检索结果-内蒙古大学图书馆

A novel dynamic integration approach for multiple load forecasts based on q-learning algorithm

INTERNATIONAL TRANSACTIONS ON ELECTRICAL ENERGY SYSTEMS 2020年第7期30卷 1-14页

作者： Ma, Minhua Jin, Bingjie Luo, Shuxin Guo, Shaoqing Huang, Hongwei CSG Guangdong Power Grid Corp Grid Planning & Res Ctr Guangzhou Guangdong Peoples R China Guangdong Power Grid Dev Res Inst Co Ltd Guangzhou Guangdong Peoples R China Beijing QU Creat Technol Co Ltd Beijing Peoples R China

A higher accurate load forecasts can significantly reduce the potential cost for power system operation and power market decision. There have been extensive load forecasting methods proposed by now. Ensemble learning is an effective way to integrate various forecasts and further improve the forecasting accuracy. Traditional ensemble learning algorithms static. However, how to select a suitable forecasting method from a large number of load forecasting methods under the complex and varying environment conditions is still challenging. In this context, this paper proposes a dynamic integration approach for multiple load forecasts based on reinforcement learning. Compared with the traditional integration methods, this method adopts q-learning algorithm to realize the adaptive selection of the forecasting methods and dynamic weight calculation for different and varying environment. The basic principles and implementation processes of q-learning algorithm is firstly introduced. Then, the implementation methodology of dynamic integration approach of multiple load forecasts is proposed. On this basis, the environment state, action space and return function are designed according to the requirements of q-learning algorithm. Finally, a case study based on the real-world data in Guangzhou shows that the average forecasting accuracy could be improved by almost 3% by adopting the dynamic integration approach with the traditional ones.

关键词： action space environmental status multiple load forecasts integration q-learning algorithm reinforcement learning return function

来源：评论

学校读者我要写书评

暂无评论

Jamming mitigation in cognitive radio networks using a modified q-learning algorithm

Jamming mitigation in cognitive radio networks using a modif...

引用

International Conference on Military Communications and Information Systems (ICMCIS)

作者： Slimeni, Feten Scheers, Bart Chtourou, Zied Le Nir, Vincent Mil Acad Tunisia VRIT Lab Nabeul Tunisia Royal Mil Acad RMA CISS Dept Brussels Belgium

ISBN: (纸本)9788393484850

The jamming attack is one of the most severe threats in cognitive radio networks, because it can lead to network degradation and even denial of service. However, a cognitive radio can exploit its ability of dynamic spectrum access and its learning capabilities to avoid jammed channels. In this paper, we study how q-learning can be used to learn the jammer strategy in order to pro-actively avoid jammed channels. The problem with q-learning is that it needs a long training period to learn the behavior of the jammer. To address the above concern, we take advantage of the wideband spectrum sensing capabilities of the cognitive radio to speed up the learning process and we make advantage of the already learned information to minimize the number of collisions with the jammer during training. The effectiveness of this modified algorithm is evaluated by simulations in the presence of different jamming strategies and the simulation results are compared to the original q-learning algorithm applied to the same scenarios.

关键词： Cognitive radio network jamming attack markov decision process q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuzzy PID Controller Design Using q-learning algorithm with a Manipulated Reward Function

Fuzzy PID Controller Design Using Q-Learning Algorithm with ...

引用

European Control Conference (ECC)

作者： Aghaei, Vahid Tavakol Onat, Ahmet Eksin, Ibrahim Guzelkaya, Mujde Sabanci Univ Fac Engn & Nat Sci Mechatron Engn Istanbul Turkey Istanbul Tech Univ Control Engn Program Fac Elect & Elect Engn Istanbul Turkey

ISBN: (纸本)9783952426937

In this paper we propose a manipulated reward function for the q-learning algorithm which is a reinforcement learning technique and utilize the proposed algorithm to tune the parameters of the input-output membership functions of fuzzy logic controllers. The use of a reward signal to formalize the idea of a goal is one of the most distinctive features of reinforcement learning. To improve both the performance and convergence criteria of the mentioned algorithm we propose a fuzzy structure for the reward function. In order to demonstrate the effectiveness of the algorithm we apply it to two second order linear systems with and without time delay and finally a nonlinear system will be examined.

关键词： q-factor control system synthesis fuzzy control fuzzy logic learning (artificial intelligence) linear systems nonlinear systems three-term control q-learning algorithm fuzzy PID controller design fuzzy logic controllers fuzzy structure input-output membership functions manipulated reward function nonlinear system reinforcement learning technique second order linear systems algorithm design and analysis Convergence Fuzzy control Fuzzy logic learning (artificial intelligence) Tuning Zirconium

来源：评论

学校读者我要写书评

暂无评论

Research on Control Method of Expressway Off-ramp Based on q-learning algorithm and Extension Control

Research on Control Method of Expressway Off-ramp Based on Q...

引用

International Conference on Materials Science and Information Technology (MSIT 2011)

作者： Liu, Xiaoming Wang, Xiuying N China Univ Technol Intelligent Transportat Res Inst Beijing Peoples R China

ISBN: (纸本)9783037853191

The movement characteristics of traffic flow nearby have the important influence on the main line. The control method of expressway off-ramp based on q-learning and extension control is established by analyzing parameters of off-ramp and auxiliary road. First, the basic description of q-learning algorithm and extension control is given and analyzed necessarily. Then reward function is gained through the extension control theory to judge the state of traffic light. Simulation results show that compared to the queue lengths of off-ramp and auxiliary road, control method based on q-learning algorithm and extension control greatly reduced queue length of off-ramp, which demonstrates the feasibility of control strategies.

关键词： q-learning algorithm extension control off-ramp reward function

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Enhanced q-learning algorithm For Mobile Robot Path Planning 36

Ant Colony Enhanced Q-Learning Algorithm For Mobile Robot Pa...

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Xie, Tian Zhou, Yi Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China

ISBN: (纸本)9798350387780;9798350387797

q-learning algorithm is a common method for solving robot path planning problems. However, it is not only significantly time-consuming, but also prone to getting stuck in local optima. This paper presents an enhanced approach to the q-learning algorithm by incorporating ant colony optimization, which leads to better convergence of the q-learning algorithm and reduces the number of iterations and computational time. Firstly, the q-table and initial paths are constructed through interactive training between the agents and the environment. Secondly, the ant colony algorithm dynamically updates the pheromone matrix and iteratively adapts the path search strategy in the q-table. Experimental results illustrate that the enhanced q-learning algorithm exhibits superior performance compared to the original q-learning algorithm in path planning simulations, as indicated by three evaluation metrics. Furthermore, improvements are observed in terms of the length of the shortest path and the quantity of turning points, yielding smoother paths.

关键词： Mobile Robot Reinforcement learning Path Planning q-learning algorithm Ant Colony algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization of Control for Stepwise Lifting Grounding Plier Using q-learning algorithm 24

Optimization of Control for Stepwise Lifting Grounding Plier...

引用

International Conference on Machine Intelligence and Digital Applications (MIDA)

作者： Chen, Xingsong Bai, Juan Guo, Zipei Chi, Xiaobing Wang, Deyin Zou, Yu China Southern Power Grid Co Ltd Guangxi Qinzhou Power Supply Bur Qinzhou 535000 Guangxi Peoples R China

ISBN: (纸本)9798400718144

This article focuses on the problem of traditional grounding plier control lacking intelligent optimization algorithm support and difficult to adapt to complex environments. Based on the q-learning (quality learning) algorithm, the optimization of stepwise lifting grounding plier control is studied. This article first defines the state space and action space of the lifting grounding plier, and applies discretization to adapt to the q-learning algorithm. Subsequently, a reward function is designed, with safety, efficiency, and energy consumption as indicators to guide the algorithm in learning the optimal control strategy. By establishing a q-table and continuously updating it, the optimization of grounding plier control has been achieved. In the experiment, the optimized lifting speed is increased to 0.4m/s, 0.5m/s, and 0.4m/s. The lowering time is shortened to 10s, 10s, and 12.5s, and the number of shaking is significantly reduced. In the response time experiment to reduce the load, under the condition of reducing the load by 2kg, the optimized reduced response times are 0.98s, 0.96s, and 0.97s, reflecting the good adaptability of the lifting grounding plier after algorithm optimization. The experimental results show that the q-learning algorithm has a good effect on improving the control performance of grounding pliers, providing a reference for similar research.

关键词： q-learning algorithm Control Optimization Reward Function State Space and Action Space Optimal Control Strategy

来源：评论

学校读者我要写书评

暂无评论

Hyper-heuristic q-learning algorithm for Flow-Shop Scheduling Problem with Fuzzy Processing Times 19th

Hyper-heuristic Q-Learning Algorithm for Flow-Shop Schedulin...

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Zhu, Jin-Han Hu, Rong Li, Zuo-Cheng qian, Bin Zhang, Zi-qi Kunming Univ Sci & Technol Sch Informat Engn & Automat Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Sch Mech & Elect Engn Kunming 650500 Yunnan Peoples R China

ISBN: (纸本)9789819947546;9789819947553

The flow-shop scheduling problem (FSP) has been extensively studied over the past few decades. q-learning algorithms (qLAs) have been shown to be effective in evolving efficient heuristics for scheduling problems. In this paper, we propose a hyper-heuristic q-learning algorithm (HHqLA) for the FSP with fuzzy processing times (FSPF) to minimize the fuzzy makespan. FSPF accounts for the existence of various disturbing factors in the manufacturing industry thatmake the processing time fuzzy. To capture this, we use triangular fuzzy numbers (TFNs) to express the processing time more realistically. Firstly, four low-level heuristics (LLHs) are designed based on the characteristics of FSPF, and the permutations of the LLHs are used as high-level individuals. Secondly, the extraction of valuable information from excellent high-level individuals by using the q-learning algorithm (qLA). Thirdly, a newsampling strategy is designed to apply the information obtained by qLA to generate new high-level individuals and search for potential regions in the solution space. Finally, the experimental results demonstrate that the proposed HHqLA can effectively solve FSPF.

关键词： Fuzzy processing times Hyper-heuristic algorithm q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal Economic Dispatch Scheduling in Competitive Energy Market Utilizing a Greedy q-learning algorithm

Optimal Economic Dispatch Scheduling in Competitive Energy M...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Arvanitidis, Athanasios Ioannis Alamaniotis, Miltiadis University of Texas at San Antonio Electrical & Computer Engineering San Antonio United States

ISBN: (纸本)9789531842976

In the realm of deregulated electricity markets, selection of power plant units for electricity generation is considered crucial for their optimal operation. In this study, an agent-involved model simulating a competitive energy market consisted of two generation companies aiming to cover load demand and maximize revenue is examined. The agent is trained through the utilization of the q-learning algorithm embedded with a greedy reward system. The results clearly illustrate that the agent driven supplier attains the optimal economic dispatch schedule, underscoring the effectiveness of a single training session, which enables the agent to learn the most cost-effective approach to cover maximum capacity while simultaneously minimizing testing errors. Finally, the findings of this study emphasize the potential for improved decision-making for more autonomous economic dispatch processes in the dynamic landscape of competitive energy markets. © 2024 IEEE.

关键词： agent-involved model deregulated electricity markets economic dispatch schedule q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Control/Operational Strategies in WWTPs through an Integrated q-learning algorithm with ASM2d-Guided Reward

引用

WATER 2019年第5期11卷 927页

作者： Pang, Jiwei Yang, Shanshan He, Lei Chen, Yidi Ren, Nanqi Harbin Inst Technol State Key Lab Urban Water Resource & Environm Harbin 150000 Heilongjiang Peoples R China

The operation of a wastewater treatment plant (WWTP) is a typical complex control problem, with nonlinear dynamics and coupling effects among the variables, which renders the implementation of real-time optimal control an enormous challenge. In this study, a q-learning algorithm with activated sludge model No. 2d-guided (ASM2d-guided) reward setting (an integrated ASM2d-qL algorithm) is proposed, and the widely applied anaerobic-anoxic-oxic (AAO) system is chosen as the research paradigm. The integrated ASM2d-qL algorithms equipped with a self-learning mechanism are derived for optimizing the control strategies (hydraulic retention time (HRT) and internal recycling ratio (IRR)) of the AAO system. To optimize the control strategies of the AAO system under varying influent loads, q matrixes were built for both HRTs and IRR optimization through the pair of based on the integrated ASM2d-qL algorithm. 8 days of actual influent qualities of a certain municipal AAO wastewater treatment plant in June were arbitrarily chosen as the influent concentrations for model verification. Good agreement between the values of the model simulations and experimental results indicated that this proposed integrated ASM2d-qL algorithm performed properly and successfully realized intelligent modeling and stable optimal control strategies under fluctuating influent loads during wastewater treatment.

关键词： machine learning q-learning algorithm optimized control strategies activated sludge model No 2d (ASM2d) enhanced nutrients removal integrated ASM-qL algorithm

来源：评论

学校读者我要写书评

暂无评论

Coherent beam combination based on q-learning algorithm

引用

OPTICS COMMUNICATIONS 2021年 490卷 126930-126930页

作者： Zhang, Xi Li, Pingxue Zhu, Yunchen Li, Chunyong Yao, Chuanfei Wang, Luo Dong, Xueyan Li, Shun Beijing Univ Technol Fac Mat & Mfg Inst Ultrashort Pulsed Laser & Applicat Beijing 10024 Peoples R China Univ Durham Dept Phys South Rd Durham DH1 3LE England

Coherent beam combination (CBC) is an effective method to break the limiting power of a single fiber laser. The q-learning algorithm is one of the reinforcement learning algorithms. We use the q-learning algorithm to do phase compensation in the field of CBC. The performance difference between the q-learning algorithm and the stochastic parallel gradient descent optimization algorithm (SPGD) is analyzed by simulating time-domain coherent synthesis. The results show that the q-learning algorithm is easier to debug and has better stability.

关键词： Coherent beam combination q-learning algorithm Stochastic parallel gradient descent optimization algorithm

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：