检索结果-内蒙古大学图书馆

Deep Reinforcement Learning for Multiobjective Optimization

IEEE TRANSACTIONS ON CYBERNETICS 2021年第6期51卷 3103-3114页

作者： Li, Kaiwen Zhang, Tao Wang, Rui Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha 410073 Peoples R China

This article proposes an end-to-end framework for solving multiobjective optimization problems (MOPs) using deep reinforcement learning (DRL), that we call DRL-based multiobjective optimization algorithm (DRL-MOA). The idea of decomposition is adopted to decompose the MOP into a set of scalar optimization subproblems. Then, each subproblem is modeled as a neural network. Model parameters of all the subproblems are optimized collaboratively according to a neighborhood-based parameter-transfer strategy and the DRL training algorithm. Pareto-optimal solutions can be directly obtained through the trained neural-network models. Specifically, the multiobjective traveling salesman problem (MOTSP) is solved in this article using the DRL-MOA method by modeling the subproblem as a Pointer Network. Extensive experiments have been conducted to study the DRL-MOA and various benchmark methods are compared with it. It is found that once the trained model is available, it can scale to newly encountered problems with no need for retraining the model. The solutions can be directly obtained by a simple forward calculation of the neural network;thereby, no iteration is required and the MOP can be always solved in a reasonable time. The proposed method provides a new way of solving the MOP by means of DRL. It has shown a set of new characteristics, for example, strong generalization ability and fast solving speed in comparison with the existing methods for multiobjective optimizations. The experimental results show the effectiveness and competitiveness of the proposed method in terms of model performance and running time.

关键词： Optimization Training Urban areas Neural networks Reinforcement learning Traveling salesman problems Modeling Deep reinforcement learning (DRL) multiobjective optimization Pointer Network traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Stochastic Optimization for the Pre-Position and Reconfiguration of Microgrid Defense Resources against Natural Disasters

引用

SENSORS 2022年第16期22卷 52-58页

作者： Jiang, Bo Lei, Hongtao Huang, Shengjun Li, Wenhua Jiao, Peng Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha 410073 Peoples R China

With the aggravation and evolution of global warming, natural disasters such as hurricanes occur more frequently, posing a great challenge to large-scale power systems. Therefore, the pre-position and reconfiguration of the microgrid defense resources by means of Mobile Energy Storage Vehicles (MEVs) and tie lines in damaged scenarios have attracted more and more attention. This paper proposes a novel two-stage optimization model with the consideration of MEVs and tie lines to minimize the shed loads and the outage duration of loads according to their proportional priorities. In the first stage, tie lines addition and MEVs pre-position are decided prior to a natural disaster;in the second stage, the switches of tie lines and original lines are operated and MEVs are allocated from staging locations to allocation nodes according to the specific damaged scenarios after the natural disaster strikes. The proposed load restoration method exploits the benefits of MEVs and ties lines by microgrid formation to pick up more critical loads. The progressive hedging algorithm is employed to solve the proposed scenario-based two-stage stochastic optimization problem. Finally, the effectiveness and superiority of the proposed model and applied algorithm are validated on an IEEE 33-bus test case.

关键词： microgrid reconfiguration stochastic programming mobile energy storage vehicle tie line

来源：评论

学校读者我要写书评

暂无评论

Reinvestigation of evolutionary many-objective optimization: Focus on the Pareto knee front

引用

INFORMATION SCIENCES 2020年 522卷 193-213页

作者： Li, Wenhua Wang, Rui Zhang, Tao Ming, Mengjun Li, Kaiwen Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha 410073 Peoples R China

Approximating the entire Pareto front (PF) in many-objective optimization is challenging but often unnecessary because a decision maker is usually only interested in a small portion of the PF. Assuming no preference, we argue that a more appropriate way to address many-objective optimization problems (MaOPs) is to find Pareto-optimal knee solutions-solutions where small improvements in one objective will lead to severe degradation in at least one other objective. Herein, we propose such a method, which uses a distance-based indicator to first identify knee points (knee-detection phase) and then uses a refined fitness assignment strategy to select solutions near the knee points (knee-selection phase). The proposed method is integrated into two traditional algorithms, resulting in k-NSGA-II and k-MOEA/D. We discuss the effects of the parameter that controls the width of the knee region(s) and then analyze the effects of different methods for identifying knee points in the knee-detection phase. Finally, we examine the performances of k-NSGA-II and k-MOEA/D on a set of knee benchmark problems. The experimental results show that k-NSGA-II is competitive on knee test problems with 2 and 4 objectives, while k-MOEA/D performs better than k-NSGA-II with 6 and 8 objectives. (C) 2020 Published by Elsevier Inc.

关键词： Multiobjective optimization Evolutionary computation Knee point NSGA-II MOEA/D

来源：评论

学校读者我要写书评

暂无评论

Path planning model for UAV collaborative search task Based on NGA 33

Path planning model for UAV collaborative search task Based ...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Huang, Hong Huang, Shengjun Qin, Weijian He, Huihui Zhang, Tao Natl Univ Def Technol Coll Syst Engn Changsha 410073 Hunan Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781665440899

To solve the problem of large search demand and insufficient search ability of UAVs, this article has proposed a task planning method of UAV group based on nested learning algorithm. According to the characteristics of the target path, the method combines task allocation strategy and path planning algorithm to make decision. This method can give reasonable suggestions on the number of UAVs, and effectively improve the efficiency of UAV group search task. The algorithm uses the elite individual selection strategy based on tournament selection method to improve the optimization efficiency. And the algorithm uses neighborhood method to avoid local optimum. Finally, the algorithm is verified by the data of a search task. The experimental results show that the planning method used in this paper is suitable for the UAVs' cooperative search problem. Compared with other planning methods, it has faster solution speed and is conducive to emergency decision-making. This method also has reference value for the cooperative planning of search tasks.

关键词： Nested genetic algorithms TSP Neighborhood method Path planning

来源：评论

学校读者我要写书评

暂无评论

A New Encoding Mechanism Embedded Evolutionary Algorithm for UAV Route Planning

A New Encoding Mechanism Embedded Evolutionary Algorithm for...

引用

IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Dong, Nanjiang Wang, Rui Zhang, Tao Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha Peoples R China

ISBN: (纸本)9781728183923

Evolutionary algorithms (EAs) are often applied to deal with UAV route planning. The solution encoding is one of important factor in designing effective EAs. In a traditional encoding mechanism, each individual represents one route. The whole population then consists of a number of routes. We argue that such an encoding is less effective in route planning, and then proposed an alternative encoding mechanism in which one individual represents only one navigation point. The whole population then represents one route. This implicitly turns EAs into single-point based search with high exploitation ability. To further improve the exploration ability of algorithms using this new encoding, a slightly modified differential evolution operator is applied. Combining the modified DE operator and the new encoding mechanism, the performance of the derived algorithm is significantly improved, obtaining much better route planning results than DE with the traditional encoding mechanism.

关键词： UAV encoding route planning evolutionary algorithm differential evolution

来源：评论

学校读者我要写书评

暂无评论

Helper Objective Assisted Evolutionary Algorithm for Multi-modal Optimization

Helper Objective Assisted Evolutionary Algorithm for Multi-m...

引用

IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Yang, Xu Wang, Rui Li, Wenhua Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha Peoples R China

ISBN: (纸本)9781728183923

Evolutionary algorithms (EAs) have been widely applied in various optimization problems. However, EAs are found as less effective on multi-modal optimization due to their multiple local optima. Inspired by the idea of self-paced learning, that is, problems can be solved step by step, from easy to difficult. In this study, we propose to design a helper objective function to assist the optimization of multi-modal problems via multi-task optimization framework. In principle the helper objective function shares common features with the original function but is easier to solve. Thus, the information gained by solving the helper objective can be utilized to tackle the multi-modal problems. Specifically, the Gaussian process is applied to build the helper objective function. The multi-factorial evolutionary algorithm is applied to optimize the helper and original objective functions simultaneously. Experimental results show that the idea is effective on a set of multi-modal optimization benchmarks.

关键词： surrogate model helper objective multi-task optimization Gaussian process modeling multi-factorial evolutionary algorithm differential evolution

来源：评论

学校读者我要写书评

暂无评论

A Dual-Population-Based Evolutionary Algorithm for Constrained Multiobjective Optimization

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2021年第4期25卷 739-753页

作者： Ming, Mengjun Trivedi, Anupam Wang, Rui Srinivasan, Dipti Zhang, Tao Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Natl Univ Def Technol Hunan Key Lab Multienergy Syst Intelligent Interc Changsha 410073 Peoples R China Natl Univ Singapore Dept Elect & Comp Engn Singapore 117581 Singapore

The main challenge in constrained multiobjective optimization problems (CMOPs) is to appropriately balance convergence, diversity and feasibility. Their imbalance can easily cause the failure of a constrained multiobjective evolutionary algorithm (CMOEA) in converging to the Pareto-optimal front with diverse feasible solutions. To address this challenge, we propose a dual-population-based evolutionary algorithm, named c-DPEA, for CMOPs. c-DPEA is a cooperative coevolutionary algorithm which maintains two collaborative and complementary populations, termed Population1 and Population2. In c-DPEA, a novel self-adaptive penalty function, termed saPF, is designed to preserve competitive infeasible solutions in Population1. On the other hand, infeasible solutions in Population2 are handled using a feasibility-oriented approach. To maintain an appropriate balance between convergence and diversity in c-DPEA, a new adaptive fitness function, named bCAD, is developed. Extensive experiments on three popular test suites comprehensively validate the design components of c-DPEA. Comparison against six state-of-the-art CMOEAs demonstrates that c-DPEA is significantly superior or comparable to the contender algorithms on most of the test problems.

关键词： Statistics Sociology Convergence Optimization Evolutionary computation Collaboration Space exploration Coevolutionary dual populations constrained multiobjective optimization convergence diversity feasibility

来源：评论

学校读者我要写书评

暂无评论

Two-stage robust optimal scheduling of cooperative microgrids based on expected scenarios

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2020年第26期14卷 6741-6753页

作者： Sang, Bo Zhang, Tao Liu, Yajie Liu, Lingshun Shi, Zhichao Naval Aeronaut & Astronaut Univ Sch Basic Sci Aviat Yantai Shandong Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha Hunan Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interc Changsha Hunan Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB Canada

Cooperative microgrids (CMGs) can effectively solve the energy interaction between microgrids (MGs) while increasing the penetration rate of renewable energy systems (RESs) and reducing the interaction frequency with the grid. However, the uncertainty of RESs will bring new challenges to the energy management and economic dispatch of CMGs, especially in increasing the number of MGs connected to the grid. Taking into account this uncertainty, it is extremely unlikely that the forecast uncertainty information will be at the worst values in every period, and this forecast uncertainty information is near the expected values in most cases. Therefore, a two-stage robust optimal model under expected scenarios for CMGs is proposed in this study to improve the conservatism of traditional models and minimise the daily cost. In this model, the first-stage decision results (FDRs) are determined by minimising the daily cost of CMGs under the expected scenarios. The proposed model is transformed based on two-stage zero-sum game theory and dual theory, a column and constraint generation algorithm is first used to test the robust feasibility of the FDR, and the second-stage decision results can be obtained without changing the FDR. Case studies verify that the proposed model can effectively solve energy transactions between MGs while mitigating the uncertainty disturbances in the operation of CMGs.

关键词： power generation dispatch scheduling renewable energy sources robust control distributed power generation game theory optimisation stage robust optimal scheduling microgrids expected scenarios CMGs energy interaction penetration rate renewable energy systems RESs interaction frequency energy management economic dispatch account this uncertainty forecast uncertainty information worst values expected values two-stage robust optimal model daily cost first-stage decision results two-stage zero-sum game theory robust feasibility second-stage decision results energy transactions uncertainty disturbances

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Detection strategy of False Data in Cooperative DC Microgrids 47

A Data-Driven Detection strategy of False Data in Cooperativ...

引用

47th Annual Conference of the IEEE-Industrial-Electronics-Society (IECON)

作者： Yang, Yixian Guo, Li Li, Xialin Li, Jiaxin Liu, Wei He, Huihui Tianjin Univ Minist Educ Key Lab Smart Grid Tianjin Peoples R China Natl Univ Def Technol Coll Syst Engn Hunan Key Lab Multienergy Syst Intelligent Interc Changsha Peoples R China

ISBN: (纸本)9781665435543

Distributed cooperative control strategies of DC microgrids (DCMG) reduce the detriment of communication delays, packet loss and link failure compared with centralized control. However, they are vulnerary to cyber-attacks. The operating objectives can be deviated by false data. Firstly, the adverse effects of false data are explained and modeled. A data-driven strategy based on linear regression is then proposed to remove the false data by offline learning and online judging of the transient process in DCMG without affecting the dynamic response. It successfully solves the problem of parameter selection of resilient control. Finally, the detection strategy is verified by detailed time-domain simulation.

关键词： DC microgrids distributed control cyber physical system false data injection attack data-driven

来源：评论

学校读者我要写书评

暂无评论

A hybrid temporal convolutional network and Prophet model for power load forecasting

引用

COMPLEX & intelligent systEMS 2023年第4期9卷 4249-4261页

作者： Mo, Jinyuan Wang, Rui Cao, Mengda Yang, Kang Yang, Xu Zhang, Tao Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China Hunan Key Lab Multienergy Syst Intelligent Interco Changsha 410073 Peoples R China

Accurate and effective power system load forecasting is an important prerequisite for the safe and stable operation of the power grid and the normal production and operation of society. In recent years, convolutional neural networks (CNNs) have been widely used in time series prediction due to their parallel computing and other characteristics, but it is difficult for CNNs to capture the relationship of sequence context and meanwhile, it easily leads to information leakage. To avoid the drawbacks of CNNs, we adopt a temporal convolutional network (TCN), specially designed for time series. TCN combines causal convolution, dilated convolution, and residual connection, and fully considers the causal correlation between historical data and future data. Considering that the power load data has strong periodicity and is greatly influenced by seasons and holidays, we adopt the Prophet model to decompose the load data and fit the trend component, season component, and holiday component. We use TCN and Prophet to forecast the power load data respectively, and then use the least square method to fuse the two models, and make use of their respective advantages to improve the forecasting accuracy. Experiments show that the proposed TCN-Prophet model has a higher prediction accuracy than the classic ARIMA, RNN, LSTM, GRU, and some ensemble models, and can provide more effective decision-making references for power grid departments.

关键词： Power load forecasting Temporal convolutional network Prophet model Least square method

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：