Open AccessGenerative Adversarial Network for Simulation of Load Balancing Optimization in Mobile Networks
Author(s) -
Fu Jie Tey Fu Jie Tey,
Tin-Yu Wu Fu Jie Tey,
Yueh Wu Tin-Yu Wu,
Jiann-Liang Chen Yueh Wu
Publication year - 2022
Publication title -
wǎngjì wǎnglù jìshù xuékān
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.231
H-Index - 22
eISSN - 2079-4029
pISSN - 1607-9264
DOI - 10.53106/160792642022032302010
Subject(s) - computer science , load balancing (electrical power) , macro , computer network , throughput , distributed computing , wireless network , network packet , wireless , telecommunications , geometry , mathematics , programming language , grid
The commercial operation of 5G networks is almost ready to be launched, but problems related to wireless environment, load balancing for example, remain. Many load balancing methods have been proposed, but they were implemented in simulation environments that greatly differ from 5G networks. Current load balancing algorithms, on the other hand, focus on the selection of appropriate Wi-Fi or macro & small cells for Device to Device (D2D) communications, but Wi-Fi facilities and small cells are not available all the time. For this reason, we propose to use the macro cells that provide large coverage to achieve load balancing. By combing Generative Adversarial Network (GAN) with the ns-3 network simulator, this paper uses neural networks in TensorFlow to optimize load balancing of mobile networks, increase the data throughput and reduce the packet loss rate. In addition, to discuss the load balancing problem, we take the data produced by the ns-3 network simulator as the real data for GAN.