Traffic prediction for dynamic traffic engineering considering traffic variation

Otoshi, Tatsuya; Ohsita, Yuichi; Murata, Masayuki; Takahashi, Yoshiko; Ishibashi, Keisuke; Shiomoto, Kohei

doi:10.1109/glocom.2013.6831297

Cited by 11 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The autoregressive models that are more commonly utilized for traffic prediction are the AutoRegressive Integrated Moving Average (ARIMA) and Seasonal ARIMA (SARIMA) models. [7] and [8] use these models to predict the traffic flow. These studies show that SARIMA can improve the prediction over ARIMA by taking into account the traffic seasonality.…”

Section: State Of the Art On Traffic Predictionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Evaluation of Deep Learning-Based Techniques for Traffic Prediction

Mena-Oreja

Gozálvez

2020

IEEE Access

View full text Add to dashboard Cite

Deep learning-based techniques are the state of the art in road traffic prediction or forecasting. Several deep neural networks have been proposed to predict the traffic but they have not been evaluated under common datasets. Current studies analyze their capacity to predict road traffic in general but do not focus on their capacity to predict the formation of congestions. This is critical for avoiding congestions or mitigate their negative impact. This paper progresses the current state of the art by presenting a comprehensive comparison of the state-of-the-art deep neural networks for road traffic prediction. The comparison is conducted using the same real traffic datasets, and under normal and congested traffic conditions. The evaluation includes new deep neural networks and error recurrent models. Our study first demonstrates that accurately predicting the traffic overall does not imply that a deep neural network can accurately predict the traffic when congestions are being formed. This reinforces the idea that prediction techniques must also be evaluated under congestion conditions. Our analysis also shows that exploiting the spatiotemporal evolution of the traffic (and not just the temporal one) provides better prediction accuracy overall and in particular under congestion conditions. The study also demonstrates that error recurrent models outperform deep neural networks that do not utilize an error feedback both under normal and congested traffic conditions. In particular, our study shows that the error recurrent model eRCNN is the deep learning technique that achieves to date the best traffic prediction accuracy. It is also important emphasizing that error recurrent models achieve better prediction accuracy with shallower neural networks and therefore lower computational cost.

show abstract

Section: State Of the Art On Traffic Predictionmentioning

confidence: 99%

“…We use same padding for every convolution operation 8. Pooling layers are used to reduce the size of the inputs.…”

mentioning

confidence: 99%

A Comprehensive Evaluation of Deep Learning-Based Techniques for Traffic Prediction

Mena-Oreja

Gozálvez

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Prediction methods for network traffic have been studied for various time scales, with variation ranging from milliseconds or seconds [11][12][13][14] up to daily [15,16] and even monthly or yearly long-term variation [17,18]. Traffic prediction that considers both daily and short-term variation has also been proposed for TE [19]. However, no prediction methods are without error, and routes calculated from incorrect traffic information become inappropriate for actual traffic and may cause congestion.…”

Section: Copyright Cmentioning

confidence: 99%

Traffic Engineering Based on Model Predictive Control

Otoshi

Ohsita

Murata

et al. 2015

IEICE Trans. Commun.

Self Cite

View full text Add to dashboard Cite

Tatsuya OTOSHI †a) , Nonmember, Yuichi OHSITA †b) , Member, Masayuki MURATA †c) , Fellow, Yousuke TAKAHASHI † †d) , Noriaki KAMIYAMA † †e) , Keisuke ISHIBASHI † †f) , Members, Kohei SHIOMOTO † †g) , Fellow, and Tomoaki HASHIMOTO † † †h) , Nonmember SUMMARY In recent years, the time variation of Internet traffic has increased due to the growth of streaming and cloud services. Backbone networks must accommodate such traffic without congestion. Traffic engineering with traffic prediction is one approach to stably accommodating time-varying traffic. In this approach, routes are calculated from predicted traffic to avoid congestion, but predictions may include errors that cause congestion. We propose prediction-based traffic engineering that is robust against prediction errors. To achieve robust control, our method uses model predictive control, a process control method based on prediction of system dynamics. Routes are calculated so that future congestion is avoided without sudden route changes. We apply calculated routes for the next time slot, and observe traffic. Using the newly observed traffic, we again predict traffic and recalculate the routes. Repeating these steps mitigates the impact of prediction errors, because traffic predictions are corrected in each time slot. Through simulations using backbone network traffic traces, we demonstrate that our method can avoid the congestion that the other methods cannot.

show abstract

“…In our earlier work [20], we only compared the effectiveness of traffic engineering using predicted traffic with observation-based traffic engineering. This paper also investigates details of the impact of traffic prediction on traffic engineering.…”

Section: Introductionmentioning

confidence: 99%