Short-Term Multi-Horizon Line Loss Rate Forecasting of a Distribution Network Using Attention-GCN-LSTM
This work addresses line loss management for distribution networks, but it appears incremental as it combines existing techniques like GCN, LSTM, and attention mechanisms.
The study tackled the problem of short-term multi-horizon line loss rate forecasting in distribution networks by proposing the Attention-GCN-LSTM method, which achieved superior prediction accuracy compared to existing algorithms using real-world data from 10KV feeders.
Accurately predicting line loss rates is vital for effective line loss management in distribution networks, especially over short-term multi-horizons ranging from one hour to one week. In this study, we propose Attention-GCN-LSTM, a novel method that combines Graph Convolutional Networks (GCN), Long Short-Term Memory (LSTM), and a three-level attention mechanism to address this challenge. By capturing spatial and temporal dependencies, our model enables accurate forecasting of line loss rates across multiple horizons. Through comprehensive evaluation using real-world data from 10KV feeders, our Attention-GCN-LSTM model consistently outperforms existing algorithms, exhibiting superior performance in terms of prediction accuracy and multi-horizon forecasting. This model holds significant promise for enhancing line loss management in distribution networks.