Dynamic Multi-Graph Spatio-Temporal Graph Traffic Flow Prediction in Bangkok:An Application of a Continuous Convolutional Neural Network

The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.

Detection and Classification of Transmission Line Transient Faults Based on Graph Convolutional Neural Network

We present a novel transient fault detection and classification approach in power transmission lines based on graph convolutional neural network.Compared with the existing techniques,the proposed approach considers explicit spatial information in sampling sequences as prior knowledge and it has stronger feature extraction ability.On this basis,a framework for transient fault detection and classification is created.Graph structure is generated to provide topology information to the task.Our approach takes the adjacency matrix of topology graph and the bus voltage signals during a sampling period after transient faults as inputs,and outputs the predicted classification results rapidly.Furthermore,the proposed approach is tested in various situations and its generalization ability is verified by experimental results.The results show that the proposed approach can detect and classify transient faults more effectively than the existing techniques,and it is practical for online transmission line protection for its rapidness,high robustness and generalization ability.

GCN-LSTM spatiotemporal-network-based method for post-disturbance frequency prediction of power systems

Owing to the expansion of the grid interconnection scale,the spatiotemporal distribution characteristics of the frequency response of power systems after the occurrence of disturbances have become increasingly important.These characteristics can provide effective support in coordinated security control.However,traditional model-based frequencyprediction methods cannot satisfactorily meet the requirements of online applications owing to the long calculation time and accurate power-system models.Therefore,this study presents a rolling frequency-prediction model based on a graph convolutional network(GCN)and a long short-term memory(LSTM)spatiotemporal network and named as STGCN-LSTM.In the proposed method,the measurement data from phasor measurement units after the occurrence of disturbances are used to construct the spatiotemporal input.An improved GCN embedded with topology information is used to extract the spatial features,while the LSTM network is used to extract the temporal features.The spatiotemporal-network-regression model is further trained,and asynchronous-frequency-sequence prediction is realized by utilizing the rolling update of measurement information.The proposed spatiotemporal-network-based prediction model can achieve accurate frequency prediction by considering the spatiotemporal distribution characteristics of the frequency response.The noise immunity and robustness of the proposed method are verified on the IEEE 39-bus and IEEE 118-bus systems.

基于多通道信号二维递归融合和ECA-ConvNeXt的永磁同步电机高阻接触故障诊断

该文提出一种基于多通道信号二维递归融合和高效通道注意力机制新一代卷积神经网络(ECA-ConvNeXt)相结合的方法,以解决永磁同步电机高阻接触故障精细定量化诊断识别的问题。首先,建立永磁同步电机仿真模型获取三相电流信号作为有效故障信号;其次,引入递归图,将三相电流信号分别映射为二维图像并进行多通道融合,以提高故障特征信息的丰富性并消除人工特征提取的影响,实现故障特征的增强显示;然后,通过在ConvNeXt中引入高效通道注意力模块,提升了网络在通道维度上的适应性,得到ECA-ConvNeXt以实现永磁同步电机故障位置类型和严重程度的精确诊断分类,分类精度达到99.18%,并通过带噪声数据验证了该方法的鲁棒性;最后,搭建了样机实验平台,验证所提方法识别精度高达97.35%,能够准确识别永磁同步电机高阻接触故障位置和严重程度。

时空注意力图卷积神经网络水下节点时钟同步算法

时钟同步是水下无线传感器网络工作的核心机制.实时、准确的节点移动速度是构建高精度时钟同步算法的重要保障,针对同步过程由于节点移动速度难以估算导致同步精度低和能耗高等问题,提出一种基于注意力机制和图卷积神经网络相结合的时钟同步算法.首先,利用深海拉格朗日洋流模型模拟节点的运动轨迹,由洋流模型粗略估计出节点的速度;对节点速度、水下环境信息集和时间占比进行融合处理,来作为图神经网络输入特征;其次使用注意力机制结合输入特征构建时空注意力权重矩阵,并根据特征数据自适应地调整权重矩阵;再联合图卷积神经网络捕捉节点速度之间、位移之间的空间性特征;在此基础上再堆叠标准卷积层进一步合并相邻时间的节点信息以获取时间相关性,然后构造节点移动模型进而实时有效地预测出节点移动速度,最后快速计算出节点动态的传播时延完成时钟同步.实验结果表明,本文算法在精度上分别比TSHL算法、D-sync算法、K-sync算法提升了26%、20%和11%,在能耗上也优于现有的时钟同步算法.

图神经网络驱动的交通预测技术:探索与挑战

随着物联网及人工智能技术的快速发展,对交通数据进行精准的分析和预测成为智慧交通的首要环节。近年来,交通预测方法逐渐从经典的模型驱动转变为数据驱动,然而,如何通过大数据有效分析路网的时空特性是预测过程中面临的关键难题之一。时空大数据分析是交通预测的利器,将交通路网建模为图网络,将深度学习方法在图网络上进行扩展,通过图神经网络建立时空预测模型,采用图卷积的方式有效地获取路网传感器节点之间的时空相关性,可以显著提高交通预测模型的精度。针对图神经网络驱动的交通预测技术进行了探索,基于深度时空特性分析提炼了两大类交通预测模型,并通过实例进行分析和验证,探讨了图神经网络在交通预测领域的技术优势和主要挑战,挖掘了图神经网络预测机制的潜在研究方向。

基于时空卷积动态知识图谱的新能源消纳评估方法

为构建新能源消纳知识图谱,首先,将电网积累的海量调度运行数据以动态四元组的形式,显式地表达调度运行数据的时空关联关系。通过滑动时间窗口快速搜索、提取局部时空图,构建子图数据集。然后,时空同步图卷积网络对局部时空图进行高维特征提取,充分挖掘历史数据的时空关联关系,利用新能源消纳知识图谱中存储的机理知识对模型进行引导,并通过多子图并行训练提升模型的学习效率。最后,基于中国西北某省级电网算例进行仿真和实验验证。结果表明,所提方法可以有效避免复杂的数学建模以及模型求解,相比于传统方法具有更高的评估精度与速度。

基于图卷积神经网络与K-means聚类的居民用户集群短期负荷预测

随着智能电表等高级量测装置在用户侧的广泛部署与使用,海量多源异构的居民用户数据得以采集与存储,为用户级负荷预测提供良好的数据基础。精准的居民用户集群负荷预测是促进智能配电网需求侧管理、辅助电网公司实现削峰填谷的重要基础。然而,现有的用户级负荷预测方法大多利用历史负荷序列的时间相关性构建数据驱动模型,却忽视相邻用户用电行为之间存在的潜在空间相关性。因此,提出一种基于K-means聚类和自适应时空同步图卷积神经网络的居民用户集群负荷预测方法。首先,采用K-means聚类将居民用户集群按照用电行为相似性划分成不同组;然后,基于居民用户集群的分组数量、各组居民用户的历史负荷数据以及各组居民用户负荷序列之间的相关性,构建面向居民用户集群负荷预测的时空图数据;最后,使用自适应时空同步图卷积神经网络实现居民用户集群短期负荷预测。文章通过真实的爱尔兰居民用户负荷公开数据集测试并验证所提方法的准确性和有效性,实验结果表明,相较于各个基准预测方法,所提方法能够充分挖掘并利用不同居民用户用电负荷之间的时空相关性,进而提高居民用户集群负荷预测精度。

计及动态时空相关性的多风电场短期功率预测

针对同一区域内多风电场出力间复杂且动态的时空相关性,提出一种基于注意力时空同步图卷积网络的多风电场短期功率预测模型。首先引入注意力机制量化天气特征对风功率的影响,构建相邻3个时间步的风功率局部时空图,卷积提取局部时空特征;然后用时空同步图卷积层聚合输入时窗的整体时空特征;最后非线性映射输出多风电场未来时段的功率预测结果。实际算例结果表明,所提模型通过学习不同天气条件下风功率的时空动态演变规律,可将多风电场日前功率预测精度提高2.10%~13.94%。