Enhanced GJO-BiLSTM Wind Power Prediction Model

Improving the accuracy of wind power generation forecasting is crucial for maintaining the safe and stable operation of power systems. To achieve this, this article has proposed a new wind power prediction model that utilizes advanced techniques like empirical mode decomposition (EMD), kernel principal component analysis (KPCA), and gold jackal optimization algorithm (GJO) optimized bidirectional long short-term memory neural network (BiLSTM). This model takes into account 12 critical environmental factors that affect wind power output. This model proposed in the article achieves greatly improves accuracy and timeliness.