基于风速预测模型的风电一次调频仿真研究

为进一步提高风速预测精度，考虑数据内部结构性与外部影响因素耦合性叠加特征，以及风电机组功率特性，构建逆向前馈神经网络自回归移动平均模型(back propagation-autoregressive integrated moving average model, BP-ARIMA)，并对风电场风速进行预测仿真，通过与实际数据对比分析，验证了所建模型具有较高预测精度。在所建预测模型基础上，基于风力发电机组典型功率特性曲线，统筹考虑储能装置容量优化配置与风电机组的致稳性问题，应用MATLAB-SIMULINK平台进行风电机组一次调频仿真。结果显示：一次调频控制策略的频率调节能力相较于常规超速减载调频控制可至少提高十个百分点。

Wind Power Primary Frequency Regulation Simulation Based on Wind Speed Prediction Model

To furtherly improve the accuracy of wind speed prediction, considering the coupled comprehensive features of data internal structure external influencing factors, and the characteristics of wind turbines power, a BP-ARIMA combined prediction model is constructed and the wind speed of wind farms is simulated. Compared with the actual data, the high prediction accuracy of the model is verified. Bases on the curve of typical power characteristic of wind turbine, the optimal configuration of energy storage device capacity and the stability of wind turbine are considered, and the MATLAB-SIMULINK platform is applied to simulate the primary frequency regulation of wind turbine, and the results show that the frequency regulation capability of the primary frequency modulation control strategy, compared with the conventional over-speed and load-shedding frequency control strategy, can be improved by at least ten percentage.