Dynamic bandwidth provisioning using ARIMA-based traffic forecasting for Mobile WiMAX

Kim, Hyun Woo; Lee, Jun-Hui; Choi, Yong-Hoon; Chung, Young-uk; Lee, Hyukjoon

doi:10.1016/j.comcom.2010.08.008

Cited by 40 publications

(22 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Train M with input Q and target T by SGD. 14: end for 15 periodicity (in both daily and weekly patterns) and relatively flat averages, if observed over long intervals [20]. This is indeed the case also for the city of Milan, as we illustrate in Fig.…”

supporting

confidence: 74%

Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks

Zhang¹,

Patras²

2018

Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing

213

121

View full text Add to dashboard Cite

Forecasting with high accuracy the volume of data traffic that mobile users will consume is becoming increasingly important for precision traffic engineering, demand-aware network resource allocation, as well as public transportation. Measurements collection in dense urban deployments is however complex and expensive, and the post-processing required to make predictions is highly non-trivial, given the intricate spatio-temporal variability of mobile traffic due to user mobility. To overcome these challenges, in this paper we harness the exceptional feature extraction abilities of deep learning and propose a Spatio-Temporal neural Network (STN) architecture purposely designed for precise network-wide mobile traffic forecasting. We present a mechanism that fine tunes the STN and enables its operation with only limited ground truth observations. We then introduce a Double STN technique (D-STN), which uniquely combines the STN predictions with historical statistics, thereby making faithful long-term mobile traffic projections. Experiments we conduct with real-world mobile traffic data sets, collected over 60 days in both urban and rural areas, demonstrate that the proposed (D-)STN schemes perform up to 10-hour long predictions with remarkable accuracy, irrespective of the time of day when they are triggered. Specifically, our solutions achieve up to 61% smaller prediction errors as compared to widely used forecasting approaches, while operating with up to 600 times shorter measurement intervals.

show abstract

supporting

confidence: 74%

Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks

Zhang¹,

Patras²

2018

Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing

213

121

View full text Add to dashboard Cite

show abstract

“…3) GPU computing enables fast training of NNs and together with parallelization techniques can support low-latency mobile traffic analysis via deep learning tools. In essence, we expect deep learning tools tailored to mobile networking, will overcome the limitation of traditional regression and interpolation tools such as Exponential Smoothing [561], Autoregressive Integrated Moving Average model [562], or unifrom interpolation, which are commonly used in operational networks.…”

Section: B Deep Learning For Spatio-temporal Mobile Data Miningmentioning

confidence: 99%

Deep Learning in Mobile and Wireless Networking: A Survey

Zhang

Patras

Haddadi

2019

IEEE Commun. Surv. Tutorials

1,330

838

View full text Add to dashboard Cite

The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure. Upcoming 5G systems are evolving to support exploding mobile traffic volumes, real-time extraction of fine-grained analytics, and agile management of network resources, so as to maximize user experience. Fulfilling these tasks is challenging, as mobile environments are increasingly complex, heterogeneous, and evolving. One potential solution is to resort to advanced machine learning techniques, in order to help manage the rise in data volumes and algorithm-driven applications. The recent success of deep learning underpins new and powerful tools that tackle problems in this space.In this paper we bridge the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas. We first briefly introduce essential background and state-of-theart in deep learning techniques with potential applications to networking. We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems. Subsequently, we provide an encyclopedic review of mobile and wireless networking research based on deep learning, which we categorize by different domains. Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.

show abstract

“…It formulates its mathematical model to fit the time series based on the Box-Jenkins autoregressive moving average (ARMA) model [43]. It is often referred to as ARIMA( , , ) model, where and are the factors of AR (autoregressive) and MA (moving average), respectively, while is the difference frequency to make time series stationary [44][45][46]. The model can be written as…”

Section: Arima Modelmentioning

confidence: 99%

Blink Number Forecasting Based on Improved Bayesian Fusion Algorithm for Fatigue Driving Detection

Sun

Zhang

Wang

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

An improved Bayesian fusion algorithm (BFA) is proposed for forecasting the blink number in a continuous video. It assumes that, at one prediction interval, the blink number is correlated with the blink numbers of only a few previous intervals. With this assumption, the weights of the component predictors in the improved BFA are calculated according to their prediction performance only from a few intervals rather than from all intervals. Therefore, compared with the conventional BFA, the improved BFA is more sensitive to the disturbed condition of the component predictors for adjusting their weights more rapidly. To determine the most relevant intervals, the grey relation entropy-based analysis (GREBA) method is proposed, which can be used analyze the relevancy between the historical data flows of blink number and the data flow at the current interval. Three single predictors, that is, the autoregressive integrated moving average (ARIMA), radial basis function neural network (RBFNN), and Kalman filter (KF), are designed and incorporated linearly into the BFA. Experimental results demonstrate that the improved BFA obviously outperforms the conventional BFA in both accuracy and stability; also fatigue driving can be accurately warned against in advance based on the blink number forecasted by the improved BFA.

show abstract

Dynamic bandwidth provisioning using ARIMA-based traffic forecasting for Mobile WiMAX

Cited by 40 publications

References 11 publications

Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks

Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks

Deep Learning in Mobile and Wireless Networking: A Survey

Blink Number Forecasting Based on Improved Bayesian Fusion Algorithm for Fatigue Driving Detection

Contact Info

Product

Resources

About