检索结果-内蒙古大学图书馆

Meta-State-Space Learning: An Identification Approach for Stochastic Dynamical systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Beintema, Gerben I. Schoukens, Maarten Toth, Roland Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Budapest Hungary

Available methods for identification of stochastic dynamical systems from input-output data generally impose restricting structural assumptions on either the noise structure in the data-generating system or the possible state probability distributions. In this paper, we introduce a novel identification method of such systems, which results in a dynamical model that is able to produce the time-varying output distribution accurately without taking restrictive assumptions on the data-generating process. The method is formulated by first deriving a novel and exact representation of a wide class of nonlinear stochastic systems in a so-called meta-state-space form, where the meta-state can be interpreted as a parameter vector of a state probability function space parameterization. As the resulting representation of the meta-state dynamics is deterministic, we can capture the stochastic system based on a deterministic model, which is highly attractive for identification. The meta-state-space representation often involves unknown and heavily nonlinear functions, hence, we propose an artificial neural network (ANN)-based identification method capable of efficiently learning nonlinear meta-state-space models. We demonstrate that the proposed identification method can obtain models with a log-likelihood close to the theoretical limit even for highly nonlinear, highly stochastic systems. © 2023, CC BY.

关键词： Stochastic systems

Optimizing Vehicle Positioning via Multi-Model Image and Radio Frequency Fusion

学校读者我要写书评

暂无评论

Optimizing Vehicle Positioning via Multi-Model Image and Rad...

IEEE International Conference on Communications (ICC)

作者： Ouwen Huan Mingzhe Chen Tao Luo Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral Gables FL USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

In this paper, a multi-modal vehicle positioning framework that jointly localizes vehicles with channel state information (CSI) and images is designed. In particular, we consider an outdoor scenario where each vehicle can communicate with only one base station (BS), and hence, it can upload its estimated CSI to only its associated BS. Each BS is equipped with a set of cameras, such that it can collect a small number of labeled CSI, a large number of unlabeled CSI, and the images taken by cameras. To exploit the unlabeled CSI data and position labels obtained from images, we design a hard expectation-maximization (EM) based deep learning (DL) algorithm. Specifically, since we do not know the corresponding relationship between unlabeled CSI and the multiple vehicle locations in images, we formulate the calculation of the log-likelihood function as a maximum matching problem. Subsequently, the model parameters are updated according to the maximum matching between unlabeled CSI and position labels obtained from images. Simulation results show that the proposed method can reduce the positioning error by up to 60% compared to a baseline that does not use images and uses only CSI fingerprint for vehicle positioning.

关键词： Training Deep learning Base stations Simulation Fingerprint recognition Cameras Data models

Dead-time Compensation Method for Bus-clamping Modulated Voltage Source Inverter

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ghaderloo, Reza Asrar Shen, Yidi Singhabahu, Chanaka Resalayyan, Rakesh Khaligh, Alireza Maryland Power Electronics Laboratory Department of Electrical and Computer Engineering The Institute for Systems Research University of Maryland College ParkMD20742 United States

Bus-clamping Pulse Width Modulation (PWM) is an effective method to reduce the switching loss in a three-phase voltage source inverter (VSI). In bus-clamping PWM scheme, the phase legs are switched using high frequency PWM signals for two-third of the line cycle, while for the remaining duration of cycle, the pole voltage is clamped to either positive or negative rail of the DC bus. In PWM operation of a half bridge, a dead-time is applied between the gate signals of complementary switches to ensure safe and reliable operation. However, introduction of dead-time leads to poor power quality, increased Total Harmonic Distortion (THD) and variation in actual voltage compared to the intended pole voltage. Moreover, when the bus-clamping technique is used, the PWM has both high frequency switching region and clamped region in a line cycle, and consequently, the undesired effects of dead-time are further aggravated. Therefore, in order to enhance the quality of output voltage, this paper presents a dead-time compensation strategy for a VSI operating with bus-clamping PWM. The proposed method calculates the required compensation term to be added on the modulation signal considering wide range of operating conditions. Additionally, the compensation includes a new strategy for low current conditions near zero-crossing to avoid distortion. The proposed method is verified by simulation and experiments in a three-phase VSI with a switching frequency of 100 kHz and a fundamental frequency of 60Hz. Copyright © 2023, The Authors. All rights reserved.

关键词： Pulse width modulation

Toward Value-oriented Renewable Energy Forecasting: An Iterative Learning Approach

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Yufan Jia, Mengshuo Wen, Honglin Bian, Yuexin Shi, Yuanyuan Department of Electrical and Computer Engineering University of California San Diego United States Power Systems Laboratory ETH Zürich Zürich8092 Switzerland Department of Electrical Engineering Shanghai Jiao Tong University China

Energy forecasting is an essential task in power system operations. Operators usually issue forecasts and use them to schedule energy dispatch in advance. However, forecasting models are typically developed in a way that overlooks the decision value of forecasts. To bridge the gap, we design a value-oriented point forecasting approach for sequential energy dispatch problems with renewable energy sources. At the training phase, we align the training objective with the decision value, i.e., minimizing the overall operating cost. The forecasting model parameter estimation is formulated as a bilevel program. Under mild assumptions, we convert the upper-level objective into an equivalent form using the dual solutions obtained from the lower-level operation problems. In addition, a novel iterative solution strategy is proposed for the newly formulated bilevel program. Under such an iterative scheme, we show that the upper-level objective is locally linear with respect to the forecasting model output and can act as the loss function. Numerical experiments demonstrate that, compared to commonly used forecasts predicting expected realization, forecasts obtained by the proposed approach result in lower operating costs. Meanwhile, the proposed approach achieves performance comparable to that of two-stage stochastic programs, but is more computationally efficient. © 2023, CC BY.

关键词： Cost functions

Predictive Prescription of Unit Commitment Decisions Under Net Load Uncertainty

学校读者我要写书评

暂无评论

Predictive Prescription of Unit Commitment Decisions Under N...

Innovative Smart Grid Technologies (ISGT)

作者： Ogun Yurdakul Feng Qiu Sahin Albayrak Department of Electrical Engineering and Computer Science Technical University of Berlin Berlin Germany Energy Systems Division Argonne National Laboratory Lemont IL USA

To take unit commitment (UC) decisions under uncertain net load, most studies utilize a stochastic UC (SUC) model that adopts a one-size-fits-all representation of uncertainty. Disregarding contextual information such as weather forecasts and temporal information, these models are typically plagued by a poor out-of-sample performance. To effectively exploit contextual information, in this paper, we formulate a conditional SUC problem that is solved given a covariate observation. The presented problem relies on the true conditional distribution of net load and so cannot be solved in practice. To approximate its solution, we put forward a predictive prescription framework, which leverages a machine learning model to derive weights that are used in solving a reweighted sample average approximation problem. In contrast with existing predictive prescription frameworks, we manipulate the weights that the learning model delivers based on the specific dataset, present a method to select pertinent covariates, and tune the hyperparameters of the framework based on the out-of-sample cost of its policies. We conduct extensive numerical studies, which lay out the relative merits of the framework vis-à-vis various benchmarks.

关键词： Radio frequency Training Costs Uncertainty Stochastic processes Weather forecasting Predictive models

Plate Shape Prediction Based on Data-Driven in Roll Quenching Process

学校读者我要写书评

暂无评论

Plate Shape Prediction Based on Data-Driven in Roll Quenchin...

2023 China Automation Congress, CAC 2023

作者： Hu, Liu Chen, Luefeng Hu, Jie Wu, Min Pedrycz, Witold Hirota, Kaoru School of Automation Ministry of Education China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems The Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2G7 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Istinye University The Department of Computer Engineering Istanbul Sariyer34396 Turkey Tokyo Institute of Technology Tokyo Yokohama226-8502 Japan

ISBN: (纸本)9798350303759

In the process of steel plate production, predicting the plate shape is of great significance for producing high-quality and consistently stable plate shapes. This paper presents a model that predicts both the defect types and flatness of the plate, providing theoretical support for setting process parameters in roller quenching production. First, the parameters of the quenching process are analyzed to identify their characteristics. Then, the K-Means clustering algorithm and correlation analysis are employed to process the quenching process parameters. A gradient boosting decision tree (GBDT) model is used to predict the defect types and flatness of the steel plates. Finally, industrial production data is utilized for experimental validation. The obtained experimental results verify the reliability of the proposed method. © 2023 IEEE.

关键词： Decision trees

A Highly Efficient Algorithm for Phased-Array mmWave Massive MIMO Beamforming

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第10期69卷 679-694页

作者： Ayman Abdulhadi Althuwayb Fazirulhisyam Hashim Jiun Terng Liew Imran Khan Jeong Woo Lee Emmanuel Ampoma Affum Abdeldjalil Ouahabi Sébastien Jacques Department of Electrical Engineering Jouf UniversitySakakaAljouf72388Kingdom of Saudi Arabia Department of Computer and Communication Systems Engineering Faculty of EngineeringUniversiti Putra Malaysia(UPM)Serdang43400Malaysia Department of Electrical Engineering University of Engineering and Technology PeshawarPakistan School of Electrical and Electronics Engineering Chung-Ang UniversitySeoul06974Korea Electrical and Electronic Department Kwame Nkrumah University of Science and TechnologyKumasiGhana UMR 1253 iBrainUniversitéde ToursINSERMToursFrance LIMPAF Laboratory Department of Computer ScienceUniversity of BouiraBouira10000Algeria University of Tours(France) GREMAN UMR 7347CNRSINSA Centre Val-de-LoireTours37100France

With the rapid development of the mobile internet and the internet of things(IoT),the fifth generation(5G)mobile communication system is seeing explosive growth in data *** addition,low-frequency spectrum resources are becoming increasingly scarce and there is now an urgent need to switch to higher frequency *** wave(mmWave)technology has several outstanding features—it is one of the most well-known 5G technologies and has the capacity to fulfil many of the requirements of future wireless ***,it has an abundant resource spectrum,which can significantly increase the communication rate of a mobile communication *** such,it is now considered a key technology for future mobile *** communication technology also has a more open network architecture;it can deliver varied services and be applied in many *** contrast,traditional,all-digital precoding systems have the drawbacks of high computational complexity and higher power *** paper examines the implementation of a new hybrid precoding system that significantly reduces both calculational complexity and energy *** primary idea is to generate several sub-channels with equal gain by dividing the channel by the geometric mean decomposition(GMD).In this process,the objective function of the spectral efficiency is derived,then the basic tracking principle and least square(LS)techniques are deployed to design the proposed hybrid *** results show that the proposed algorithm significantly improves system performance and reduces computational complexity by more than 45%compared to traditional algorithms.

关键词： 5G mmWave phased array algorithm antenna beamforming

Online Demand Peak Shaving with Machine-Learned Advice in Cyber-Physical Energy systems

学校读者我要写书评

暂无评论

Online Demand Peak Shaving with Machine-Learned Advice in Cy...

IEEE International Symposium on Dependable, Autonomic and Secure computing (DASC)

作者： Minxi Fengl Wei Li Boyu Qin Albert Y. Zomaya Centre for Distributed and High Performance Computing School of Computer Science The University of Sydney Australia Department of Electrical Engineering State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University China

With the deep integration of cyber tools, control algorithms are increasingly employed in cyber-physical energy systems to enhance management, cost efficiency, and robustness. Effective demand load management is crucial in cyber-physical energy systems as it directly impacts operational costs. Failure to adequately manage spiky or seasonal demand loads can lead to significant expenses on monthly utility bills. In this study, we propose AMPAMOD, a randomized online algorithm with machine-learned advice, to optimize battery operations and mitigate highly dynamic peak loads. AMPAMOD utilizes limited advice from machine learning algorithms to guide our online algorithm and ensure cost-effective peak load management. The theoretical analysis shows that our solution has minimal advice complexity, a linear computational cost, and an improved competitive ratio. Finally, we conduct extensive trace-driven experiments on real-world datasets. AMPAMOD achieves a peak shaving success rate of over 90%, outperforming baselines by at least 50%. These experimental results confirm theoretical findings and demonstrate the potential of AMPAMOD.

关键词：

Exploring the use of deep learning in task-flexible ILC

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Vinjarapu, Anantha Sai Hariharan Broens, Yorick Butler, Hans Tóth, Roland The Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands The Systems and Control Laboratory Institute for Computer Science and Control Hungary Asml Veldhoven Netherlands

Growing demands in today's industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional model-based feedforward approaches are no longer sufficient to satisfy the challenging performance requirements. An attractive method for systems with repetitive motion tasks is iterative learning control (ILC) due to its superior performance. However, for systems with non-repetitive motion tasks, ILC is generally not applicable, despite of some recent promising advances. In this paper, we aim to explore the use of deep learning to address the task flexibility constraint of ILC. For this purpose, a novel Task Analogy based Imitation Learning (TAIL)-ILC approach is developed. To benchmark the performance of the proposed approach, a simulation study is presented which compares the TAIL-ILC to classical model-based feedforward strategies and existing learning-based approaches, such as neural network based feedforward *** Codes 37M15 © 2023, CC BY.

关键词： Feedforward control