Page 97 - ITU Journal Future and evolving technologies Volume 2 (2021), Issue 4 – AI and machine learning solutions in 5G and future networks

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 4

AI-BASED NETWORK TOPOLOGY OPTIMIZATION SYSTEM
Han Zengfu, Kong Jiankun, Wang Zhiguo, Zhang Yiwei, Liu Ke, Pan Liang, Li Sicong, Wu Desheng
China Mobile Shandong Branch, 20569, Jingshi road, Jinan, Shandong

NOTE: Corresponding author: Han Zengfu, hanzengfu@sd.chinamobile.com

Abstract – Existing network topology planning does not fully consider the increasing network traffic and
problem of uneven link capacity utilization, resulting in lower resource utilization and unnecessary
investments in network construction. The AI-based network topology optimization system introduced in this
paper builds a Long Short-Term Memory (LSTM) model for time series traffic forecasting, which uses
NetworkX, a Python library, for graph analysis, dynamically optimizes the network topology by edge
deletion or addition based on traffic over nodes, and ensures network load balancing when node traffic
increases, mainly introducing the LSTM forecasting model building process, parameter optimization
strategy, and network topology optimization in some detail. As it effectively enhances resource utilization,
this system is vital to the optimization of complex network topology. The end of this paper looks forward to
the future development of artificial intelligence, and suggests the possibility of how to cooperate with
operator networks and how to establish cross-border ecological development.

Keywords –Artificial intelligence, capacity utilization, communication network, traffic forecast, network
topology

1. INTRODUCTION exponential computing [4,5], making manual
network topology optimization very difficult. With
With the development of 5G technology, operators the development of Artificial Intelligence (AI)
need to rebuild or expand their transport networks, technology, Machine Learning (ML) algorithms
as their existing network topology planning does offer a helping hand to resolve complex issues [6,7].
not fully consider the increasing network traffic and A new ecosystem which needs to be established to
problem of uneven link capacity utilization [1]. The advance such technical developments as applying
utilization of more than 40% of the transmission AI and big data technologies to networks is new to
links of the existing networks is low [2,3], which the industry, and the "AI-ML in 5G Challenge"
increases operators' network construction costs. organized by ITU paves the way for such study. This
Therefore, how to optimize the network structure paper introduces an AI-based network topology
to make it adapt to future network changes and how optimization system that makes in-depth analysis of
to improve resource utilization to save construction network topology and proposes a solution to
costs have greatly challenged today's operators [7]. maintain high resource utilization when network
For complex networks, topology analysis requires traffic keeps growing [2]. It is especially crucial for
the optimization of complex network topology.

Fig. 1 – Complicated network topology analysis

© International Telecommunication Union, 2021 81