检索结果-内蒙古大学图书馆

A q-learning-based approach for virtual network embedding in data center

NEURAL COMPUTING & APPLICATIONS 2020年第7期32卷 1995-2004页

作者： Yuan, Ying Tian, Zejie Wang, Cong Zheng, Fanghui Lv, Yanxia Northeastern Univ Qinhuangdao Comp Ctr Qinhuangdao 066004 Hebei Peoples R China Northeastern Univ Qinhuangdao Dept Comp & Commun Engn Qinhuangdao 066004 Hebei Peoples R China

Virtual network embedding (VNE) refers to allocating reasonable substrate network resources for virtual network (VN) requests that include computing resources and network resources, so as to obtain optimal income from leasing virtual resources. Such a way of providing virtual resources is the key technology of cloud computing and can greatly save the operating cost of enterprises and provide flexibility of application deployment. However, the existing VNE algorithms are mostly oriented to traditional stochastic network topologies. Due to the high connectivity and server density of data centers and the complexity of the user's resource requirements, the traditional VNE algorithms suffer from low resource utilization rate and revenues in the VNE on the data centers. Different from the existing algorithms which are often based on heuristic algorithms, this paper proposes a VNE algorithm for data center topology based on the q-learning algorithm which is a typical reinforcement learning method. The algorithm an agent for each VN designs a reward function related to the effect of virtual link embedding, which is used to update the q-matrix through unsupervised learning process. Then, the agent can find the optimal embedding strategy based on the q-table from each learning. Simulation results demonstrate that the proposed algorithm can improve the resource utilization ratio and obtain a better revenue/cost ratio of the substrate network compared with the traditional heuristic algorithms.

关键词： Virtual tenant network Network virtualization Virtual network embedding Virtual data center q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Anisotropic q-learning and waiting estimation based real-time routing for automated guided vehicles at container terminals

引用

JOURNAL OF HEURISTICS 2023年第2-3期29卷 207-228页

作者： Zhou, Pengfei Lin, Li Kim, Kap Hwan Dalian Univ Technol Fac Infrastruct Engn State Key Lab Coastal & Offshore Engn Dalian 116024 Peoples R China Dalian Jiaotong Univ Sch Management Dalian 116028 Peoples R China Pusan Natl Univ Dept Ind Engn Busan 609735 South Korea

Finding short and convenient routes for vehicles is an important issue on efficient operations of Automated Guided Vehicle (AGV) systems at container terminals. This paper proposes an anisotropic q-learning method for AGVs to find the shortest-time routes in the guide-path network of cross-lane type according to real-time vehicle states, which includes current and destination positions, heading direction and the number of vehicles at anisotropic four-direction neighboring locations. The vehicle waiting time of AGV systems is discussed and its estimation is suggested to improve the policy to select actions in the q-learning method. An improved anisotropic q-learning routing algorithm is developed with the vehicle-waiting-time-estimation based selecting-action policy. The parameter settings and performance of the proposed methods are analyzed based on simulations. The numerical experiments show that the improved anisotropic q-learning method can provide stable and dynamic solutions for AGV routing, and achieve 9.5% improvement in optimization efficiency compared to the Jeon learning Method (Jeon et al. in Logist Res 3(1):19-27, 2011).

关键词： Container transportation Automated guided vehicle routing q-learning algorithm Waiting time estimation

来源：评论

学校读者我要写书评

暂无评论

q-learning-Based Damping Control of Wide-Area Power Systems Under Cyber Uncertainties

引用

IEEE TRANSACTIONS ON SMART GRID 2018年第6期9卷 6408-6418页

作者： Duan, Jiajun Xu, Hao Liu, Wenxin Lehigh Univ Dept Elect & Comp Engn Bethlehem PA 18015 USA Univ Nevada Dept Elect & Biomed Engn Reno NV 89557 USA

The installation of phasor measurement units brings about system-wide synchronized real-time measurements, which makes advanced closed-loop control of wide-area power systems (WAPSs) possible. In addition to uncertainties with the physical system, network imperfections are also critical for control performance and even stability of the system. This paper targets at wide-area damping control of WAPS under both physical and cyber uncertainties. The cyber uncertainties addressed in this paper include both communication delay and package dropout. First, a linearized WAPS model is developed with considerations of random control signal arrivals. Then, a q-learning-based control algorithm is designed to learn the optimal control under both physical and cyber uncertainties. Finally, to further counteract the communication uncertainties between the control center and actuators, a novel control law is designed based on the statistical analysis to make the long-term control performance approach that under ideal communications. The designed control algorithm is tested with both simplified linear model and detailed nonlinear model of WAPSs. Simulation results demonstrate the effectiveness of the designed algorithm.

关键词： Wide-area power systems networked control system network imperfections communication delay package dropout q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

q-learning-Based Priority Dispatching Rule Preference Model for Non-Permutation Flow Shop

引用

JOURNAL OF ADVANCED MANUFACTURING SYSTEMS 2024年第3期23卷 601-612页

作者： Zhao, Anran Liu, Peng Jilin Univ Sch Mech & Aerosp Engn Changchun 130025 Jilin Peoples R China

Non-permutation flow shop scheduling (NPFS) is an extension of the traditional permutation flow shop scheduling, with a broader solution space. The effectiveness of reinforcement learning in solving flow shop scheduling problems has been demonstrated through its powerful combinatorial optimization capabilities. However, the design and training of the end-to-end policy network is complex, leading to long online training time and limited adaptability of offline training. To overcome these problems, we introduced a NPFS dynamic decision-making process and then proposed a novel NPFS method that combines the q-learning algorithm with the priority dispatching rule (PDR) set. The NPFS dynamic decision-making process involves decomposing the entire process into multiple sub-job queues for scheduling. The PDR demonstrates better scheduling performance when applied to smaller job queues. By utilizing the q-learning algorithm, PDRs with superior performance are assigned to sub-scheduling queues based on the generation process of sub-job sequences, resulting in an optimized NPFS strategy. The limited number of PDRs in the PDR set and the small number of sub-job queues in the NPFS process contribute to the efficiency of q-learning in solving NPFS problem. Finally, we demonstrate the superiority of the proposed NPFS method by a series of numerical experiments using the machine-based assignment PDR method and NSGA-II algorithms as performance benchmarks.

关键词： q-learning algorithm non-permutation flow shop priority dispatching rules Makespan

来源：评论

学校读者我要写书评

暂无评论

q-learning-Based Teaching-learning Optimization for Distributed Two-Stage Hybrid Flow Shop Scheduling with Fuzzy Processing Time

引用

Complex System Modeling and Simulation 2022年第2期2卷 113-129页

作者： Bingjie Xi Deming Lei School of Automation Wuhan University of TechnologyWuhan 430070China

Two-stage hybrid flow shop scheduling has been extensively considered in single-factory ***,the distributed two-stage hybrid flow shop scheduling problem(DTHFSP)with fuzzy processing time is seldom investigated in multiple ***,the integration of reinforcement learning and metaheuristic is seldom applied to solve *** the current study,DTHFSP with fuzzy processing time was investigated,and a novel q-learning-based teaching-learning based optimization(qTLBO)was constructed to minimize *** teachers were recruited for this *** teacher phase,learner phase,teacher’s self-learning phase,and learner’s self-learning phase were *** q-learning algorithm was implemented by 9 states,4 actions defined as combinations of the above phases,a reward,and an adaptive action selection,which were applied to dynamically adjust the algorithm structure.A number of experiments were *** computational results demonstrate that the new strategies of qTLBO are effective;furthermore,it presents promising results on the considered DTHFSP.

关键词： teaching-learning based optimization q-learning algorithm two-stage hybrid flow shop scheduling fuzzy processing time

来源：评论

学校读者我要写书评

暂无评论

q-learning optimized diagonal recurrent neural network control strategy for brushless direct current motors

引用

ADVANCES IN MECHANICAL ENGINEERING 2020年第9期12卷

作者： Hu, Huangshui Wang, Tingting Wang, Hongzhi Wang, Chuhang Changchun Univ Technol Coll Comp Sci & Engn Changchun Peoples R China Jilin Univ Architecture & Technol Coll Comp Sci & Engn Changchun 130114 Peoples R China Changchun Normal Univ Coll Comp Sci & Technol Changchun Peoples R China

In order to improve the working stability of brushless direct current motors (BLDCM), a diagonal recursive neural network (DRNN) control strategy based on q-learning algorithm is proposed in this paper which is called as q-DRNN. In q-DRNN, DRNN iterates over the output variables through a unique recursive loop in the hidden layer, and its key weight is optimized to speed up the iteration. Moreover, an improved q-learning algorithm is introduced to modify the weight momentum factor of DRNN, which makes DRNN have the ability of learning and online correction so as to make the BLDCM achieve better control effect. In MATLAB/Simulink environment, q-DRNN is tested and compared with other popular control methods in terms of speed and torque response under different operating conditions, and the results show that q-DRNN has better adaptive and anti-interference ability as well as stronger robustness.

关键词： DRNN q-learning algorithm optimal control strategy key weight BLDCM

来源：评论

学校读者我要写书评

暂无评论

Simulation Model for the AGC System of Isolated Microgrid Based on q-learning Method 7

Simulation Model for the AGC System of Isolated Microgrid Ba...

引用

IEEE 7th Data Driven Control and learning Systems Conference (DDCLS)

作者： Wang, Penghu Tang, Hao Lv, Kai Hefei Univ Technol Sch Elect Engn & Automat Hefei 230009 Anhui Peoples R China

ISBN: (纸本)9781538626184

The automatic generation control (AGC) in isolated microgrid with multiple distributed energy resources is concerned in this study. First, the load frequency control (LFC) model of an isolated microgrid, which contains diesel engine generators, super-magnetic magnetic energy storage, wind turbines and photovoltaic power system, is established through the analysis of the power generation characteristics of each distributed generation (DG). The LFC model of an isolated microgrid is built by MATLAB/Simulink with diesel generators as frequency control units. Based on the AGC principle of power grid, the AGC controller of the microgrid system is designed by the q learning algorithm based on the discount compensation model to complete the frequency control. The simulation results verify the feasibility of the isolated microgrid model, showing the efficient dynamic performance of q controller by compared with PI controller.

关键词： Microgrid Distributed generation Automatic generation control Load frequency control q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Self-tuning CPS Controller Based on q-learning Method

A Novel Self-tuning CPS Controller Based on Q-learning Metho...

引用

General Meeting of the IEEE-Power-and-Energy-Society

作者： Tao, Yu Bin, Zhou S China Univ Technol Coll Elect Engn Guangzhou 510640 Guangdong Peoples R China

ISBN: (纸本)9781424419050

This paper describes an application of q-learning method based on-line self-tuning control methodology to solve the automatic generation control (AGC) under NERC's new control performance standards (CPS). The AGC problem is a stochastic multistage decision problem, which can be modeled as a Markov Decision Process (MDP). This model-free q-learning algorithm regards, the CPS values as the rewards from the interconnected power systems. By regulating a closed-loop CPS control rule to maximize the total reward in the procedure of on-line learning, the optimal CPS control strategy can gradually obtained. The case study shows that after adding the q-learning controller, the robustness and adaptability of AGC system is enhanced obviously and the CPS compliance is ensured.

关键词： q-learning algorithm Reinforcement learning Automatic generation control Control performance standard Self-tuning control

来源：评论

学校读者我要写书评

暂无评论

A q-learning Based Dynamic Event-Triggered Control for Load Frequency Regulation of Power Systems with Denial-of-Service Attacks 30

A Q-Learning Based Dynamic Event-Triggered Control for Load ...

引用

30th IEEE International Symposium on Industrial Electronics (ISIE)

作者： Chen, Pengcheng Liu, Shichao Zhang, Dan Carleton Univ Dept Elect Ottawa ON K1S 5B6 Canada Zhejiang Univ Technol Dept Automat Hangzhou 310023 Peoples R China

ISBN: (纸本)9781728190235

This work proposes a novel q-learning based dynamic event-triggered strategy integrated with decentralized output feedback controller for the load frequency regulation scheme to alleviate the influence of Denial-of-Service(DoS) attacks with the given maximum attack duration and load fluctuations. The q-learning algorithm is applied in dynamic event-triggered strategy to optimize the threshold of the release condition through maximizing the cumulative discount reward, which can greatly reduce the amount of data transmission and preserve a satisfactory system performance. A three-area power system with LFC scheme is simulated to affirm the effectiveness of the proposed results.

关键词： q-learning algorithm Load frequency control Event-triggered scheme Denial-of-Service attacks

来源：评论

学校读者我要写书评

暂无评论

An electricity supplier bidding strategy through q-learning

An electricity supplier bidding strategy through Q-learning

引用

IEEE Power-Engineering-Society Summer Meeting

作者： Xiong, GF Hashiyama, T Okuma, S Nagoya Univ Dept Elect Engn Nagoya Aichi 4648603 Japan

ISBN: (纸本)0780375181

One of the most important issues for power suppliers in the deregulated electric industry is how to bid into the electricity auction market to satisfy their profit-maximizing goals. Based on the q-learning algorithm, this paper presents a novel supplier bidding strategy to maximize supplier's profit in a long term. A perfectly competitive day-ahead electricity auction market, where no supplier posses the market power and all suppliers winning the market are paid on their own bids, is assumed here. The dynamics and the incomplete information of the market are emphasized. The impact of suppliers' strategic biddings on the market price is analyzed. Agent-based simulations are presented in this paper. The simulation results show the feasibility of the proposed bidding strategy.

关键词： deregulation day-ahead electricity auction market q-learning algorithm supplier bidding strategy

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：