An Unsupervised Learning Approach for Performance and Configuration Optimization of 4G Networks

Santos, Roger R. dos; Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, António

doi:10.1109/wcnc.2019.8885524

Cited by 7 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the most widely used techniques include artificial neural networks for configuration optimization, demand prediction, or resource allocation [12]. Unsupervised techniques that have been tested in the context of SON include self-organized maps, game theory, hidden Markov models, and of course, clustering [13,14]. Clustering-based solutions appear in various use cases.…”

Section: Related Workmentioning

confidence: 99%

“…Analysis of the measurement data can also be conducted with automated methods [12] to generate reconfiguration actions that will change the layout of the network, further improving the radio coverage and quality and increasing the capacity layer's performance. In this paper, we analyzed the literature of model-based and data-driven algorithms for cell reconfiguration, and focused on unsupervised learning [13][14][15][16] methodologies that have proven their effectiveness in a large number of network-related optimization tasks. Traditional approaches such as the clustering of network KPIs has been shown to correctly detect and segment the network elements into meaningful groups, which greatly reduces the processing overhead and is very robust to the noisy nature of network data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Network–Spatial Clustering for Optimizing 5G Mobile Networks

Margaris¹,

Filippas²,

Tsagkaris³

2022

Applied Sciences

View full text Add to dashboard Cite

5G is the new generation of 3GPP-based cellular communications that provides remarkable connectivity capabilities and extreme network performance to mobile network operators and cellular users worldwide. The rollout process of a new capacity layer (cell) on top of the existing previous cellular technologies is a complex process that requires time and manual effort from radio planning-engineering teams and parameter optimization teams. When it comes to optimum configuration of the 5G gNB cell parameters, the maximization of achieved coverage (RSRP) and quality (SINR) of the served mobile terminals are of high importance for achieving the very high data transmission rates expected in 5G. This process strongly relies on network measurements that can be even more insightful when mobile terminal localization information is present. This information can be generated by modern algorithmic techniques that act on the cellular network signaling measurements. Configuration algorithms can then use these measurements combined with location information to optimize various cell deployment parameters such as cell azimuth. Furthermore, data-driven approaches are shown in the literature to outperform traditional, model-based algorithms as they can automate the optimization of parameters while specializing in the characteristics of each individual geographical zone. In the context of the above, in this paper, we tested the automated network reconfiguration schemes based on unsupervised learning and applied statistics for cell azimuth steering. We compared network metric clustering and geospatial clustering to be used as our baseline algorithms that are based on K-means with the proposed scheme—hybrid network and spatial clustering based on hierarchical DBSCAN. Each of these algorithms used data generated by an initial scenario to produce cell re-configuration actions and their performance was then evaluated on a validated simulation platform to capture the impact of each set of gNB reconfiguration actions. Our performance evaluation methodology was based on statistical distribution analysis for RSRP and SINR metrics for the reference scenario as well as for each reconfiguration scheme. It is shown that while both baseline algorithms improved the overall performance of the network, the proposed hybrid network–spatial scheme greatly outperformed them in all statistical criteria that were evaluated, making it a better candidate for the optimization of 5G capacity layers in modern urban environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid Network–Spatial Clustering for Optimizing 5G Mobile Networks

Margaris¹,

Filippas²,

Tsagkaris³

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…At the same time, similar research to our work was conducted in [14]and this article analyzes the call detailed records by comparing the detected anomalies with ground truth information to verify whether the two algorithms correctly assess user mobility and traffic usage and it only uses a feature corresponding to mobile user activity, namely counting the number of incoming and outgoing calls and text messages. Finally, a study closer to ours was conducted in [15], which compared three clustering algorithms using performance indicators. The research revealed that there were no significant differences in the obtained results with both Expectation-Maximization (EM) using Gaussian Mixture Models (GMM) and spectral clustering in LTE cells clustering based on different KPIs when compared to the ones obtained with K-means.…”

Section: Related Workmentioning

confidence: 99%

“… Compared to [13] using classified UEs datasets under the 3G network, we investigate the performance of all unsupervised learning algorithms on clustering based on different correlated groups dataset to analyze the results of LTE cell clusters in the low dimensional field.  Compared to [15] using traditional ML algorithms (i.e., EM-GMM and spectral clustering), this is the first time that k-means has been compared with SOM neural network (NN) for LTE high/low-dimensional datasets clustering in RAN.…”

Section: Related Workmentioning

confidence: 99%

The comparison of Self-organized map and k-means algorithms used for 4G network performance evaluation

Wang

2021

Preprint

View full text Add to dashboard Cite

With the increasing complexity of mobile networks, it has become more and more difficult to perform effective management of mobile networks, which has led to more data to be evaluated and optimized. This article focuses on the performance evaluation of Long Term Evolution (LTE) networks by using two unsupervised learning techniques. Besides, this paper aims to identify the pros and cons of these two clustering algorithms as well. To achieve the above goals, different dimensional datasets for learning a process based on two classic unsupervised clustering methods are introduced to this work. A Self-organized map (SOM) neural network and k-means are as a comparison algorithm and the sample data with three different degree correlation coefficients features with 63 LTE cells, which is from a major European city. The purpose behind using these two methods is to see how different dimensions of the datasets can be used for testing clustering effectiveness and we propose a method based on the features extracted from key performance indicators (KPIs) and Euclidean distance is used as the evaluation standard for the distance between different clusters and samples within clusters. The comparing results show that k-means has a better cluster performance in low dimension data set, whereas the SOM’s performance unsatisfactory. On the other hand, the SOM’s clustering performance is better than k-means in high dimension and big data set and it could visualize results. It was verified that there is a significant difference in the obtained results using different clustering algorithms.

show abstract

“…One of the most prominent issues that current and nextgeneration wireless network operators will face is assuring high Quality of Experience (QoE) to an increasing number of users, in services that generate a high network load, as video streaming [1]. In this context, much work has been done on assessing Quality of Service (QoS) through the measurement of specific network key performance indicators (KPIs) and drive tests (DTs) (e.g., [2] [3] [4]). However, these metrics cannot directly assess the user's QoE.…”

Section: Introductionmentioning

confidence: 99%

A No-Reference Video Streaming QoE Estimator based on Physical Layer 4G Radio Measurements

Moura

Sousa

Vieira

et al. 2020

2020 IEEE Wireless Communications and Networking Conference (WCNC)

Self Cite

View full text Add to dashboard Cite

With the increase in consumption of multimedia content through mobile devices (e.g., smartphones), it is crucial to find new ways of optimizing current and future wireless networks and to continuously give users a better Quality of Experience (QoE) when accessing that content. To achieve this goal, it is necessary to provide Mobile Network Operator (MNO) with real time QoE monitoring for multimedia services (e.g., video streaming, web browsing), enabling a fast network optimization and an effective resource management. This paper proposes a new QoE prediction model for video streaming services over 4G networks, using layer 1 (i.e., Physical Layer) key performance indicators (KPIs). The model estimates the service Mean Opinion Score (MOS) based on a Machine Learning (ML) algorithm, and using real MNO drive test (DT) data, where both application layer and layer 1 metrics are available. From the several considered ML algorithms, the Gradient Tree Boosting (GTB) showed the best performance, achieving a Pearson correlation of 78.9%, a Spearman correlation of 66.8% and a Mean Squared Error (MSE) of 0.114, on a test set with 901 examples. Finally, the proposed model was tested with new DT data together with the network's configuration. With the use case results, QoE predictions were analyzed according to the context in which the session was established, the radio transmission environment and radio channel quality indicators.

show abstract

An Unsupervised Learning Approach for Performance and Configuration Optimization of 4G Networks

Cited by 7 publications

References 6 publications

Hybrid Network–Spatial Clustering for Optimizing 5G Mobile Networks

Hybrid Network–Spatial Clustering for Optimizing 5G Mobile Networks

The comparison of Self-organized map and k-means algorithms used for 4G network performance evaluation

A No-Reference Video Streaming QoE Estimator based on Physical Layer 4G Radio Measurements

Contact Info

Product

Resources

About