This paper proposes a custom Clarke transformation applied to linearized voltage modulated direct power sliding mode control of three-phase rectifiers in unbalanced power grids to improve the three-phase current disto...
详细信息
A Renewable Smart energy grid is a global challenge which has to address varied complex issues. In response to this challenge, we present an algorithm for Real-Time Price Suggestion (RTPS) that allows for utilisation ...
详细信息
In recent years, the construction of the power Internet of Things continues to advance, and the number of power terminal equipment is growing. However, thecomputing power and storage capacity of these terminal device...
详细信息
Due to the variability of video length and action duration, the temporal action detection task faces the problem of blurred action boundaries that are difficult to capture accurately. To alleviate this problem, this p...
详细信息
ISBN:
(纸本)9798350352481;9798350352474
Due to the variability of video length and action duration, the temporal action detection task faces the problem of blurred action boundaries that are difficult to capture accurately. To alleviate this problem, this paper proposes a Frequency Attention Mechanism (FAM) that adaptively models the frequency dependencies between video signal channels, enabling the model to better understand the frequency variations in the video and to handle the complexity of different action durations, thus enhancing the sensitivity and discriminative power of the action boundaries, and still providing powerful action recognition even in long video sequences Capabilities. Through comprehensiveexperimental validation on a series of representative benchmark datasets (e.g. THUMOS14 and ActivityNet1.3), our approach demonstrates significant performance improvement.
In general cases, the weakness of the national electric grid is due to overloading, infrastructures aging, high temperatures, bad weather and cyber risks. In such systems, the interruptions of electricity supply can t...
详细信息
ISBN:
(纸本)9798350337938
In general cases, the weakness of the national electric grid is due to overloading, infrastructures aging, high temperatures, bad weather and cyber risks. In such systems, the interruptions of electricity supply can take several hours to days. The smartness of the Modern electrical networks and the using of grid-tied microgrids are an important means to improve their resilience. But, to perform strong and powerful resiliency of thegrid, it is necessary to develop strong background and experiences of the weakness analyzing and detection. The development of real time analyzing tools based on deep learning and data science can help for more security and savings of the power supply. In this paper, a methodology of grid weakness analyzing is presented. It is based on long term real data collected, more than ten years, from theelectrical company of Niger (Nigelec). Theieee Std 1366 (TM)-2012 indexes and the statistical based methodology called "Beta Method" are applied to the data to identify the outlying performance of the utility. Then, the interest of the Deep learning for real-time weakness analysis and resiliency improving is introduced. Also, thanks to the laboratory experimental tests, a methodological approach of the training algorithm criteria and decision laws estimation is presented. These tests consider the main defaults that can induce a loss of power supply and thegrid disconnection. The data driven models, based on informational and analytical methods, are necessary for real time assessment and improving of thegrid resiliency.
This paper describes a dense fisheye camera network for pedestrian tracking in an indoor environment, with the target scenario being an unmanned store. each fisheye camera is connected to a single-board computer for l...
详细信息
ISBN:
(纸本)9781728198354
This paper describes a dense fisheye camera network for pedestrian tracking in an indoor environment, with the target scenario being an unmanned store. each fisheye camera is connected to a single-board computer for local tracking using its own images. The local tracks are integrated and global tracks generated at a central computer in an online manner. The local trackers are based on the popular DeepSORT algorithm, and the global tracker combines distance and novel specialization based factors to update global tracks from local tracks, avoiding the need of matching local tracks. experiments on a self-collected dataset demonstrate highly accurate tracking over several minutes of videos.
The study of non-iterative schemes for near-surface tu rbulent flux parameterization is significant for model forecasting and climate prediction. In this paper, four machine learning algorithms (Random Forest, CatBoos...
详细信息
In order to solve the problem of poor learning effect caused by data heterogeneity among different participants in theexisting federated learning methods, this paper proposes a federated data augmentation algorithm b...
详细信息
In the future retail electricity market, deviation penalties will be one of the largest challenges faced by energy aggregators, directly impacting their profitability. With the objective of minimizing the penalty cost...
详细信息
In order to address the issue of Smart grid Communication's inability to quickly recover from congestion that causes the original path forwarding of traffic. The self-healing, self-organizing, and self-configuring...
详细信息
暂无评论