Big Data-Driven Short-Term Load Forecasting in Smart Grids: A Spatio-Temporal Dynamic Graph Transformer with Uncertainty-Aware Attention
TL;DR
Experiments indicate that learning dynamic, data-drivenspatial dependencies is beneficial for multi-node load forecasting where correlations evolve over time.
Abstract
Short-term load forecasting for modern smart grids must jointly model long-range temporal patterns, correlations across many metering points, and the uncertainty required for operational decision-making. We propose ST-DGT-UA, a spatio-temporal dynamic graph Transformer that (i) embeds heterogeneous covariates with convolutional projections and Time2Vec, (ii) learns a time-varying adjacency matrix from node representations, (iii) couples spatial graph attention with temporal ProbSparse attention for efficient long-sequence modeling, and (iv) outputs multiple conditional quantiles trained with multi-quantile Pinball loss. Experiments on GEFCom2014 and the UCI Electricity Load Diagrams datasets show that ST-DGT-UA achieves MAPE/RMSE of 1.92/145.6 on GEFCom2014 and 2.65/42.3 on UCI, and improves probabilistic quality with Pinball Loss 0.024 and CRPS 0.043. These results indicate that learning dynamic, data-drivenspatial dependencies is beneficial for multi-node load forecasting where correlations evolve over time.