检索结果-内蒙古大学图书馆

Proceedings of the 2021 4th International Conference on algorithms, Computing and Artificial Intelligence

作者： Jie Fang Yunqing Rao Xiaoqiang Guo Xusheng Zhao School of Mechanical Science & Engineering Huazhong University of Science and Technology China

ISBN: (纸本)9781450385053

The two-dimensional(2D) irregular packing problem is a classical optimization problem with NP-Hard characteristics, which has high computational complexity. The traditional heuristic algorithm and meta heuristic algorithm are usually used to solve packing problems, which has low packing efficiency and high time cost. Inspired by reinforcement learning(RL) and combined with the characteristics of 2D irregular pieces packing, a novel method to solve multi-constraint packing problem based on reinforcement learning is proposed in this paper. A reinforcement learning model based on monte- carlo (MC) method and a reward mechanism based on packing height return are designed. Finally, an example is used to analyze the optimization effect of the algorithm. The experimental results show that the proposed method can quickly and efficiently realize the packing of 2D irregular pieces, and a better solution can be obtained in an acceptable time.

关键词： reinforcement learning machine learning irregular pieces monte-carlo algorithm two-dimensional packing optimization

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning algorithm for two-dimensional irregular packing problems

A reinforcement learning algorithm for two-dimensional irreg...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Jie Fang Yunqing Rao Xiaoqiang Guo Xusheng Zhao School of Mechanical Science & Engineering Huazhong University of Science and Technology

The two-dimensional(2 D) irregular packing problem is a classical optimization problem with NP-Hard characteristics, which has high computational complexity. The traditional heuristic algorithm and meta heuristic algorithm are usually used to solve packing problems, which has low packing efficiency and high time *** by reinforcement learning(RL) and combined with the characteristics of 2 D irregular pieces packing, a novel method to solve multi-constraint packing problem based on reinforcement learning is proposed in this paper. A reinforcement learning model based on monte-carlo(MC) method and a reward mechanism based on packing height return are designed. Finally, an example is used to analyze the optimization effect of the algorithm. The experimental results show that the proposed method can quickly and efficiently realize the packing of 2 D irregular pieces, and a better solution can be obtained in an acceptable time.

关键词： reinforcement learning machine learning monte-carlo algorithm two-dimensional packing optimization irregular pieces

来源：评论

学校读者我要写书评

暂无评论

A hierarchical energy management strategy for interconnected microgrids considering uncertainty

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2019年 109卷 597-608页

作者： Bazmohammadi, Najmeh Tahsiri, Ahmadreza Anvari-Moghaddam, Amjad Guerrero, Josep M. KN Toosi Univ Technol Dept Elect Engn Tehran Iran Aalborg Univ Dept Energy Technol DK-9220 Aalborg Denmark

Coordinating the operation of neighboring microgrids is a promising solution for the problem of growing penetration of renewable-based microgrids into the power system. In this paper, a hierarchical stochastic energy management system is proposed for operation management of interconnected microgrids. At the upper-level, a central entity is responsible for coordinating the operation of microgrids. Based on the energy scheduling made at this level, the power reference values to be exchanged within the microgrids network and between the microgrids and the main grid are calculated and communicated with the local energy management systems. At the lower-level, a decision making approach based on chance-constrained model predictive control is adopted for local operation management of each microgrid taking into account different sources of uncertainties. The results show that the proposed strategy provides the microgrids with the opportunity of exploiting maximum available capacity in the network. Consequently, the microgrids dependency on the main grid will be reduced and some important performance indices such as multi-microgrid system cost and real-time power deviations will be improved.

关键词： Energy management Multi-microgrid system Chance-constrained model predictive control Uncertainty management monte-carlo algorithm

来源：评论

学校读者我要写书评

暂无评论

Stochastic Predictive Control of Multi-Microgrid Systems

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2019年第5期55卷 5311-5319页

作者： Bazmohammadi, Najmeh Tahsiri, Ahmadreza Anvari-Moghaddam, Amjad Guerrero, Josep M. KN Toosi Univ Technol Dept Elect Engn Tehran 163171419 Iran Aalborg Univ Dept Energy Technol DK-9220 Aalborg Denmark

In this paper, integrated operation management of cooperative microgrids is formulated in the framework of stochastic predictive control. In the proposed scheme, a joint probabilistic constraint on the microgrids power exchange with the main grid couples operation of individual microgrids. In order to tackle the coupling constraint, a cooperative energy management strategy is proposed in which based on the statistical characteristics of uncertain parameters, the deterministic counterpart of the problem is derived and an efficient solution strategy is achieved. The proposed strategy is evaluated for an illustrative test case including two microgrids based on modified CIGRE benchmark. Moreover, statistical analysis is conducted to evaluate robustness characteristics of the solution strategy.

关键词： Chance constraints energy management system (EMS) model predictive control (MPC) monte-carlo algorithm multi-microgrid systems

来源：评论

学校读者我要写书评

暂无评论

SAlign-a structure aware method for global PPI network alignment

引用

BMC BIOINFORMATICS 2020年第1期21卷 500-500页

作者： Ayub, Umair Haider, Imran Naveed, Hammad Natl Univ Comp & Emerging Sci Dept Comp Islamabad 40100 Pakistan Computat Biol Res Lab Islamabad 40100 Pakistan

Background: High throughput experiments have generated a significantly large amount of protein interaction data, which is being used to study protein networks. Studying complete protein networks can reveal more insight about healthy/disease states than studying proteins in isolation. Similarly, a comparative study of protein-protein interaction (PPI) networks of different species reveals important insights which may help in disease analysis and drug design. The study of PPI network alignment can also helps in understanding the different biological systems of different species. It can also be used in transfer of knowledge across different species. Different aligners have been introduced in the last decade but developing an accurate and scalable global alignment algorithm that can ensures the biological significance alignment is still challenging. Results: This paper presents a novel global pairwise network alignment algorithm, SAlign, which uses topological and biological information in the alignment process. The proposed algorithm incorporates sequence and structural information for computing biological scores, whereas previous algorithms only use sequence information. The alignment based on the proposed technique shows that the combined effect of structure and sequence results in significantly better pairwise alignments. We have compared SAlign with state-of-art algorithms on the basis of semantic similarity of alignment and the number of aligned nodes on multiple PPI network pairs. The results of SAlign on the network pairs which have high percentage of proteins with available structure are 3-63% semantically better than all existing techniques. Furthermore, it also aligns 5-14% more nodes of these network pairs as compared to existing aligners. The results of SAlign on other PPI network pairs are comparable or better than all existing techniques. We also introduce SAlignmc, a monte carlo based alignment algorithm, that produces multiple network alignments with si

关键词： Protein-protein interaction Global network alignment Sequence similarity Structure similarity monte-carlo algorithm

来源：评论

学校读者我要写书评

暂无评论

Auto-tune of PVT data using an efficient engineering method: Application of sensitivity and optimization analyses

引用

FLUID PHASE EQUILIBRIA 2018年 473卷 70-79页

作者： Zarifi, Abdolhadi Daryasafar, Amin NISOC Dept Petr Engn Ahvaz Iran

In reservoir simulation, it is crucial to have a physical model of the reservoir fluid that can give the properties and behavior of the fluid at different conditions. Phase behavior of a reservoir hydrocarbon is modeled through an equation of state (EOS) by adjustment of some of the parameters in EOS so as to reproduce measured data of the mixture. Since the EOSs have some inherent deficiencies which may cause erroneous predictions, these models have to be tuned against experimental data. Conventionally, the methods and algorithms that have been proposed for tuning EOS models are tedious and really time consuming;therefore, a simple and accurate algorithm that can find the best match between EOS and measured data, automatically is really needed. For this purpose, a generalized auto-tune procedure based on monte-carlo and genetic algorithms is proposed in this study. In the presented method, first of all, the matching parameters for regression process are found in an automatic manner by using monte-carlo sensitivity analysis. Then, the selected parameters are fed to the PVT analyzer coupled with genetic algorithm and therefore, the best EOS model is searched and found. Three fluid samples (one gas condensate and two black oils) were used in order to test the proposed method and the matches were found by using Peng-Robindon (PR) EOS. The results illustrated the surprising high performance of the developed algorithm in matching the experimental data. The main advantages of this method is its high speed in finding the best EOS model, working automatically, reducing costs and also having the possibility of evaluating the model at different conditions. (C) 2018 Elsevier B.V. All rights reserved.

关键词： PVT match EOS model Sensitivity analysis Genetic algorithm monte-carlo algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Optimal Inspection Strategy for Overhead Transmission Line Based on Smart Grid 9th

Research on Optimal Inspection Strategy for Overhead Transmi...

引用

9th International Conference on Ambient Systems, Networks and Technologies (ANT) / 8th International Conference on Sustainable Energy Information Technology (SEIT)

作者： Liu Jian Gao Feng Zhao Ming Chen Liuning Li Weiyao Wuhan Univ Sch Elect Engn Wuhan 430072 Peoples R China State Grid Zhengzhou Power Supply Co Zhengzhou 450052 Henan Peoples R China State Grid Nanyang Power Supply Co Nanyang 473005 Henan Peoples R China

Due to the urgent demand for the monitoring of overhead transmission lines in smart grid, this paper proposes an optimal inspection strategy for overhead transmission line considering time-varying failure rate. Based on the goal benefit function of inspection cost, failure electric cost and the maintaining reliability cost, modal of the inspection strategy is established with genetic algorithm. The reliability index could contribute to a dynamic and variable inspection cycle of transmission line via genetic algorithm. According to the calculation results of the middle area of China, it is presented that the algorithm can work out inspection strategy according to the actual failure rate, and get a rational and economical, regional, seasonal, dynamic inspection cycle plan. Thus, it can avoid the traditional over-inspection and lack-inspection problems. The state of transmission line can be guaranteed in more economical way, satisfying the demand of real-time capability and reliability (C) 2018 The Authors. Published by Elsevier B.V.

关键词： smart grid overhead transmission line inspection strategy time-varying failure rate monte-carlo algorithm

来源：评论

学校读者我要写书评

暂无评论

Coordination of repeaters based on Simulated Annealing algorithm and monte-carlo algorithm

引用

Neurocomputing 2012年 97卷 9-15页

作者： Ya Cai Yuanqing Xia Li Dai Chi Xiao Jiaxiang Wu School of Automation Beijing Institute of Technology Beijing 100081 PR China

This paper considers the design of repeaters network in both flat and mountainous area. The main purpose is to design a network that is not only able to accommodate the communication need of all users in a certain area, but also with lower cost than previous design methods of the network. Considering the propagation and attenuation of radio signals, the problem can be transformed to search for best locations of centers of circles in order to reach maximum coverage percent in the whole area. Applying the Simulated Annealing algorithm and monte-carlo algorithm, numerical examples are given to show the potential of the proposed techniques. Compared with previous method, our proposed method shows its effectiveness.

关键词： Repeaters network Wireless communication Simulated Annealing algorithm monte-carlo algorithm

来源：评论

学校读者我要写书评

暂无评论

Nonequilibrium Phase Transition in Spin-S Ising Ferromagnet Driven by Propagating and Standing Magnetic Field Wave

引用

Communications in Theoretical Physics 2017年第11期67卷 600-610页

作者： Ajay Halder Muktish Acharyya Department of Physics Presidency University

The dynamical response of spin-S(S=1, 3/2, 2, 3) Ising ferromagnet to the plane propagating wave, standing magnetic field wave and uniformly oscillating field with constant frequency are studied separately in two dimensions by extensive monte carlo simulation. Depending upon the strength of the magnetic field and the value of the spin state of the Ising spin lattice two different dynamical phases are observed. For a fixed value of S and the amplitude of the propagating magnetic field wave the system undergoes a dynamical phase transition from propagating phase to pinned phase as the temperature of the system is cooled down. Similarly in case with standing magnetic wave the system undergoes dynamical phase transition from high temperature phase where spins oscillate coherently in alternate bands of half wavelength of the standing magnetic wave to the low temperature pinned or spin frozen phase. For a fixed value of the amplitude of magnetic field oscillation the transition temperature is observed to decrease to a limiting value as the value of spin S is increased. The time averaged magnetisation over a full cycle of the magnetic field oscillation plays the role of the dynamic order parameter. A comprehensive phase boundary is drawn in the plane of magnetic field amplitude and dynamic transition temperature. It is found that the phase boundary shrinks inwards for high value of spin state *** in the low temperature(and high field) region the phase boundaries are closely spaced.

关键词： Ising model dynamic phase transition monte-carlo algorithm propagating wave standing wave

来源：评论

学校读者我要写书评

暂无评论

Impact of Brillouin Backscattering on Signal Distortions in Single-Fiber Diversity Loop Based Polarization-Insensitive FOPAs

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2017年第19期35卷 4137-4144页

作者： Jazayerifar, Mahmoud Sackey, Isaac Elschner, Robert Richter, Thomas Molle, Lutz Berenguer, Pablo Wilke Schubert, Colja Jamshidi, Kambiz Petermann, Klaus Tech Univ Dresden Inst Nachrichtentech D-01069 Dresden Germany Heinrich Hertz Inst Nachrichtentech Berlin GmbH Fraunhofer Inst Telecommun D-10587 Berlin Germany ADVA Opt Networking North Amer Inc Norcross GA 30071 USA Tech Univ Berlin Fachgebiet Hochfrequenztech D-10587 Berlin Germany

We both experimentally and numerically investigate the impact of Brillouin backscattering in single-fiber-loop-based polarization-insensitive fiber-optical parametric amplifiers. We show that the loop configuration can cause distortions in the pump spectra due to Brillouin interactions of the counter-propagating pumps. This can result in significant distortions for amplified data signals at high gain when conventional highly nonlinear fibers are used. We thoroughly investigate the effect in experiments and derive a numerical model. This allows us to compare the results from system experiments with 28 GBd quadrature-phase shift keying signals to system simulations showing a good agreement on the system. Based on the model, we finally estimate that a large gain (similar to 20 dB) with a low optical signal-to-noise ratio penalty (0.15 dB at bit error rate of 1 x 10(-4)) for the amplified data signal should be possible in a single-fiber loop with Brillouin-suppressed highly nonlinear fibers.

关键词： Brillouin scattering coherent detection four-wave mixing monte-carlo algorithm nonlinear optics optical amplifiers optical fiber communication

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：