A Framework for Analyzing 4G/LTE-A Real Data Using Machine Learning Algorithms

Mohammed, Nihal H.; Nashaat, Heba; Abdel-Mageid, Salah; Rizk, Rawia Y.

doi:10.1007/978-3-030-58669-0_73

Cited by 3 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sklearn's SelectKBest chooses the most important features to include in the learning process [42]. It also analyzes the correlation between features as in [7], [43]. The proposed AML-CTP framework normalizes the traffic load using Min-Max scaling to avoid significant data variance.…”

Section: A Phase 1: Data Preprocessingmentioning

confidence: 99%

“…Second, a minimum minPoints can be derived from several dimensions (D) in the dataset, as minPoints ≥ D + 1. Larger values are usually better for noisy data sets and will form more significant clusters [7].…”

Section: B Phase 2: Data Reduction Based On Homogeneitymentioning

confidence: 99%

“…It is collected from the traffic data from one of Egypt's most popular telecommunication equipment corporations. Our previous work thoroughly analyzes the used dataset [7]. Traditionally, Key Performance Indicators are divided into radio network KPIs and service.…”

Section: A Datasets Characteristics and Evaluation Setupmentioning

confidence: 99%

“…Traffic KPIs assess traffic volumes on LTE Radio Access Network, categorized by the type of traffic, including radio bearers, downlink traffic volume, and uplink traffic volume. The final dataset used in the first case study consists of 77 features and 259.223 rows [7]. Moreover, over four weeks, another dataset is collected for the second case study from 6,000 cells in 200 telecommunication network sites.…”

Section: A Datasets Characteristics and Evaluation Setupmentioning

confidence: 99%

“…Steering traffic from congested cells frees the physical resource blocks (PRBs) of congested cells and is considered a network that optimizes resource allocation [4], [5]. Hence, predicting 4G and 5G LTE-A traffic became essential to significantly enhance telecommunications QoS [6], [7]. Accurate monitoring and prediction of mobile traffic help improve optimizer goals; consequently, any overload or congestion in any band can be detected [3], [8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning-Based Cellular Traffic Prediction Using Data Reduction Techniques

Nashaat,

Mohammed,

Abdel-Mageid

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Estimating and analyzing traffic patterns become essential in managing Quality of Service (QoS) metrics while assessing internet data traffic in cellular networks. Cellular network planners frequently apply various approaches to predict network traffic. However, most existing studies focus on using the available local data to jointly build prediction models, facing data security challenges and time complexity, especially with multi-dimensional datasets. Therefore, this paper proposes a framework to handle traffic prediction with the considerable potential of Machine Learning (ML) algorithms. An Adaptive Machine Learning-based Cellular Traffic Prediction (AML-CTP) framework is presented to select a suitable ML algorithm for multi-dimensional datasets. Its objective is to streamline and speed up the selection of an appropriate model for predicting network traffic load. The framework employs two density-based clustering algorithms to categorize similar nearby traffic into various clusters, considering data similarity and convergence. Additionally, it assesses data quality and homogeneity by training models with data samples from each cluster to accurately determine the most suitable machine learning model. The optimal model is selected from four supervised predicting algorithms, reducing training time and hardware complexity. Two case studies from a popular telecommunication equipment corporation in Egypt are implemented using reallife cellular traffic with multi-dimensional features. The case studies show that the framework can help reduce the computational cost of training the model and reduce the risk of overfitting. The experimental results show that selecting the best prediction model training could save up to 85% of computational time compared to two state-of-the-art techniques while achieving an accuracy of 98.8%.

show abstract

Section: A Phase 1: Data Preprocessingmentioning

confidence: 99%

Section: B Phase 2: Data Reduction Based On Homogeneitymentioning

confidence: 99%

Section: A Datasets Characteristics and Evaluation Setupmentioning

confidence: 99%

Section: A Datasets Characteristics and Evaluation Setupmentioning

confidence: 99%