Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis

TL;DR

This paper introduces a Bayesian LSTM-based spatio-temporal model to predict and refine the uncertainty set of aggregated wind power generation across multiple farms, improving reliability for system operation.

Contribution

It presents a novel probabilistic spatio-temporal approach combining Bayesian LSTM and spatial correlation analysis for uncertainty set prediction of distributed wind farms.

Findings

Uncertainty set of aggregated wind generation is less volatile than individual farms.

The model effectively captures dynamic wind field features.

Spatial correlation improves prediction accuracy.

Abstract

Aggregated stochastic characteristics of geographically distributed wind generation will provide valuable information for secured and economical system operation in electricity markets. This paper focuses on the uncertainty set prediction of the aggregated generation of geographically distributed wind farms. A Spatio-temporal model is proposed to learn the dynamic features from partial observation in near-surface wind fields of neighboring wind farms. We use Bayesian LSTM, a probabilistic prediction model, to obtain the uncertainty set of the generation in individual wind farms. Then, spatial correlation between different wind farms is presented to correct the output results. Numerical testing results based on the actual data with 6 wind farms in northwest China show that the uncertainty set of aggregated wind generation of distributed wind farms is less volatile than that of a single wind farm.