PV Fleet Modeling via Smooth Periodic Gaussian Copula
This work addresses the need for scalable and interpretable probabilistic modeling of PV fleet output for applications in energy management, though it appears incremental as it builds on existing copula-based methods with a focus on smooth periodic transforms.
The paper tackles the problem of jointly modeling power generation from a fleet of photovoltaic systems by proposing a white-box method that invertibly maps time-series data to standard normal variables, capturing diurnal variations and dependencies, and demonstrates applications like synthetic data generation and anomaly detection.
We present a method for jointly modeling power generation from a fleet of photovoltaic (PV) systems. We propose a white-box method that finds a function that invertibly maps vector time-series data to independent and identically distributed standard normal variables. The proposed method, based on a novel approach for fitting a smooth, periodic copula transform to data, captures many aspects of the data such as diurnal variation in the distribution of power output, dependencies among different PV systems, and dependencies across time. It consists of interpretable steps and is scalable to many systems. The resulting joint probability model of PV fleet output across systems and time can be used to generate synthetic data, impute missing data, perform anomaly detection, and make forecasts. In this paper, we explain the method and demonstrate these applications.