检索结果-内蒙古大学图书馆

12th International Conference on Smart Grid (ICSmartGrid)

作者： Nuvvula, Ramakrishna S. S. Kumar, Polamarasetty P. Ahammed, Syed Riyaz Hushein, R. Reddy, R. Siva Subramanyam Babu, Bachina Harish Ali, Ahmed NITTE Deemed be Univ NMAM Inst Technol Deparmtent Elect & Elect Engn Mangaluru Karnataka India GMR Inst Technol Dept Elect & Elect Engn Rajam India NITTE Deemed be Univ NMAM Inst Technol Dept Elect & Commun Engn Mangaluru Karnataka India Vel Tech RanagarajanDrSagunthala R&D Inst Sci & Dept Elect & Commun Chennai Tamil Nadu India Sri Kalahasteeswara Inst Technol SKIT Dept EEE Srikalahasti Andhra Pradesh India VNR Vignana Jyothi Inst Engn & Technol Dept Automobile Engn Hyderabad Telangana India Univ Johannesburg Dept Elect & Elect Engn Technol Johannesburg South Africa

ISBN: (纸本)9798350361612;9798350361629

This paper presents a comprehensive study on the application of a distributed reinforcement learning (DRL) framework for the optimization of grid-scale energy storage systems within the context of renewable energy integration. Our objective was to evaluate the framework's impact on grid stability, energy efficiency, and operational *** study involved a 12-month analysis comparing the DRL framework to a conventional baseline system. Results indicated that the DRL framework significantly improved grid stability, reducing grid disruptions by 40% and decreasing the average duration of these disruptions by 44%. This marked reduction contributed to enhanced reliability and fewer maintenance *** terms of energy efficiency, the DRL framework showed a 5.2% improvement, increasing from 86.5% to 91.7% compared to the conventional baseline. This improvement was accompanied by a 10.5% reduction in energy purchase costs, illustrating a more sustainable approach to energy storage and grid *** cost reduction was another key outcome, with the DRL framework achieving a total operational cost reduction of 12.2% over the 12-month period. This reduction included lower maintenance costs, energy purchase costs, and downtime costs, highlighting the economic benefits of implementing the DRL framework. Our discussion explores the broader implications of these findings, suggesting that the DRL framework can play a crucial role in the transition to more sustainable energy systems. Recommendations for future research include further optimization of the DRL framework, integration with smart grid technologies, and long-term studies to evaluate its robustness and adaptability.

关键词： distributed reinforcement learning Grid-Scale Energy Storage Renewable Energy Integration Smart Grids Grid Stability

来源：评论

学校读者我要写书评

暂无评论

distributed reinforcement learning for Privacy-Preserving Dynamic Edge Caching

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2022年第3期40卷 749-760页

作者： Liu, Shengheng Zheng, Chong Huang, Yongming Quek, Tony Q. S. Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China Singapore Univ Technol & Design Informat Syst Technol & Design Pillar Singapore 487372 Singapore

Mobile edge computing (MEC) is a prominent computing paradigm which expands the application fields of wireless communication. Due to the limitation of the capacities of user equipments and MEC servers, edge caching (EC) optimization is crucial to the effective utilization of the caching resources in MEC-enabled wireless networks. However, the dynamics and complexities of content popularities over space and time as well as the privacy preservation of users pose significant challenges to EC optimization. In this paper, a privacy-preserving distributed deep deterministic policy gradient (P2D3PG) algorithm is proposed to maximize the cache hit rates of devices in the MEC networks. Specifically, we consider the fact that content popularities are dynamic, complicated and unobservable, and formulate the maximization of cache hit rates on devices as distributed problems under the constraints of privacy preservation. In particular, we convert the distributed optimizations into distributed model-free Markov decision process problems and then introduce a privacy-preserving federated learning method for popularity prediction. Subsequently, a P2D3PG algorithm is developed based on distributed reinforcement learning to solve the distributed problems. Simulation results demonstrate the superiority of the proposed approach in improving EC hit rate over the baseline methods while preserving user privacy.

关键词： Servers Vehicle dynamics Privacy Optimization Training reinforcement learning Wireless networks Edge caching mobile edge computing privacy preservation distributed reinforcement learning federated learning

来源：评论

学校读者我要写书评

暂无评论

distributed reinforcement learning for Age of Information Minimization in Real-Time IoT Systems

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2022年第3期16卷 501-515页

作者： Wang, Sihua Chen, Mingzhe Yang, Zhaohui Yin, Changchuan Saad, Walid Cui, Shuguang Poor, H. Vincent State Key Lab Networking & Switching Technol Beijing Peoples R China Beijing Lab Adv Informat Network Beijing Peoples R China Beijing Univ Posts & Telecommun Beijing Key Lab Network Syst Architecture & Conve Beijing 100876 Peoples R China Princeton Univ Dept Elect & Comp Engn Princeton NJ 08544 USA UCL Dept Elect & Elect Engn London WC1E 6BT England Bradley Dept Elect & Comp Engn Virginia Tech Wireless VT Arlington VA USA Chinese Univ Hong Kong Sch Sci & Engn SSE Shenzhen 518172 Peoples R China Chinese Univ Hong Kong Future Network Intelligence Inst FNii Shenzhen 518172 Peoples R China Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China

In this paper, the problem of minimizing the weighted sum of age of information (AoI) and total energy consumption of Internet of Things (IoT) devices is studied. In the considered model, each IoT device monitors a physical process that follows nonlinear dynamics. As the dynamics of the physical process vary over time, each device should find an optimal sampling frequency to sample the real-time dynamics of the physical system and send sampled information to a base station (BS). Due to limited wireless resources, the BS can only select a subset of devices to transmit their sampled information. Thus, edge devices can cooperatively sample their monitored dynamics based on the local observations and the BS will collect the sampled information from the devices immediately, hence avoiding the additional time and energy used for sampling and information transmission. To this end, it is necessary to jointly optimize the sampling policy of each device and the device selection scheme of the BS so as to accurately monitor the dynamics of the physical process using minimum energy. This problem is formulated as an optimization problem whose goal is to minimize the weighted sum of AoI cost and energy consumption. To solve this problem, we propose a novel distributed reinforcement learning (RL) approach for the sampling policy optimization. The proposed algorithm enables edge devices to cooperatively find the global optimal sampling policy using their own local observations. Given the sampling policy, the device selection scheme can be optimized thus minimizing the weighted sum of AoI and energy consumption of all devices. Simulations with real PM 2.5 pollution data show that the proposed algorithm can reduce the sum of AoI by up to 17.8% and 33.9%, respectively, and the total energy consumption by up to 13.2% and 35.1%, respectively, compared to a conventional deep Q network method and a uniform sampling policy.

关键词： Monitoring Optimization Internet of Things Energy consumption Nonlinear dynamical systems Vehicle dynamics Real-time systems Physical process sampling frequency age of information distributed reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Platoons In Urban Road Networks:A Joint distributed reinforcement learning and Model Predictive Control Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 141-156页

作者： Luigi D’Alfonso Francesco Giannini Giuseppe Franzè Giuseppe Fedele Francesco Pupo Giancarlo Fortino IEEE the Department of Computer Engineering ModelingElectronics and SystemsUniversitàdella CalabriaVia Pietro BucciCubo 42-CRende(CS)87036Italy the Department of Mechanical Engineering Energy Engineering and ManagementUniversitàdella CalabriaVia Pietro BucciCubo 42-CRende(CS)87036Italy

In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the a

关键词： distributed model predictive control distributed reinforcement learning routing decisions urban road networks

来源：评论

学校读者我要写书评

暂无评论

RHRA-DRL: RSU-Assisted Hybrid Road-Aware Routing Using distributed reinforcement learning in Internet of Vehicles

引用

IEEE ACCESS 2024年 12卷 25385-25396页

作者： Park, Joo-Hyung Yang, Qin Yoo, Sang-Jo Inha Univ Dept Elect & Comp Engn Incheon 402751 South Korea

In this paper, we propose a novel RSU-assisted hybrid road-aware routing algorithm, RHRA-DRL, designed for urban vehicular networks to optimize real-time data delivery considering dynamic road conditions. The algorithm minimizes broadcast overhead and efficiently determines optimal routing paths by incorporating two key components. Firstly, a multihop road-segment reward-based ad-hoc (RRAH) routing algorithm is introduced to adaptively respond to changing vehicle topologies within road segments. Rewards are calculated based on performance metrics, and the segment reward integrates into RSU-to-RSU (R2R) routing. Secondly, a distributed Q-learning-based road-aware (DQRA) routing algorithm determines RSUs traversed during data transmission using a decentralized agent reinforcement learning approach. The combination of these algorithms in RHRA-DRL ensures effective and consistent path establishment with a unified reward system. Simulation results demonstrate the superiority of RHRA-DRL over AODV in Internet of Vehicles (IoV) networks, showcasing enhanced communication, prolonged link lifetime, rapid establishment and repair of routing paths, and reduced overhead.

关键词： Routing Roads Vehicle dynamics Q-learning Heuristic algorithms Routing protocols Vehicular ad hoc networks reinforcement learning Intelligent transportation systems Internet of Vehicles distributed management Data routing distributed reinforcement learning intelligent transportation system vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

distributed reinforcement learning for Real-Time Batteries Control Using Lagrangian Decomposition 5

Distributed Reinforcement Learning for Real-Time Batteries C...

引用

5th International Conference on Smart Energy Systems and Technologies (SEST)

作者： Stai, Eleni Stanojev, Ognjen di Prata, Riccardo de Nardis Hug, Gabriela Swiss Fed Inst Technol EEH Power Syst Lab Phys Str 3 CH-8092 Zurich Switzerland

ISBN: (数字)9781665405577

ISBN: (纸本)9781665405577

This paper presents an efficient distributed realtime control scheme for a set of batteries in power grids to follow a day-ahead dispatch plan. The problem of controlling the batteries is cast as a multistep optimization problem aiming to minimize the error in dispatch following while satisfying lookahead constraints of the individual batteries. To achieve a computationally efficient solution, Lagrangian decomposition is used to distribute the task into subproblems pertaining to each battery. Finally, each subproblem is reformulated as a Markov Decision Process and solved with the fitted Q-iteration. Communication among subproblems is achieved via the common Lagrange multiplier value. Simulation results demonstrate that this approach has a similar cost performance to the state-of-the-art model predictive control solution, while achieving better performance in terms of computation time.

关键词： active distribution grids battery energy storage real-time control distributed reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for distributed reinforcement learning

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2024年第1期17卷 1-18页

作者： Ren, Jineng Wenzhou Univ Chashan Univ Town Sch Comp Sci & Artificial Intelligence Wenzhou 325035 Zhejiang Peoples R China Wenzhou Univ Chashan Univ Town Artificial Intelligence & Adv Mfg Inst Yongjia Wenzhou 325035 Zhejiang Peoples R China

This paper proposes a gradient-based multi-agent actor-critic algorithm for off-policy reinforcement learning using importance sampling. Our algorithm is incremental with full gradients, and its complexity per iteration scales linearly with the size of approximation features. Previous multi-agent actor-critic algorithms are limited to the on-policy setting or off-policy emphatic temporal difference (TD) learning and they do not take advantage of the advances in off-policy gradient temporal difference learning (GTD). As a theoretical contribution, we establish that the critic step of the proposed algorithm converges to the TD solution of the projected Bellman equation and the actor step converges to the set of asymptotically stable fixed points. Numerical experiments on the multi-agent generalization of the Boyan's chain problem show that the proposed approach provides improved performances in terms of stability and convergence rate as compared with the state-of-the-art baseline algorithm.

关键词： Multi-agent actor-critic algorithm Off policy Gradient temporal difference distributed reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

distributed reinforcement learning Algorithm for Multi-Wave Fire Fighting Scheduling Problem 16th

Distributed Reinforcement Learning Algorithm for Multi-Wave ...

引用

16th IFAC Symposium on Large Scale Complex Systems - Theory and Applications (LSS)

作者： Chen, Xiaoyu Fu, Junjie Zhou, Jialing Li, Yuheng Liaoning Technolog Univ Coll Sci Fuxin Peoples R China Southeast Univ Sch Math Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Automat Nanjing Peoples R China Purple Mt Labs Nanjing Peoples R China

This paper studies the distribution of FFEs (fire fighting equipments) carried by UAVs (unmanned aerial vehicles) from FFUs (fire fighting units) under the background of multi-wave forest fire. The objective is to allocate the FFEs of each FFU to minimize the sum of the probabilities of each fire site's unsuccessful extinguishment. In order to solve the multi-wave equipment distribution problem of the FFUs, a distributed reinforcement learning algorithm is designed in this paper. In the algorithm, agents cooperate to find the optimal distribution of FFEs based on information exchange, and a local Q-function is established for each agent to find the optimal FFE distribution combination. Simulation results demonstrate the effectiveness of the algorithm.

关键词： Multi-agent systems distributed reinforcement learning FFE UAV fire fighting

来源：评论

学校读者我要写书评

暂无评论

Topology Optimization of Wireless Sensor Networks based on Full Interactive distributed reinforcement learning 9

Topology Optimization of Wireless Sensor Networks based on F...

引用

9th IEEE World Forum on the Internet of Things (WF-IoT) - The Blue Planet - A Marriage of Sea and Space

作者： Sun, Wei Wang, Wenhao Li, Qiyue Li, Weitao Hefei Univ Technol Sch Elect & Automat Engn Hefei Peoples R China

ISBN: (纸本)9798350311617;9798350311624

Deploying a large number of sensor nodes within a certain area can form Wireless Sensor Networks. Wireless Sensor Networks enable real-time collection and monitoring of environmental information through communication between sensor nodes and adjust the number of sensor nodes to meet the requirements of different application scenarios. However, Wireless Sensor Networks are susceptible to environmental influences. Dynamic changes in the environment may lead to a decrease in communication quality or even interruptions of communication links, resulting in changes in the network's topology structure. This paper proposes a topology optimization method for WSNs based on Fully Interactive distributed reinforcement learning. The algorithm equips the agent with the ability to assess correlations between sensor nodes and update its parameters by obtaining global parameter information, which benefits its learning process. Subsequently, the agent devises a strategy based on the updated parameters. Through this distributed reinforcement learning method, the transmission power of sensor nodes can be dynamically and efficiently adjusted, providing a low-latency and highly stable communication network for wireless sensor networks.

关键词： Wireless Sensor Networks Full Interaction distributed reinforcement learning Topological optimization

来源：评论

学校读者我要写书评

暂无评论

A distributed reinforcement learning and model predictive control architecture for routing decisions in urban road networks 22

A distributed reinforcement learning and model predictive co...

引用

22nd World Congress of the International Federation of Automatic Control (IFAC)

作者： Giannini, Francesco Fortino, Giancarlo Franze, Giuseppe Pupo, Francesco Univ Calabria DIMES Calabria Italy Univ Calabria DIMEG Calabria Italy

ISBN: (纸本)9781713872344

In this paper, platoons of autonomous vehicles in urban road networks are considered. From a methodological point of view, the problem consists in characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data and a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Copyright (c) 2023 The Authors.

关键词： Autonomous vehicles Routing decisions distributed reinforcement learning distributed Model Predictive Control

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：