基于奇异谱分析和局部敏感哈希的调频辅助服务市场短期容量需求预测方法

Forecast Method of Short-term Capacity Demand in Frequency Regulation Auxiliary Service Market Based on Singular Spectrum Analysis and Locality-sensitive Hashing Method

为了满足电网频率评估的要求,降低电网风险,保证发电与用电的实时平衡,需要对电网短期调频需求进行预测。为此提出基于奇异谱分析(singular spectrum analysis,SSA)和局部敏感哈希(locality-sensitive hashing,LSH)的调频容量需求预测方法。首先,为了处理频率信号高波动性的影响,SSA将频率信号分解为2个分量——代表原始时间序列平均趋势的平均趋势分量和揭示随机特征的波动分量,2个分量均在相空间中被重构,以获得平均趋势段和波动分量段;然后利用LSH选择平均趋势段的相似段,用于局部预测,从而提高预测的精度和效率;最后,采用支持向量回归(support vector regression,SVR)进行预测,其中训练输入为相似平均趋势段和相应波动分量段的合成。结果表明,与其他模型相比,该模型具有更高的精度和稳定性,所提方法不但能够降低调频容量,还能提升调频表现。

In order to meet the requirements of power grid frequency assessment,reduce grid risks and ensure the real-time balance of power generation and utilization,it is necessary to predict the demand for short-term regulation capacity of the power grid.This paper proposes a forecast method for short-term regulation capacity demand based on singular spectrum analysis(SSA)and locality-sensitive hashing(LSH).To deal with the impact of high volatility of the frequency signal,SSA is applied to decompose it into two components including the mean trend,which represents the mean tendency of the original time series,and the fluctuation component,which reveals the stochastic characteristics.Both components are reconstructed in a phase space to obtain mean trend segment sand fluctuation component segments.After that,LSH is utilized to select the similar segments of the mean trend segments for local forecasting,so as to improve prediction accuracy and efficiency.Finally,the paper uses support vector regression(SVR)for prediction.The training input is the synthesis of the similar mean trend segments and the corresponding fluctuation component segments.The numerical simulation results show that the proposed model has higher precision and stability and the proposed method can reduce capacity demand as well as improve the control performance.