Title

Resource Allocation in Moving Small Cell Network using Deep Learning based Interference Determination

Document Type

Conference Proceeding

Source of Publication

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC

Publication Date

9-1-2019

Abstract

© 2019 IEEE. Mobile cellular users traveling in city buses are experiencing poor quality of signals due to the interference and the large number of mobile devices. To enhance the Quality-of-Service (QoS), deployment of small cell networks in city buses is a promising solution. The deployment of small cells in vehicular environment makes the resource allocation more challenging because of the dynamic interference relationships experienced by them. Therefore, resource allocation in vehicular environment within moving small cells (MSCs) needs to be handled carefully. In this study, we investigate the problem of resource allocation in city bus transit system with multiple routes. Then, we propose a Percentage Threshold Interference Graph (PTIG) based allocation of resources to MSCs in a network. City buses of multiple routes travel with variable speed and may share some of the same road segments which make it difficult to extract the exact interference patterns between them. Therefore, Long Short Term Memory (LSTM) neural networks are used to predict the city buses locations. The predicted locations of city buses are then used to generate PTIG by finding the dynamic interference relationship between MSCs. Graph coloring algorithm is used to allocate the resources to PTIG. Numerical results are presented to show the comparison of resource allocation using PTIG and Time Interval based Interference Graph (TIIG) in terms of resource block utilization and time complexity.

ISBN

9781538681107

Publisher

Institute of Electrical and Electronics Engineers Inc.

Volume

2019-September

Last Page

6

Disciplines

Computer Sciences

Keywords

Deep Learning, Percentage Threshold Interference Graph, Resource allocation, Small cells, Time Interval based Interference Graph

Scopus ID

85075897687

Indexed in Scopus

yes

Open Access

no

Share

COinS