Conditional Kernel Density Estimation Considering Autocorrelation for Renewable Energy Probabilistic Modeling

TL;DR

This paper introduces a conditional kernel density estimation method that accounts for autocorrelation in renewable energy data, improving probabilistic modeling for forecasting and equipment monitoring.

Contribution

The paper presents a novel autocorrelation-aware kernel density estimation technique for renewable energy data, enhancing short-term forecasting and condition monitoring accuracy.

Findings

Effective in modeling renewable power output distribution.

Outperforms existing methods in real-world applications.

Reduces bias in density estimation through iterative procedures.

Abstract

Renewable energy is essential for energy security and global warming mitigation. However, power generation from renewable energy sources is uncertain due to volatile weather conditions and complex equipment operations. To improve equipment's operation efficiency, it is important to understand and characterize the uncertainty in renewable power generation. In this paper, we proposed a conditional kernel density estimation method to model the distribution of equipment's power output given any weather conditions. It explicitly accounts for the temporal dependence in the data stream and uses an iterative procedure to reduce the bias in kernel density estimation. Compared with existing literature, our approach is especially useful for the purposes of equipment condition monitoring or short-term renewable energy forecasting, where the data dependence plays a more significant role. We demonstrate our method and compare it with alternatives through real applications.