基于短时间尺度相关性聚类的负荷预测

负荷预测不仅是电力系统稳定、安全运行的基础,同样也是实现电力需求侧智能用电管理的基础。短时间尺度相关性分析能够挖掘一段时间内负荷的用电行为,相似用电行为分析有助于改善负荷预测效果,因此本文提出了基于短时间尺度相关性聚类的负荷预测方法。首先,根据短时间尺度用电时间序列之间的皮尔逊相关系数构造相关系数矩阵,并对相关系数矩阵进行去噪处理；然后,基于相关系数矩阵,利用模糊c均值聚类的方法来实现不同用电特性负荷之间的聚类,每类中负荷具有相似的用电行为；再分别对每一类中所有负荷数据求和并利用人工神经网络进行超短期负荷预测,基于每类的负荷预测结果计算系统的负荷预测；最后,通过对某110kV变电站10kV负荷馈线的实际数据进行分析,分析结果表明基于短时间尺度相关性分析的聚类提升了负荷预测的效果,从而验证了本文所提方法的有效性。

Load Forecasting Based on Short-term Correlation Clustering

Load forecasting is the basis not only of power system stable and safe operation, but also of power demand side intelligent electricity management. Short-term correlation analysis can be used to mine the electricity consumption of a period of time. The analysis of similar electricity consumption can improve the effect of load forecasting. Therefore, this paper proposes a load forecasting method based on short-time correlation clustering. First, a method is proposed to analyze the correlation matrix of electricity sequences, and then eliminate the effects of noise information of the correlation matrix. Then, clustering to identify groups of loads with similar load consumption behavior based on fuzzy C-means clustering algorithm, after each load is assigned to a special cluster, we sum the load data in the group to obtain the partial system load. And then forecast this partial system load at each group based on artificial neural network. The partial system load forecasts are summed to obtain total system load forecast. Finally, the case studies with instance data verify the load clustering based on short-term correlation analysis for power sequences can improve load forecasting..