Improving predicted coverage accuracy in macrocells by use of measurement-based predictions

Belloul, B.; Saunders, S.R.

doi:10.1049/cp:20030067

Cited by 3 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…metal contents of buildings, non-stationary environmental influences such as traffic and weather conditions) to be precise. In practice, predictions are verified and fine-tuned with measurements [19]. This shows that even very complex models represent the physical environment inadequately.…”

Section: Iiib Parametric Versus Nonparametric Modelingmentioning

confidence: 95%

“…Sophisticated models use terrain information for relatively precise predictions. Unfortunately, even with these models the standard deviation of the prediction error is in the order of 10 dB [19] as the physical reality contains too many unknown factors (e.g. metal contents of buildings, non-stationary environmental influences such as traffic and weather conditions) to be precise.…”

Section: Iiib Parametric Versus Nonparametric Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Centralized modeling of the communication space for spectral awareness in cognitive radio networks

Elsner

Koerner

Jondral

2009

SIGMOBILE Mob. Comput. Commun. Rev.

View full text Add to dashboard Cite

The communication space is five dimensional: its degrees of freedom are frequency, time and space. The use of the electromagnetic spectrum depends on these parameters. With future applications such as opportunistic overlay access or distributed spectrum monitoring in mind, it is important to estimate the state of the communication space on the basis of incomplete or imprecise information. A promising approach are technology centric Cognitive Radio networks. In these networks, nodes cooperate to infer information on spectral occupancy. This conceptual paper proposes a novel approach for centralized modeling of the communication space with emphasis on spatial dependencies through the use of a regression model. The modeling approach is verified with practical measurements.

show abstract

Section: Iiib Parametric Versus Nonparametric Modelingmentioning

confidence: 95%

Section: Iiib Parametric Versus Nonparametric Modelingmentioning

confidence: 99%

Centralized modeling of the communication space for spectral awareness in cognitive radio networks

Elsner

Koerner

Jondral

2009

SIGMOBILE Mob. Comput. Commun. Rev.

View full text Add to dashboard Cite

show abstract

“…The measurements covered all the major accessible parts of the LTE network target area, with over 5,000 data points, collected around the four base station sites. To eliminate or curtail small-scale fading effect on the measured RSRP values, all field test measurements were postprocessed to a single median value (Belloul & Saunders, 2003). At every measurement distance (d) from the BS, the RSRP is related to effective radiated power (ERP) and propagation loss ( ) by the expressions in equations (1) and (2) (Ebhota et al, 2018):…”

Section: Field Measurementmentioning

confidence: 99%

Investigating Predictive Capabilities of RBFNN, MLPNN and GRNN Models for LTE Cellular Network Radio Signal Power Datasets

Isabona

Osaigbovo²

2019

FUOYEJET

View full text Add to dashboard Cite

Efficient radio frequency signal coverage planning with well configured transmitters and receivers’ communication channels, is the heart of any cost-effective cellular network design, deployment and operation. It ensures that both network quality and coverage are simultaneously make best use of (i.e. maximized). This work aim to appraise the adaptive learning and predictive capacity of three neural network models on spatial radio signal power datasets obtained from commercial LTE cellular networks. The neural network models are radial basis function neural network (RBFNN), multilayer perceptron neural network (MLPNN) trained with Bayesian regulation algorithms and general regression neural network (GRNN) models. Largely, it is established from the results that ANN prediction methods can tolerate and adapt to measurement errors of attenuating LTE radio signals. Performance comparisons reveal that all the neural network models can predict the propagated LTE radio signals with considerable errors. Specifically, RBFNN delivered the overall best performance with the smallest mean absolute percentage error, root mean square error, mean absolute error and standard deviation values. The GRNN model also gave better prediction results with marginal errors compared to the MLPNN. Thus, the predictive abilities of RBFNN and GRNN models can be explored as a useful tool to successfully plan or fine-tune mobile radio signal coverage area. Keywords: Neural networks; Signal power; attenuating radio signals; radial basis function multilayer perceptron, general regression neural network, Adaptive signal prediction

show abstract

Non-Parametric Modeling with Gaussian Processes for Spatial Radio-Scene Analysis

Elsner

Koerner

Jondral

2008

2008 5th IEEE Consumer Communications and Networking Conference

View full text Add to dashboard Cite

Improving predicted coverage accuracy in macrocells by use of measurement-based predictions

Cited by 3 publications

References 2 publications

Centralized modeling of the communication space for spectral awareness in cognitive radio networks

Centralized modeling of the communication space for spectral awareness in cognitive radio networks

Investigating Predictive Capabilities of RBFNN, MLPNN and GRNN Models for LTE Cellular Network Radio Signal Power Datasets

Non-Parametric Modeling with Gaussian Processes for Spatial Radio-Scene Analysis

Contact Info

Product

Resources

About