Data analytics for forecasting cell congestion on LTE networks

Torres, Pedro; Marques, Paulo; Marques, Hugo; Dionísio, Rogério; Alves, Tiago M. F.; Pereira, L.C.P.; Ribeiro, Jorge

doi:10.23919/tma.2017.8002917

Cited by 24 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A traffic-measurement-based modeling method has been proposed in [33] to look for relationships between LTE network resources and key performance indicators for resourceconsumption forecasting based on traffic and service growth. The work in [34] uses ARIMA to forecast the average downlink throughput to anticipate cell congestion in LTE networks. Time series modeling is used in [35] to forecast LTE resource consumption to identify unused resources.…”

Section: Related Workmentioning

confidence: 99%

A Method for Improving Imputation and Prediction Accuracy of Highly Seasonal Univariate Data with Large Periods of Missingness

Chaudhry

Basri

et al. 2019

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Imputation of missing data in datasets with high seasonality plays an important role in data analysis and prediction. Failure to appropriately account for missing data may lead to erroneous findings, false conclusions, and inaccurate predictions. The essence of a good imputation method is its missingness-recovery-ability, i.e., the ability to deal with large periods of missing data in the dataset and the ability to extract the right characteristics (e.g., seasonality pattern) buried under the dataset to be analyzed. Univariate imputation is usually incapable of providing a reasonable imputation for a variable when periods of missing values are large. On the other hand, the default multivariate imputation approach cannot provide an accurate imputation for a variable when missing values of other correlated variables used for imputation occur at exactly the same time intervals. To deal with these drawbacks and to provide feasible imputations in such scenarios, we propose a novel method that converts a single variable into a multivariate form by exploiting the high seasonality and random missingness of this variable. After this conversion, multivariate imputation can then be applied. We then test the proposed method on an LTE spectrum dataset for imputing a single variable, such as the average cell throughput. We compare the performance of our proposed method with Kalman filtering and default method for multivariate imputation. The performance evaluation results clearly show that the proposed method significantly outperforms Kalman filtering and default method in terms of imputation and prediction accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

A Method for Improving Imputation and Prediction Accuracy of Highly Seasonal Univariate Data with Large Periods of Missingness

Chaudhry

Basri

et al. 2019

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Jiang et al [72] have proposed a SON decision-making framework for 5G environment and machine learning algorithms to analyze the measurement patterns of unidentified problems in order to decide proper actions for them. Torres et al [140] have addressed the SON management by learning measurement patterns with regression forecasting methods to predict cell congestions that need to be targeted with some SON functions. Xu et al [158] have learned regularities from the mobile traffic data and utilized that information in order to forecast upcoming traffic patterns for individual cells.…”

Section: Pattern Mining In Network Managementmentioning

confidence: 99%

“…CONTRIB3.1 is novel in view of using measurement-based pattern mining to characterize SON functions and network contexts. Instead, other SON-related and measurement-based pattern mining methods address anomaly detection in order to trigger suitable SON functions and other algorithms with targeted configurations [72,140,158]. Particularly related to the association rule learning, some earlier methods have been developed in the field of IoT and sensor networks [22,49].…”

Section: Measurement-based Pattern Miningmentioning

confidence: 99%

Correlation-Based Feature Mapping of Crowdsourced LTE Data

Apajalahti

Walelgne

Manner

et al. 2018

2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

View full text Add to dashboard Cite

“…Forecasting LTE cell congestion. In [21], the authors try to forecast the average downlink throughput for LTE cells using data collected from multiple probes and to apply that knowledge to Self-Organizing Network (SON) strategies to shift coverage and capacity according to predicted demand. This group updated some MON-ROE nodes to address the benchmarking of voice calls, showing the flexibility of the platform nodes.…”

Section: Experiments From External Projectsmentioning

confidence: 99%

Results from Running an Experiment as a Service Platform for Mobile Networks

Peón-Quirós

Mancuso

Comite

et al. 2017

Proceedings of the 11th Workshop on Wireless Network Testbeds, Experimental Evaluation &Amp; CHaracterization

View full text Add to dashboard Cite

In this paper we present a selection from a vast range of experiments run with MONROE, our experiment as a service platform open to external researchers. We show that the platform can be used to benchmark network performance in a repeatable and controlled manner thanks to the collection of a rich set of geotagged metadata and the execution of discretionary user experiments. Indeed, with the sheer amount of data collected from 12 commercial mobile operators across Europe, MONROE offers an unprecedented opportunity to monitor, analyze and ultimately improve the status of current and future mobile broadband networks. We also show how flexibly the platform allows combining metadata and experimental data series during the experiments or by means of post-processing, and show results produced by our own experiments as well as by external research groups and developers that have been granted access to the platform. 1 INTRODUCTION The field of networking offers the possibility of gathering large volumes of information from network elements and end hosts. Analyzing these data is crucial to understand how networks perform under different usage patterns and adapt them to future requirements. This is particularly important for mobile broadband networks (MBBs), which are the segment with the strongest growth forecast and higher variability in operating conditions. Two main

show abstract

Data analytics for forecasting cell congestion on LTE networks

Cited by 24 publications

References 7 publications

A Method for Improving Imputation and Prediction Accuracy of Highly Seasonal Univariate Data with Large Periods of Missingness

A Method for Improving Imputation and Prediction Accuracy of Highly Seasonal Univariate Data with Large Periods of Missingness

Correlation-Based Feature Mapping of Crowdsourced LTE Data

Results from Running an Experiment as a Service Platform for Mobile Networks

Contact Info

Product

Resources

About