A new method for traffic forecasting in urban wireless communication network

Zhang, Kaisa; Chuai, Gang; Gao, Weidong; Li, Xuewen; Maimaiti, Saidiwaerdi; Si, Zhiwei

doi:10.1186/s13638-019-1392-6

Cited by 27 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This scheme also takes many input data for estimations. Reference [12] also focuses on forecasting the future mobile traffic data in urban areas. They used various network oscillation factors, such as jitter, packet loss, and delay (i.e., call detail record (CDR)) for enhancing the forecast ability; in addition, they adopted LSTM architecture [7] for realizing long term forecasting.…”

Section: Related Workmentioning

confidence: 99%

A Comprehensive Evaluation of Generating a Mobile Traffic Data Scheme without a Coarse-Grained Process Using CSR-GAN

Tokunaga

Mizutani

2022

Sensors

View full text Add to dashboard Cite

Large-scale mobile traffic data analysis is important for efficiently planning mobile base station deployment plans and public transportation plans. However, the storage costs of preserving mobile traffic data are becoming much higher as traffic increases enormously population density of target areas. To solve this problem, schemes to generate a large amount of mobile traffic data have been proposed. In the state-of-the-art of the schemes, generative adversarial networks (GANs) are used to transform a large amount of traffic data into a coarse-grained representation and generate the original traffic data from the coarse-grained data. However, the scheme still involves a storage cost, since the coarse-grained data must be preserved in order to generate the original traffic data. In this paper, we propose a scheme to generate the mobile traffic data by using conditional-super-resolution GAN (CSR-GAN) without requiring a coarse-grained process. Through experiments using two real traffic data, we assessed the accuracy and the amount of storage data needed. The results show that the proposed scheme, CSR-GAN, can reduce the storage cost by up to 45% compared to the traditional scheme, and can generate the original mobile traffic data with 94% accuracy. We also conducted experiments by changing the architecture of CSR-GAN, and the results show an optimal relationship between the amount of traffic data and the model size.

show abstract

Section: Related Workmentioning

confidence: 99%

A Comprehensive Evaluation of Generating a Mobile Traffic Data Scheme without a Coarse-Grained Process Using CSR-GAN

Tokunaga

Mizutani

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…A multivariate Long Short-Term Memory (LSTM) algorithm was designed in [11] to predict the traffic networks by performing the call detail record (CDR) data analysis. The designed algorithm failed to consider the large volume of wireless data and complex data types for network prediction.…”

Section: Related Workmentioning

confidence: 99%

ECMCRR-MPDNL for Cellular Network Traffic Prediction With Big Data

et al. 2020

View full text Add to dashboard Cite

Big data comprises a large volume of data (i.e., structured and unstructured) stored on a daily basis. Processing such volume of data is a complex task as well as the challenging one. This big data is applied in the cellular network for traffic prediction. Now, benefiting from the big data in cellular networks, it becomes possible to make the analyses one step further into the application level. In order to improve the traffic prediction accuracy with minimum time, Expected Conditional Maximization Clustering and Ruzicka Regression-based Multilayer Perceptron Deep Neural Learning (ECMCRR-MPDNL) technique is introduced. The ECMCRR-MPDNL technique initially collects a large volume of data over the spatial and temporal aspects of cellular networks. Then the collected data are trained with multiple layers such as one input layer, two hidden layers, and one output layer. The activation function is used at the output layer to predict the network traffic based on the similarity value with higher accuracy. These predictors are evaluated using real network traces. Finally, the error rate is calculated for minimizing the prediction error. Experimental evaluation is carried out using a big dataset with different metrics such as prediction accuracy, false-positive and prediction time. The observed result confirms that the proposed ECMCRR-MPDNL technique improves on an average the 98% of performance of network traffic prediction with higher accuracy and 20 % minimum time as well as the false-positive rate as compared to the state-of-the-art methods.

show abstract

“…However, the performance of accurate traffic predictions was not attained. Multivariate prediction algorithms were designed in Zhang et al [4] for cellular network traffic analysis.…”

Section: Introductionmentioning

confidence: 99%

Network Traffic Prediction Using Radial Kernelized-Tversky Indexes-Based Multilayer Classifier

Govindarajan¹,

Chandrasekaran²,

Pillai³

2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Accurate cellular network traffic prediction is a crucial task to access Internet services for various devices at any time. With the use of mobile devices, communication services generate numerous data for every moment. Given the increasing dense population of data, traffic learning and prediction are the main components to substantially enhance the effectiveness of demand-aware resource allocation. A novel deep learning technique called radial kernelized LSTM-based connectionist Tversky multilayer deep structure learning (RKLSTM-CTMDSL) model is introduced for traffic prediction with superior accuracy and minimal time consumption. The RKLSTM-CTMDSL model performs attribute selection and classification processes for cellular traffic prediction. In this model, the connectionist Tversky multilayer deep structure learning includes multiple layers for traffic prediction. A large volume of spatial-temporal data are considered as an input-to-input layer. Thereafter, input data are transmitted to hidden layer 1, where a radial kernelized long short-term memory architecture is designed for the relevant attribute selection using activation function results. After obtaining the relevant attributes, the selected attributes are given to the next layer. Tversky index function is used in this layer to compute similarities among the training and testing traffic patterns. Tversky similarity index outcomes are given to the output layer. Similarity value is used as basis to classify data as heavy network or normal traffic. Thus, cellular network traffic prediction is presented with minimal error rate using the RKLSTM-CTMDSL model. Comparative evaluation proved that the RKLSTM-CTMDSL model outperforms conventional methods.

show abstract

A new method for traffic forecasting in urban wireless communication network

Cited by 27 publications

References 19 publications

A Comprehensive Evaluation of Generating a Mobile Traffic Data Scheme without a Coarse-Grained Process Using CSR-GAN

A Comprehensive Evaluation of Generating a Mobile Traffic Data Scheme without a Coarse-Grained Process Using CSR-GAN

ECMCRR-MPDNL for Cellular Network Traffic Prediction With Big Data

Network Traffic Prediction Using Radial Kernelized-Tversky Indexes-Based Multilayer Classifier

Contact Info

Product

Resources

About