ABSTRACT
The overall aim of this project is to investigate the application of a machine learning method in finding the optimized length of asleep time interval (TAS) in a cyclic sleep mechanism (CSM). Since past decade, the implementations of CSM in the optical network unit (ONU) to reduce the energy consumption in 10 gigabit-passive optical network (XG-PON) were extensively researched. However, the newest era sees the emergence of various network traffic with stringent demands that require further improvements on the TAS selection. Since conventional methods utilize complex algorithm, this paper presents the employment of an artificial neural network (ANN) to facilitate ONU to determine the optimized TAS values using learning from past experiences. Prior to simulation, theoretical analysis was done using the M/G/1 queueing system. The ANN was than trained and tested for the XG-PON network for optimal TAS decisions. Results have shown that towards higher network load, a decreasing TAS trend was observed from both methods. A wider TAS range was recorded from the ANN network as compared to the theoretical values. Therefore, these findings will benefit the network operators to have a flexibility measure in determining the optimal TAS values at current network conditions.