基于SSA-ELM的短期风电功率预测

准确的风电功率预测可以有效地保证电力系统的安全运行，进而影响电网的电力调度，所以高精度的预测方法变得至关重要。针对极限学习机（ELM）随机产生输入权值和阈值导致回归模型不稳定性与预测结果不准确性，以及风电波动性和间歇性等问题，提出一种基于麻雀算法（SSA）优化极限学习机的组合预测模型（SSA-ELM）。利用收敛速度快、精度高、稳定性好的SSA对ELM的权值和阈值进行寻优，实现了对风电功率的精确预测。仿真结果表明，所提出的SSA-ELM模型的预测精度较高、泛化能力强，能够为风电的功率预测及并网安全的稳定运行提供决策支持。

Short-term Wind Power Prediction Based on SSA-ELM

Accurate wind power prediction can effectively ensure the safe operation of the power system， and then affect the power dispatching of power grid， so high-precision prediction method becomes very important. In the light of the instability of regression model and the inaccuracy of prediction resulted from input weights and thresholds randomly generated by extreme learning machine （ELM）， as well as the dynamic and intermittent of wind waves， a combined prediction model （SSA-ELM） based on sparrow search algorithm （SSA） optimization extreme learning machine is proposed. The sparrow algorithm with fast convergence speed， high precision and good stability is used to optimize the weights and thresholds of ELM to realize the accurate prediction of wind power. The simulation results show that the proposed SSA-ELM model has higher prediction accuracy and strong generalization ability， and can provide decision support for wind power prediction， safe & stable operation of grid-connected wind power.