考虑风电并网的分时段短期电价预测

考虑了并网风电量对电价影响，并将相关系数作为选取电价影响因素的标准，考虑了历史电价、负荷、并网风电量与负荷的比值等影响电价的因素。分别将负荷与历史清算电价，等效负荷与历史清算电价，负荷、并网风电量与负荷的比值及历史清算电价作为神经网络的输入因子对市场清算电价进行分时段预测。算例采用丹麦电力市场的历史数据，分别对其2010年并网风电量所占比例较大和较小的日期进行预测，验证了选择负荷、并网风电量与负荷的比值及历史清算电价作为预测神经网络的输入变量是恰当的，其预测精度能够满足电力市场实际运行的需要。

Short-Term Electricity Price Forecasting Based on Period-Decoupled Price Sequence with Grid-Connected Wind Power

In this paper, considering the effects of the grid-connected wind power on electricity price, the correlation coefficient with electricity price sequence is determined as the standard to select the influence factors based on the historical power price, system load, ratio between the load and grid-connected wind power in the price forecasting. The paper takes the load and historical clearing price, equivalent load and historical clearing price, load and the ratio between the load and grid-connected wind power and historical clearing price as input factors of the neural network respectively, and then conducts the calculation of the market clearing price. The historical data from Denmark market is used to predict the dates of both a higher wind power percentage and a lower percentage in 2010. The prediction verifies that selection of load, ratio between the load and connected wind power and historical clearing price as inputs of the neural network is appropriate, and the precision of prediction can meet needs for the practical operation of the power market.