Combining Measurements and Propagation Models for Estimation of Coverage in Wireless Networks

Fernandes, Daniel; Soares, Gabriela; Clemente, Diogo; Cortesao, Rodrigo; Sebastião, Pedro; Cercas, Francisco; Dinis, Rui; Ferreira, Lucio Studer

doi:10.1109/vtcfall.2019.8891451

Cited by 10 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the service package offered is usually suited to most end users' preferences and financial capabilities. The identical framework has been applied by Internet giant companies such as Amazon, Microsoft, and Google in their cloud computing services [33]- [35].…”

Section: Recent Progress In Ml-based Propagation Modellingmentioning

confidence: 99%

Machine Learning-Based Online Coverage Estimator (MLOE): Advancing Mobile Network Planning and Optimization

et al. 2023

View full text Add to dashboard Cite

Nowadays, the dependency on high-performance digital mobile connectivity is not limited to human usage but also the intelligent objects increasingly deployed to serve the needs of Internet of Things (IoT) applications. However, the current network planning technique limitation has constrained the real potential of mobile digital connectivity development. This situation has hindered sustainable Internet-oriented economic and technological development. The 3 rd generation partnership project (3GPP), through its specification release 18 (Rel.18), has included and leveraged the potential capabilities of machine learning (ML) technologies in advanced mobile network planning. The main objective is to enhance mobile network planning performance and reduce complexity. To materialize this aim, we propose a novel ML-based Online coverage Estimator (MLOE) tool developed based on Random Forest (RF) ML algorithm. It uses seven unique features to predict the mobile network performance through reference signal received power (RSRP). Accordingly, the results showed that MLOE outperformed traditional empirical techniques and previous works. The final trained RF algorithm has achieved an outstanding root mean square error (RMSE) of 2.65 dB and a coefficient of determination (𝑅𝑅 2 ) of 0.93. With the dynamic and fast-growing mobile technology, MLOE has been deployed on an online platform using MATLAB ® Web App Server, which offers a modular and scalable architecture.

show abstract

Section: Recent Progress In Ml-based Propagation Modellingmentioning

confidence: 99%

Machine Learning-Based Online Coverage Estimator (MLOE): Advancing Mobile Network Planning and Optimization

et al. 2023

View full text Add to dashboard Cite

show abstract

“…• Cell coverage estimation and grid generation AWS Lambda (L1): Using client information imported from a S3 bucket (B0), this lambda creates a pixelized grid with coverage information around an antenna. This coverage is calculated using propagation modules, drive tests, and other cell parameters, such as elevation, azimuth, and tilt [32]. Those grids will be saved in an S3 bucket (B1); • Intersections AWS Lambda (L2): Using a metadata file imported from B1, L2 compiles that data verifying which cells' coverage intersects, by getting two opposite max distance corners.…”

Section: Implementation Of the Work Patternmentioning

confidence: 99%

A Novel Way to Automatically Plan Cellular Networks Supported by Linear Programming and Cloud Computing

Godinho

Fernandes

Soares³

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

With the increasing number of mobile subscribers worldwide, there is a need for fast and reliable algorithms for planning/optimization of mobile networks, especially because, in order to maintain a network’s quality of service, an operator might need to deploy more equipment. This paper presents a quick and reliable way to automatically plan a set of frequencies in a cellular network, using both cloud technologies and linear programming. We evaluate our pattern in a realistic scenario of a Global System for Mobile communications protocol (GSM) network and compare the results to another already implemented commercial tool. Results show that even though network quality was similar, our algorithm was twelve times faster and used four times less memory. It was also able to frequency plan seventy cells simultaneously in less than three minutes. This mechanism was successfully integrated in the professional tool Metric, and is currently being used for cellular planning. Its extension for application to 3/4/5G networks is under study.

show abstract

“…To begin the process, a grid of geo-referenced pixels must be created for each antenna that's given, combining different types of information such as location, height, tilt, vertical and horizontal diagrams, transmission power level, terrain data using a calibrated Standard Propagation Model (SPM) and the Walfish-Ikegami propagation model [13]. A graphical example of a generated propagation grid can be seen in Fig.…”

Section: B Cell Coverage Estimation Modulementioning

confidence: 99%

Automatic Coverage Based Neighbour Estimation System: A Cloud-Based Implementation

et al. 2020

Self Cite

View full text Add to dashboard Cite

Over the years, mobile networks have grown exponentially due to rising demand. These networks mix different types of cells, which makes manual configuration difficult, costly and tedious. Furthermore, inefficiencies stemming from these problems can cause problems in Handover performance, since a mobile device may not always connect to the optimal cell upon switching from one to the other, potentially harming service quality and increasing Operational Costs (OPEX). Existing solutions, like Automatic Neighbour Relations (ANR), while they are valuable in estimating the best neighbouring cells through the rate of successful Handovers, fail to take into account topological coverage factors and fictional cells, therefore inefficiencies lie hidden and it isn't suited to calculate relations between planned cells and active cells. In this article, a proposal of a cloud-based, on-demand automatic coverage based neighbour estimation system is proposed, which utilises topological signal coverage data from each cell provided by the network's operations support system, in order to mitigate the aforementioned issues and provide a reliable and convenient coverage analysis paradigm.

show abstract

Combining Measurements and Propagation Models for Estimation of Coverage in Wireless Networks

Cited by 10 publications

References 6 publications

Machine Learning-Based Online Coverage Estimator (MLOE): Advancing Mobile Network Planning and Optimization

Machine Learning-Based Online Coverage Estimator (MLOE): Advancing Mobile Network Planning and Optimization

A Novel Way to Automatically Plan Cellular Networks Supported by Linear Programming and Cloud Computing

Automatic Coverage Based Neighbour Estimation System: A Cloud-Based Implementation

Contact Info

Product

Resources

About