Abstract
An Ethernet passive optical network (EPON) is an optical access network that allows a higher data rate with low power consumption. To improve energy savings for an EPON, the sleep and doze modes for the optical network units (ONUs) play a pivotal role. Many prediction schemes have been proposed to control these modes. To increase the prediction accuracy, this study proposes an energy-efficient approach that uses a support vector regression (SVR) model. A dynamic bandwidth allocation (DBA) scheme called SVR-DBA is designed to allocate bandwidth to ONUs more efficiently and fairly. To determine the effectiveness of the proposed scheme, simulations are performed. The simulation results show that the proposed scheme decreases energy consumption for ONUs by up to 47% and fulfills the quality-of-service (QoS) requirements in terms of delay, jitter, and packet loss.
Highlights
Today more than 53.6% of people worldwide have internet access, which causes increasing energy consumption in the access networks
This study proposes a dynamic bandwidth allocation scheme called SVR-DBA that uses the support vector regression (SVR) model [18,19]
Compared with the IPACT (Interleaved Polling with Adaptive Cycle Time) scheme [5], the Green DBA (GDBA) scheme [13], and the LRDBA (Logistic Regression DBA) [15], SVR-DBA gives energy savings for optical network units (ONUs) by up to 47% and fulfills QoS requirements in terms of delay, jitter, and packet loss
Summary
Today more than 53.6% of people worldwide have internet access, which causes increasing energy consumption in the access networks. Several schemes have been proposed for ONU sleep/doze time allocation [10–16] Most of these studies determine the duration of the sleep/doze by analyzing the current status in the buffers of ONUs and do not consider upcoming traffic from users. They use a greedy approach to achieve energy savings by allowing ONUs to enter the sleep/doze mode for a long period. This greedy approach results in an overly long delay and violates the delay restrictions for the different QoS requirements in the optical access networks [14].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
