Multi-Horizon Short-Term Load Forecasting for Electric Power System Dispatch Optimization: A Bidirectional Gated Recurrent Unit Framework with Forecast-Origin Prior Integration and Aligned Evaluation

Accurate short-term load forecasting is essential for power system operations, including unit commitment, economic dispatch, and reserve scheduling. Regional load series exhibit temporal variation and horizon-dependent dynamics that make multi-horizon forecasting challenging. This paper proposes a bidirectional gated recurrent unit-based multi-head joint forecasting framework (EA-BiGRU-Multi) for one-step, six-step, and 24-step-ahead electricity load prediction. A shared recurrent encoder captures temporal dependencies from historical observations, while horizon-specific forecasting heads produce separate predictions for each lead time. A terminal-anchor injection strategy incorporates day-ahead demand information only at the forecast origin, preserving the distinction between historical observations and known-future priors. Feature-channel recalibration adjusts heterogeneous input contributions before temporal encoding. Experiments on three regional load zones from a regional independent system operator in the northeastern United States show that the proposed model achieves competitive multi-horizon performance. In the Southeast Massachusetts six-step-ahead case, the proposed model increases the mean coefficient of determination from 0.7604 to 0.8346 and reduces the mean absolute error from 100.44 MW to 79.07 MW compared with the linear baseline. Ablation analysis confirms that the terminal-anchor prior is essential for medium- and long-horizon accuracy. The results indicate that model suitability depends jointly on forecast horizon, regional load characteristics, and availability of forecast-origin demand information.