检索结果-内蒙古大学图书馆

Service placement strategies in mobile edge computing based on an improved genetic algorithm

PERVASIVE AND MOBILE COMPUTING 2024年 105卷

作者： Zheng, Ruijuan Xu, Junwei Wang, Xueqi Liu, Muhua Zhu, Junlong Henan Univ Sci & Technol Sch Informat Engn Luoyang 471023 Henan Peoples R China

In mobile edge computing (MEC), quality of service (QoS) is closely related to optimizing service placement strategies, which is crucial to providing efficient services that meet user needs. However, due to the mobility of users and the energy consumption limit of edge servers, the existing policies make it difficult to ensure the QoS level of users. In this paper, a novel genetic algorithm based on a simulated annealing algorithm is proposed to balance the QoS of users and the energy consumption of edge servers. Finally, the effectiveness of the algorithm is verified by experiments. The results show that the QoS value obtained by the proposed algorithm is closer to the maximum value, which has significant advantages in improving QoS value and resource utilization. In addition, in software development related to mobile edge computing, our algorithm helps improve the program's running speed.

关键词： Energy consumption Genetic algorithm nonlinear function approximation Mobile edge computing Service placement

来源：评论

学校读者我要写书评

暂无评论

A novel self-constructing Radial Basis function Neural-Fuzzy System

引用

APPLIED SOFT COMPUTING 2013年第5期13卷 2390-2404页

作者： Yang, Ying-Kuei Sun, Tsung-Ying Huo, Chih-Li Yu, Yu-Hsiang Liu, Chan-Cheng Tsai, Cheng-Han Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei 106 Taiwan Natl Dong Hwa Univ Dept Elect Engn Hualien Taiwan QNAP Syst Inc Taipei Taiwan Getac Technol Corp Taipei Taiwan

This paper proposes a novel self-constructing least-Wilcoxon generalized Radial Basis function Neural-Fuzzy System (LW-GRBFNFS) and its applications to non-linear function approximation and chaos time sequence prediction. In general, the hidden layer parameters of the antecedent part of most traditional RBFNFS are decided in advance and the output weights of the consequent part are evaluated by least square estimation. The hidden layer structure of the RBFNFS is lack of flexibility because the structure is fixed and cannot be adjusted effectively according to the dynamic behavior of the system. Furthermore, the resultant performance of using least square estimation for output weights is often weakened by the noise and outliers. This paper creates a self-constructing scenario for generating antecedent part of RBFNFS with particle swarm optimizer (PSO). For training the consequent part of RBFNFS, instead of traditional least square (LS) estimation, least-Wilcoxon (LW) norm is employed in the proposed approach to do the estimation. As is well known in statistics, the resulting linear function by using the rank-based LW norm approximation to linear function problems is usually robust against (or insensitive to) noises and outliers and therefore increases the accuracy of the output weights of RBFNFS. Several nonlinear functions approximation and chaotic time series prediction problems are used to verify the efficiency of self-constructing LW-GRBFNIS proposed in this paper. The experimental results show that the proposed method not only creates optimal hidden nodes but also effectively mitigates the noise and outliers problems. (C) 2013 Elsevier B. V. All rights reserved.

关键词： Radial Basis function Neural-Fuzzy System (RBFNFS) Self-constructing Least-Wilcoxon norm nonlinear function approximation Chaotic time series prediction Outliers

来源：评论

学校读者我要写书评

暂无评论

approximation bounds of three-layered neural networks - A theorem on an integral transform with ridge functions

引用

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE 1996年第3期79卷 23-33页

作者： Murata, N Member Faculty of Engineering the University of Tokyo Bunkyo-ku Tokyo Japan 113

Neural networks have attracted attention due to their capability to perform nonlinear function approximation. In this paper, in order to better understand this capability, a new theorem on an integral transform was derived by applying ridge functions to neural networks. From the theorem, it is possible to obtain approximation bounds which clarify the quantitative relationship between the function approximation accuracy and the number of nodes in the hidden layer. The theorem indicates that the approximation accuracy depends on the smoothness of the target function. Furthermore, the theorem also shows that this type of approximation method differs from usual methods and is able to escape the so-called ''curse of dimensionality,'' in which the approximation accuracy depends strongly of the input dimension of the function and deteriorates exponentially.

关键词： nonlinear function approximation ridge functions integral transform neural networks curse of dimensionality

来源：评论

学校读者我要写书评

暂无评论

A data-driven implicit deep adaptive neuro-fuzzy inference system capable of manifold learning for function approximation

引用

APPLIED SOFT COMPUTING 2024年 155卷

作者： Salimi-Badr, Armin Shahid Beheshti Univ Fac Comp Sci & Engn Tehran Iran

Fuzzy Neural Networks (FNN) have the ability of decision-making based on constructing semi-ellipsoidal clusters in the input space as the antecedent parts of their fuzzy rules. To determine the output value for each input instance, FNNs consider its membership degree to different sub-regions of the input space. However, forming such meaningful sub-regions is not possible in all applications due to the nonlinear interactions among input variables and their low information gain. Indeed, the samples could be distributed on a manifold in the input space. Therefore, to cover the input space, we need lots of rules, each representing a small region of input space. This issue decreases the generalization ability of the model along with its explainability. Consequently, to efficiently form fuzzy rules, first, it is necessary to unfold the manifold by mapping the samples to an appropriate embedding space. Next, the fuzzy rules in the form of semi-ellipsoidal regions should be constructed in this extracted feature space. Deep Fuzzy Neural Networks address this problem by representation learning through stacking multiple cascade mapping layers. In this paper, we propose a novel approach for nonlinear function approximation and time-series prediction problems, based on using the kernel trick to implicitly learn the mapping function to the new feature space. Moreover, to initialize the fuzzy rules, a KNN-based method using the kernel trick is proposed. A hierarchical Levenberg-Marquardt approach is applied to learn the model's parameters. The performance and structure of the proposed method are studied and compared with some other relevant methods in synthetic and real-world benchmarks. Based on these experiments, the proposed method has the best performance with the most parsimonious architecture. According to these experiments, the test RMSE of the proposed method is 0.002 for Mc-Glass chaotic time-series prediction, 0.015 for a nonlinear dynamic system identification, 0.0345 f

关键词： Kernel trick Manifold learning Fuzzy neural networks Representation learning nonlinear function approximation

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement of Direct Torque Control System Based on Dynamic Parameter Identification Technology

Performance Improvement of Direct Torque Control System Base...

引用

21st Chinese Control and Decision Conference

作者： Liu Hua Zhao Wei Li Zhanfeng Hebei Univ Engn Handan 056038 Peoples R China

ISBN: (纸本)9781424427239

In traditional direct torque control system, the torque and flux are directly controlled by means of optimum voltage vectors, where the stator resistance variation deteriorates the dynamic performance. It is necessary to improve estimation accuracy for stator flux and torque. Considering the effects of the stator resistance variation on direct torque control, a novel approach of stator resistance identification based on wavelet network is presented for dynamic performance in low speed status, optimizing the inverter control strategy. The wavelet transform decomposes the signal using dilated and translated wavelets in time-frequency domain into a series of correlation factors or wavelet coefficients. The wavelet network combines the mathematical feature of wavelet transform with learning scheme of conventional neural network into an organic unit, which has been applied to nonlinear function approximation and dynamical system modeling. The improved training algorithm is utilized to fulfill the network parameter initialization, increasing the network stabilization and convergence property. Therefore, the stator voltage vector can be obtained from the stator resistance identification result of wavelet network output, reducing the number of voltage sensors. The simulation results show that the steady state and dynamic performance was improved.

关键词： Torque and flux voltage vector resistance variation wavelet network optimization strategy nonlinear function approximation system modeling

来源：评论

学校读者我要写书评

暂无评论

Temperature Error Compensation for Open-Loop Fiber Optical Gyro using Back-Propagation Neural Networks with Optimal Structure

Temperature Error Compensation for Open-Loop Fiber Optical G...

引用

2014中国制导、导航与控制学术会议

作者： Limei Song Wei Zhang AVIC XI''AN Fight Automatic Control Research Institute Xi''an710065 China Delegation of Air ForceXi''an710065 China

ISBN: (纸本)9781479946983

Open-Loop Fiber Optic Gyroscopes (FOG) is widely used,which is easily affected by the temperature around *** temperature model has a very complicated nonlinear characteristic.A BP neural network model with advantage of approximating the nonlinear function was developed to simulate outputs of an open-loop FOG and then compensate the FOG's temperature error in full temperature range??–50??~ +70????.With experimental data,the networks with one-hidden-layer structure adopted the temperature and the temperature change rate as network inputs,and the outputs of FOG as network *** results showed that the number of hidden-layer neurons plays an important role in simulation performance,and the network with 11 hidden-layer neurons offered better precision and ***,the comparison of 4 different training algorithms demonstrated that the Levenberg-Marquardt algorithm resulted in a better convergence during training *** the chosen structure and training algorithm,the BP neural network model was used to compensate the temperature error of the *** was found that the compensated outputs of the FOG became more accurate and more *** addition,the neural network model further proved its superiority of precision and robustness by comparison with a multiple linear regression model and a quadratic curve fitting model.

关键词： backpropagation computerised instrumentation curve fitting error compensation fibre optic gyroscopes neural nets regression analysis BP neural network model FOG Levenberg-Marquardt algorithm backpropagation neural network model hidden-layer neuron multiple linear regression model nonlinear function approximation one-hidden-layer structure open-loop fiber optical gyroscope optimal structure quadratic curve fitting model temperature error compensation training algorithm Biological neural networks Neurons Stability analysis Temperature distribution Temperature measurement Thermal stability Training

来源：评论

学校读者我要写书评

暂无评论

An Improved Cobb-Douglas Production function and Its Artificial Neural Network Model

An Improved Cobb-Douglas Production Function and Its Artific...

引用

2012 International Conference on Electrical and Computer Engineering(ICECE2012)

作者： Jihong Shen 1,Canxin Zhang 2,Hao Hu 1 and Chunbo Lian 1 1 College of Science,Harbin Engineering University,Harbin 150001,P.R.China2 College of Automation,Harbin Engineering University,Harbin 150001,P.R.China

For the problem of economic growth,the Cobb-Douglas(CD) production function is deformed by putting the labor and capital input into the three industries,and then a new production function is created by furtherly improving the *** artificial neural network(ANN) model is also established to simulate the new production *** model can present the economic growth factors,and it can also reflect the highly nonlinear internal relations among industrial structures by simulation of the relations between input elements and total *** show that the results given by this model are reliable and the artificial neural network algorithm is easy to *** model can be widely applied in economic problems.

关键词： Artificial neural network nonlinear function approximation Production function Economic growth.

来源：评论

学校读者我要写书评

暂无评论

An Improved Cobb-Douglas Production function and its Artificial Neural Network Model

An Improved Cobb-Douglas Production Function and its Artific...

引用

2011 International Conference on Fuzzy Systems and Neural Computing(FSNC 2011)

作者： Jihong Shen Canxin Zhang Hao Hu Chunbo Lian College of Science Harbin Engineering University College of Automation Harbin Engineering University

For the problem of economic growth,the CobbDouglas(CD)production function is deformed by putting the labor and capital input into the three industries,and then a new production function is created by furtherly improving the *** artificial neural network(ANN)model is also established to simulate the new production *** model can present the economic growth factors,and it can also reflect the highly nonlinear internal relations among industrial structures by simulation of the relations between input elements and total *** show that the results given by this model are reliable and the artificial neural network algorithm is easy to *** model can be widely applied in economic problems.

关键词： Artificial neural network nonlinear function approximation Production function Economic growth.

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：