检索结果-内蒙古大学图书馆

Next-Generation Edge Computing Assisted Autonomous Driving Based Artificial Intelligence algorithms

IEEE ACCESS 2022年 10卷 53987-54001页

作者： Ibn-Khedher, Hatem Laroui, Mohammed Moungla, Hassine Afifi, Hossam Abd-Elrahman, Emad Capgemini Engn F-75017 Paris France Univ Djillali Liabes Sidi Bel Abbes Comp Sci Dept Sidi Bel Abbes 22000 Algeria Univ Paris Cite Lab Informat Paris Descartes LIPADE F-75006 Paris France Inst Polytech Paris Telecom SudParis F-91764 Palaiseau France Natl Telecommun Inst NTI Cairo 11768 Egypt

Edge Computing and Network Function Virtualization (NFV) concepts can improve network processing and multi-resources allocation when intelligent optimization algorithms are deployed. Multiservice offloading and allocation approaches pose interesting challenges in the current and next-generation vehicle networks. The state-of-the-art optimization approaches still formulate exact algorithms, and tune approximation methods to get sufficient solutions. These approaches are data-centric that aim to use heterogeneous data inputs to find the near optimal solutions. In the context of connected and autonomous vehicles (CAVs), these techniques show an exponential computational time and deal only with small and medium scale networks. Therefore, we are motivated by using recent Deep Reinforcement Learning (DRL) techniques to learn the behavior of exact optimization algorithms while enhancing the Quality of Service (QoS) of network operators and satisfying the requirements of the next-generation Autonomous Vehicles (AVs). DRL algorithms can improve AVs service offloading and optimize edge resources. An Optimal Virtual Edge Autopilot Placement (OVEAP) algorithm is proposed using Integer Linear Programming (ILP). Moreover, an autopilot placement protocol is presented to support the algorithm. Optimal allocation and Virtual Network Function (VNF) placement and chaining of the autopilot, based on several new constraints such as computing and networking loads, network edge infrastructure, and placement cost, are designed. Further, a DRL approach is formulated to deal with dense Internet of Autonomous Vehicle (IoAV) networks. Extensive simulations and evaluations are carried out. Results show that the proposed allocation strategies outperform the state-of-the-art solutions and give better performance in terms of Total Edge Servers Utilization, Total Edge Servers Allocation Time, and Successfully Allocated autopilots.

关键词： Autonomous vehicles Autopilot Servers Sensors Resource management Artificial intelligence optimization Edge computing artificial intelligence autonomous driving optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

XRF Overlapping Spectra Analysis Method Based on a Cascade Equilibrium Optimizer and Trust Region Algorithm

XRF Overlapping Spectra Analysis Method Based on a Cascade E...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Yue, Mohai Zhang, Qi Xin, Xiangjun Gao, Ran Li, Jiajie Rao, Lan Tian, Feng Teng, Yun Wang, Fu Wang, Yongjun Tian, Qinghua Beijing100876 China Beijing100876 China Guangdong University of Technology Guangzhou China Beijing100081 China Beijing Key Laboratory of Space-Ground Interconnection and Convergence BUPT Beijing100876 China

XRF overlapping spectra analysis method based on a cascade equilibrium optimizer and trust region algorithm is proposed to fit overlapping spectra peaks. Experiment results show that performance is better than that of... 详细信息

ISBN: (纸本)9798350379266

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Model-based Gradient Search using the Plackett-Luce model

Model-based Gradient Search using the Plackett-Luce model

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Santucci, Valentino Ceberio, Josu University for Foreigners of Perugia Perugia Italy University of Basque Country San Sebastian Spain

ISBN: (纸本)9798400704956

Computational optimization and optimization algorithms form a cornerstone area of computer science that has been extensively explored due to its myriad applications in many practical and real-world scenarios. At a high level, we can categorize computational optimization algorithms into two main classes: white-box and black-box algorithms. While the former require a certain degree of knowledge about the problem domain, the latter are more versatile and rely solely on basic domain information, such as the structure or representation of a solution. Perhaps, the most prominent examples of white-box algorithms are those which iteratively refine a solution based on the gradient of the objective function at hand. While widely used, particularly in the field of machine learning, these techniques have limited applicability in other domains where gradient information is unavailable. This is the case of Combinatorial optimization Problems (COPs), where the domain consists of discrete solutions and, for this reason, the concept of gradient is not applicable. © 2024 Copyright held by the owner/author(s).

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimized Operation Model of Electro-Hydrogen System Based on Improved Meta-Heuristic Algorithm 4

Optimized Operation Model of Electro-Hydrogen System Based o...

引用

4th International Conference on Electronic Information Engineering and Computer Technology, EIECT 2024

作者： Xiang, Yujin Li, Jitong Liu, Deqi Yin, Xiaojun State Grid Gansu Electric Power Company Jiuquan Power Supply Company Gansu Jiuquan China

ISBN: (纸本)9798331528850

With the increase of clean energy demand, the electro-hydrogen coupling system has gradually become an important way to achieve energy structure optimization due to its potential in power peak shaving, energy storage and fluctuating supply and demand balance. Traditional optimization methods are usually difficult to solve effectively in multi-objective and multi-constraint electro-hydrogen systems, and it is easy to fall into local optimums and slow convergence speeds. In this paper, an optimized operation method of electro-hydrogen coupling system based on improved sparrow search algorithm is proposed. In this paper, the standard sparrow search algorithm is improved by introducing Sinusoidal chaos initialization, information sharing factor and random walk strategy, and the global search ability and local optimization efficiency of the algorithm are enhanced. The improved algorithm excels at the goals of minimizing costs, maximizing energy efficiency, and minimizing carbon emissions. Simulation results show that compared with traditional algorithms, the proposed method has significant advantages in convergence speed, solution distribution and energy efficiency of system operation. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel approach for identification of PV cell model parameters with Grey Wolf Election-Based optimization algorithm

引用

Optik 2025年 320卷

作者： Lidaighbi, Souad Ghiaus, Adrian-Gabriel Elyaqouti, Mustapha Laboratory of Materials Signals Systems and Physical Modeling Faculty of Science Ibn Zohr University Agadir Morocco Thermal Engineering Department Technical University of Civil Engineering of Bucharest Bucharest Romania

In the past few years, photovoltaic production has significantly increased worldwide and has become a necessary element for achieving global agreements to minimize carbon dioxide emissions. Therefore, a precise and reliable simulation of PV panels is of increasing interest to researchers. However, this task is predicated on determining the PV model parameters;thus, it continues to be a highly challenging task. To overcome this challenge, we propose a swarm-based human optimization algorithm, i.e. the Grey Wolf Election-Based optimization algorithm. This new approach combines inventive human behavior in the election process with the powerful search ability of grey wolves. The root-mean-square deviations predicted by the Grey Wolf Election-Based optimization algorithm for a RTC France cell are 7.7386E-04, 7.5644E-04, and 7.4965E-04 for single, double, and triple-diode models, respectively. A total of thirteen of the most cited and newest meta-heuristic algorithms were employed as competitors to adequately assess the performance of the proposed algorithm. The experimental results demonstrate that the proposed algorithm outperformed the compared algorithms and provided more efficient solutions. © 2024 Elsevier GmbH

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Constrained Multi-Modal Multi-Objective Evolutionary Algorithm with Problem Transformation into Two-Objective Subproblems 13

Constrained Multi-Modal Multi-Objective Evolutionary Algorit...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Tokusaka, Teruhiko Masuyama, Naoki Nojima, Yusuke Graduate School of Informatics Osaka Metropolitan University Osaka Japan

ISBN: (纸本)9798350373332

Real-world optimization problems often have multi-ple conflicting objective functions to be optimized simultaneously. In some of them, there are different Pareto optimal solutions with the same objective function values. Those problems are called multi-modal multi-objective optimization problems (MMOPs). For MMOPs, we proposed a decomposition-based multi-modal multi-objective evolutionary algorithm called MM2T in our previous study. However, MM2T does not consider constraints and thus cannot solve constrained MMOPs (CMMOPs). To apply MM2T to CMMOPs, we introduce the constrained dominance principle (CDP) into MM2T. We examine the search performance of MM2T with CDP through computational experiments. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Faster Adaptive Decentralized Learning algorithms 41

Faster Adaptive Decentralized Learning Algorithms

引用

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Feihu Zhao, Jianyu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show superior performances in many machine learning tasks such as training neural networks. Although some works focus on studying decentralized optimization algorithms with adaptive learning rates, these adaptive decentralized algorithms still suffer from high sample complexity. To fill these gaps, we propose a class of faster adaptive decentralized algorithms (i.e., AdaMDOS and AdaMDOF) for distributed nonconvex stochastic and finite-sum optimization, respectively. Moreover, we provide a solid convergence analysis framework for our methods. In particular, we prove that our AdaMDOS obtains a near-optimal sample complexity of Õ(ϵ-3) for finding an ϵ-stationary solution of nonconvex stochastic optimization. Meanwhile, our AdaMDOF obtains a near-optimal sample complexity of O(√nϵ-2) for finding an ϵ-stationary solution of for nonconvex finite-sum optimization, where n denotes the sample size. To the best of our knowledge, our AdaMDOF algorithm is the first adaptive decentralized algorithm for nonconvex finite-sum optimization. Some experimental results demonstrate efficiency of our algorithms. Copyright 2024 by the author(s)

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Direction Estimation for Collaborative Search in MOEA/D

Direction Estimation for Collaborative Search in MOEA/D

引用

2024 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2024

作者： Chen, Jingjing Li, Genghui Lin, Xi Zhang, Qingfu City University of Hong Kong Department of Computer Science Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen China Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798331504755

The decomposition-based multi-objective evolutionary algorithm (MOEA/D) is an efficient framework for solving multi-objective optimization problems. It decomposes a multi-objective optimization problem into a set of single-objective optimization subproblems and solves them collaboratively. However, most MOEA/D variants use heuristic operators to generate new solutions, which might lead to inefficient search performance. Direction estimation is a powerful derivative-free technique for tackling black-box optimization problems. By iteratively estimating valid search directions, this method can efficiently search for the optimal solution in a principled way;yet it suffers from high computational cost since it requires a number of function evaluations to approximate the true gradient. In this work, we leverage the neighborhood structure of MOEA/D and interactions among different subproblems to estimate a promising descent direction. We demonstrate that sharing and exploiting valuable information among neighboring subproblems can significantly reduce the overall computational budget for direction estimation in MOEA/D (MOEA/D-DirE). Experimental results demonstrate that the proposed MOEAD-DirE algorithm outperforms many multi-objective evolutionary algorithms on various multi-objective optimization problems. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Universal Class of Sharpness-Aware Minimization algorithms 41

A Universal Class of Sharpness-Aware Minimization Algorithms

引用

41st International Conference on Machine Learning, ICML 2024

作者： Tahmasebi, Behrooz Soleymani, Ashkan Bahri, Dara Jegelka, Stefanie Jaillet, Patrick MIT CSAIL United States MIT LIDS United States Google DeepMind United Kingdom TU Munich Germany

Recently, there has been a surge in interest in developing optimization algorithms for overparameterized models as achieving generalization is believed to require algorithms with suitable biases. This interest centers on minimizing sharpness of the original loss function;the Sharpness-Aware Minimization (SAM) algorithm has proven effective. However, most literature only considers a few sharpness measures, such as the maximum eigenvalue or trace of the training loss Hessian, which may not yield meaningful insights for non-convex optimization scenarios like neural networks. Additionally, many sharpness measures are sensitive to parameter invariances in neural networks, magnifying significantly under rescaling parameters. Motivated by these challenges, we introduce a new class of sharpness measures in this paper, leading to new sharpness-aware objective functions. We prove that these measures are universally expressive, allowing any function of the training loss Hessian matrix to be represented by appropriate hyperparameters. Furthermore, we show that the proposed objective functions explicitly bias towards minimizing their corresponding sharpness measures, and how they allow meaningful applications to models with parameter invariances (such as scale-invariances). Finally, as instances of our proposed general framework, we present Frob-SAM and Det-SAM, which are specifically designed to minimize the Frobenius norm and the determinant of the Hessian of the training loss, respectively. We also demonstrate the advantages of our general framework through extensive experiments. Copyright 2024 by the author(s)

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparing Solvability Patterns of algorithms across Diverse Problem Landscapes

Comparing Solvability Patterns of Algorithms across Diverse ...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Nikolikj, Ana Eftimov, Tome Jožef Stefan Institute Jozef Stefan International Postgraduate School Ljubljana Slovenia Jožef Stefan Institute Ljubljana Slovenia

ISBN: (纸本)9798400704956

In the field of continuous single-objective black-box optimization, understanding the varying performances of algorithms across different problem instances is crucial. A recent approach based on the concept of "algorithm footprint"identifies both easy and challenging problem instances for an algorithm. However, a major challenge persists - - the lack of comparability among different algorithm footprints for effective benchmarking. This study introduces a solution through a multi-target regression model (MTR), which predicts the performance of multiple algorithms simultaneously, using a common set of problem landscape features. By establishing a common landscape feature set and using a single performance prediction model, not only can algorithm footprints be compared, but the explanations for the predicted algorithm performance derived with Explainable Artificial Intelligence (XAI) techniques can also be analyzed systematically. The methodology is applied to a set of three distinct algorithms, revealing their respective strengths and weaknesses on the Black-Box optimization Benchmarking (BBOB) suite. © 2024 Copyright held by the owner/author(s).

关键词： optimization algorithms

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：