In recent years, power quality (PQ) measurement system have become essential for enhancing the performance and reliability of power distribution networks. The number of PQ analyzers installed in these networks has inc...
详细信息
ISBN:
(纸本)9798350377958;9798350377941
In recent years, power quality (PQ) measurement system have become essential for enhancing the performance and reliability of power distribution networks. The number of PQ analyzers installed in these networks has increased significantly. Moreover, PQ measurements are now often integrated into various devices, including balance and industrial energy meters. However, the sheer volume of data generated by these meters makes manual inspection and analysis impractical. This highlights the need for advanced automated tools to manage and interpret these vast datasets. This paper presents an approach that uses aggregated 10-minute PQ measurement data from these meters as a screening method to locate sources of PQ disturbances. By employing both deterministic indicators and machine learning techniques, specifically neural network classification, this approach opens new possibilities for automating the analysis process, enabling network operators to effectively identify and prioritize significant sources of disturbances in distribution networks.
In this paper, a network switch performance anomaly detection method of the instrumentation and control (I&C) systems in nuclear power plants (NPP) based on network calculus is proposed. In the Ethernet-based pack...
详细信息
Traffic signal control(TSC) has become an important issue for urban traffic management. Recent studies utilize reinforcement learning(RL) in traffic signal control since it has the advantages of no requirement for pri...
详细信息
ISBN:
(纸本)9798350399462
Traffic signal control(TSC) has become an important issue for urban traffic management. Recent studies utilize reinforcement learning(RL) in traffic signal control since it has the advantages of no requirement for prior knowledge and real-time control. However, these studies mainly focused on controlperformance of training scenarios, but ignore the adaptability to different intersection topologies and flow distributions. Furthermore, most studies employed an impractical phase-selection scheme with an unfixed phase order that may confuse human drivers. To address these issues, we propose PhaseLight, a method combining lane-based representation, sophisticated network structure and advanced reinforcement learning algorithm. It is capable of adapting to various intersection topologies and flow distributions without additional training. Meanwhile, it employs a phase-switching scheme to improve practicality with little performance loss. Comprehensive experiment are conducted using the Simulation of Urban MObility(SUMO) simulator. The results in both training and testing scenarios demonstrate the effectiveness of PhaseLight, indicate its potential in real-world applications.
The control of an Inverted Pendulum (IP) is one of the benchmark problems in controlsystems. It is very difficult to control due to its innate instability and extremely nonlinear properties. Here, a novel supervisory...
详细信息
In recent years, model predictive control has been widely used in converters because of its high robustness and fast dynamic response. However, the conventional model predictive control uses only one voltage vector in...
详细信息
Wireless ad hoc network nodes suffer from limited energy supply. To reduce the power consumption of the routing protocols, many routing algorithms use a subset of the nodes to participate in the routing task. For that...
详细信息
Accidents related to autonomous driving are being reported one after another, and the commercialization and diffusion of autonomous driving technology may be further into the future than we think. From this perspectiv...
详细信息
ISBN:
(纸本)9798331517939;9788993215380
Accidents related to autonomous driving are being reported one after another, and the commercialization and diffusion of autonomous driving technology may be further into the future than we think. From this perspective, vehicle teleoperation technology is being considered as a complement to fully autonomous driving technology and is being piloted in some countries such as the United States. Teleoperation is used when encountering an emergency during autonomous driving, delivering a shared vehicle, or loading a new car into a transport vehicle. Despite the efforts of many researchers, Wireless Teleoperation is not free from the effects of communication delay due to physical limitations. The communication delay makes it difficult to guarantee real-time, resulting in poor teleoperation performance. Therefore, in order to perform smooth teleoperation, it is necessary to reduce the communication delay sufficiently, even if it cannot be completely eliminated. This study used RNN-based Long Short-Term Memory(LSTM) to reduce the impact of inevitable delays in teleoperation. The proposed model predicted the current control command of the steering angle considering communication delay and resulted in a smaller error from the real value compared to the raw sample. Given these results, it is expected that this study will contribute to real-time teleoperation that is robust to the communication delay.
In response to the problem of poor detection performance of the traditional Sobel operator in edge detection, a high-precision edge detection algorithm based on Sobel operator-assisted Holistically-nested Edge Detecti...
详细信息
A decentralized control algorithm for routing flow in complex networks is proposed. The aim is to fairly distribute the supply/demand among the nodes while maintaining maximum flow in the network and satisfying the fl...
详细信息
Convolutional Neural networks (CNNs), a deep learning application, are powerful tools particularly suited for image processing and classification applications. Pooling is a major component of CNNs and significantly in...
详细信息
ISBN:
(纸本)9783031821493;9783031821509
Convolutional Neural networks (CNNs), a deep learning application, are powerful tools particularly suited for image processing and classification applications. Pooling is a major component of CNNs and significantly influences learning. In this step, data is reduced in size through a specific algorithm or technique, resulting in the reduction of the computational load on the layers. The various pooling techniques in CNNs have specific uses, features, and effects, some desirable and others counterproductive to the training goal. Using one pooling technique can produce results that other techniques cannot. Some cases can benefit differently from different pooling techniques. This raises the question of whether combining these pooling techniques could achieve a collective positive impact, potentially leading to performance gains beyond those achievable by individual techniques used separately. A control parameter is added to optimize the selection of the pooling method or could be a weighted combination of more than one method. The results show that the presented method guarantees the same performance as a single pooling layer at least and could be improved when weighted pooling layers are involved in some datasets.
暂无评论