Photovoltaic technologies provide significant capacity to electric grids,however,resource variability and production uncertainty complicate power balancing and reserve management.A crucial step in predicting solar gen...Photovoltaic technologies provide significant capacity to electric grids,however,resource variability and production uncertainty complicate power balancing and reserve management.A crucial step in predicting solar generation is determining clear-sky irradiance.Clear-sky attenuation can be modeled using broadband atmospheric turbidity factors,but model accuracy is dependent on the measurements used to determine the current and future state of aerosol loading and water vapor content,which requires close proximity measurements,in time and space,to account for turbidity variability.Such measurements,though,are only available in near real-time at a limited,and decreasing,number of sites.This paper proposes a new method for estimating time-varying local turbidity conditions from more readily available pyranometer or PV output data.The method employs a long short-term memory recurrent neural network to distill the turbidity-driven signal from global irradiance(or global irradiance driven)observations,despite an inherent dampening issue.The method is developed to operate in near real-time for solar forecasting applications.Validation examines the ability of the method to(1)reproduce turbidity estimates derived from historical measurements of beam irradiance under clear-sky conditions;and(2)provide input for clear-sky models in the form of persistence forecasts generated from daily mean values.展开更多
基金This work was funded by the Office of Naval Research(ONR),United States under the Asia Pacific Research Initiative for Sustainable Energy Systems(APRISES)project,Grant Award Number N00014-16-1-2116by the U.S.Department of Energy,United States under the U.S.-India collAborative for smart diStribution System wIth STorage(UI-ASSIST)project,Award Number DE-IA0000025.
文摘Photovoltaic technologies provide significant capacity to electric grids,however,resource variability and production uncertainty complicate power balancing and reserve management.A crucial step in predicting solar generation is determining clear-sky irradiance.Clear-sky attenuation can be modeled using broadband atmospheric turbidity factors,but model accuracy is dependent on the measurements used to determine the current and future state of aerosol loading and water vapor content,which requires close proximity measurements,in time and space,to account for turbidity variability.Such measurements,though,are only available in near real-time at a limited,and decreasing,number of sites.This paper proposes a new method for estimating time-varying local turbidity conditions from more readily available pyranometer or PV output data.The method employs a long short-term memory recurrent neural network to distill the turbidity-driven signal from global irradiance(or global irradiance driven)observations,despite an inherent dampening issue.The method is developed to operate in near real-time for solar forecasting applications.Validation examines the ability of the method to(1)reproduce turbidity estimates derived from historical measurements of beam irradiance under clear-sky conditions;and(2)provide input for clear-sky models in the form of persistence forecasts generated from daily mean values.
