Although the recent load information is critical to very short-term load forecasting(VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF applicatio...Although the recent load information is critical to very short-term load forecasting(VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF applications.This paper tackles the problem of real-time anomaly detection in most recent load information used by VSTLF.This paper proposes a model-based anomaly detection method that consists of two components, a dynamic regression model and an adaptive anomaly threshold. The case study is developed using the data from ISO New England. This paper demonstrates that the proposed method significantly outperforms three other anomaly detection methods including two methods commonly used in the field and one state-of-the-art method used by a winning team of the Global Energy Forecasting Competition 2014. Finally, a general anomaly detection framework is proposed for the future research.展开更多
风电功率预测对电力系统的安全稳定运行具有重要意义。针对多风电场的超短期概率预测问题,提出了一种基于Bagging混合策略和核密度估计(kernel density estimation,KDE)的稀疏向量自回归预测方法。首先通过时间序列分解和余项自举,生成...风电功率预测对电力系统的安全稳定运行具有重要意义。针对多风电场的超短期概率预测问题,提出了一种基于Bagging混合策略和核密度估计(kernel density estimation,KDE)的稀疏向量自回归预测方法。首先通过时间序列分解和余项自举,生成若干自举时间序列。对于每个时间序列,采用向量自回归(vector autoregression,VAR)模型进行预测。针对传统模型在风场数量较多时容易出现的过拟合问题,采用稀疏向量自回归模型,筛选最有效的回归系数,得到稀疏系数矩阵。每个时间序列训练的预测模型分别产生点预测结果,对于多重点预测结果,使用KDE方法产生概率密度的预测结果。在真实风电集群数据上,验证所提多场站概率预测方法的有效性,采用分位数得分评估概率预测精度。相关实验结果表明,该方法可以有效提高概率预测精度。展开更多
基金supported in part by the National Natural Science Foundation of China(No.71701035)the US Department of Energy,Cybersecurity for Energy Delivery Systems(CEDS)Program(No.M616000124)
文摘Although the recent load information is critical to very short-term load forecasting(VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF applications.This paper tackles the problem of real-time anomaly detection in most recent load information used by VSTLF.This paper proposes a model-based anomaly detection method that consists of two components, a dynamic regression model and an adaptive anomaly threshold. The case study is developed using the data from ISO New England. This paper demonstrates that the proposed method significantly outperforms three other anomaly detection methods including two methods commonly used in the field and one state-of-the-art method used by a winning team of the Global Energy Forecasting Competition 2014. Finally, a general anomaly detection framework is proposed for the future research.
文摘风电功率预测对电力系统的安全稳定运行具有重要意义。针对多风电场的超短期概率预测问题,提出了一种基于Bagging混合策略和核密度估计(kernel density estimation,KDE)的稀疏向量自回归预测方法。首先通过时间序列分解和余项自举,生成若干自举时间序列。对于每个时间序列,采用向量自回归(vector autoregression,VAR)模型进行预测。针对传统模型在风场数量较多时容易出现的过拟合问题,采用稀疏向量自回归模型,筛选最有效的回归系数,得到稀疏系数矩阵。每个时间序列训练的预测模型分别产生点预测结果,对于多重点预测结果,使用KDE方法产生概率密度的预测结果。在真实风电集群数据上,验证所提多场站概率预测方法的有效性,采用分位数得分评估概率预测精度。相关实验结果表明,该方法可以有效提高概率预测精度。
