XGBIR: An XGBoost-based IR Drop Predictor for Power Delivery Network
Chi-Hsien Pao, An-Yu Su, Yu‐Min Lee
Abstract
This work utilizes the XGBoost to build a machine-learning-based IR drop predictor, XGBIR, for the power grid. To capture the behavior of power grid, we extract its several features and employ its locality property to save the extraction time. XGBIR can be effectively applied to large designs and the average error of predicted IR drops is less than 6 mV.
Topics & Concepts
Computer scienceLocalityDrop (telecommunication)GridPower network designPower gridPower (physics)Power demandDrop outPower networkWork (physics)Artificial intelligenceElectric power systemMathematicsEngineeringTelecommunicationsPower consumptionPhysicsEconomicsQuantum mechanicsMechanical engineeringDemographic economicsGeometryChipLinguisticsPhilosophyAdvanced Optical Network TechnologiesOptical Network TechnologiesIslanding Detection in Power Systems