The electrical transmission networks are complex systems that are commonly run near their operational limits. Such systems can undergo major disturbances that have serious consequences. Individually, these disturbance...The electrical transmission networks are complex systems that are commonly run near their operational limits. Such systems can undergo major disturbances that have serious consequences. Individually, these disturbances can be attributed to specific causes, such as lightning strikes, ice storms, equipment failure, shorts resulting from untrimmed trees, excessive customer demand, or human errors. In the paper, the human errors from electrical transmission networks of Romanian Power Grid Company over period of 10 years are analyzed. It is hoped that obtained results will provide engineers a better understanding so they can cater to the needs of the human operators when to implement new interfaces for network monitoring tasks, not for the other technical objectives.展开更多
In recent years,several efforts have been made to develop power transmission line abnormal target detection models based on edge devices.Typically,updates to these models rely on participation of the cloud,which means...In recent years,several efforts have been made to develop power transmission line abnormal target detection models based on edge devices.Typically,updates to these models rely on participation of the cloud,which means that network resource shortages can lead to update failures,followed by unsatisfactory recognition and detection performance in practical use.To address this problem,this article proposes an edge visual incremental perception framework,based on deep semisupervised learning,for monitoring power transmission lines.After generation of the initial model using a small amount of labeled data,models trained using this framework can update themselves based on unlabeled data.A teacher-student joint training strategy,a data augmentation strategy,and a model updating strategy are also designed and adopted to improve the performance of the models trained with this framework.The proposed framework is then examined with various transmission line datasets with 1%,2%,5%,and 10%labeled data.General performance enhancement is thus confirmed against traditional supervised learning strategies.With the 10%labeled data training set,the recognition accuracy of the model is improved to exceed 80%,meeting the practical needs of power system operation,and thus clearly validating the effectiveness of the framework.展开更多
文摘The electrical transmission networks are complex systems that are commonly run near their operational limits. Such systems can undergo major disturbances that have serious consequences. Individually, these disturbances can be attributed to specific causes, such as lightning strikes, ice storms, equipment failure, shorts resulting from untrimmed trees, excessive customer demand, or human errors. In the paper, the human errors from electrical transmission networks of Romanian Power Grid Company over period of 10 years are analyzed. It is hoped that obtained results will provide engineers a better understanding so they can cater to the needs of the human operators when to implement new interfaces for network monitoring tasks, not for the other technical objectives.
基金supported by the National Key R&D Program of China (2020YFB0905900).
文摘In recent years,several efforts have been made to develop power transmission line abnormal target detection models based on edge devices.Typically,updates to these models rely on participation of the cloud,which means that network resource shortages can lead to update failures,followed by unsatisfactory recognition and detection performance in practical use.To address this problem,this article proposes an edge visual incremental perception framework,based on deep semisupervised learning,for monitoring power transmission lines.After generation of the initial model using a small amount of labeled data,models trained using this framework can update themselves based on unlabeled data.A teacher-student joint training strategy,a data augmentation strategy,and a model updating strategy are also designed and adopted to improve the performance of the models trained with this framework.The proposed framework is then examined with various transmission line datasets with 1%,2%,5%,and 10%labeled data.General performance enhancement is thus confirmed against traditional supervised learning strategies.With the 10%labeled data training set,the recognition accuracy of the model is improved to exceed 80%,meeting the practical needs of power system operation,and thus clearly validating the effectiveness of the framework.
