A new combined model is proposed to obtain predictive data value applied in state estimation for radial power distribution networks. The time delay part of the model is calculated by a recursive least squares algorith...A new combined model is proposed to obtain predictive data value applied in state estimation for radial power distribution networks. The time delay part of the model is calculated by a recursive least squares algorithm of system identification, which can gradually forget past information. The grey series part of the model uses an equal dimension new information model (EDNIM) and it applies 3 points smoothing method to preprocess the original data and modify remnant difference by GM(1,1). Through the optimization of the coefficient of the model, we are able to minimize the error variance of predictive data. A case study shows that the proposed method achieved high calculation precision and speed and it can be used to obtain the predictive value in real time state estimation of power distribution networks.展开更多
分布式状态传感器可用来实时监测配电主设备,提高电力系统稳定性和用户体验,其可靠性对电网安全稳定运行至关重要。提出一种配电主设备分布式状态传感器可靠性评估方法,基于自注意力机制的时空图卷积神经网络(Self-attention based spat...分布式状态传感器可用来实时监测配电主设备,提高电力系统稳定性和用户体验,其可靠性对电网安全稳定运行至关重要。提出一种配电主设备分布式状态传感器可靠性评估方法,基于自注意力机制的时空图卷积神经网络(Self-attention based spatial-temporal graph convolutional networks,SASTGCN)。首先,从传感器装置形式、信号传输等方面开展可靠性研究,构建了主设备状态传感器可靠性评估指标体系。然后,基于自注意力机制更擅长捕捉数据或特征的内部相关性机制,将自注意力机制融入基于注意力机制的时空图卷积神经网络(Attention based spatial-temporal graph convolutional networks,ASTGCN)中,提出一种新的可靠性评估模型。最后,通过对比实验验证了所提模型的正确性和有效性。展开更多
文摘A new combined model is proposed to obtain predictive data value applied in state estimation for radial power distribution networks. The time delay part of the model is calculated by a recursive least squares algorithm of system identification, which can gradually forget past information. The grey series part of the model uses an equal dimension new information model (EDNIM) and it applies 3 points smoothing method to preprocess the original data and modify remnant difference by GM(1,1). Through the optimization of the coefficient of the model, we are able to minimize the error variance of predictive data. A case study shows that the proposed method achieved high calculation precision and speed and it can be used to obtain the predictive value in real time state estimation of power distribution networks.
