Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization

TLDR

Short‑term electrical load forecasting is crucial for power production safety, stability, and sustainability, and accurate predictions support reliable power system management. This study proposes an attention‑based encoder‑decoder network with Bayesian optimization to improve short‑term power load forecasting accuracy and stability. The model uses a GRU‑based encoder‑decoder architecture with a temporal attention layer to highlight key input features, and Bayesian optimization tunes hyperparameters for optimal predictions. Experiments on 24‑hour load data from American Electric Power show the model outperforms other methods in accuracy and stability, demonstrating its effectiveness for deep‑learning power load prediction.

Abstract

Short-term electrical load forecasting plays an important role in the safety, stability, and sustainability of the power production and scheduling process. An accurate prediction of power load can provide a reliable decision for power system management. To solve the limitation of the existing load forecasting methods in dealing with time-series data, causing the poor stability and non-ideal forecasting accuracy, this paper proposed an attention-based encoder-decoder network with Bayesian optimization to do the accurate short-term power load forecasting. Proposed model is based on an encoder-decoder architecture with a gated recurrent units (GRU) recurrent neural network with high robustness on time-series data modeling. The temporal attention layer focuses on the key features of input data that play a vital role in promoting the prediction accuracy for load forecasting. Finally, the Bayesian optimization method is used to confirm the model’s hyperparameters to achieve optimal predictions. The verification experiments of 24 h load forecasting with real power load data from American Electric Power (AEP) show that the proposed model outperforms other models in terms of prediction accuracy and algorithm stability, providing an effective approach for migrating time-serial power load prediction by deep-learning technology.