 January 2020| Version 2 | DOI: 10.17632/czkn9c4wk6.2
Contributors:
divya mohan,

Description

Scheduling procedures implemented in the wireless networks include a variety of workflows such as resource allocation, channel gain improvement and reduction in packet arrival delay. Among these techniques, the Long Term Evolution (LTE) scheduling is highly preferable due to its high speed of communication and less bandwidth consumption. The LTE assigns resources to the workflows based on the time and frequency domains. Normally, the information gathering prior to scheduling increases the processing time due to the verification of each attribute of the user. To solve this issue, parallel processing through data mining is employed in the recent research studies. The label can be assigned to the user attributes which contributes highly towards scheduling of time slots effectively. The label assignment and parallel processing through data mining concept reduces the delay and increases the throughput. Besides, the extraction of matched data from the library and the prediction of available channels with fewer dimensions are the major issues in the LTE scheduling. Traditionally, numerous approaches are developed for LTE scheduling by solving the problems related to data missing values and classification. Based on this, a powerful setup is created for data mining on handoff procedures in LTE communication. The data initially can be obtained from the network service providers, based on our process the data is taken for analysis. This dataset provides you the information on user handoff related data attributes for analysis.

Files

Institutions

VIT University

Categories

Wireless Communication, Machine Learning, Knowledge Discovery, Wireless Network, Network Optimization

Licence