Optical Fiber Communication Conference · 2017 · 21 citations · 4 references
EngineeringComputer EngineeringElectrical EngineeringDesign OptimizationMachine LearningOptimizationChannel Performance AnalysisChannel PowerDynamic Power ReductionPower ManagementPower OptimizationPower-aware DesignDynamic Power ModelingEnergy-aware OptimizationMachine Learning-based Power EstimationPower AdaptationPower EnhancementPower Modeling And EstimationPower Profiling
We examine EDFA power excursions during three defragmentation methods of flexgrid super-channels. Using a machine learning approach, we demonstrate automatic and dynamic adjustments of pre-EDFA power levels, and show the mitigation of post-EDFA power discrepancy among channels by over 62%.
4