检索结果-内蒙古大学图书馆

Decentralized control in active distribution grids via supervised and reinforcement learning

Energy and AI 2024年第2期16卷 137-149页

作者： Stavros Karagiannopoulos Petros Aristidou Gabriela Hug Audun Botterud Laboratory for Information and Decision Systems(LIDS) Massachusetts Institute of TechnologyCambridgeUSA EEH-Power Systems Laboratory ETH Zurichhysikstrasse 38092 ZurichSwitzerland Department of Electrical Engineering Computer Engineering&InformaticsCyprus

While moving towards a low-carbon, sustainable electricity system, distribution networks are expected to host a large share of distributed generators, such as photovoltaic units and wind turbines. These inverter-based resources are intermittent, but also controllable, and are expected to amplify the role of distribution networks together with other distributed energy resources, such as storage systems and controllable loads. The available control methods for these resources are typically categorized based on the available communication network into centralized, distributed, and decentralized or local. Standard local schemes are typically inefficient, whereas centralized approaches show implementation and cost concerns. This paper focuses on optimized decentralized control of distributed generators via supervised and reinforcement learning. We present existing state-of-the-art decentralized control schemes based on supervised learning, propose a new reinforcement learning scheme based on deep deterministic policy gradient, and compare the behavior of both decentralized and centralized methods in terms of computational effort, scalability, privacy awareness, ability to consider constraints, and overall optimality. We evaluate the performance of the examined schemes on a benchmark European low voltage test system. The results show that both supervised learning and reinforcement learning schemes effectively mitigate the operational issues faced by the distribution network.

关键词： Supervised learning Reinforcement learning Deep deterministic policy gradient Decentralized control Active distribution systems

来源：评论

学校读者我要写书评

暂无评论

Position Regulation of Industrial Robots via Bounded Integral Terminal Sliding Mode Control Algorithm

引用

IEEE Transactions on Industrial Electronics 2024年第7期71卷 7403-7412页

作者： Cong, Yongzheng Du, Haibo Zhu, Wenwu Chen, Chih-Chiang Hefei University of Technology School of Electrical Engineering and Automation Hefei230009 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China National Cheng Kung University Department of Systems and Naval Mechatronic Engineering Tainan70101 Taiwan

For the position regulation problem of six degrees of freedom (6-DOF) industrial robots, a novel bounded finite-time position regulate algorithm is developed and employed to improve the dynamic performance of the industrial robots. First, based on the model feature, a bounded finite-time position regulate law is proposed to overcome input saturation constraints for the considered systems. Rigorous analysis guarantees the finite-time stability of the closed-loop system in the absence of disturbance. Then, to improve the disturbance rejection property of the robot systems in the presence of disturbance, an improved bounded finite-time control law based on the integral terminal sliding mode is constructed. Finally, simulations and experimental results are provided to show the effectiveness of the proposed bounded control law. © 1982-2012 IEEE.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Islanding Detection In Bulk Power systems: A Data-Driven Approach

Islanding Detection In Bulk Power Systems: A Data-Driven App...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Golpîra, Hêmin Kuzle, Igor University of Kurdistan Power Systems Modeling & Simulation Lab. Department of Electrical Engineering Sanandaj Iran University of Zagreb Faculty of Electrical Engineering and Computing Department of Energy and Power Systems Zagreb Croatia

ISBN: (纸本)9789531842976

An attempt is made to propose a data-driven approach for detecting islanding in large-scale power systems. The method utilizes data collected by phasor measurement units (PMUs) to develop an equivalent model of the system. In this model, the system is represented by multiple centers of inertia (COIs) linked to a central point known as the center of gravity (COG) through fictitious reactances. These reactances, which are interpreted as the electrical distances between the local COIs and the COG, serve as a valuable indicator for detecting islanding. The occurrence of islanding can be identified by comparing the temporal trends of electrical distance variations across different areas. The effectiveness of the proposed methodologies is evaluated using simulated data from the 73-bus IEEE test system. © 2024 IEEE.

关键词： Phasor measurement units

来源：评论

学校读者我要写书评

暂无评论

High-Voltage Autonomous Current-Fed Push-Pull Converter with Wireless Communication Applied to X-Ray Generation

引用

IEEE Transactions on Circuits and systems II: Express Briefs 2024年第2期71卷 902-906页

作者： Lin, Chang-Hua Ahmad, Javed Liu, Hwa-Dong Kao, Tzu-Hsien National Taiwan University of Science and Technology Department of Electrical Engineering Taipei106 Taiwan National Taiwan Normal University Undergraduate Program of Vehicle and Energy Engineering Taipei106 Taiwan

This brief presents an adjustable 100 kV high voltage DC power supply with ZigBee wireless feedback for the X-ray system. The proposed system is powered by a 48 V DC power source, and a combination of an autonomous current-fed push-pull converter with a high voltage transformer is used to step up the output voltage. At the end of the secondary of the high voltage transformer, a combination of half-wave voltage multipliers is used to achieve desired output of DC high voltage. Two microcontrollers with wireless communication modules are used to control the output voltage. Moreover, the equivalent inductance of the high voltage transformer with an extra capacitor is utilized to form a parallel resonant circuit to lead the power switch of the autonomous current-fed push-pull converter can achieve zero voltage switching to reduce the switching loss. The mathematical model of the system is derived, and the complete design considerations are established. Finally, the feasibility of the proposed system is verified by the experimental results efficiency of the developed model reaches 95% under low power high voltage applications. © 2004-2012 IEEE.

关键词： Inductance

来源：评论

学校读者我要写书评

暂无评论

Metasurfaces for next-generation wireless communication systems

引用

National Science Review 2023年第8期10卷 17-19页

作者： Younes Ra'di Nikita Nefedkin Petar Popovski Andrea Alù Department of Electrical Engineering and Computer Science Syracuse University Photonics Initiative Advanced Science Research Center City University of New York Department of Electronic Systems Aalborg University Physics Program Graduate Center City University of New York

The pace of development in the world of 5G communication systems has proven to be much more demanding than previous generations, with 5G-Advanced seemingly around the corner [1]. Extensive research is already underway to structure the next generation of wireless systems(i.e. 6G), which may potentially enable an unprecedented level of human–machine interaction [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Near-Optimal Streaming Codes with Linear Field Size

Near-Optimal Streaming Codes with Linear Field Size

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Ramkumar, Vinayak Bhatnagar, Shobhit Kumar, P. Vijay Tel Aviv University Department of Electrical Engineering-Systems Israel IISc Bangalore Department of Electrical Communication Engineering India

ISBN: (纸本)9781665475549

Streaming codes are codes designed to ensure erased packet recovery with a decoding-delay deadline. In streaming code literature, an (a, b, w) sliding-window (SW) channel model is considered, in which within any window of w time slots, either a burst of = b packets, or else = a random packets can be erased. An (a, b, w, t) streaming code is a packet-level code capable of recovering messages under a decoding delay of t time slots, from any erasure pattern produced by an (a, b, w)-SW channel. For any given (a, b, w)-SW channel, the minimum delay with which the maximum rate possible over this channel can be achieved is t = w-1. Rate-optimal constructions of streaming codes for any parameter tuple of the form (a, b, w, t = w-1) are known in the literature. However, these constructions require a field size that is quadratic in w in general, and linear field size constructions are known only for a subset of {a, b, w} parameters. The current paper shows that it is possible to construct linear field size streaming codes for all {a, b, w} parameters, by sacrificing a little on either delay or rate. When the allowed delay is one more than the minimum, i. e., when t = w, we construct linear field size rate-optimal streaming codes for all possible {a, b, w} parameters. This construction also leads to an O(w) field size (a, b, w, t = w - 1) streaming code whose rate is close to the optimal rate. Additionally, we show that our construction can be modified to get binary streaming codes without too much loss in rate. © 2023 IEEE.

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Autoencoder-Based Detection of False Data Injection Attacks Against Data Poisoning in Smart Grids

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1287-1301页

作者： Takiddin, Abdulrahman Ismail, Muhammad Atat, Rachad Davis, Katherine R. Serpedin, Erchin Department of Electrical and Computer Engineering Texas A and M University College StationTX77843 United States Department of Computer Science Tennessee Tech University CookevilleTN38505 United States Department of Electrical and Computer Engineering Program Texas A and M University Qatar Doha23874 Qatar

Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Mechanisms for electric field induced color change in coupled colloidal quantum dot molecules revealed by low temperatures single particle spectroscopy

引用

Nano Research 2024年第12期17卷 10346-10354页

作者： Yossef E.Panfil Adar Levi Somnath Koley Einav Scharf Yonatan Ossia Uri Banin Institute of Chemistry and the center for nanoscience and nanotechnology The Hebrew University of JerusalemJerusalem 91904Israel Quantum Engineering Laboratory the Department of Electrical&Systems EngineeringUniversity of PennsylvaniaPhiladelphiaPA 19104-6314USA Institute of Physics BhubaneswarOdisha-751005India

Colloidal quantum dots(QDs),the building blocks of modern displays and optoelectronic devices,have reached the highest level of size and shape control,and stability during the last 30 ***,full utilization of their potential requires integration or assembly of more than one nanocrystal as in the case of coupled quantum dots molecules(CQDM),where two core–shell QDs are fused to form two emission centers in close *** CQDMs were recently shown to switch color under an applied electric field at room *** we use cryogenic single particle spectroscopy of single CQDMs under an electric field to show that various mechanisms can contribute to the spectrum change under an applied electric field at cryogenic *** first mechanism is the control of the delocalized electron wave function when the electric field is applied along the dimer *** electric field bends the conduction band and forces the electron wave function to localize in one of the QDs yielding preferential emission of that particular *** addition,we found that QDs and CQDMs could become sensitive to surface traps under an electric *** the case of CQDMs,that can result in decreasing the intensity of one of the QDs while increasing the other QD’s ***,we show that there are surface charges which screen the applied electric field in some of the *** as well can result in electric field-induced color-tuning of *** the underlying mechanisms responsible for spectral shifts under applied electric fields is critical for the development of color-tunable devices utilizing CQDMs,including efficient displays and single photon sources.

关键词： colloidal quantum dots(QDs) quantum dot molecule nanocrystals single particle spectroscopy electric field

来源：评论

学校读者我要写书评

暂无评论

Reactive Planning for Teams of Heterogeneous Robots with Dynamic Collaborative Temporal Logic Missions 63

Reactive Planning for Teams of Heterogeneous Robots with Dyn...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhang, Yuqing Kalluraya, Samarth Pappas, George J. Kantaros, Yiannis Washington University in St. Louis Department of Electrical and Systems Engineering St. LouisMO United States University of Pennsylvania Department of Electrical and Systems Engineering PhiladelphiaPA United States

ISBN: (纸本)9798350316339

Several task and motion planning algorithms have been proposed recently for teams of robots assigned to collaborative high-level tasks specified using Linear Temporal Logic (LTL). However, the majority of prior works cannot effectively adapt to new missions that may arise in the field due to unexpected service requests. To address this novel challenge, we propose a reactive planning algorithm for teams of heterogeneous robots with collaborative LTL-encoded missions that dynamically change. The robots are heterogeneous in terms of their skills while the mission requires them to apply these skills in specific regions/objects in a temporal/logical order. Our method designs paths that can adapt to unexpected changes in the mission and effectively address potential mission violations arising due to conflicting logical task requirements or a limited number of robots. We achieve this by locally allocating new subtasks to the robots based on their capabilities, minimizing disruptions to the existing team plan, and strategically prioritizing the most crucial sub-tasks according to user-specified priorities. We provide theoretical guarantees and numerical experiments to demonstrate the efficiency of our method. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning and Mathematical Optimization for Job Shop Scheduling

引用

IEEE Transactions on Automation Science and engineering 2024年第3期21卷 4829-4850页

作者： Liu, Anbang Luh, Peter B. Sun, Kailai Bragin, Mikhail A. Yan, Bing Department of Automation and BNRist Beijing100084 China University of Connecticut Department of Electrical and Computer Engineering StorrsCT06269 United States National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan Tsinghua University Chaired Professors Group Center for Intelligent and Networked Systems Department of Automation Beijing100084 China Rochester Institute of Technology Department of Electrical and Microelectronic Engineering RochesterNY14623 United States

Job-shop scheduling is an important but difficult combinatorial optimization problem for low-volume and high-variety manufacturing, with solutions required to be obtained quickly at the beginning of each shift. In view of the increasing demand for customized products, problem sizes are growing. A promising direction is to take advantage of Machine Learning (ML). Direct learning to predict solutions for job-shop scheduling, however, suffers from major difficulties when problem scales are large. In this paper, a Deep Neural Network (DNN) is synergistically integrated within the decomposition and coordination framework of Surrogate Lagrangian Relaxation (SLR) to predict good-enough solutions for subproblems. Since a subproblem is associated with a single part, learning difficulties caused by large scales are overcome. Nevertheless, the learning still presents challenges. Because of the high-variety nature of parts, the DNN is desired to be able to generalize to solve all possible parts. To this end, our idea is to establish 'surrogate' part subproblems that are easier to learn, develop a DNN based on Pointer Network to learn to predict their solutions, and calculate the solutions of the original part subproblems based on the predictions. Moreover, a masking mechanism is developed such that all the predictions are feasible. Numerical results demonstrate that good-enough subproblem solutions are predicted in many iterations, and high-quality solutions of the overall problem are obtained in a computationally efficient manner. The performance of the method is further improved through continuous learning. Note to Practitioners - Scheduling is important for the planning and operation of job shops, and high-quality schedules need to be obtained quickly at the beginning of each shift. To take advantage of ML, in this paper, a DNN is integrated within our recent decomposition and coordination approach to learn to predict 'good-enough' solutions to part subproblems. To be able t

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：