检索结果-内蒙古大学图书馆

Multimodal Optimization of Edge Server Placement Considering System Response Time

ACM TRANSACTIONS ON SENSOR NETWORKS 2023年第1期19卷 13-13页

作者： Zhang, Xinglin Zhang, Jinyi Peng, Chaoqun Wang, Xiumin South China Univ Technol Sch Comp Sci & Engn 382 Huandong Rd Guangzhou Guangdong Peoples R China

Mobile edge computing (MEC) deploys computing and storage resources close to mobile devices, enabling resource demanding applications to run on mobile devices with short network latency. In the past few years, large numbers of research works focused on the research hotspots in MEC, such as computation offloading and energy efficiency. However, few researchers have investigated the deployment of edge servers. On the one hand, blindly deploying numerous edge servers will result in a large amount of capital expenditure. On the other hand, the deployment of edge servers is a multimodal problem that should provide decision makers with multiple deployment options to deal with the impact of unmeasured real-world factors. Considering these factors, we study the multimodal optimization problem of edge server placement (MESP) with the goal of minimizing the average system response time in this work. Regarding the difficulty of the MESP problem, we propose a heuristic algorithm that combines particle swarm optimization and niching technology to obtain a set of competitive placement solutions. Extensive experiments over a real-world dataset show that the proposed algorithm can significantly reduce the system response time.

关键词： Mobile edge computing multimodal optimization particle swarm algorithm server placement problem

来源：评论

学校读者我要写书评

暂无评论

Research on the application of traditional culture in landscape design

引用

APPLIED MATHEMATICS AND NONLINEAR SCIENCES 2023年第1期8卷 3203-3216页

作者： Liu, Zhihong Hunan Vocat & Tech Coll Environm Biol Hengyang 421005 Hunan Peoples R China

In order to make the landscape design concept break through the traditional barriers and achieve diversification and nationalized development, this paper proposes a landscape design model that integrates traditional culture to effectively integrate traditional culture and landscape design. First use active adaptation technology to test the algorithm convergence ability, and then sample the basic situation of landscape design, reconstruct the collected information, construct the characteristic information flow, and use the linear regression analysis model and the Internet of Things technology to construct the distribution The structure model is used to analyze its characteristics. Then, by introducing the nonlinear dynamic inertia weight coefficient, according to the traditional particle swarm algorithm, the optimized particle swarm algorithm is proposed, and its robustness is tested, the error is analyzed, and the error values are all less than ***, the model in this paper is experimentally tested in a quantitative way. The results show that the traditional culture and landscape design fusion model proposed in this paper has a reasonable error value and has practical application significance.

关键词： Traditional culture Landscape design particle swarm algorithm Linear regression analysis Weight coefficient

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Diagnosis Based on Optimised Stacked Auto-Encoders and Fractional-order Gradient Descent with Momentum BP Neural Network

Bearing Fault Diagnosis Based on Optimised Stacked Auto-Enco...

引用

第43届中国控制会议

作者： Xinyi Lei Sai Li Zhixia Ding Le Yang Yong Zhang School of Electrical and Information Engineering Wuhan Institute of Technology Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Wuhan University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The health condition of bearings determines whether mechanical equipment can operate normally,and it is very important for bearings to carry out timely fault identification and *** process of bearing diagnosis can be improved mainly from feature extraction and fault classification *** this paper,an innovative approach for feature selection and fault diagnosis is proposed,utilizing a bearing fault diagnosis method that employs an optimized stacked auto-encoder combined with a momentum fractional-order BP neural *** approach firstly uses stacked auto-encoder optimised by particle swarm algorithm to select the deep features in time and frequency domains respectively,and then fuses the selected deep features to build the fault feature ***,in order to solve the problem of slow convergence speed of traditional BP neural network,a momentum fractional order BP neural network is established to achieve fault *** results from the experiments indicate that the developed approach exhibits a notable advancement in characterizing bearing features,and enhanced classification accuracy and efficiency.

关键词： Fault Diagnosis Auto-Encoder particle swarm algorithm Fractional-order gradient Momentum gradient

来源：评论

学校读者我要写书评

暂无评论

Modeling and control method of combined heat and power plant with integrated hot water storage tank

引用

APPLIED THERMAL ENGINEERING 2023年第1期226卷

作者： Wang, Di Han, Xinrui Li, Haoyu Li, Xiaoli Northeast Elect Power Univ Sch Automat Engn Jilin Peoples R China Northeast Elect Power Univ Sch Energy & Power Engn Jilin Peoples R China Shenzhen Machinery Inst Architectural Design Co Lt Shenzhen Peoples R China

To enhance the flexibility of conventional power plants, a dynamic mathematical model of a combined heat and power unit is developed and verified in this study using field data, and the maximum relative error is less than 5%. Subsequently, the dynamic characteristics of the coal-fired power plant with the hot water storage tank are studied, and the temperature distribution curve inside the hot water storage tank is obtained. Finally, a new coordinated control system with an integrated hot water storage tank is designed. The new coordinated control system reduces the fluctuation in the heating load caused by the unit in the process of changing the load. The integral of absolute value of the error criterion and integral of time multiplied by the squared error criterion results for unit loads at different variable load rates are at least 200 and 50,000 lower compared to conventional control methods. This study provides a new solution to the problem that the current conventional turbine and boiler coordinated control system cannot address the difficulty of renewable energy power consumption, which is important for the safe and stable power grid operation after the large-scale grid connection of renewable energy power.

关键词： Mechanism model Combined heat and power unit Hot water storage tank Flexibility particle swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Current sharing optimization of multilayer high temperature superconducting cable

引用

PHYSICA C-SUPERCONDUCTIVITY AND ITS APPLICATIONS 2023年第1期611卷

作者： Wang, Lina Liu, Jun Sun, Dong Li, Wei Xu, Hongguang Working Stn Postdoctoral Sci Res Shengli Oil Adm Dongying 257000 Peoples R China SINOPEC Tech Inspection Ctr Shengli Oilfield Co Dongying 257000 Peoples R China Shengli Oil Adm Dongying 257000 Peoples R China Petr Engn Technol Res Inst Shengli Oilfield Co SINOPEC Dongying 257000 Peoples R China

Large-capacity high-temperature superconducting (HTS) cables generally adopt a multilayer structure to increase the current-carrying capacity. However, the multilayer structure of the HTS cables will increase the uneven current distribution, decreasing the critical current and heighten the AC loss. Therefore, the current sharing technology between each layer of the HTS cable is essential to improve transmission performance. This paper proposes two hybrid HTS current sharing optimization algorithms based on particle swarm optimization and artificial bee colonies. The current distribution of the HTS cable in each layer under pre-and post-optimization is estimated and the structure parameters are obtained. A 3D model is established to evaluate the characteristics of the optimized HTS cable. The results show that the proposed hybrid current sharing optimization schemes can well improve the inner current sharing of the HTS cable, and the feasibility and effectiveness are therefore demonstrated.

关键词： High -temperature superconductor HTS tape particle swarm algorithm Artificial bee colony algorithm Hybrid algorithm HTS current sharing

来源：评论

学校读者我要写书评

暂无评论

Research on interval multi-objective optimal power flow in AC-DC systems considering wind power fluctuation

引用

WIND ENGINEERING 2021年第6期45卷 1587-1600页

作者： Zhang, Hongfen Zhang, Youchao GuiZhou Vocat Technol Coll Elect & Informat Kaili Guizhou Peoples R China

Aiming at the influence of the uncertainty of power system operating parameters such as wind power fluctuation on AC-DC hybrid system, an interval optimal power flow calculation method based on interval and affine arithmetic is proposed in this paper. First, AC and DC interval power flow model is constructed based on the relationship between interval and affine arithmetic, and the uncertainties such as the new energy generation output of the system are expressed as interval variables;static security performance index (PI) is introduced in AC-DC multi-objective optimal power flow objective functions, which take the system's power generation cost and network loss into account;the Pareto optimal solution set is distributed uniformly in space by using the particle swarm algorithm to solve the interval optimal power flow model. Finally, MATLAB simulation examples are used to verify that the method can optimize the system's power generation cost, network loss and static safety index while considering wind power fluctuation.

关键词： AC-DC hybrid system interval optimal power flow wind power fluctuation PI sensitivity particle swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Optimal Preventive Control Model Incorporating Transient Stability Constraints in the Presence of Multi-Resource Uncertainties

引用

PROCESSES 2023年第8期11卷 2258页

作者： Ni, Qiulong Sun, Jingliao Zha, Xianyu Zhou, Taibin Sun, Zelun Zhao, Ming State Grid Zhejiang Elect Power Co Ltd Hangzhou 310000 Peoples R China State Grid Wenzhou Elect Power Supply Co Wenzhou 325000 Peoples R China NARI Grp Corp State Grid Elect Power Res Inst Nanjing 210000 Peoples R China

The volatility and uncertainty introduced by increasingly integrated renewable energy pose challenges to the reliable and stable operation of the power system. To mitigate the operation risks, a two-stage optimal preventive control model that incorporates transient stability constraints and considers uncertainties from multiple resources is proposed. First, the uncertainties of different re-sources are modeled, with which the non-sequential Monte Carlo sampling method is used to correspondingly generate the scenarios. Thereafter, a two-stage control model that balances operational safety and economy and realizes preventive control and emergency control is built. The operation schedule from the preventive control stage aims to minimize the transient stability probability and operation costs. If any faults destabilize the system, the emergency control stage will be activated immediately to help the system recover stability with minimal control costs. To expedite the solving of the two-stage model, a multi-objective particle swarm algorithm based on entropy-TOPSIS is proposed. Finally, the effectiveness of the proposed model and solving algorithm are validated with the modified IEEE118 node system.

关键词： preventive control transient stability constraints multi-resource uncertainties two-stage model particle swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

OPTIMAL REGULATION MODEL OF INTEGRATED ENERGY SYSTEM CONTAINING HYDROGEN STORAGE CONSIDERING ELECTROTHERMAL COUPLING

引用

INTERNATIONAL JOURNAL OF POWER AND ENERGY SYSTEMS 2023年第10期43卷 1页

作者： Wei, Xuan China Elect Power Res Inst Beijing Key Lab Demand Side Multi Energy Carriers Beijing 100192 Peoples R China Nanchang Univ Sch Informat Engn Nanchang 330031 Peoples R China

As an important way to improve energy efficiency, IES plays a key role in promoting sustainable development of energy. In order to optimise the regulation effect of hydrogen storage IES, from the perspective of electrothermal coupling, the optimisation regulation model of hydrogen storage IES was constructed, and its effectiveness was tested. The results show that under this control strategy, the consumption of wind power, photovoltaic power, and hydrogen power generation is maintained in the range of 2,500-3,500 kWh, 1,500-2,500 kWh, and 3,500-4,500 kWh, respectively. Compared with the control strategy without considering the electric heating coupling, the coal consumption per unit time under this method is reduced by 40-80 J. This shows that the regulation method has improved the consumption of clean energy, greatly reduced coal consumption and economic costs, improved the utilisation rate of clean energy, optimised the regulation effect of IES, and is conducive to promoting the development of renewable energy.

关键词： Electrothermal hydrogen energy storage particle swarm algorithm IES

来源：评论

学校读者我要写书评

暂无评论

Application of hybrid neural network in discharge coefficient prediction of triangular labyrinth weir

引用

FLOW MEASUREMENT AND INSTRUMENTATION 2022年 83卷

作者： Wang, Fei Zheng, Shengyi Ren, Yiming Liu, Weidong Wu, Chao Hohai Univ Coll Energy & Elect Engn 8 Fochengxi Rd Nanjing 211100 Peoples R China Hohai Univ Coll Publ Adm 8 Fochengxi Rd Nanjing 211100 Peoples R China

Discharge coefficient (Cd) is an important parameter of triangular labyrinth weir. It is of great significance to predict the discharge coefficient accurately. In this research, in order to more accurately predict the Cd, in view of the traditional BP neural network is easy to fall into the local minimum in the training process, genetic algorithm (GA) and particle swarm optimization (PSO) are employed to optimize the traditional BP neural network's initial weights and thresholds. Nonlinear regression analysis (NLR) is also added to compare with these intelligent methods and four discharge coefficient prediction models are built, namely the NLR, the BPNN, the GA-BPNN and the PSO-BPNN. After the completion of the model construction, in order to objectively evaluate the performance of these models, the prediction results of these models are compared with the experiment results, and the determination coefficient (R2), the mean absolute error (MAE) and the root mean square error (RMSE) are introduced as the performance indicators to quantify the model performance. The results show that the accuracy and stability of the NLR are much worse than that of the intelligent models. The prediction results of the GABPNN and the PSO-BPNN are quite accurate with a higher decision coefficient than the BPNN. Moreover, the MAEs and the RMSEs of the GA-BPNN and the PSO-BPNN were significantly reduced by 25 and 40% compared with BPNN, respectively, and the maximum prediction errors were 4.4% and 2.6%, severally. Meanwhile, the width of error uncertainty band of GA-BPNN and PSO-BPNN is narrower than BPNN. By comparing GA-BPNN and PSO-BPNN with the discharge coefficient prediction models of triangular labyrinth weir in previous literatures, it is found that the mean absolute percentage error (MAPE) values of GA-BPNN and PSO-BPNN are 1.504% and 1.225% respectively, which are lower than other existing models. At the same time, the other performance indexes are better than most existing model

关键词： Discharge coefficient Genetic algorithm particle swarm algorithm Triangular labyrinth weir Neural network

来源：评论

学校读者我要写书评

暂无评论

Magnetic Target Localization Correction Based on Variance Weight Distribution of Eigenvalue

Magnetic Target Localization Correction Based on Variance We...

引用

IEEE International Magnetic Conference (INTERMAG)

作者： Xie, D. Qiu, J. Ou, J. D. Wang, Z. Du, J. Z. Xu, Q. Chongqing Univ Key Lab Optoelect & Syst Minist Educ Coll Optoelect Engn Chongqing 400044 Peoples R China

ISBN: (纸本)9780738130996

Magnetic target localization has high application value in the fields of underwater target detection and mineral exploration. To address the problems of limited detection range and blind area of single-point detection method, the detection and positioning method based on the weight distribution correction algorithm is proposed. By designing an algorithm that combines the characteristics of the magnetic field gradient matrix to optimize the distribution of the detection array, the precise regional localization of the target is achieved. Firstly, based on the detection range and the characteristics of the obstacle area, the multi-point detection array is analyzed and the weight distribution correction model is established, then the feasibility of the positioning method is analyzed using experiment data, and finally the detection system is built to conduct positioning experiments on specific target. The results show that the multi-point weight distribution correction localization method can effectively obtain the target location information, and the detection accuracy is improved to a certain extent.

关键词： Magnetic anomaly target localization sensor array optimization particle swarm algorithm Detection reliability weight distribution

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：