A practical model for traffic forecasting based on big data, machine-learning, and network KPIs

Le, Luong-Vy; Do, Sinh; Tung, Li-Ping; Lin, Bor‐Shyh

doi:10.1109/ccnc.2018.8319255

Cited by 25 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study done by [18] used both ARIMA and FARIMA models for 3G network traffic forecasting. The traffic forecasting application is presented by [21], based on AR, NN and GP algorithms and they used both voice and data traffic of 2G, 3G and 4G. The forecasting of TCH mobile traffic and daily traffic of mobile network are done using multiplicative seasonal ARIMA by [22] and [23] respectively.…”

Section: A Forecasting Network Activities For Better Network Managementmentioning

confidence: 99%

Capacity and Frequency Optimization of Wireless Backhaul Network Using Traffic Forecasting

et al. 2020

View full text Add to dashboard Cite

Telecom operators are aiming to provide high-grade data, multimedia applications and low latency videos for smart devices. As today's mobile data is experiencing rapid growth and the usage of smart devices are fabricating unparalleled challenges for telecom operators to meet the global bandwidth requirement. From the first generation to fourth generation, the technology evolution is predominantly governed by the hardware side but now it is moving towards the concept of cognitive network management, resource orchestration and machine learning-based solutions. In this paper, we propose the adaptive capacity and frequency optimization (ACFO) method for adaptive optimization based on time series forecasting approach. The daily capacity utilization of microwave (MW) links is analyzed to use forecasted demand. Based on the projected demand, the capacity and frequency optimization will be executed. The two main forecasting models 1) SARIMA and 2) MLP are used and for performance evaluation, we used RMSE and MAPE criterion. The analytic outcomes show that MLP with two layers and six hidden nodes (6/6) are good enough to achieve the desired results. In some cases, we need to exceed the hidden nodes up to fifteen (15/15). By using the forecasting approach, the reactive optimization will successfully shift to the predicted/ proactive optimization, will balance the resource distribution and can condense the wastage of resources. The outcome of the study will be a contribution to the dynamic resource optimization in wireless backhaul network. INDEX TERMS Time series forecasting, capacity planning, dynamic resource optimization, wireless backhaul optimization.

show abstract

Section: A Forecasting Network Activities For Better Network Managementmentioning

confidence: 99%

Capacity and Frequency Optimization of Wireless Backhaul Network Using Traffic Forecasting

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The analysis and understanding of mobile data traffic can be realized at aggregate level and at peruser level [1]. The mobile traffic prediction schemes at aggregate level are based on time series prediction models, for instance, seasonal auto regression integrated moving average (ARIMA) in [2], and machine learning algorithms, like neural networks (NN), Gaussian process (GP) in [3,4]. Recently, more sophisticated methods like deep learning based approaches are employed to predict network traffic in [5].…”

Section: Introductionmentioning

confidence: 99%

“…It is used to predict holiday traffic [16] and temporal performance measurements [17] in mobile cellular networks. GPR is a powerful machine learning method [17], which is used to predict spatial performance measurements [17] and network traffic in [3,4]. Owing to more serious fluctuation in user's network traffic, existing timeseries prediction algorithms cannot be directly applied to the network traffic prediction of individual user.…”

Section: Introductionmentioning

confidence: 99%

Prophet model and Gaussian process regression based user traffic prediction in wireless networks

Pan

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

User traffic prediction is an important topic for wireless network operators. A user traffic prediction method based on Prophet and Gaussian process regression is proposed in this paper. The proposed method first employs discrete wavelet transform to decompose the user traffic time series to high-frequency component and low-frequency component. The low-frequency component bears the long-range dependence of user network traffic, while the high-frequency component reveals the gusty and irregular fluctuations of user network traffic. Then Prophet model and Gaussian process regression are applied to predict the two components respectively based on the characteristics of the two components. Experimental results demonstrate that the proposed model outperforms the existing time series prediction method.

show abstract

“…This helps the SON keeps track of network parameters and deploys further optimization applications. For example, in studies [15] and [16], we proposed several models to accurately and efficiently forecast future handover numbers and the traffic of a huge number of cells by using several ML algorithms: Neural network (NN), Gaussian process (GP), and linear regression.…”

Section: Open Platform For 5g Sonmentioning

confidence: 99%

Applying Big Data, Machine Learning, and SDN/NFV for 5G Early-Stage Traffic Classification and Network QoS Control

Lin

2018

TNC

Self Cite

View full text Add to dashboard Cite

Due to the rapid growth of mobile broadband and IoT applications, the early-stage mobile traffic classification becomes more important for traffic engineering to guarantee Quality of Service (QoS), implement resource management, and network security. Therefore, identifying traffic flows based on a few packets during the early state has attracted attention in both academic and industrial fields. However, a powerful and flexible platform to handle millions of traffic flows is still challenging. This study aims to demonstrate how to integrate various state-of-the-art machine learning (ML) algorithms, big data analytics platforms, software-defined networking (SDN), and network functions virtualization (NFV) to build a comprehensive framework for developing future 5G SON applications. This platform successfully collected, stored, analyzed, and identified a huge number of real-time traffic flows at broadband Mobile Lab (BML), National Chiao Tung University (NCTU). Moreover, we also implemented network QoS control to configure priorities per-flow traffic to enable bandwidth guarantees for each application by using SDN. Finally, the performance of the proposed models was evaluated by applying them to a real testbed environment. The powerful computing capacity of the platform was also analyzed.

show abstract

A practical model for traffic forecasting based on big data, machine-learning, and network KPIs

Cited by 25 publications

References 10 publications

Capacity and Frequency Optimization of Wireless Backhaul Network Using Traffic Forecasting

Capacity and Frequency Optimization of Wireless Backhaul Network Using Traffic Forecasting

Prophet model and Gaussian process regression based user traffic prediction in wireless networks

Applying Big Data, Machine Learning, and SDN/NFV for 5G Early-Stage Traffic Classification and Network QoS Control

Contact Info

Product

Resources

About