Forecasting Network Traffic at Large Time Scales by Using Dual-Related Method
Summary :
Network traffic forecasts, as it is well known, can be useful for network resource optimization. In order to minimize the forecast error by maximizing information utilization with low complexity, this paper concerns the difference of traffic trends at large time scales and fits a dual-related model to predict it. First, by analyzing traffic trends based on user behavior, we find both hour-to-hour and day-to-day patterns, which means that models based on either of the single trends are unable to offer precise predictions. Then, a prediction method with the consideration of both daily and hourly traffic patterns, called the dual-related forecasting method, is proposed. Finally, the correlation for traffic data is analyzed based on model parameters. Simulation results demonstrate the proposed model is more effective in reducing forecasting error than other models.
- Publication
- IEICE TRANSACTIONS on Communications Vol.E100-B No.11 pp.2049-2059
- Publication Date
- 2017/11/01
- Publicized
- 2017/04/24
- Online ISSN
- 1745-1345
- DOI
- 10.1587/transcom.2017EBP3014
- Type of Manuscript
- PAPER
- Category
- Network
Authors
Liangrui TANG
NCEPU
Shiyu JI
NCEPU
Shimo DU
China Mobile Communication Group Ltd
Yun REN
State Grid Zhejiang Electric Power Company
Runze WU
NCEPU
Xin WU
NCEPU
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Liangrui TANG, Shiyu JI, Shimo DU, Yun REN, Runze WU, Xin WU, "Forecasting Network Traffic at Large Time Scales by Using Dual-Related Method" in IEICE TRANSACTIONS on Communications,
vol. E100-B, no. 11, pp. 2049-2059, November 2017, doi: 10.1587/transcom.2017EBP3014.
Abstract: Network traffic forecasts, as it is well known, can be useful for network resource optimization. In order to minimize the forecast error by maximizing information utilization with low complexity, this paper concerns the difference of traffic trends at large time scales and fits a dual-related model to predict it. First, by analyzing traffic trends based on user behavior, we find both hour-to-hour and day-to-day patterns, which means that models based on either of the single trends are unable to offer precise predictions. Then, a prediction method with the consideration of both daily and hourly traffic patterns, called the dual-related forecasting method, is proposed. Finally, the correlation for traffic data is analyzed based on model parameters. Simulation results demonstrate the proposed model is more effective in reducing forecasting error than other models.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2017EBP3014/_p
Copy
@ARTICLE{e100-b_11_2049,
author={Liangrui TANG, Shiyu JI, Shimo DU, Yun REN, Runze WU, Xin WU, },
journal={IEICE TRANSACTIONS on Communications},
title={Forecasting Network Traffic at Large Time Scales by Using Dual-Related Method},
year={2017},
volume={E100-B},
number={11},
pages={2049-2059},
abstract={Network traffic forecasts, as it is well known, can be useful for network resource optimization. In order to minimize the forecast error by maximizing information utilization with low complexity, this paper concerns the difference of traffic trends at large time scales and fits a dual-related model to predict it. First, by analyzing traffic trends based on user behavior, we find both hour-to-hour and day-to-day patterns, which means that models based on either of the single trends are unable to offer precise predictions. Then, a prediction method with the consideration of both daily and hourly traffic patterns, called the dual-related forecasting method, is proposed. Finally, the correlation for traffic data is analyzed based on model parameters. Simulation results demonstrate the proposed model is more effective in reducing forecasting error than other models.},
keywords={},
doi={10.1587/transcom.2017EBP3014},
ISSN={1745-1345},
month={November},}
Copy
TY - JOUR
TI - Forecasting Network Traffic at Large Time Scales by Using Dual-Related Method
T2 - IEICE TRANSACTIONS on Communications
SP - 2049
EP - 2059
AU - Liangrui TANG
AU - Shiyu JI
AU - Shimo DU
AU - Yun REN
AU - Runze WU
AU - Xin WU
PY - 2017
DO - 10.1587/transcom.2017EBP3014
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E100-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2017
AB - Network traffic forecasts, as it is well known, can be useful for network resource optimization. In order to minimize the forecast error by maximizing information utilization with low complexity, this paper concerns the difference of traffic trends at large time scales and fits a dual-related model to predict it. First, by analyzing traffic trends based on user behavior, we find both hour-to-hour and day-to-day patterns, which means that models based on either of the single trends are unable to offer precise predictions. Then, a prediction method with the consideration of both daily and hourly traffic patterns, called the dual-related forecasting method, is proposed. Finally, the correlation for traffic data is analyzed based on model parameters. Simulation results demonstrate the proposed model is more effective in reducing forecasting error than other models.
ER -
English
