Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Photovoltaic Timeseries Data Imputation

TL;DR

This paper introduces a novel spatio-temporal graph autoencoder framework that significantly improves the accuracy of missing PV power data imputation by leveraging domain knowledge and correlations.

Contribution

The proposed STD-GAE framework is the first to integrate spatio-temporal correlations and domain knowledge for PV data imputation, outperforming existing methods.

Findings

Achieves 43.14% improvement in imputation accuracy.

Less sensitive to missing data rates and seasonal variations.

Outperforms state-of-the-art methods like MIDA and LRTC-TNN.

Abstract

The integration of the global Photovoltaic (PV) market with real time data-loggers has enabled large scale PV data analytical pipelines for power forecasting and long-term reliability assessment of PV fleets. Nevertheless, the performance of PV data analysis heavily depends on the quality of PV timeseries data. This paper proposes a novel Spatio-Temporal Denoising Graph Autoencoder (STD-GAE) framework to impute missing PV Power Data. STD-GAE exploits temporal correlation, spatial coherence, and value dependencies from domain knowledge to recover missing data. Experimental results show that STD-GAE can achieve a gain of 43.14% in imputation accuracy and remains less sensitive to missing rate, different seasons, and missing scenarios, compared with state-of-the-art data imputation methods such as MIDA and LRTC-TNN.