Enhancing Energy Efficiency of the Doze Mode Mechanism in Ethernet Passive Optical Networks Using Support Vector Regression

An Ethernet passive optical network (EPON) is an access that allows a higher data rate with low power consumption. To improve energy savings for EPON, the sleep and doze modes units (ONUs) play pivotal role. Many prediction schemes have been proposed to control these modes. increase accuracy, this study proposes energy-efficient approach uses support vector regression (SVR) model. A dynamic bandwidth allocation (DBA) scheme called SVR-DBA designed allocate ONUs more efficiently fairly. determine effectiveness of scheme, simulations are performed. The simulation results show decreases consumption by up 47% fulfills quality-of-service (QoS) requirements in terms delay, jitter, packet loss.