检索结果-内蒙古大学图书馆

Model Predictive Adaptive Cruise Control of Intelligent Electric Vehicles Based on deep reinforcement learning algorithm FWOR Driver Characteristics

引用

INTERNATIONAL JOURNAL OF AUTOMOTIVE TECHNOLOGY 2023年第4期24卷 1175-1187页

作者： Guo, Jinghua Li, WenChang Luo, Yugong Li, Keqiang Xiamen Univ Dept Mech & Elect Engn Xiamen 361005 Peoples R China Tsinghua Univ State Key Lab Automot Safety & Energy Beijing 100084 Peoples R China

This paper presents a novel model predictive adaptive cruise control strategy of intelligent electric vehicles based on deep reinforcement learning algorithm for driver characteristics. Firstly, the influence mechanism of factors such as inter-vehicle distance, relative speed and time headway (THW) on the driver's behavior in the process of car following is analyzed by the correlation coefficient method. Then, the driver behavior in the process of car following is learned from the natural driving data, the car following model is established by the deep deterministic policy gradient (DDPG) algorithm, and the output acceleration of the DDPG model is used as the reference trajectory of the ego vehicle's acceleration. Next, in order to reflect the driver behavior and achieve multi performance objective optimization of adaptive cruise control of intelligent electric vehicles, the model predictive controller (MPC) is designed and used for tracking the desired acceleration produced by the car following DDPG model. Finally, the performance of the proposed adaptive cruise control strategy is evaluated by the experimental tests, and the results demonstrate the effectiveness of proposed control strategy.

关键词： Intelligent electric vehicles Adaptive cruise control deep reinforcement learning algorithm Naturalistic driving data Driver model

来源：评论

学校读者我要写书评

暂无评论

A Pareto-Efficient Task-Allocation Framework Based on deep reinforcement learning algorithm in MEC 18th

A Pareto-Efficient Task-Allocation Framework Based on Deep R...

引用

18th European-Alliance-for-Innovation (EAI) International Conference on Collaborative Computing - Networking, Applications and Worksharing (CollaborateCom)

作者： Liu, Wenwen Zhao, Sinong Yu, Zhaoyang Wang, Gang Liu, Xiaoguang Nankai Univ Coll Comp Sci TJ Key Lab NDST Tianjin Peoples R China

ISBN: (纸本)9783031243851;9783031243868

Mobile-edge computing (MEC) has emerged as a promising paradigm that moves tasks running in the cloud to edge servers. In MEC systems, there are various individual requirements, such as less user-perceived time and lower energy consumption. In this case, substantial efforts have been paid to task allocation, aiming at enabling lower latency and higher resource utilization. However existing studies on multiple-objectives task allocation algorithms rarely consider the Pareto efficient problem, where no objective could be further improved without vitiating the other objectives optimization. In this paper, we propose a Pareto-efficient task-allocation framework based on a deep reinforcement learning algorithm. We give the formal formulations for objectives and construct a multi-objectives' optimization model for task allocation. Then a Pareto efficient algorithm is proposed to solve the problem of conflicting among multi-objectives. By coordinating multi-objectives parameters get from Pareto efficient algorithm, the deep reinforcement learning model takes a Pareto-efficient task allocation to improve real-time and resource utilization performance. We evaluate the proposed framework over various real-world tasks and compare it with existing allocating tasks models in edge computing networks. By using the proposed framework, we can get an accuracy that not be lower than 90% under the 0.6 s latency requirement. The simulation results also show that the proposed framework achieves lower latency and higher resource utilization compared to other task allocation methods.

关键词： Mobile edge computing Pareto-efficient Task-allocation framework deep reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

deep reinforcement learning for Mobility-Aware Digital Twin Migrations in Edge Computing

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2025年第2期18卷 704-717页

作者： Zhang, Yuncan Wang, Luying Liang, Weifa City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410017 Peoples R China

The past decade witnessed an explosive growth on the number of IoT devices (objects/suppliers), including portable mobile devices, autonomous vehicles, sensors and intelligence appliances. To realize the digital representations of objects, Digital Twins (DTs) are key enablers to provide real-time monitoring, behavior simulations and predictive decisions for objects. On the other hand, Mobile Edge Computing (MEC) has been envisioned as a promising paradigm to provide delay-sensitive services for mobile users (consumers) at the network edge, e.g., real-time healthcare, AR/VR, online gaming, smart cities, and so on. In this paper, we study a novel DT migration problem for high quality service provisioning in an MEC network with the mobility of both suppliers and consumers for a finite time horizon, with the aim to minimize the sum of the accumulative DT synchronization cost of all suppliers and the total service cost of all consumers requesting for different DT services. To this end, we first show that the problem is NP-hard, and formulate an integer linear programming solution to the offline version of the problem. We then develop a deep reinforcement learning (DRL) algorithm for the DT migration problem, by considering the system dynamics and heterogeneity of different resource consumptions, mobility traces of both suppliers and consumers, and workloads of cloudlets. We finally evaluate the performance of the proposed algorithms through experimental simulations. Simulation results demonstrate that the proposed algorithms are promising.

关键词： Costs Synchronization Computational modeling Internet of Things Heuristic algorithms Digital twins Real-time systems Delays Hands deep reinforcement learning Digital twin synchronization mobility-aware DT migration cost modeling of DT migration deep reinforcement learning algorithm mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Online topology-based voltage regulation: A computational performance enhanced algorithm based on deep reinforcement learning

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2022年第24期16卷 4879-4892页

作者： Xu, Peng Wang, Beibei Zhang, Yue Zhu, Hong Southeast Univ Coll Elect Engn Nanjing 210096 Peoples R China State Grid Nanjing Power Supply Co Ltd Nanjing Peoples R China

The increasing use of distributed generation (DG) in power systems can result in frequent online voltage problems. In scenarios in which substantial DG prediction errors occur because of high DG accommodation levels, traditional technical solutions cannot meet the online voltage regulation requirements. Hence, new resources for online voltage regulation are needed. Here, flexible network reconfiguration is proposed to coordinate with the existing resources for severe online voltage deviations. For online topology-based voltage regulation (OTVR), the authors develop a deep reinforcement learning (DRL) algorithm based on the following specially designed modelling to enhance the computational performance. The mechanism of action incorporates the concepts of local research, branch exchange, and action separation, and it effectively simplifies the action dimension and action space. In addition, for the graph data in OTVR, a graph convolution network (GCN) is applied to obtain better feature extraction. Case studies performed on IEEE 14-bus, 33-bus, 141-bus systems and a practical system verify that our proposed algorithm can obtain close to optimal solutions in 2 s which can meet the needs of online voltage regulation. Moreover, we verify that the developed OTVR effectively increases DG penetration and decreases the need for investment in additional regulating devices.

关键词： substantial DG prediction errors high DG accommodation levels voltage control deep reinforcement learning algorithm online voltage regulation requirements frequent online voltage problems distributed power generation computational performance enhanced algorithm online topology-based voltage regulation reinforcement learning deep learning (artificial intelligence) graph theory feature extraction additional regulating devices power engineering computing action dimension severe online voltage deviations action space

来源：评论

学校读者我要写书评

暂无评论

deep reinforcement learning based optimal channel selection for cognitive radio vehicular ad-hoc network

引用

IET COMMUNICATIONS 2020年第19期14卷 3464-3471页

作者： Pal, Raghavendra Gupta, Nishu Prakash, Arun Tripathi, Rajeev Rodrigues, Joel J. P. C. Madanapalle Inst Technol & Sci Dept Elect & Commun Engn Madanapalle 517325 Andhra Pradesh India Vaagdevi Coll Engn Dept Elect & Commun Engn Warangal 506005 Telangana India Motilal Nehru Natl Inst Technol Allahabad Dept Elect & Commun Engn Prayagraj 211004 UP India Univ Fed Piaui Teresina PI Brazil Inst Telecomunicac Oes Aveiro Portugal

Channel selection is a challenging task in cognitive radio vehicular networks. Vehicles have to sense the channels periodically. Due to this, a lot of time is wasted which could have been utilised for transmission of data. Employing road side units (RSUs) in sensing can prove to be useful for this purpose. The RSUs may select the channel and allocate it to the vehicles on demand. However, this sensing should be proactive. RSUs should know in advance the channel to be allocated when requested. For this purpose, a deep reinforcement learning algorithm namely deep reinforcement learning based optimal channel selection is proposed in this study for training the network according to the previously sensed data. Proposed protocol is simulated and results are compared with the existing methods. The packet delivery ratio is increased by 2%, throughput is increased by 1.8%, average delay is decreased by 2% and primary user collision ratio is reduced by 3.2% when compared with similar recent work by varying number of vehicles. On the other hand, when compared with similar recent work by varying channel availability, the packet delivery ratio is increased by 4.5 %, throughput by 4.3%, average delay is decreased by 3% and PU collision ratio by 5.5%.

关键词： vehicular ad hoc networks radio spectrum management learning (artificial intelligence) cognitive radio telecommunication congestion control resource allocation protocols neural nets telecommunication computing data handling RSU deep reinforcement learning algorithm optimal channel selection sensed data packet delivery ratio channel availability cognitive radio vehicular ad-hoc network data transmission road side units proposed protocol primary user collision ratio PU collision ratio

来源：评论

学校读者我要写书评

暂无评论

Data-driven optimal PEMFC temperature control via curriculum guidance strategy-based large-scale deep reinforcement learning

引用

IET RENEWABLE POWER GENERATION 2022年第7期16卷 1283-1298页

作者： Li, Jiawen Yang, Shengchun Yu, Tao Zhang, Xiaoshun South China Univ Technol Coll Elect Power Guangzhou 510640 Peoples R China China Elect Power Res Inst Nanjing Nanjing Peoples R China Shantou Univ Coll Engn Shantou Peoples R China

As the proton exchange membrane fuel cell (PEMFC) is a nonlinear, time-varying, multiple-input multiple-output system, an advanced controller with strong robustness and adaptability is required for controlling PEMFC stack temperature and achieve a high operation efficiency. In this paper, a data driven optimal controller is proposed for controlling the stack temperature, which is based on large-scale deep reinforcement learning. In addition, a new deep reinforcement learning algorithm termed curriculum guidance strategy large-scale dual-delay deep deterministic policy gradient (CGS-L4DPG) algorithm is proposed for this controller. The design of this algorithm introduces the concepts of the curriculum guidance strategy and imitation learning, and its inclusion improves the performance and robustness of the proposed controller. The simulation results show that, taking advantage of the high adaptability and robustness of CGS-L4DPG algorithm, the proposed controller can more effectively control the PEMFC stack temperature than existing control algorithms.

关键词： deep learning (artificial intelligence) optimal controller learning (artificial intelligence) strong robustness optimisation proton exchange membrane fuel cell advanced controller controlling PEMFC stack temperature proton exchange membrane fuel cells optimal control temperature control CGS-L4DPG algorithm control algorithms curriculum guidance strategy-based large-scale reinforcement learning deep deterministic policy gradient high adaptability data-driven optimal PEMFC temperature control large-scale deep reinforcement learning curriculum guidance strategy large-scale dual-delay gradient methods imitation learning nonlinear time-varying multiple-input multiple-output system deep reinforcement learning algorithm high operation efficiency

来源：评论

学校读者我要写书评

暂无评论

Cost-Aware Digital Twin Migration in Mobile Edge Computing via deep reinforcement learning 23

Cost-Aware Digital Twin Migration in Mobile Edge Computing v...

引用

23rd International-Federation-for-Information-Processing (IFIP) Networking Conference (IFIP Networking)

作者： Zhang, Yuncan Liang, Weifa City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

ISBN: (纸本)9798350390605;9783903176638

The past decade experienced an explosive growth on the number of IoT devices connected to the Internet. Digital twins (DTs) emerge as key enablers to provide digital representations of objects for their monitoring, simulation, prediction and maintenance. At the same time, mobile edge computing (MEC) is envisioned as a promising paradigm to provide various delay-sensitive services for mobile users at the edge of core networks. In this paper, we study a novel cost-aware DT migration problem for effective service provisioning in an DT-empowered MEC network within a finite time horizon, with the aim to minimize the service cost. We first show the NP-hardness of the problem, and formulate an integer linear programming solution to the offline version of the problem, assuming that the mobility information of both objects and users for the given time horizon is given. Considering the system dynamics and heterogeneity of various resource usages, the mobility of objects and users, we then develop an efficient deep reinforcement learning algorithm for the online DT migration problem. We finally evaluate the performance of the proposed algorithms. Experimental results demonstrate that the proposed algorithms are promising.

关键词： Digital twin synchronization cost-aware DT migration mobility of suppliers and consumers deep reinforcement learning algorithm and mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

deep reinforcement learning Based on Optical Neural Networks in Path Planning

Deep Reinforcement Learning Based on Optical Neural Networks...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Yang, Zhiwei Lai, Yihang Dai, Jian Zhang, Tian Xu, Kun Beijing University of Posts and Telecommunications State Key Laboratory of Information Photonics and Optical Communications Beijing100876 China

ISBN: (纸本)9798350312614

We propose the optical deep Q network (ODQN) algorithm based on optical neural networks (ONNs) to accelerate calculation in 2D grid path planning task. The calculated results demonstrate that the innovative algorithm is competitive with the original deep Q network (DQN) algorithm based on artificial neural networks (ANNs). Further, we analyze the noise errors of ONNs and prove the relatively good robustness of the ODQN algorithm in the 2D grid world. Compared to previous works, we introduce an efficient learning strategy for ONNs and demonstrate its broad application prospects in reinforcement learning and so on. © 2023 IEEE.

关键词： deep reinforcement learning algorithm optical neural network optical noise path planning

来源：评论

学校读者我要写书评

暂无评论

A High Reliable Computing Offloading Strategy Using deep reinforcement learning for IoVs in Edge Computing

引用

JOURNAL OF GRID COMPUTING 2021年第2期19卷 15-15页

作者： Wang, Kun Wang, Xiaofeng Liu, Xuan Shanxi Univ Coll Phys & Elect Engn Taiyuan 030006 Shanxi Peoples R China State Grid Shanxi Elect Power Co Maintenance Branch Taiyuan 030000 Shanxi Peoples R China

In view of the serious problems of increasing delay energy consumption and decreasing service quality caused by complex network state and massive computing data in Internet of vehicles (IOT), a high reliable computing offloading strategy based on edge computing is proposed in this paper. Firstly, the architecture of the Internet of vehicles is designed. The real-time business of terminal vehicles is directly unloaded to the mobile edge computing (MEC) equipment for processing, which reduces the high transmission delay of data on the core network. The combination of software defined network (SDN) and MEC is used to provide flexible network control and centralized resource management for the Internet of vehicles. Then, according to the computing model, communication model and privacy protection model, a joint computing offload and resource allocation strategy is proposed. Finally, taking the shortest time delay and minimum computing cost as the optimization objectives, Q-learning is used to solve the problem to achieve the optimization of unloading strategy, that is, the optimal allocation of communication and computing resources, and the system security is the best. Based on the Matlab simulation platform, the system model is built to carry out the experimental test. The results show that compared with other strategies, the unloading strategy can achieve fast convergence and reduce the system overhead effectively, and the computation complexity, data size and the number of computation nodes have the least impact on the delay.

关键词： Internet of vehicles Edge computing Computing offloading Software defined network Privacy protection deep reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A deep reinforcement learning approach to energy management control with connected information for hybrid electric vehicles

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期123卷

作者： Mei, Peng Karimi, Hamid Reza Xie, Hehui Chen, Fei Huang, Cong Yang, Shichun Beihang Univ Sch Transportat Sci & Engn Beijing Peoples R China Politecn Milan Dept Mech Engn Milan Italy Beijing Syst Design Inst Electro Mech Engn Beijing Peoples R China Nantong Univ Sch Transportat & Civil Engn Nantong Peoples R China

Considering the importance of the energy management strategy for hybrid electric vehicles, this paper is aiming at addressing the energy optimization control issue using reinforcement learning algorithms. Firstly, this paper establishes a hybrid electric vehicle power system model. Secondly, a hierarchical energy optimization control architecture based on networked information is designed, and a traffic signal timing model is used for vehicle target speed range planning in the upper system. More specifically, the optimal vehicle speed is optimized by a model predictive control algorithm. Thirdly, a mathematical model of vehicle speed variation in connected and unconnected states is established to analyze the effect of vehicle speed planning on fuel economy. Finally, three learning-based energy optimization control strategies, namely Q-learning, deep Q network (DQN), and deep deterministic policy gradient (DDPG) algorithms, are designed under the hierarchical energy optimization control architecture. It is shown that the Q-learning algorithm is able to optimize energy control;however, the agent will meet the "dimension disaster" once it faces a high-dimensional state space issue. Then, a DQN control strategy is introduced to address the problem. Due to the limitation of the discrete output of DQN, the DDPG algorithm is put forward to achieve continuous action control. In the simulation, the superiority of the DDPG algorithm over Q-learning and DQN algorithms in hybrid electric vehicles is illustrated in terms of its robustness and faster convergence for better energy management purposes.

关键词： Hybrid electric vehicles Energy management strategy Connected vehicle deep reinforcement 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

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

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：