检索结果-内蒙古大学图书馆

A Risk-Averse Just-In-Time Scheme for Learning-Based Operation of Microgrids With Coupled Electricity-Hydrogen-Ammonia Under Uncertainties

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Li, Longyan Ning, Chao Pan, Guangsheng Zhang, Leiqi Gu, Wei Zhao, Liang Du, Wenli Shahidehpour, Mohammad Shanghai Jiao Tong University Department of Automation Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China School of Electrical Engineering Southeast University Nanjing210096 China Zhejiang Key Laboratory of Distributed Generations and Microgrid Technology State Grid Zhejiang Electric Power Research Institute Hangzhou310014 China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology China Department of Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States

This paper proposes a Risk-Averse Just-In-Time (RAJIT) operation scheme for Ammonia-Hydrogen-based Micro-Grids (AHMGs) to boost electricity-hydrogen-ammonia coupling under uncertainties. First, an off-grid AHMG model is developed, featuring a novel multi-mode ammonia synthesis process and a hydrogen-ammonia dual gas turbine with tunable feed-in ratios. Subsequently, a state-behavior mapping strategy linking hydrogen storage levels with the operation modes of ammonia synthesis is established to prevent cost-ineffective shutdowns. The proposed model substantially improves operational flexibility but results in a challenging nonlinear fractional program. Based upon this model, a data-driven RAJIT scheme is developed for the real-time rolling optimization of AHMGs. Unlike conventional one-size-fits-all schemes using one optimization method throughout, the data-driven RAJIT intelligently switches between cost-effective deterministic optimization and risk-averse online-learning distributionally robust optimization depending on actual risk profiles, thus capitalizing on the respective strengths of these two optimization methods. To facilitate the solution of the resulting nonlinear program, we develop an equivalent-reformulation-based solution methodology by leveraging a constraint-tightening technique. Numerical simulations demonstrate that the proposed scheme guarantees safety and yields an overall cost reduction up to 14.6% compared with several state-of-the-art methods. © 2025 IEEE.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Flexibility Improvement of 1000mw Ultra-Supercritical Unit Under Full Operating Conditions by Error-Based Adrc and Fast Pigeon-Inspired Optimizer

SSRN

引用

SSRN 2022年

作者： Hou, Guolian Huang, Ting Huang, Congzhi School of Control and Computer Engineering North China Electric Power University Beijing102206 China Key Laboratory of Power Station Energy Transfer Conversion and System North China Electric Power University Beijing102206 China

The operational flexibility of ultra-supercritical (USC) unit must be promoted to adapt a larger-scale renewable energy integrated into the power grid. Under this circumstance, a flexible operation method fusing the error-based ADRC and fast pigeon-inspired optimizer is designed and employed to USC unit. The urgency of the proposed method is illustrated via analyzing the control difficulties of USC unit in the flexibility requirements. Then, the error-based ADRC scheme which can precisely estimate and compensate the unknown uncertainties in real-time is formulated for USC unit. Furthermore, a fast pigeon-inspired optimizer combined with two-stage optimization and biquantum parallel search is used to attain the optimal parameters of error-based ADRC. Smoothness of manipulated variable and ITAE are considered in the multi-criteria optimization function. Finally, the integrated control scheme which effectively blends the features of fast disturbance rejection, distinguished search accuracy and convergence is taken as the flexible operation approach of unit. Simulations of the load tracking under different load tracking rates and disturbance rejection under the coal quality variation are carried out. Abundant comparison results validly proved the flexible operation of USC unit under full operating conditions based on the proposed algorithm. © 2022, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Distributed Nash Equilibrium Seeking for Aggregative Games with Mismatched Disturbances

Distributed Nash Equilibrium Seeking for Aggregative Games w...

引用

Chinese control and Decision Conference, CCDC

作者： Qi Wang Feng Xiao Bo Wei State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources North China Electric Power University Beijing China School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781665478977

In this paper, we focus on the distributed Nash equilibrium seeking problem for aggregative games for players described by double-integrator dynamics. Each player in the game is subject to unknown mismatched time-varying disturbances. To solve the Nash equilibrium seeking problem with mismatched disturbances, a distributed Nash equilibrium seeking algorithm is proposed. In aggregative games, the proposed algorithm guarantees the convergence of strategies of players to the Nash equilibrium of aggregative games and suppresses the influence of mismatched disturbances.

关键词： Heuristic algorithms Games Nash equilibrium Convergence Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Multi-microgrid Energy Management systems: Architecture, Communication, and Scheduling Strategies

引用

Journal of Modern Power systems and Clean Energy 2021年第3期9卷 463-476页

作者： Bin Zhou Jianting Zou Chi Yung Chung Huaizhi Wang Nian Liu Nikolai Voropai Daosen Xu the College of Electrical and Information Engineering Hunan UniversityChangsha 410082China the Department of Electrical and Computer Engineering University of SaskatchewanSaskatoonSK S7N5A9Canada the College of Mechatronics and Control Engineering Shenzhen UniversityShenzhen 518060China the State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China the Melentiev Energy Systems Institute of Siberian Branch of the Russian Academy of Sciences Irkutsk 664033Russia

The increasing penetration of various distributed and renewable energy resources at the consumption premises,along with the advanced metering,control and communication technologies,promotes a transition on the structure of traditional distribution systems towards cyber-physical multi-microgrids(MMGs).The networked MMG system is an interconnected cluster of distributed generators,energy storage as well as controllable loads in a distribution *** its operation complexity can be decomposed to decrease the burdens of communi-cation and control with a decentralized ***,the multi-microgrid energy management system(MIVIGEIV1S)plays a significant role in improving energy efficiency,power quality and reliability of distribution systems,especially in enhancing system resiliency during contingencies.A comprehensive overview on typical functionalities and architectures of MMGEMS is ***,the emerging communication technologies for information monitoring and interaction among MMG clusters are ***,various energy scheduling and control strategies of MMGs for interactive energy trading,multi-energy management,and resilient operations are thoroughly analyzed and ***,some challenges with great importance in the future research are presented.

关键词： Energy management system(EMS) microgrid communication renewable energy multi-energy system

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Combined with Heuristic Search for Solving Discrete Space Path Planning Problems

Reinforcement Learning Combined with Heuristic Search for So...

引用

第33届中国控制与决策会议

作者： Xiuling Zhang Xuenan Kang Kailun Wei Jinxiang Li Kai Ma Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan University

Reinforcement learning(RL) has been successfully applied to solve path planning problems,but learning is generally *** main reason is not making full use of information collected during interaction with the *** paper proposes a novel method to solve the discrete space path planning problem in an environment without prior knowledge with intensive obstacles based on RL and heuristic ***,we apply Dyna-Q algorithm of RL to explore the map and search for the target point and optimize its policy with upper confidence bound(UCB).Then,when the target point is found,we use heuristic search to plan the path from the starting point to the target point and narrow the path to a small ***,we combine Dyna-Q algorithm with the heuristic search recommended path for path *** evaluate our algorithm using maze navigation *** results verify that heuristic search accelerates Dyan-Q convergence.

关键词： Dyna-Q algorithm Heuristic search Path planning Discrete space

来源：评论

学校读者我要写书评

暂无评论

RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation

RLSAC: Reinforcement Learning enhanced Sample Consensus for ...

引用

International Conference on computer Vision (ICCV)

作者： Chang Nie Guangming Wang Zhe Liu Luca Cavalli Marc Pollefeys Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University Department of Computer Science ETH Zürich MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Microsoft Mixed Reality and AI Zürich Lab

Robust estimation is a crucial and still challenging task, which involves estimating model parameters in noisy environments. Although conventional sampling consensus-based algorithms sample several times to achieve robustness, these algorithms cannot use data features and historical information effectively. In this paper, we propose RLSAC, a novel Reinforcement Learning enhanced SAmple Consensus framework for end-to-end robust estimation. RLSAC employs a graph neural network to utilize both data and memory features to guide exploring directions for sampling the next minimum set. The feedback of downstream tasks serves as the reward for unsupervised training. Therefore, RL-SAC can avoid differentiating to learn the features and the feedback of downstream tasks for end-to-end robust estimation. In addition, RLSAC integrates a state transition module that encodes both data and memory features. Our experimental results demonstrate that RLSAC can learn from features to gradually explore a better hypothesis. Through analysis, it is apparent that RLSAC can be easily transferred to other sampling consensus-based robust estimation tasks. To the best of our knowledge, RLSAC is also the first method that uses reinforcement learning to sample consensus for end-to-end robust estimation. We release our codes at https://***/IRMVLab/RLSAC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Retina-LGN-V1 Structure-like Spiking Neuron Network for Image Feature Extraction 21

A Retina-LGN-V1 Structure-like Spiking Neuron Network for Im...

引用

Proceedings of the 2021 5th International Conference on Video and Image Processing

作者： Sheng Ji Qijun Gu Ye Yuan Peng Zhao Tao Fang Hong Huo Xin Niu Department of Automation_School of Electronic Information and Electrical Engineering_Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University China College of Computer Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology China

ISBN: (纸本)9781450385893

SNNs have achieved great attention in recent years as they contain neurons more like those in the brain and use spikes to encode and transmit information efficiently among neurons with lower energy consumption. A Retina-LGN-V1 structure-like spiking neuron network (RLVSL-SNN) is proposed in this paper. It is inspired by the structure of mammalian primary visual pathway, and simulates different biological structures of Retina, LGN and V1. Noise reduction circuit and light adaptation circuit are also simulated for enhancing the robustness of its extracted features. RLVSL-SNN is a bio-plausible neuron network as it has firing rates of neurons in each layer that are similar to those of biological experiments. Besides, a full-connected SNN (FC SNN) is implemented following RLVSL-SNN for classification to evaluate the extracted features. The additive spiking timing dependent plasticity (STDP) learning rules and the ANN-to-SNN conversion method are utilized to train RLVSL-SNN and FC SNN, respectively. The experiments on MNIST dataset have verified that RLVSL-SNN is comparable to AlexNet for classification by features from spikes.

关键词： Additive Spiking Timing Dependent Plasticity Learning Primary Visual Pathway Image Classification Spiking Neural Network

来源：评论

学校读者我要写书评

暂无评论

Mesenchymal stem cells loaded on 3D-printed gradient poly(e-caprolactone)/methacrylated alginate composite scaffolds for cartilage tissue engineering

引用

Regenerative Biomaterials 2021年第3期8卷 70-83页

作者： Yanyan Cao Peng Cheng Shengbo Sang Chuan Xiang Yang An Xiaochun Wei Zhizhong Shen Yixia Zhang Pengcui Li Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education MicroNano System Research CenterCollege of Information and ComputerTaiyuan University of TechnologyTaiyuan 030024China College of Information Science and Engineering Hebei North UniversityZhangjiakou 075000China Shanxi Key Laboratory of Bone and Soft Tissue Injury Repair Department of OrthopedicsThe Second Hospital of Shanxi Medical UniversityTaiyuan 030001China Department of Plastic Surgery Peking University Third HospitalBeijing 100191China Department of Biomedical Engineering College of Biomedical EngineeringTaiyuan University of TechnologyTaiyuan 030024China

Cartilage has limited self-repair ability due to its avascular,alymphatic and aneural *** combination of three-dimensional(3D)printing and tissue engineering provides an up-and-coming approach to address this ***,we designed and fabricated a tri-layered(superficial layer(SL),middle layer(ML)and deep layer(DL))stratified scaffold,inspired by the architecture of collagen fibers in native cartilage *** scaffold was composed of 3D printed depth-dependent gradient poly(e-caprolactone)(PCL)impregnated with methacrylated alginate(ALMA),and its morphological analysis and mechanical properties were *** prove the feasibility of the composite scaffolds for cartilage regeneration,the viability,proliferation,collagen deposition and chondrogenic differentiation of embedded rat bone marrow mesenchymal stem cells(BMSCs)in the scaffolds were assessed by Live/dead assay,CCK-8,DNA content,cell morphology,immunofluorescence and real-time reverse transcription polymerase chain ***-loaded gradient PCL/ALMA scaffolds showed excellent cell survival,cell proliferation,cell morphology,collagen II deposition and hopeful chondrogenic differentiation compared with three individual-layer ***,our study demonstrates the potential use of the gradient PCL/ALMA construct for enhanced cartilage tissue engineering.

关键词： three-dimensional printing cartilage tissue engineering PCL methacrylated alginate bone marrow mesenchymal stem cells

来源：评论

学校读者我要写书评

暂无评论

Platoon-Based Distributed control for Automated Material Handling systems

Platoon-Based Distributed Control for Automated Material Han...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Alessandro Bozzi Jose-Fernando Jimenez Camilo Hernandez-Rodriguez Eliana-Maria Gonzalez-Neira Damien Trentesaux Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS) University of Genova Italy Laboratory System and Materials for Mechatronics (SYMME) Université Savoie Mont Blanc Annecy France Industrial Engineering Department Pontificia Universidad Javeriana Bogota Columbia Laboratory of Industrial and Human Automation Control Mechanical Engineering and Computer Science (LAMIH) Université Polytechnique Hauts-de-France Valenciennes France

Smart manufacturing systems combine collaborative and autonomous control systems to provide optimal performance and respond to volatile demands. A key component of smart manufacturing is material management, as raw materials, work-in-progress, and finished products must be transported to the right location at the right time. However, during the production phase, it is imperative to establish an optimal traffic control scheme in order to avoid congestion and optimize material flow. This paper proposes a platooning-based control procedure implemented in a virtual agent-based manufacturing environment to increase the material flow efficiency on a manufacturing shop floor. An analysis of the production makespan and an indicator of the level of congestion in the material handling system was conducted in order to determine productivity improvements. An agent-based simulation is used to test the effectiveness of the novel platooning approach versus a traditional basic approach. A multivariate analysis of variance (MANOVA) reveals that the inclusion of a platoon-based procedure improves production performance and reduces congestion risks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Difference Learning for Noisy Rigid Image Alignment

arXiv

引用

arXiv 2022年

作者： Chen, Yu-Xuan Feng, Dagan Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China School of Computer Science University of Sydney Sydney2006 Australia

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer networks show an improved performance on clean images but will not achieve satisfactory performance on noisy images due to its heavy reliance on pixel value comparations. To handle such challenging applications, we report a new unsupervised difference learning (UDL) strategy and apply it to rigid image alignment. UDL exploits the quantitative properties of regression tasks and converts the original unsupervised problem to pseudo supervised problem. Under the new UDL-based image alignment pipeline, rotation can be accurately estimated on both clean and noisy images and translations can then be easily solved. Experimental results on both nature and cryo-EM images demonstrate the efficacy of our UDL-based unsupervised rigid image alignment method. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

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：