Recent advances in communication and networking technologies are leading to a plethora of novel wireless services that range from unmanned aerial vehicle(UAV)communication to smart cognitive networks and massive Inter...Recent advances in communication and networking technologies are leading to a plethora of novel wireless services that range from unmanned aerial vehicle(UAV)communication to smart cognitive networks and massive Internet of Things(IoT)systems.Enabling these emerging applications over the fifth generation(5G)of wireless cellular systems requires meeting numerous challenges pertaining to spectrum sharing and management.In fact,most 5G applications will be highly reliant on intelligent spectrum management techniques,which should adapt to dynamic network environments while also guaranteeing high reliability and high quality-of-experience(QoE).展开更多
Prediction of indoor airflow distribution often relies on high-fidelity,computationally intensive computational fluid dynamics(CFD)simulations.Artificial intelligence(Al)models trained by CFD data can be used for fast...Prediction of indoor airflow distribution often relies on high-fidelity,computationally intensive computational fluid dynamics(CFD)simulations.Artificial intelligence(Al)models trained by CFD data can be used for fast and accurate prediction of indoor airflow,but current methods have limitations,such as only predicting limited outputs rather than the entire flow field.Furthermore,conventional Al models are not always designed to predict different outputs based on a continuous input range,and instead make predictions for one or a few discrete inputs.This work addresses these gaps using a conditional generative adversarial network(CGAN)model approach,which is inspired by current state-of-the-art Al for synthetic image generation.We create a new Boundary Condition CGAN(BC-CGAN)model by extending the original CGAN model to generate 2D airflow distribution images based on a continuous input parameter,such as a boundary condition.Additionally,we design a novel feature-driven algorithm to strategically generate training data,with the goal of minimizing the amount of computationally expensive data while ensuring training quality of the Al model.The BC-CGAN model is evaluated for two benchmark airflow cases:an isothermal lid-driven cavity flow and a non-isothermal mixed convection flow with a heated box.We also investigate the performance of the BC-CGAN models when training is stopped based on different levels of validation error criteria.The results show that the trained BC-CGAN model can predict the 2D distribution of velocity and temperature with less than 5%relative error and up to about 75,ooo times faster when compared to reference CFD simulations.The proposed feature-driven algorithm shows potential for reducing the amount of data and epochs required to train the Al models while maintaining prediction accuracy,particularly when the flow changes non-linearlywith respectto an input.展开更多
文摘Recent advances in communication and networking technologies are leading to a plethora of novel wireless services that range from unmanned aerial vehicle(UAV)communication to smart cognitive networks and massive Internet of Things(IoT)systems.Enabling these emerging applications over the fifth generation(5G)of wireless cellular systems requires meeting numerous challenges pertaining to spectrum sharing and management.In fact,most 5G applications will be highly reliant on intelligent spectrum management techniques,which should adapt to dynamic network environments while also guaranteeing high reliability and high quality-of-experience(QoE).
基金supported in part by the U.S.Defense Threat Reduction Agency and performed under U.S.Department of Energy Contract No.DE-AC02-05CH11231supported by the National Science Foundation under Awards No.IIS-1802017,CBET-2217410,CNS-2025377,CNS-2241361.
文摘Prediction of indoor airflow distribution often relies on high-fidelity,computationally intensive computational fluid dynamics(CFD)simulations.Artificial intelligence(Al)models trained by CFD data can be used for fast and accurate prediction of indoor airflow,but current methods have limitations,such as only predicting limited outputs rather than the entire flow field.Furthermore,conventional Al models are not always designed to predict different outputs based on a continuous input range,and instead make predictions for one or a few discrete inputs.This work addresses these gaps using a conditional generative adversarial network(CGAN)model approach,which is inspired by current state-of-the-art Al for synthetic image generation.We create a new Boundary Condition CGAN(BC-CGAN)model by extending the original CGAN model to generate 2D airflow distribution images based on a continuous input parameter,such as a boundary condition.Additionally,we design a novel feature-driven algorithm to strategically generate training data,with the goal of minimizing the amount of computationally expensive data while ensuring training quality of the Al model.The BC-CGAN model is evaluated for two benchmark airflow cases:an isothermal lid-driven cavity flow and a non-isothermal mixed convection flow with a heated box.We also investigate the performance of the BC-CGAN models when training is stopped based on different levels of validation error criteria.The results show that the trained BC-CGAN model can predict the 2D distribution of velocity and temperature with less than 5%relative error and up to about 75,ooo times faster when compared to reference CFD simulations.The proposed feature-driven algorithm shows potential for reducing the amount of data and epochs required to train the Al models while maintaining prediction accuracy,particularly when the flow changes non-linearlywith respectto an input.
