The cloud-edge collaborative interaction technology, leveraging computing power boards, comprises cloud application management services, edge application management clients, and computing power boards. This technology...
详细信息
In this paper, a model of active distribution network safety monitoring system based on big data mining platform is established. This model combines multiple detection techniques and uses three-stage detection methods...
详细信息
This paper employs theentropy-Max method to determine the optimal number of classes in an image, utilizes the Markov Random Field (MRF) method to complete the image segmentation, and addresses the computation of maxi...
详细信息
Flexible interconnection devices enhance the ability of distribution network to accommodate large-scale distributed sources and loads, while the interactive coupling among high proportion of power electronic devices m...
详细信息
ISBN:
(纸本)9798350377477;9798350377460
Flexible interconnection devices enhance the ability of distribution network to accommodate large-scale distributed sources and loads, while the interactive coupling among high proportion of power electronic devices may affect the operational stability of the distribution network. To quantify theeffects of system parameters, control modes, and control parameters on the stability of the interconnection systems between different distribution areas via energy-storage Flexible Multi-State Switch (e-SOP), this paper conducts a study on the large-signal stability of e-SOP based on the T-S fuzzy model. According to the topology and control strategy of thee-SOP, the T-S fuzzy model is derived, the attraction domain estimation method based on the model is given, and theeffects of the main circuit parameters, the parameters characterizing the operating point information, and the control parameters on the large-signal stability of thee-SOP are analyzed using the attraction domain. The theoretical analysis results are compared and analyzed with the time-domain simulation results to verify the correctness of the proposed method for estimating attraction domain to judge the large-signal stability of e-SOP using the T-S fuzzy model.
With the proliferation of Internet of Things (IoT) devices in smart gridedgecomputingenvironments, ensuring robust data security has become paramount. This research explores an enhanced blockchain layer to strength...
详细信息
With the growth of China's economy, electricity demand has surged, making efficient demand-side resource utilization essential. However, the randomness of energy consumption has led to increased grid load fluctuat...
详细信息
Lightning disaster is one of the most harmful disasters to the power system. The current research on lightning proximity warning based on a single class of data is difficult to make a breakthrough in warning accuracy ...
详细信息
In order to improve the utilization efficiency of renewableenergy and promote the consumption of photovoltaic energy. Firstly, an economic scheduling model considering flexible load is constructed with the minimum co...
详细信息
Detecting insulators and their defects is a key task in real-time power grid surveillance with the rapid development of national smart grid. Traditional surveillance usually relies on maintenance personnel, leading to...
详细信息
ISBN:
(纸本)9781665493130
Detecting insulators and their defects is a key task in real-time power grid surveillance with the rapid development of national smart grid. Traditional surveillance usually relies on maintenance personnel, leading to the issues of inefficiency and unsafety. Thus, with the prosperity of deep learning, we proposed a detection algorithm, named e-VarifocalNet, which is an enhanced version of the basic VarifocalNet method. The proposed e-VarifocalNet is specifically designed for detecting insulators and their defects. We developed a classification loss based on varifocal loss and the number of samples to solve the imbalance problem in object detection. Furthermore, a regression loss based on GIoU loss and Wasserstein distance is designed to gain higher flexibility in the representation of bounding boxes. Additionally, we applied a feature pyramid network based on dilated convolution and heatmap to build global and local semantic relations among pixels so as to enhance the detection accuracy on salient areas. Our dataset containing 2,100 images and 5,217 object instances was collected through real-time drones and an open data platform. Our e-VarifocalNet gets the highest mAP and a low model complexity on our dataset among state-of-the-art object detectors, indicating the potential of our algorithm in real-time power grid surveillance applications.
This article first introduces the security requirements of the current Stategrid for edge site resource management, and then introduces the current edge platform and zero trust architecture. Next, a cloud-edge resour...
详细信息
暂无评论