检索结果-内蒙古大学图书馆

A Short-Term Load Forecasting Model with a modified particle swarm optimization algorithm and Least Squares Support Vector Machine Based on the Denoising Method of Empirical Mode Decomposition and Grey Relational Analysis

引用

ENERGIES 2017年第3期10卷 408页

作者： Niu, Dongxiao Dai, Shuyu N China Elect Power Univ Sch Econ & Management Beijing 102206 Peoples R China North China Elect Power Univ Sch Econ & Management Beijing 102206 Peoples R China

As an important part of power system planning and the basis of economic operation of power systems, the main work of power load forecasting is to predict the time distribution and spatial distribution of future power loads. The accuracy of load forecasting will directly influence the reliability of the power system. In this paper, a novel short-term Empirical Mode Decomposition-Grey Relational Analysis-modified particle swarm optimization-Least Squares Support Vector Machine (EMD-GRA-MPSO-LSSVM) load forecasting model is proposed. The model uses the de-noising method combining empirical mode decomposition and grey relational analysis to process the original load series and forecasts the processed subsequences by the algorithm of modified particle swarm optimization and least square support vector machine. Then, the final forecasting results can be obtained after reconstructing the forecasting series. This paper takes the Jibei area as an example to produce an empirical analysis for load forecasting. The model input includes the hourly load one week before the forecasting day and the daily maximum temperature, daily minimum temperature, daily average temperature, relative humidity, wind force, date type of the forecasting day. The model output is the hourly load of the forecasting day. The models of BP neural network, SVM (Support vector machine), LSSVM (Least squares support vector machine), PSO-LSSVM (particle swarm optimization-Least squares support vector machine), MPSO-LSSVM (modified particle swarm optimization-Least squares support vector machine), EMD-MPSO-LSSVM are selected to compare with the model of EMD-GRA-MPSO-LSSVM using the same sample. The comparison results verify that the short-term load forecasting model of EMD-GRA-MPSO-LSSVM proposed in this paper is superior to other models and has strong generalization ability and robustness. It can achieve good forecasting effect with high forecasting accuracy, providing a new idea and reference for accurate s

关键词： short-term load forecasting empirical mode decomposition grey relational analysis modified particle swarm optimization algorithm least square support vector machine

来源：评论

学校读者我要写书评

暂无评论

Micro Evolutionary particle swarm optimization (MEPSO): A new modified metaheuristic

引用

SYSTEMS AND SOFT COMPUTING 2023年 5卷

作者： Solano-Rojas, Braulio J. Villalon-Fonseca, Ricardo Batres, Rafael Univ Costa Rica ECCI CITIC Ciudad Univ Rodrigo FacioSan Pedro Montes De Oca San Jose 11501 Costa Rica Tecnol Monterrey Prolongac Ezequiel Montes Santiago De Queretaro 76140 Queretaro Mexico

This work introduces the algorithm Micro Evolutionary particle swarm optimization (MEPSO), which is based on the particle swarm optimization algorithm (PSO). MEPSO's main idea is to replace PSO's update of velocity with evolutionary mutations and crossovers that occur probabilistically. MEPSO uses two control hyperparameters of the evolutionary operators, alpha and beta, to improve convergence ability. These hyperparameters allow the algorithm to adapt to different problems. MEPSO algorithm has a crucial feature: the use of micropopulations. This results in reduced computational complexity, faster convergence rate, prevention of premature convergence, and easy implementation. The proposed approach provides the basis for further study of MEPSO's suitability for dynamic and multiobjective optimization. We evaluated MEPSO and PSO against 14 chosen benchmark functions. PSO's results revealed that it had an average success rate of 84% and a median computation time of 49.9 s. MEPSO, on the other hand, had a success rate of 81% and a computation time of 8 s. We found MEPSO to be faster when we performed a right-tail Wilcoxon Signed-Rank statistical test against the Mean Computation Time of 30 runs for each function for each algorithm.

关键词： swarm intelligence modified particle swarm optimization algorithm Evolutionary computing

来源：评论

学校读者我要写书评

暂无评论

Energy-optimization Route and Cluster Head Selection Using M-PSO and GA in Wireless Sensor Networks

引用

WIRELESS PERSONAL COMMUNICATIONS 2024年 1-26页

作者： Prakash, Ved Singh, Deepti Pandey, Suman Singh, Samayveer Singh, Pradeep Kumar Kamla Nehru Inst Technol Sultanpur Uttar Pradesh India Netaji Subhas Inst Technol New Delhi India Natl Inst Technol Dept CSE Jalandhar Punjab India Cent Univ Jammu Dept CS & IT Jammu J&K India

Wireless sensor network (WSN) clustering techniques play a crucial role in extending the network's lifespan through various methods. In WSN, the clustering techniques elect the best cluster heads (CHs) among the deployed sensor nodes in terms of their computational, energy, and link capabilities. The CHs nodes expend more energy than other sensor nodes due to a heavier workload, such as receiving messages from their cluster members and other cluster heads, aggregating all messages, and transmitting them to the base station with the help of non-cluster head nodes in the layered sensor network. Thus, there is a dire need to develop an efficient CHs election algorithm. In this paper, the modified particle swarm optimization (M-PSO) method, along with the Genetic algorithm (GA), is considered for selecting cluster heads and non-cluster heads. The proposed method computes the probability of choosing the best nodes as cluster heads, and the GA is employed to discover the optimum shortest path. The selection of the optimum route is based on the employed objective function. Additionally, the proposed method demonstrates superior performance compared to existing state-of-the-art techniques such as GAPSO-H, EC-PSO, and NEST. However, DMPRP performs 12% better than NEST, EC-PSO, and GAPSO-H overall.

关键词： Clustering Crossover Genetic algorithm modified particle swarm optimization algorithm Wireless sensor network Mutation

来源：评论

学校读者我要写书评

暂无评论

A modified particle swarm optimization algorithm with applications

引用

APPLIED MATHEMATICS AND COMPUTATION 2012年第3期219卷 1053-1060页

作者： He, Guang Huang, Nan-jing Sichuan Univ Dept Math Chengdu 610064 Sichuan Peoples R China

In this paper, firstly a modified particle swarm optimization algorithm (MPSO) is developed, in which the mean value of past optimal positions for each particle and the mutation operation are considered for avoiding premature. In the optimization test, MPSO performs better than particle swarm optimization algorithm (PSO). Then MPSO is applied to solve four portfolio optimization models with the real data from the Hong Kong Stock Market, and optimal values are obtained when the number of swarm n = 80;160, respectively. Finally, actual return rates of these models are calculated in numerical experiments, and it is illustrated from these graphs of actual return rates that when considering higher return, Cai's model performs better in short-term investment. (C) 2012 Elsevier Inc. All rights reserved.

关键词： modified particle swarm optimization algorithm Mutation operation Optimal position Portfolio optimization model Actual return rate Numerical experiment

来源：评论

学校读者我要写书评

暂无评论

modified particle swarm algorithm for scheduling agricultural products

引用

ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH 2021年第3期24卷 818-828页

作者： Khalid, Qazi Salman Azim, Shakir Abas, Muhammad Babar, Abdur Rehman Ahmad, Imran Univ Engn & Technol Dept Ind Engn POB 814 Peshawar Kpk Pakistan

Industries tend to manufacture higher quality products with a low cost due to the competitive environmental loop and dynamic customers' demand. The integration of intelligent manufacturing planning to agricultural operations and products will permit a spike in efficiency of yield, especially in the regions of agriculturally based economies. Though, to gain a vivid exploitation, the old-fashioned agriculture products manufacturing planning and scheduling techniques needs to be revised, especially the methodology in job shop planning must be augmented with efficient operational sequential scheduling. Cellular Manufacturing Systems (CMS) inclined to possess a higher complexity than the traditional manufacturing systems. Three major problems are coping in CMS domain: cell formation, product family selection, and product scheduling. This work deals with the problem of product scheduling in the CMS environment. A mixed integer linear programming mathematical model is introduced for the conflicting performance measures i.e. minimization of work in process (WIP) and maximization of average machine cell utilization. Since the current problem is considered as NP-hard problem, so a modified particle swarm optimization (MPSO) algorithm is proposed to find the optimum scheduling under the given constraint model of conflicting objectives. In the proposed MPSO, basic PSO is integrated with NEH heuristic to achieve better optimal sequence in less computation time. The obtained results are compared with other hybrid PSO algorithms with seed solutions from Gupta and Palmer heuristics. Furthermore, results are also compared against meta-heuristics such as genetic algorithm (GA), standard PSO, and artificial bee colony (ABC) algorithm. It shows that the proposed MPSO algorithm performs better than the existing compared algorithms. A real time case scenario of agriculture-based manufacturing industry is solved to validate the proposed planning algorithm. (C) 2021 Karabuk University. Pub

关键词： Intelligent agri-manufacturing Cellular manufacturing system Work in process Machine cell utilization modified particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Fault Location Method in Active Distribution Network Based on Voltage Information of PQMS 4

Fault Location Method in Active Distribution Network Based o...

引用

4th International Conference on Smart Power and Internet Energy Systems (SPIES)

作者： Liu, Boliang Xiang, Jiawei Xia, Kai Xu, Yiqing Cheng, Jinmin Bao, Aixia State Grid Jiangsu Elect Power Co Ltd Nanjing 210009 Peoples R China East China Elect Power Design Inst Co Ltd China Power Engn Consulting Grp Shanghai 200001 Peoples R China

ISBN: (纸本)9781665489577

In this paper, by establishing the Low Voltage Ride Through (LVRT) fault output model of Inverter Interfaced Distributed Generation (IIDG), the voltage information of the power quality detection device (PQMS) is used to establish the fault. Based on the location evaluation function, a new fault location method for an inverter-type DG distribution network is proposed. Firstly, the paper studies the low-voltage ride-through control strategy of inverter DG, establishes the fault characterization model of inverter DG, and analyzes the output characteristics under symmetrical and asymmetrical fault conditions. Then use the distribution network model with inverter type DG to analyze the fault characteristics under different fault conditions. By analyzing the fault component network, the equation of the node voltage with respect to the fault distance and the transition resistance is established, and the precise fault distance is solved by the improved particle swarm optimization algorithm. The method considers the influence of DG output characteristics on fault location of distribution network under fault conditions. Using the voltage information of PQMS, it solves the fault location problem of inverter DG active distribution network under low voltage ride through operation. Finally, an IEEE33 distribution network simulation system with inverter DG is built in DigSilent software to verify the effectiveness and accuracy of the proposed method.

关键词： Inverter interfaced distributed generation voltage information active distribution network modified particle swarm optimization algorithm fault location

来源：评论

学校读者我要写书评

暂无评论

Structural optimization strategy of pipe isolation tool by dynamic plugging process analysis

引用

Petroleum Science 2021年第6期18卷 1829-1839页

作者： Ting-Ting Wu Hong Zhao Bo-Xuan Gao Fan-Bo Meng College of Mechanical and Transportation Engineering China University of PetroleumBeijing102249China

During the pipeline plugging process,both the pipeline and the pipe isolation tool(PIT)will be greatly damaged,due to the violent vibration of the flow *** this study,it was proposed for the first time to reduce the vibration of the flow field during the plugging process by optimizing the surface structure of the ***,the central composite design(CCD)was used to obtain the optimization schemes,and the drag coefficient and pressure coefficient were proposed to evaluate the degree of flow field ***,a series of computational fluid dynamics(CFD)simulations were performed to obtain the drag coefficient and pressure coefficient during dynamic *** the mathematical model of drag coefficient and pressure coefficient with the surface structure of the PIT were established ***,a modified particle swarm optimization(PSO)was applied to predict the optimal value of the surface structure of the ***,an experimental rig was built to verify the effectiveness of the *** results showed that the improved method could reduce the flow field vibration by 49.56%.This study provides a reference for the design of the PIT surface structure for flow field vibration technology.

关键词： Pipe isolation tool Dynamic analysis Drag coefficient Pressure coefficient modified particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A modified particle swarm algorithm for Solving Group Robotics Problem

A Modified Particle Swarm Algorithm for Solving Group Roboti...

引用

International Symposium on Computer Science, Digital Economy and Intelligent Systems (CSDEIS)

作者： Liang, Kang Karpenko, A. P. Shanghai Polytech Univ Jin Hai Rd 2360 Shanghai 201209 Peoples R China Bauman Moscow State Tech Univ Ul Baumanskaya 2 Ya 5-1 Moscow 10005 Russia

ISBN: (纸本)9783030392161;9783030392154

The paper proposes modifications of the PSO+ global optimization algorithm, which is based on the canonical particle swarm algorithm (PSO). The PSO+ algorithm is designed to solve the group robotics problem that comes down to the localization of the global extremum of a certain scalar objective function when there are no obstacles for robots' movement. The PSO+ algorithm modifications proposed in the paper make allowance for a possibility that such obstacles are present. The paper objective is to study the obstacles effect on the efficiency of the modified PSO+ algorithm. We consider two possible options of the problem: a priori information about the obstacle sizes and locations is available and specified prior information is non-available. The results of computational experiments to study the effectiveness of the modified PSO+ algorithm is presented. The experimental results show that the modification of the PSO+ algorithm proposed in the work provides a high quality solution to the considered task of group robotics under conditions when there is an obstacle to the movement of robots in the search area.

关键词： Group robotics modified particle swarm optimization algorithm Global optimization

来源：评论

学校读者我要写书评

暂无评论

Study on modified particle swarm optimization for indoor lighting control

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2018年第3期18卷 645-653页

作者： Yang, Ping Chun, Jiang-Feng Shaanxi Univ Sci & Technol Coll Elect & Informat Engn Xian 710021 Shaanxi Peoples R China

In order to simultaneous meet the requirements of indoor lighting comfort and minimum energy consumption, the intelligent control strategy is studied, which apply the natural light and best combination of lighting lamps in the indoor lighting. The modified particle swarm optimization (PSO) algorithm is introduced. The system combines natural light with artificial lighting. The comfort function is established in the system. The particle swarm optimization algorithm with constraint condition is used to search the best brightness combination of lighting equipment. At last, the goal of energy saving can be achieved while meeting the comfort and personalized needs of the staff. The MATLAB simulation results show that the modified PSO can avoid the local optimal solution in the optimization. Finally, the experimental platform of indoor lighting system is built, and the effectiveness of the control strategy is verified. The calculation shows that the energy consumption of one day is about 47%, and it has good energy saving effect.

关键词： modified particle swarm optimization algorithm comfort function indoor lighting control strategy

来源：评论

学校读者我要写书评

暂无评论

A modified PSO assisted blind modulation format identification scheme for elastic optical networks

引用

OPTICS COMMUNICATIONS 2020年 476卷 126280-126280页

作者： Yu, Xinkuo Bai, Chenglin Xu, Hengying Sun, Weibin Yang, Lishan Zheng, Hongjun Hu, Weisheng Shandong Prov Key Lab Opt Commun Sci & Technol Liaocheng 252000 Shandong Peoples R China Liaocheng Univ Sch Phys Sci & Informat Engn Liaocheng 252000 Shandong Peoples R China Shanghai Jiao Tong Univ State Key Lab Adv Opt Commun Syst & Networks Shanghai 200240 Peoples R China

By using a modified particle swarm optimization (M-PSO) design, a novel and blind modulation format identification (MFI) scheme was proposed for elastic optical networks (EONs) in this study. Compared with the traditional PSO algorithm, the sight of each particle in our M-PSO algorithm was strictly restricted to perform search of local extremum points (LEPs) on density distribution histograms (DDHs). In the experiment, the distributions of LEPs on DDHs depended on signals' modulation formats, and then were regarded as the key identification metric. The proposed MFI scheme did not need prior information of optical signal noise rate (OSNR) in the identification processes, and showed a natural resistance to frequency offset and line width. The feasibility of the proposed scheme was verified by 28 GBaud polarization division multiplexing (PDM)-BPSK/QPSK/8QAM/16QAM transmission system, where the simulation results showed that the lowest OSNRs required to achieve 100% identification rate were all lower than their corresponding 7% forward error correction (FEC) thresholds (BER=3.8e-3). Furthermore, the tolerance of the residual chromatic dispersion (CD), differential group delay (DGD) and nonlinear effect were also verified under the simulation conditions. The study results manifest that the proposed MFI scheme showed interesting robustness to both linear and nonlinear impairments. Moreover, we also demonstrated a relatively simpler calculation complexity under the proposed MFI scheme.

关键词： Blind modulation format identification modified particle swarm optimization algorithm Stokes components Elastic optical networks

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：