检索结果-内蒙古大学图书馆

17th IEEE International Conference on Parallel and Distributed Systems (ICPADS)

作者： Chen, Jiann-Liang Larosa, Yanuarius Teofilus Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei Taiwan

ISBN: (纸本)9780769545769

In realizing cyber-physical systems, research on developing network supported with predictable quality of Service (qoS) is extremely important. This study exploits heterogeneous networking as communication medium of cyber-physical application using a distributed multi-agent scheme (DMAS). The DMAS is based on the concept of cooperation and the awareness algorithm. The proposed scheme is developed for supporting qoS management which consists of a collection of problem-solving agents with three modules: the knowledge source, the in-cloud blackboard system, and the control engine built into the scheme. A set of problem-solving agents autonomously process local tasks and cooperatively interoperate via an in-cloud blackboard system to guarantee qoS. An awareness algorithm, called the q-learning algorithm, calculates the exceptive rewards of a handoff to all access networks. These rewards are then used by these problem-solving agents to determine what to do. Through operations and cooperation among the active agents, a policy is selected and a user-accepted schedule that meets the specified qoS is generated. In addition, to realize actual results, an integrated test-bed emulation network based on NetFPGA-OpenFlow platform is purposed in this paper.

关键词： Heterogeneous Wireless Networks Cooperative Networking Distributed Multi-Agent Scheme q-learning algorithm quality of Service NetFPGA

来源：评论

学校读者我要写书评

暂无评论

Research on comprehensive assessment of regional renewable energy consumption in the electricity market environment 6

Research on comprehensive assessment of regional renewable e...

引用

6th International Conference on Energy, Power and Grid, ICEPG 2024

作者： Cai, qiuna Dong, Kai Wu, Guobing Lu, En Chen, Zhongfei Li, Yupeng Jing, Zhaoxia Guangdong Power Grid Co. Ltd China Electric Power Dispatching Control Center Guangzhou510600 China South China University of Technology School of Electric Power Engineering Guangzhou510641 China

ISBN: (纸本)9798350377798

Building a new power system with renewable energy as the main body is a key measure and inevitable requirement to help achieve the goals of carbon peaking and carbon neutrality. The electricity market is an essential source of support for the construction of new power systems. Research on the role of renewable energy in the assessment of the electricity market environment consumption is of great significance. First, a threestage mathematical model of the regional electricity market evolution process is constructed, and the market equilibrium at each stage is solved. Then, based on the q-learning reinforcement learning algorithm, a multi-agent market clearing model regarding the subject's quotation strategy under imperfect competition was established, and an evaluation system including multi-dimensional indicators such as renewable energy consumption space and adequacy was built. Finally, standard node examples are used to systematically analyze carbon emission models, market equilibrium results, renewable energy consumption, multi-agent simulation, and other scenarios under different regional electricity market evolution stages, providing feasible policy suggestions for the problems. © 2024 IEEE.

关键词： electricity market multi-agent model q-learning algorithm renewable energy consumption

来源：评论

学校读者我要写书评

暂无评论

A Personalized E-learning System Using Reinforcement learning Through Satellite 20

A Personalized E-Learning System Using Reinforcement Learnin...

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Kiran, Pooja Prasad, B K Swathi Sivasubramanian, Jayahar University of Applied Sciences Dept. of Cse Fet Ms Ramaiah Bengaluru560058 India University of Applied Sciences Dept. of Ee Fet Ms Ramaiah Bengaluru560058 India University of Applied Sciences Dept of Ase Fet Ms Ramaiah Bengaluru560058 India

ISBN: (纸本)9798350305593

This paper discusses an educational system that leverages Reinforcement learning (RL) to facilitate interactive learning experiences for students. The system consists of a web server, a student environment, and a satellite connection. The web server serves as the central hub for managing the educational content and facilitating communication between the student environment and the satellite. The student environment comprises a Math quiz and a question Generator, providing interactive learning activities for students. Through RL techniques, the system adapts to students' learning progress and dynamically adjusts the difficulty level of the quizzes. The RL agent within the student environment uses a q-learning algorithm to update its policy based on the feedback received from the students' responses. Overall, this E-learning system provides an engaging and personalized learning experience by combining RL, interactive quizzes, and real-time feedback, empowering students to enhance their knowledge and skills. © 2023 IEEE.

关键词： q-learning algorithm Reinforcement learning (RL) Satellite Communication Student Environment Web Server

来源：评论

学校读者我要写书评

暂无评论

Application and Comparison of Search algorithms in Artificial Intelligence 24

Application and Comparison of Search Algorithms in Artificia...

引用

8th International Conference on Big Data and Internet of Things

作者： Yuan, Hang China Commun Informat Technol Grp Beijing Peoples R China

ISBN: (纸本)9798400717529

Searching for people after an earthquake is an important part of emergency rescue work. Finding trapped people in a timely and accurate manner is crucial to reducing casualties and improving rescue efficiency. Traditional blind search algorithms are often inefficient due to the lack of effective guidance strategies. Heuristic search algorithms improve search efficiency by combining heuristic functions, but they still have limitations in complex environments. To solve this problem, this paper proposes an improved q-learning algorithm based on reinforcement learning that combines dynamic exploration rate, experience replay, and target network for searching for people after an earthquake. The algorithm reduces the randomness in the exploration process by dynamically adjusting the exploration rate, uses experience replay to improve learning efficiency, and introduces a target network to stabilize the training process. Experimental results show that the improved reinforcement learning q-learning algorithm is significantly superior to traditional blind search and heuristic search algorithms in terms of search efficiency and accuracy.

关键词： Artificial Intelligence Search algorithm Reinforcement learning q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Path planning for unmanned vehicles based on reinforcement learning 24

Path planning for unmanned vehicles based on reinforcement l...

引用

8th International Conference on Big Data and Internet of Things

作者： Yao, Junfeng China Commun Informat Technol Grp Wuhan Hubei Peoples R China

ISBN: (纸本)9798400717529

In recent years, the rapid development of the express delivery industry has made the logistics delivery problem a key bottleneck in the logistics field. This problem not only affects delivery efficiency, but also increases operating costs and reduces customer satisfaction. With the development of science and technology, the application of unmanned vehicles has provided a new opportunity to solve this problem. This paper aims to optimize the logistics delivery path by improving the q-learning algorithm in reinforcement learning to improve logistics efficiency and customer experience. In the study, we first established a simulated urban delivery environment and defined the state, action and reward functions. Using the improved q-learning algorithm, the delivery path was trained and optimized multiple times to find the optimal path strategy. The experimental results show that compared with the traditional algorithm, the q-learning algorithm performs well in path optimization and time saving, and effectively improves the delivery efficiency. Through this study, the potential of reinforcement learning in logistics distribution optimization is verified, and it provides a valuable reference for future intelligent logistics systems.

关键词： Artificial Intelligence Reinforcement learning Route Plan Driver-less Vehicle q-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Flexible q-relearning Method to Accelerate learning Under the Change of Environments by Reusing a Portion of Useful Policies

A Flexible Q-relearning Method to Accelerate Learning Under ...

引用

Society of Instrument and Control Engineers Annual Conference

作者： Masanori Saito Kazuaki Masuda Kenzo Kurihara Faculty of Engineering Kanagawa University

ISBN: (纸本)9781467322591

We propose a relearning method for q-learning algorithm, called "q-relearning," to accelerate learning under the change of environments by reusing a portion of useful policies. To deal with the problem that q-learning algorithm can't adapt to the change of environments efficiently, we developed an original q-relearning method in the past study. However, there was little flexibility in choosing the portion to be reused. In this paper, we revise the q-relearning method to permit any choice of the portion by adding the possibility to update the fixed q-values under particular conditions. We show the effectiveness of the improved q-relearning method by numerical experiments.

关键词： Machine learning Reinforcement learning q-learning algorithm Relearning

来源：评论

学校读者我要写书评

暂无评论

Smart City Distributed Trade Economy Dynamic Scheduling of E-Commerce Platform Based on Reinforcement learning algorithm

引用

JOURNAL OF TESTING AND EVALUATION 2024年第3期52卷 1804-1816页

作者： Tang, Yimeng Chongqing Inst Foreign Studies Sch Int Business & Management 18 Longshi Rd Chongqing 401120 Peoples R China

In order to improve the reliability and economy of decentralized trade economy dynamic scheduling on e-Commerce platforms and shorten the running time of decentralized trade economy dynamic scheduling on e-Commerce platforms, a decentralized trade economy dynamic scheduling method based on the reinforcement learning algorithm is proposed. In this paper, we analyze the basic theory of the reinforcement learning algorithm, study the q -learning algorithm, build a neural network to fit the value model, and initialize the reinforcement learning algorithm. With Markov decision process as the framework model, the optimal state behavior value function is updated by using the modeless discounted reward reinforcement learning algorithm q-learning as the value iteration method. Gibbs distribution is used to construct exploratory random strategies to select behaviors with probability. Using the reinforcement learning algorithm and the three-layer feedforward neural network as the approximator of the state behavior value function, this paper studies the generalization of the value function faced by the decentralized trade economy dynamic scheduling of e-Commerce platforms and realizes the decentralized trade economy dynamic scheduling of e-Commerce platforms. The experimental results show that the proposed method can effectively improve the reliability and economy of the decentralized trade economy dynamic scheduling of e-Commerce platforms.

关键词： reinforcement learning algorithm q-learning algorithm e-Commerce platform decentralized trade economy dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

RLEAFS: Reinforcement learning-Based Energy Aware Forwarding Strategy for NDN-Based IoT Networks

引用

IEEE ACCESS 2024年 12卷 177173-177188页

作者： Askar, Naeem Ali Habbal, Adib Karabuk Univ Fac Engn Dept Comp Engn TR-78050 Karabuk Turkiye

Named data networking (NDN) is a recently developed Internet paradigm that satisfies the majority of the Internet of Things (IoT) requirements and may eventually replace the current Internet architecture. The new features introduced by NDN, such as self-certifying contents, receiver-based service, caching, and name-based routing, clearly increase the effectiveness of data transmission. NDN additionally provides lightweight forwarding rules that are appropriate for limited devices. Because of these characteristics, NDN is a very promising for IoT communication. IoT networks, composed of a large number of heterogeneous and resource-constrained devices, benefit from NDN's ability to handle challenges related to mobility, scalability, and security. However, deploying NDN-based IoT networks raises several issues caused by excessive interest packet forwarding. To address these challenges, we propose Reinforcement learning-based Energy-Aware Forwarding Strategy (RLEAFS), a novel strategy for NDN-based IoT communications that leverages reinforcement learning to optimize forwarding decisions. Our Strategy integrates q learning algorithm into path selection procedure, focusing on minimizing energy consumption and extending network lifetime while maintaining efficient data delivery. The proposed RLEAFS Strategy consists of two schemes: one designed to handle the dynamic and complex nature of real-world IoT environments, and another focused on improving the interest forwarding strategy to reduce network overhead. We implemented RLEAFS in ndnSIM to evaluate its performance against state-of-the-art NDN-based IoT forwarding strategies. The results demonstrated that RLEAFS significantly outperforms existing forwarding strategies in terms of energy consumption, network lifetime, data retrieval time, user satisfaction rates, and scalability, proving its effectiveness and robustness for IoT communications.

关键词： Internet of Things Storms q-learning Energy consumption Ad hoc networks Wireless communication Security named data networking forwarding strategy machine learning q-learning algorithm efficient energy consumption

来源：评论

学校读者我要写书评

暂无评论

A learning algorithm for TWDM-PON' DWBA with 5G fronthaul networks

引用

OPTICAL FIBER TECHNOLOGY 2019年 53卷 102039-000页

作者： Liang, Siyuan Zhao, Feng Jiang, Wenli Xian Univ Posts & Telecommun Shaanxi Key Lab Informat Commun Network & Secur Xian 710121 Shaanxi Peoples R China Xi An Jiao Tong Univ 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China

Time and wavelength-division multiplexed passive optical network (TWDM-PON) is expected to be the fronthaul networks of 5G, which requires low latency and large bandwidth. In this paper, we propose a q-learning based dynamic wavelength and bandwidth allocation (DWBA) algorithm for TWDM-PON. Simulation results show that the proposed DWBA algorithm can reduce the number of active channels by 40% and provide larger bandwidth with same wavelength number in comparation with the existing algorithms while satisfying the latency requirement of 5G fronthaul networks.

关键词： 5G networks Dynamic wavelength and bandwidth allocation NG-PON2 q-learning algorithm TWDM-PON

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Wheeled Mobile Robot in Partially Known Uneven Terrain

引用

SENSORS 2022年第14期22卷 5217-5217页

作者： Zhang, Bo Li, Guobin Zheng, qixin Bai, Xiaoshan Ding, Yu Khan, Awais Shenzhen Univ Coll Mechatron & Control Engn Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen City Joint Lab Autonomous Unmanned Syst Shenzhen 518060 Peoples R China

Path planning for wheeled mobile robots on partially known uneven terrain is an open challenge since robot motions can be strongly influenced by terrain with incomplete environmental information such as locally detected obstacles and impassable terrain areas. This paper proposes a hierarchical path planning approach for a wheeled robot to move in a partially known uneven terrain. We first model the partially known uneven terrain environment respecting the terrain features, including the slope, step, and unevenness. Second, facilitated by the terrain model, we use A(star) algorithm to plan a global path for the robot based on the partially known map. Finally, the q-learning method is employed for local path planning to avoid locally detected obstacles in close range as well as impassable terrain areas when the robot tracks the global path. The simulation and experimental results show that the designed path planning approach provides satisfying paths that avoid locally detected obstacles and impassable areas in a partially known uneven terrain compared with the classical A(star) algorithm and the artificial potential field method.

关键词： hierarchical path planning uneven terrain A(star) algorithm q-learning 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：