检索结果-内蒙古大学图书馆

Hybrid optimization for charge planning problem in twin strands continuous casting production

Journal of Iron and Steel Research International 2021年第5期28卷 520-529页

作者： Jian Yi Shu-jin Jia Bin Du College of Information Science and Engineering Northeastern UniversityShenyang 110819LiaoningChina Institute of Intelligent Manufacturing Baosteel Central Research InstituteShanghai 201900China

Charge planning is one of batching problems for steelmaking and continuous casting production,and its optimization will be conducive to subsequent cast *** planning problem in the twin strands continuous casting production was studied,where casting width of the odd strand might be different from that of the even *** the different widths in the twin strands,the resulting counterweights and the constraints of steelmaking and continuous casting,a multiobjective optimization model was established to minimize the number of charges,the number of scale pairs,the surplus and the upgrading costs of steel ***,a hybrid optimization algorithm combined with heuristic and mutation-based estimation of distribution algorithm was proposed to solve the *** were conducted on several groups of test data collected from practical production orders of *** computational results demonstrate that the proposed algorithm can generate better solutions than the manual *** proposed model and algorithm proved to be effective and practical.

关键词： Steelmaking Continuous casting Production planning Charge Cast estimation of distribution algorithm

来源：评论

学校读者我要写书评

暂无评论

An EDA-based Genetic algorithm for EV Charging Scheduling under Surge Demand

An EDA-based Genetic Algorithm for EV Charging Scheduling un...

引用

IEEE International Conference on Services Computing (IEEE SCC)

作者： Li, Tianyang Li, Xiaolong He, Ting Zhang, Yufeng Northeast Elect Power Univ Sch Comp Sci Jilin Jilin Peoples R China Jiangxi New Energy Technol Inst Nanchang Jiangxi Peoples R China Bank Inner Mongolia Co Ltd Harbin Branch Harbin Peoples R China Huaqiao Univ Coll Comp Sci & Technol Xiamen Peoples R China Univ Birmingham Birmingham Business Sch Birmingham W Midlands England

ISBN: (数字)9781665481465

ISBN: (纸本)9781665481465

With continually increased Electric Vehicles (EVs), the EVs Charging Scheduling is of great importance to managing multiple charging demands for maximizing user satisfactions and minimizing adverse influences on the grid. However, it is challenging to effectively manage EVs charging schedules when a large number of (on-the-move) EVs are planning to charge at the same time. With this concern, we focus on Charging Station (CS)-selection decision making by the global aggregator that is taken as controller to implement charging management for EVs and CSs. An estimation of distribution algorithm (EDA)-based genetic algorithm is proposed to find constrained charging scheduling plans to maximize the charging efficiency, which may improve user satisfaction and alleviate impacts on the grid. Experimental results under a city scenario with realistic EVs and CSs show the advantage of our proposal, in terms of minimized queuing time and maximized charging performance at both the EV and CS sides. The code and data are available at https://***/EV-charging-scheduling-algorithm.

关键词： EV charging charging scheduling estimation of distribution algorithm genetic algorithm surge demand

来源：评论

学校读者我要写书评

暂无评论

A two-stage approach for multicast-oriented virtual network function placement

引用

APPLIED SOFT COMPUTING 2021年 112卷 107798-107798页

作者： Wang, Xinhan Xing, Huanlai Zhan, Dawei Luo, Shouxi Dai, Penglin Iqbal, Muhammad Azhar Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu Peoples R China

Network function virtualization (NFV) is an emerging network paradigm that decouples softwarized network functions from proprietary hardware. Nowadays, resource allocation has become one of the hot topics in the NFV domain. In this paper, we formulate a service function chain (SFC) mapping problem in the context of multicast, which is also referred to as the multicast-oriented virtual network function placement (MVNFP) problem. The objective function considers end-to-end delay as well as compute resource consumption, with bandwidth requirements met. A two-stage approach is proposed to address this problem. In the first stage, Dijkstra's algorithm is adopted to construct a multicast tree. In the second stage, a novel estimation of distribution algorithm (nEDA) is developed to map a given SFC over the multicast tree. Simulation results show that the proposed two-stage approach outperforms a number of state-of-the-art evolutionary, approximation, and heuristic algorithms, in terms of the solution quality. (C) 2021 Elsevier B.V. All rights reserved.

关键词： estimation of distribution algorithm Multicast Network function virtualization Virtual network function placement

来源：评论

学校读者我要写书评

暂无评论

Collaborative Optimization Design for Centralized Networked Control System

引用

IEEE ACCESS 2021年 9卷 19479-19487页

作者： Yan, Xiang Li, Jun Mei, Bizhou Zhejiang Wanli Univ Sch Informat & Intelligence Engn Ningbo 315000 Peoples R China Zhejiang Yi Duan Machinery Co Ningbo 315000 Peoples R China

This paper proposes a collaborative optimization design for a kind of centralized networked control system based on jitter. After the analysis of the network delay and jitter on the performance of the Train Networked Control System (TNCS) based on the MVB (Multifunction Vehicle Bus) network, the proposed strategy modifies the media allocating model of MVB directly related to the performance of the control system. Under the premise of ensuring the stability of the control system, and taking into account the impact of transmission jitter on the dynamic performance of the closed-loop control, this collaborative design method can minimize the network resource occupancy rate of the subsystem. Thus, it can overcome schedule failure in the traditional algorithm that excessively occupies network resources in order to reduce jitter. Finally, the authors present an algorithm based on EDA to find the optimal solution of the proposed strategy and illustrate the effectiveness of the strategy through numerical simulation and experimental tests.

关键词： Delays Control systems Collaboration Stability analysis Jitter Networked control systems Real-time systems Train networked control system jitter estimation of distribution algorithm

来源：评论

学校读者我要写书评

暂无评论

Binary ant colony optimization algorithm in learning random satisfiability logic for discrete hopfield neural network

引用

APPLIED SOFT COMPUTING 2024年 166卷

作者： Gao, Yuan Kasihmuddin, Mohd Shareduwan Mohd Chen, Ju Zheng, Chengfeng Romli, Nurul Atiqah Mansor, Mohd. Asyraf Zamri, Nur Ezlin Chengdu Univ Tradit Chinese Med Sch Med Informat Engn Chengdu 610037 Peoples R China Univ Sains Malaysia Sch Math Sci George Town 11800 Malaysia Univ Sains Malaysia Sch Distance Educ George Town 11800 Malaysia Univ Putra Malaysia Fac Sci Dept Math & Stat Serdang 43400 Selangor Malaysia

This study introduced a novel ant colony optimization algorithm that implements the population selection strategy of the estimation of distribution algorithm and a new pheromone updating formula. It aimed to optimize the performance of G-type random high-order satisfiability logic structures embedded in Discrete Hopfield Neural Networks, thereby enhancing the efficiency of the Hopfield Neural Network learning algorithm. Through comparative analysis with other metaheuristic algorithms, our model demonstrated superior performance in terms of global convergence, time complexity, and algorithm complexity. Additionally, we evaluated the learning phase, retrieval phase, and similarity analysis using various ratios of literals and clauses. It was shown that our proposed model exhibits stronger search ability compared to other metaheuristic algorithms and Exhaustive Search. Our model enhanced the efficiency of the learning phase, resulting in the number of global solutions accounting for 100 %, and significantly improved the global solution diversity. These advancements contributed to the efficiency of the model in convergence, rendering it applicable to a wide range of nonlinear classification and prediction problems.

关键词： Ant colony optimization estimation of distribution algorithm Discrete Hopfield neural network Metaheuristic algorithms Classification

来源：评论

学校读者我要写书评

暂无评论

Neural Architecture Search by estimation of Network Structure distributions

引用

IEEE ACCESS 2021年 9卷 15304-15319页

作者： Muravev, Anton Raitoharju, Jenni Gabbouj, Moncef Tampere Univ Fac Informat Technol & Commun Sci FI-33100 Tampere Finland Finnish Environm Inst Programme Environm Informat FI-40500 Jyvaskyla Finland

The influence of deep learning is continuously expanding across different domains, and its new applications are ubiquitous. The question of neural network design thus increases in importance, as traditional empirical approaches are reaching their limits. Manual design of network architectures from scratch relies heavily on trial and error, while using existing pretrained models can introduce redundancies or vulnerabilities. Automated neural architecture design is able to overcome these problems, but the most successful algorithms operate on significantly constrained design spaces, assuming the target network to consist of identical repeating blocks. While such approach allows for faster search, it does so at the cost of expressivity. We instead propose an alternative probabilistic representation of a whole neural network structure under the assumption of independence between layer types. Our matrix of probabilities is equivalent to the population of models, but allows for discovery of structural irregularities, while being simple to interpret and analyze. We construct an architecture search algorithm, inspired by the estimation of distribution algorithms, to take advantage of this representation. The probability matrix is tuned towards generating high-performance models by repeatedly sampling the architectures and evaluating the corresponding networks, while gradually increasing the model depth. Our algorithm is shown to discover non-regular models which cannot be expressed via blocks, but are competitive both in accuracy and computational cost, while not utilizing complex dataflows or advanced training techniques, as well as remaining conceptually simple and highly extensible.

关键词： Automatic architecture design estimation of distribution algorithm deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A scheduling algorithm for heterogeneous computing systems by edge cover queue

引用

KNOWLEDGE-BASED SYSTEMS 2023年第1期265卷

作者： Chen, Yu-meng Liu, Song -lin Chen, Yan-jun Ling, Xiang Univ Elect Sci & Technol China Natl Key Lab Sci & Technol Commun Chengdu 611731 Sichuan Peoples R China

In heterogeneous computing systems, excellent task scheduling algorithms can shorten the task completion time and improve system parallelism. With the large-scale deployment of edge computing, the task scheduling algorithm in heterogeneous edge computing servers has become a critical factor in improving the overall system performance. This paper proposes a new task scheduling algorithm called the edge cover scheduling algorithm (ECSA), which schedules tasks based on the edge cover queue of the directed acyclic graph (DAG) for heterogeneous computing systems. Based on the estimation of distribution algorithm (EDA) and the graph random walk algorithm, the ECSA generates an edge cover queue from DAG. Then, the ECSA uses the heuristics greedy method with low time and computational complexity to allocate the edge cover queue to processors. Theoretical analysis and simulation results on random DAGs and real-world DAGs show that the ECSA can achieve better scheduling results in terms of makespan, the schedule length ratio (SLR), efficiency, and frequency of best results with low time and computational complexity.(c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Heterogeneous computing system Edge cover queue estimation of distribution algorithm Graph random walk algorithm

来源：评论

学校读者我要写书评

暂无评论

Data-driven topology design using a deep generative model

引用

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION 2021年第3期64卷 1401-1420页

作者： Yamasaki, Shintaro Yaji, Kentaro Fujita, Kikuo Osaka Univ Dept Mech Engn 2-1 Yamadaoka Suita Osaka 5650871 Japan

In this paper, we propose a sensitivity-free and multi-objective structural design methodology called data-driven topology design. It is schemed to obtain high-performance material distributions from initially given material distributions in a given design domain. Its basic idea is to iterate the following processes: (i) selecting material distributions from a dataset of material distributions according to eliteness, (ii) generating new material distributions using a deep generative model trained with the selected elite material distributions, and (iii) merging the generated material distributions with the dataset. Because of the nature of a deep generative model, the generated material distributions are diverse and inherit features of the training data, that is, the elite material distributions. Therefore, it is expected that some of the generated material distributions are superior to the current elite material distributions, and by merging the generated material distributions with the dataset, the performances of the newly selected elite material distributions are improved. The performances are further improved by iterating the above processes. The usefulness of data-driven topology design is demonstrated through numerical examples.

关键词： Data-driven design Topology optimization Deep generative model Sensitivity-free methodology Multi-objective methodology estimation of distribution algorithm

来源：评论

学校读者我要写书评

暂无评论

An evolutionary fuzzy scheduler for multi-objective resource allocation in fog computing

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2021年 117卷 498-509页

作者： Wu, Chu-ge Li, Wei Wang, Ling Zomaya, Albert Y. Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Univ Sydney Ctr Distributed & High Performance Comp Sch Comp Sci Sydney NSW 2006 Australia

With rapid development of the Internet of Things (IoT), a vast amount of raw data produced by IoT devices needs to be processed promptly. Compared to cloud computing, fog computing nodes are closer to data resource for decreasing the end-to-end transmission latency. Considering the limited resource of IoT devices, offloading computationally-intensive tasks to the servers with high computing capability is essential in the IoT-fog-cloud system to complete those tasks on time. In this work, we propose a fuzzy logical offloading strategy for IoT applications characterized by uncertain parameters to optimize both agreement index and robustness. A multi-objective estimation of distribution algorithm (EDA) is designed to learn and optimize the fuzzy offloading strategy from a diversity of the applications. The algorithm partitions applications into independent clusters, so that each cluster can be allocated to the corresponding tier for further processing. Thus, system resources are saved by making scheduling decisions in a reduced search space. Simulation studies on benchmark problems and real-world cases are carried out to verify the efficiency of our proposed algorithm. Pareto sets produced by our algorithm outperformed classic heuristic solutions for 88.3% benchmark cases and dominated Pareto sets of two state-of-art multi-objective algorithms for 92.7% and 94.4% cases correspondingly. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Edge computing Internet of Things Evolutionary computation estimation of distribution algorithm Fuzzy scheduling Agreement index Robustness

来源：评论

学校读者我要写书评

暂无评论

Probabilistic distribution learning algorithm based transmit antenna selection and precoding for millimeter wave massive MIMO systems

引用

TELECOMMUNICATION SYSTEMS 2021年第3期76卷 449-460页

作者： Khalid, Salman Mehmood, Rashid bin Abbas, Waqas Khalid, Farhan Naeem, Muhammad Natl Univ Comp & Emerging Sci NUCES Islamabad Pakistan COMSATS Univ Wah Campus Islamabad Pakistan

In modern day communication systems, the massive MIMO architecture plays a pivotal role in enhancing the spatial multiplexing gain, but vice versa the system energy efficiency is compromised. Consequently, resource allocation in-terms of antenna selection becomes inevitable to increase energy efficiency without having any obvious effect or compromising the system spectral efficiency. Optimal antenna selection can be performed using exhaustive search. However, for a massive MIMO architecture, exhaustive search is not a feasible option due to the exponential growth in computational complexity with an increase in the number of antennas. We have proposed a computationally efficient and optimum algorithm based on the probability distribution learning for transmit antenna selection. An estimation of the distribution algorithm is a learning algorithm which learns from the probability distribution of best possible solutions. The proposed solution is computationally efficient and can obtain an optimum solution for the real time antenna selection problem. Since precoding and beamforming are also considered essential techniques to combat path loss incurred due to high frequency communications, so after antenna selection, successive interference cancellation algorithm is adopted for precoding with selected antennas. Simulation results verify that the proposed joint antenna selection and precoding solution is computationally efficient and near optimal in terms of spectral efficiency with respect to exhaustive search scheme. Furthermore, the energy efficiency of the system is also optimized by the proposed algorithm, resulting in performance enhancement of massive MIMO systems.

关键词： Millimeter wave propagation Hybrid (analog and digital)precoding estimation of distribution algorithm Spectral efficiency Exhaustive search Random search Transmit antenna selection

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

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

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：