检索结果-内蒙古大学图书馆

A new hybrid gravitational search-teaching-learning-based optimization method for the solution of economic dispatch of power systems

引用

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES 2019年第4期27卷 2962-+页

作者： Tefek, Mehmet Fatih Uguz, Harun Ahi Evran Univ Kaman Vocat Sch Dept Comp Technol Kirsehir Turkey Selcuk Univ Fac Engn Dept Comp Engn Konya Turkey

The economic dispatch problem (EDP) is a complex, constrained, and nonlinear optimization problem. In the EDP, the active power bus should operate between the minimum and maximum bus limits to minimize the fuel cost. In this study, a fast, efficient, and reliable hybrid gravitational search algorithm-teaching learning based optimization (GSA-TLBO) method was proposed for the purpose of solving the EDP in power systems. The proposed method separates the search space into two sections as global and local searching. In the first part, searching was carried out by GSA method effectively to form the second search space. In the second part, the optimum solution was sought in the local search space by the TLBO method. The proposed method was implemented to a constrained benchmark G01 problem. The proposed hybrid method was then applied to the constrained EDP in IEEE 30-bus and IEEE 57-bus test systems and Turkey's 22-bus power system to minimize the fuel cost. Obtained results were compared with other methods. Experimental results show that the proposed method results in shorter, more reliable, and efficient lowest fuel cost solutions. It has been found that the proposed method can be used to solve constrained optimization problems.

关键词： Hybrid optimization method gravitational search algorithm teaching-learning-based optimization algorithm economic dispatch power systems

来源：评论

学校读者我要写书评

暂无评论

An evolutionary gravitational search-based feature selection

引用

INFORMATION SCIENCES 2019年 497卷 219-239页

作者： Taradeh, Mohammad Mafarja, Majdi Heidari, Ali Asghar Faris, Hossam Aljarah, Ibrahim Mirjalili, Seyedali Fujita, Hamido Birzeit Univ Fac Engn & Technol Birzeit Palestine Birzeit Univ Dept Comp Sci Birzeit Palestine Univ Tehran Sch Surveying & Geospatial Engn Tehran Iran Natl Univ Singapore Sch Comp Dept Comp Sci Singapore Singapore Univ Jordan King Abdullah II Sch Informat Technol Amman Jordan Griffith Univ Inst Integrated & Intelligent Syst Brisbane Qld 4111 Australia Ho Chi Minh City Univ Technol HUTECH Fac Informat Technol Ho Chi Minh City Vietnam

With recent advancements in data collection tools and the widespread use of intelligent information systems, a huge amount of data streams with lots of redundant, irrelevant, and noisy features are collected and a large number of features (attributes) should be processed. Therefore, there is a growing demand for developing efficient Feature Selection (FS) techniques. gravitational search algorithm (GSA) is a successful population-based meta-heuristic inspired by Newton's law of gravity. In this research, a novel GSA-based algorithm with evolutionary crossover and mutation operators is proposed to deal with feature selection (FS) tasks. As an NP-hard problem, FS finds an optimal subset of features from a given set. For the proposed wrapper FS method, both K-Nearest Neighbors (KNN) and Decision Tree (DT) classifiers are used as evaluators. Eighteen well-known UCI datasets are utilized to assess the performance of the proposed approaches. In order to verify the efficiency of proposed algorithms, the results are compared with some popular nature-inspired algorithms (i.e. Genetic algorithm (GA), Particle Swarm Optimizer (PSO), and Grey Wolf Optimizer (GWO)). The extensive results and comparisons demonstrate the superiority of the proposed algorithm in solving FS problems. (C) 2019 Elsevier Inc. All rights reserved.

关键词： gravitational search algorithm Genetic algorithm Feature selection Supervised learning Classification Optimization

来源：评论

学校读者我要写书评

暂无评论

Application of data computing for resource scheduling in manufacturing industries 3

Application of data computing for resource scheduling in man...

引用

3rd International Conference on Materials, Manufacturing and Modelling (ICMMM)

作者： Brintha, N. C. Jappes, J. T. Winowlin Khan, M. Adam Christo, N. Johnny Kalasalingam Acad Res & Educ Dept Comp Sci & Engn Krishnankoil Tamil Nadu India Kalasalingam Acad Res & Educ KARE Sch Automot & Mech Engn SAME Krishnankoil Tamil Nadu India Intel Corp Util & Infrastruct Bangalore Karnataka India

Cloud based solutions and services can be used in production sectors to maximize profit and to develop complex products through reconfiguration of manufacturing supply chain through dynamic process. Scheduling and allocation of resources to tasks is a critical issue, since inappropriate allocation and scheduling may affect the utilization rate, cost and time. Cloud manufacturing encompass flexible services from manufacturing enterprise with IT based services to improve the performance of an application. This work considers Differential Evolutionary (DE) and gravitational search algorithm for implementation, since these approaches can narrow the solution search space and improves convergence rate. The tasks and resources used for the experimentation process were classified and incorporated from casting industries. The computational results on the identified workflow proves that, DEGSA algorithm maximizes resource utilization, maintains load balance and minimizes the computational time of jobs. (c) 2021 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the 3rd International Conference on Materials, Manufacturing and Modelling.

关键词： Cloud manufacturing Differential evolution gravitational search algorithm Casting Scheduling

来源：评论

学校读者我要写书评

暂无评论

Combining density peaks clustering and gravitational search method to enhance data clustering

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2019年 85卷 865-873页

作者： Sun, Liping Tao, Tao Zheng, Xiaoyao Bao, Shuting Luo, Yonglong Anhui Normal Univ Sch Comp & Informat Wuhu 241002 Peoples R China Anhui Prov Key Lab Network & Informat Secur Wuhu 241002 Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Peoples R China

Data clustering is a valuable field for extracting effective information and hidden patterns from datasets. In this paper we propose a clustering approach based on density peaks clustering (DPC) and a modified gravitational search algorithm (GSA), called GSA-DPC. To take advantage of the distance measure and nearest neighbor rule among the data points, our method simultaneously combines the distance and density mechanisms. Based on the optimized cluster center set selected by DPC working with density measure, the best clustering distribution is achieved according to the distance criterion of GSA. We compare the performance of GSA-DPC with other well-known clustering approaches, including density-based spatial clustering of applications with noise (DBSCAN), density peaks clustering, K-Means, spectral clustering (SC), grey wolf optimizer for clustering (GWO-C), gravitational search algorithm for clustering (GSA-C) and data clustering algorithm based on GSA and K-Means (GSA-KM). The experimental results indicate that GSA-DPC outperforms these competing approaches.

关键词： Data clustering gravitational search algorithm Density peaks clustering GSA-DPC algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel method based on fuzzy logic to evaluate the storage and backup systems in determining the optimal size of a hybrid renewable energy system

引用

JOURNAL OF ENERGY STORAGE 2022年 49卷

作者： Mahmoudi, Sayyed Mostafa Maleki, Akbar Ochbelagh, Dariush Rezaei Amirkabir Univ Technol Tehran Polytech Dept Energy Engn & Phys Tehran Iran Shahrood Univ Technol Fac Mech Engn Shahrood Iran

Renewable energy sources are one of the most popular sources of energy for supplying load demand in remote areas. For this purpose, a hybrid renewable energy system can be used which includes Photovoltaic panels (PVs) and Wind turbines (WTs). To meet load demand, due to the dependence of these energy sources on environmental conditions, energy storage systems such as batteries or backup systems such as diesel generators (DG) should be used. Therefore, the idea of this work is to investigate the effect of the energy storage and backup systems in a hybrid energy system (HES) with respect to environmental conditions and load demand for a remote area. Thus, with the goal of reducing costs and checking reliability based on the loss of power supply probability (LPSP), economic and sensitivity analysis is done for six cases of PV/Battery, Wind/Battery, PV/Wind/Battery, PV/DG, Wind/DG, and PV/Wind/DG. Hence, to design the optimal size of the hybrid energy system, a new technique based on the fuzzy logic controller in combination with a gravitational search algorithm (GSA) has been used. Based on this, appropriate membership functions and fuzzy rules were designed to improve the efficiency of the GSA algorithm. Also, to evaluate and validate the proposed method, the Drop-Wave function was tested and compared with other valid methods. The results show that by removing the storage system and using a diesel generator, in addition to reducing economic costs, the reliability of the system is also provided. Therefore, PV/Wind/DG system was introduced as the most cost-effective system. In this case, for LPSP equal to 0%, 1%, 2%, 5%, and 10%, the amount of total annual cost is equal to $88,853, $80,838, $78,038, $72,616, and $66,265, respectively. Also, the results showed that fuel costs and battery costs have the greatest impact on the total annual cost. In addition, pollution emission calculations including CO2, NOX, and SO2 were examined. Finally, the use of a fuzzy logic control

关键词： Hybrid energy system Storage and backup systems Optimal design gravitational search algorithm Fuzzy logic controller

来源：评论

学校读者我要写书评

暂无评论

An experimental realization of improved grid integrated multilevel inverter based PV systems with MPPT

引用

IET RENEWABLE POWER GENERATION 2022年第0期

作者： Priyadarshi, Neeraj Bhaskar, Mahajan Sagar Hussien, Mohamed G. Khan, Baseem Hassan, Abd El-Wahab JIS Coll Engn Dept Elect Engn Kolkata India Prince Sultan Univ Coll Engn Renewable Energy Lab Riyadh Saudi Arabia Tanta Univ Fac Engn Elect Power & Machines Engn Dept Tanta Egypt Hawassa Univ Inst Technol Sch Elect & Comp Engn Hawassa Ethiopia El Shorouk Acad Higher Inst Engn HIE Dept Elect Power & Machines Engn El Shorouk City Egypt

This research work explains a sliding mode controller-based multilevel inverter for grid integrated photovoltaic power structure. A gravitational search algorithm based on maximum power point tracking has also been discussed for optimal photovoltaic power achievement. Moreover, a two-stage cascaded interleaved boost converter has been employed, which provides minimised voltage/current ripple, higher current/power density, better efficacy, faster response, and reduced electromagnetic interference as major benefits. The multilevel inverter's proposed constant frequency-based sliding mode controller provides better transient responses, high photovoltaic power tracking, and good robust behaviour under changing operating conditions. The proposed sliding mode controller has a fixed frequency operation and has low reactivity to parameter divergence. The proposed multilevel diode clamped inverter for grid integrated photovoltaic system provides a reduced number of components and a power rating. The gravitational search algorithm-based swarm technique as a maximum power point tracking provides high convergence velocity, better accuracy, and good local search capability. The experimentation was carried out to implement control algorithms using the dSPACE platform. The designed multilevel inverter system with proposed control provides average 89.2% inverter efficiency under variation of sun insolations.

关键词： gravitational search algorithm maximum power point tracking multilevel converter photovoltaic sliding mode controller

来源：评论

学校读者我要写书评

暂无评论

A hybrid structure of an extreme learning machine combined with feature selection, signal decomposition and parameter optimization for short-term wind speed forecasting

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2020年第1期42卷 3-21页

作者： Sun, Sizhou Fu, Jingqi Zhu, Feng Du, Dajun Shanghai Univ Sch Mechatron Engn & Automat Shanghai Peoples R China Anhui Polytech Univ Sch Elect Engn Wuhu Peoples R China Shanghai Univ Shanghai Key Lab Power Stn Automat Technol Shanghai Peoples R China

Influenced by various environmental and meteorological factors, wind speed presents stochastic and unstable characteristics, which makes it difficult to forecast. To enhance the forecasting accuracy, this study contributes to short-term multi-step hybrid wind speed forecasting (WSF) models using wavelet packet decomposition (WPD), feature selection (FS) and an extreme learning machine (ELM) with parameter optimization. In the model, the WPD technique is applied to decompose the empirical wind speed data into different, relatively stable components to reduce the influence of the unstable characteristics of wind speed. A hybrid particle swarm optimization gravitational search algorithm (HPSOGSA) combining conventional PSOGSA with binary PSOGSA (BPSOGSA) is utilized to realize the FS and parameter optimization simultaneously. The PSOGSA is employed to tune the parameter combination of input weights and biases in ELM, while BPSOGSA is exploited to select the most suitable features from the candidate input variables determined by a partial autocorrelation function for reconstruction of the input matrix for ELM. The proposed forecasting strategy carries out multi-step short-term WSF using mean half-hour historical wind speed data collected from a wind farm situated in Anhui, China. To investigate the forecasting results of the hybrid model, a lot of comparisons and analyses are executed. Simulation results illustrate that the proposed WPD-ELM model with FS and parameter optimization can effectively catch the non-linear characteristics hidden in wind speed data and provide satisfactory WSF performance.

关键词： Wind speed forecasting extreme learning machine wavelet packet decompositions gravitational search algorithm particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Memetic quantum evolution algorithm for global optimization

引用

NEURAL COMPUTING & APPLICATIONS 2020年第13期32卷 9299-9329页

作者： Tang, Deyu Liu, Zhen Zhao, Jie Dong, Shoubin Cai, Yongming Guangdong Pharmaceut Univ Sch Med Informat & Engn Guangzhou 510006 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guangdong Univ Technol Sch Management Dept Informat Management Engn Guangzhou 510520 Peoples R China

Quantum-inspired heuristic search algorithms have attracted considerable research interest in recent years. However, existing quantum simulation methods are still limited on the basis of particle swarm optimizer. This paper explores the principle of memetic computing to develop a novel memetic quantum evolution algorithm for solving global optimization problem. First, we design a quantum theory-based memetic framework to handle multiple evolutionary operators, in which multiple units of different kinds of algorithmic information are harmoniously combined. Second, we propose the memetic evolutionary operator and the quantum evolutionary operator to complete the balance between the global search and the local search. The memetic evolutionary operator emphasizes meme diffusion by the shuffled process to enhance the global search ability. The quantum evolutionary operator utilizes an adaptive selection mechanism for different potential wells to tackle the local search ability. Furthermore, the Newton's gravity laws-based gravitational center and geometric center as two important components are introduced to improve the diversity of population. These units can be recombined by means of different evolutionary operators that are based on the synergistic coordination between exploitation and exploration. Through extensive experiments on various optimization problems, we demonstrate that the proposed method consistently outperforms 11 state-of-the-art algorithms.

关键词： Quantum evolution Memetic algorithm Evolutionary computation gravitational search algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel opposition-based gravitational search algorithm for combined economic and emission dispatch problems of power systems

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2012年第1期35卷 21-33页

作者： Shaw, Binod Mukherjee, V. Ghoshal, S. P. Asansol Engn Coll Dept Elect Engn Asansol W Bengal India Indian Sch Mines Dept Elect Engn Dhanbad 826004 Jharkhand India Natl Inst Technol Dept Elect Engn Durgapur W Bengal India

gravitational search algorithm (GSA) is based on the law of gravity and interaction between masses. In GSA, the searcher agents are a collection of masses, and their interactions are based on the Newtonian laws of gravity and motion. This paper proposes a novel algorithm to accelerate the performance of the GSA. The proposed opposition-based GSA (OGSA) of the present work employs opposition-based learning for population initialization and also for generation jumping. In the present work, opposite numbers have been utilized to improve the convergence rate of the GSA. For the experimental verification of the proposed algorithm, a comprehensive set of 23 complex benchmark test functions including a wide range of dimensions is employed. Additionally, four standard power systems problems of combined economic and emission dispatch (CEED) are solved by the OGSA to establish the optimizing efficacy of the proposed algorithm. The results obtained confirm the potential and effectiveness of the proposed algorithm compared to some other algorithms surfaced in the recent state-of-the art literatures. Both the near-optimality of the solution and the convergence speed of the proposed algorithm are promising. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Benchmark test function Combined economic emission dispatch gravitational search algorithm Opposite numbers Optimization

来源：评论

学校读者我要写书评

暂无评论

Path planning of unmanned aerial vehicle based on improved gravitational search algorithm

引用

Science China(Technological Sciences) 2012年第10期55卷 2712-2719页

作者： LI Pei DUAN HaiBin Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical EngineeringBeihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

Path planning of Uninhabited Aerial Vehicle(UAV) is a complicated global optimum *** the paper,an improved gravitational search algorithm(GSA) was proposed to solve the path planning *** search algorithm(GSA) is a newly presented under the inspiration of the Newtonian gravity,and it is easy to fall local *** the basis of introducing the idea of memory and social information of Particle Swarm Optimization(PSO),a novel moving strategy in the searching space was designed,which can improve the quality of the optimal ***,a weighted value was assigned to inertia mass of every agent in each iteration process to accelerate the convergence speed of the *** position was updated according to the selection rules of survival of the *** this way,the population is always moving in the direction of the optimal *** feasibility and effectiveness of our improved GSA approach was verified by comparative experimental results with PSO,basic GSA and two other GSA models.

关键词： uninhabited aerial vehicle path planning gravitational search algorithm social information weighted value selection rules

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：