Propagation-Model-Free Base Station Deployment for Mobile Networks: Integrating Machine Learning and Heuristic Methods

Abstract

As densification is the promising trend of future mobile networks, deployment of base stations (BSs) becomes increasingly difficult due to the laborious procedures in network planning; besides, unreasonable layout may lead to poor coverage performance. Hence, this paper firstly trains a propagationmodel-free received signal strength (RSS) predictor based on machine learning (ML) models, and then optimizes coverage performance of BS deployment via multi-objective heuristic methods. Specifically, many practical features that affect signal propagation like geographical types and operating parameters of BS, are fed into ML models to predict RSS in a rasterized area; then based on the trained model, a well-designed multi-objective genetic algorithm (GA) is proposed to minimize the number of deployed BSs with coverage constraint. For the practical considerations of fast convergence and output-consistence, greedy algorithm with fixed initial solution and searching direction is also carried out. Moreover, the typical scenarios of incremental deployment (the mobile operator needs to deploy more BSs on the basis of the existing deployment) and BS outage compensation (one BS fails and other BSs need to adjust their configurations to fill the coverage gap), are also investigated for practical needs. Simulations show that multi-layer perceptron outperforms other ML algorithms in terms of RSS prediction with mean absolute error (MAE) yielded to 3.78 dB; and numerical results verify the convergence and availability of the proposed algorithms, which shows 18.5% gain than the real-world deployment in terms of coverage rate.

On Mathematical Modelling of Automated Coverage Optimization in Wireless 5G and beyond Deployments

“…The papers touching that topic are mostly focused on specific parts of the deployment. From the authors' point of view, the papers are mostly targeting the problem of dynamically modifying the gNodeB parameters as-is: downtilt, the collection of three azimuths, mechanical downtilt, electrical downtilt, heigh of gNodeB and transmit power [46,47]. Further, the papers are targeting the deployment algorithms to determine the most suitable positions of gNodeB nodes.…”

“…However, these works only consider the impact of location, where other parameters that affect the performance indicators are not taken into consideration. Moreover, those algorithms optimize only one variable in each iteration and are performed in an exhaustive manner, which is inefficient with poor performance [47]. The overview of the recent literature in gNodeB optimization and deployment is shown in the Table 3.…”

“…An important note here is that, before the actual deployment of the proposed models, it is appropriate to consider whether the network infrastructure can be optimized by changing the parameters of gNodeB nodes only. With this in mind, we recommend testing methods aimed at optimizing the gNodeB parameters of the network before deploying these models [47]. If it is not possible to meet the requirements of end-users by simply changing the parameters of gNodeB nodes, it is suitable to apply the proposed computational model.…”

“…Lingcheng and Hongtao [47] This paper is mainly focused on the deployment of algorithms with the focus on the research of optimal machine learning (ML) model to deploy gNodeB nodes. It has found that multi-layer perceptron outperforms other ML algorithms.…”

Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique

“…Machine learning, which can be used to build a model to learn the accurate correlation between the input parameters and output target, is a powerful tool for parameter optimization [21]- [23]. Furthermore, Gaussian processes (GP) based on Bayesian statistics have characteristics relevant to machine learning, and their flexible nonparametric nature and computational simplicity have attracted researchers from many fields [24]- [27].…”