DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU

Abstract

In an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasting technique using Delaunay triangulation, of which the vertices are three weather stations that enclose a target PV site. By leveraging a Transformer encoder and gated recurrent unit (GRU), the proposed TransGRU model is robust against weather forecast error as it learns feature representation from weather data. We construct a framework based on Delaunay triangulation and TransGRU and verify that the proposed framework shows a 7–15% improvement compared to other state-of-the-art methods in terms of the normalized mean absolute error. Moreover, we investigate the effect of PV aggregation for virtual power plants where errors can be compensated across PV sites. Our framework demonstrates 41–60% improvement when PV sites are aggregated and achieves as low as 3–4% of forecasting error on average.

Scalable multi‐site photovoltaic power forecasting based on stream computing

“…Owing to the robust feature extraction capabilities of convolutional neural networks (CNN) [10, 11], CNN‐based models have been effectively applied to PV forecasting. Moreover, due to their efficacy in addressing time‐series challenges, both long short‐term memory (LSTM) networks [12] and transformer models [13] have been employed in PV forecasting tasks. Wang K et al.…”

“…Owing to the robust feature extraction capabilities of convolutional neural networks (CNN) [10,11], CNN-based models have been effectively applied to PV forecasting. Moreover, due to their efficacy in addressing time-series challenges, both long short-term memory (LSTM) networks [12] and transformer models [13] have been employed in PV forecasting tasks. Wang K et al [14] introduce a model that combines CNN with LSTM, and this hybrid model with the numerical weather prediction (NWP) as input has higher forecasting accuracy and excellent references.…”