# Toward Intelligent Network Optimization in Wireless Networking: An Auto-learning Framework

## TL;DR

This paper proposes an auto-learning framework utilizing machine learning to automate and improve network optimization in wireless communication systems, addressing issues of human intervention, model invalidity, and high computational costs.

## Contribution

It introduces a novel auto-learning framework (ALF) that applies ML techniques to automate and enhance network optimization in wireless systems, with models for automatic construction, experience replay, and complexity reduction.

## Key findings

- Framework facilitates automatic network optimization
- ML techniques improve efficiency and accuracy
- Provides new insights for future research in WCSs

## Abstract

In wireless communication systems (WCSs), the network optimization problems (NOPs) play an important role in maximizing system performances by setting appropriate network configurations. When dealing with NOPs by using conventional optimization methodologies, there exist the following three problems: human intervention, model invalid, and high computation complexity. As such, in this article we propose an auto-learning framework (ALF) to achieve intelligent and automatic network optimization by using machine learning (ML) techniques. We review the basic concepts of ML techniques, and propose their rudimentary employment models in WCSs, including automatic model construction, experience replay, efficient trial-and-error, RL-driven gaming, complexity reduction, and solution recommendation. We hope these proposals can provide new insights and motivations in future researches for dealing with NOPs in WCSs by using ML techniques.