短期风电供需平衡性智能预警与仿真

Intelligent Early Warning and Simulation of Short-Term Wind Power Supply and Demand Balance

当前的风电供需预警方法忽略了以大数据为基础的风电数据分析,导致上述方法无法有效预测风电的短期功率,出现预测偏差大、预警不及时的问题,提出基于大数据的短期风电供需平衡性预警方法。分析风电数据的相似度,并对风电的功率数据以及风速数据完成归一化处理;优化极限学习机参数,结合自适应的关联度模型建立风电功率的混合预测模型;利用上述模型预测风电短期功率,实现风电并网时供需平衡性预警。实验结果表明:运用所提方法预警风电供需平衡性时,能够预测风电的短期功率,且预测误差更小。

At present, some method ignores the analysis of wind power data based on big data, leading to large prediction error. Therefore, an early-warning method for balance between supply and demand of short-term wind power based on big data was put forward. Firstly, the similarity of wind power data was analyzed, and the wind power data and wind speed data were normalized. After optimizing the parameters of extreme learning machine, a hybrid prediction model of wind power was built by combining an adaptive association model. Then, this model was used to predict the short-term power and thus to achieve the balance of supply and demand during the wind power integration. Experimental results show that the proposed method can predict the short-term power of wind power with smaller error when predicting the balance between supply and demand.