Clustering Interval Load with Weather to Create Scenarios of Behind-the-Meter Solar Penetration
Forecasting load at the feeder level has become increasingly challenging with the penetration of behind-the-meter solar, as this self-generation (also called total generation) is only visible to the utility as aggregated net-load. This work proposes a methodology for creation of scenarios of solar penetration at the feeder level for use by forecasters to test the robustness of their algorithm to progressively higher penetrations of solar. The algorithm draws on publicly available observations of weather \emph{condition} (e.g., rainy/cloudy/fair) for use as proxies to sky clearness. These observations are used to mask and weight the interval deviations of similar native usage profiles from which average interval usage is calculated and subsequently added to interval net generation to reconstruct interval total generation. This approach improves the estimate of annual energy generation by 23\%; where the net generation signal currently only reflects 52\% of total annual generation, now 75\% is captured via the proposed algorithm. This proposed methodology is data driven and extensible to service territories which lack information on irradiance measurements and geo-coordinates.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Feature Engineering Approach to Building Load Prediction: A Case Study for Commercial Building Chiller Plant Optimization in Tropical Weather
In tropical countries with high humidity, air conditioning can account for up to 60% of a building's energy use. For commercial buildings with centralized systems, the efficiency of the chiller plant is vital, and model …
ClusteringFeature EngineeringModel Predictive ControlPredictionUncertainty-Aware Solar Flare Regression
Current solar flare predictions often lack precise quantification of their reliability, resulting in frequent false alarms, particularly when dealing with datasets skewed towards extreme events. To improve the trustworth…
Weather ForecastingA Synthetic Texas Power System with Time-Series Weather-Dependent Spatiotemporal Profiles
We developed a synthetic Texas 123-bus backbone transmission system (TX-123BT) with spatio-temporally correlated grid profiles of solar power, wind power, dynamic line ratings and loads at one-hour resolution for five co…
Time SeriesTime Series AnalysisPrediction Interval Construction Method for Electricity Prices
Accurate prediction of electricity prices plays an essential role in the electricity market. To reflect the uncertainty of electricity prices, price intervals are predicted. This paper proposes a novel prediction interva…
Generative Adversarial NetworkPredictionPrediction IntervalsDetecting British Columbia Coastal Rainfall Patterns by Clustering Gaussian Processes
Functional data analysis is a statistical framework where data are assumed to follow some functional form. This method of analysis is commonly applied to time series data, where time, measured continuously or in discrete…
ClusteringGaussian ProcessesTime SeriesTime Series Analysis