Short-term wind power prediction model based on ARMA-GRU-QPSO and error correction

Abstract Power system dispatch benefits from accurate wind power predictions. To increase the prediction precision for power, this paper proposes a combined model predicting short-term based on autoregressive moving average-gated recurrent unit (ARMA-GRU). Firstly, we build ARMA and GRU respectively to predict power. Then optimize model’s weights by quantum particle swarm algorithm (QPSO). Finally, an error correction errors acquire final results Our experimental prove reliability high predictability is verified comparing different models.