PV Fleet Modeling via Smooth Periodic Gaussian Copula

TL;DR

This paper introduces a scalable, interpretable Gaussian copula-based method for joint modeling of PV fleet power generation, capturing dependencies and diurnal patterns to enable data simulation, imputation, anomaly detection, and forecasting.

Contribution

A novel smooth, periodic copula transform method that accurately models dependencies and diurnal variations in PV fleet data, scalable to many systems.

Findings

Effective in capturing diurnal variation and dependencies

Enables realistic synthetic data generation

Improves anomaly detection and forecasting accuracy

Abstract

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.