检索结果-内蒙古大学图书馆

IEEE International Mediterranean Conference on Communications and Networking (IEEE MeditCom)

作者： Mohamed, Ramy Avgeris, Marios Leivadeas, Aris Lambadaris, Ioannis Carleton Univ Dept Syst & Comp Engn Ottawa ON Canada Ecole Technol Super Dept Software & IT Engn Montreal PQ Canada

ISBN: (纸本)9798350309492;9798350309485

Appropriate deployment of Virtual Network Functions (VNFs) within the network infrastructure to optimize resource utilization, while fulfilling performance criteria, is critical to Network Function Virtualization (NFV). However, traditional optimization methods frequently struggle to deal with the dynamic and complex nature of the VNF placement problem. Therefore, this study proposes an online VNF placement approach that addresses these problems by leveraging Deep Reinforcement Learning (DRL) and Reward Constrained Policy optimization (RCPO). This technique combines DRL's adaptability with RCPO's constraint incorporation capabilities, ensuring that the learned policies satisfy performance and resource restrictions while optimizing the overall VNF placement. Hence, the VNF placement problem is formulated as a constrained optimization problem and adapted to the DRL setting. We demonstrate that our proposed framework outperforms certain state-of-the-art VNF placement techniques when it comes to resource utilization and constraint satisfaction.

关键词： neural combinatorial optimization Reinforcement Learning 5G NFV SFC VNF Placement

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Method for Optical Thin-Film Design

引用

IEICE TRANSACTIONS ON ELECTRONICS 2022年第2期E105C卷 95-101页

作者： Jiang, Anqing Yoshie, Osamu Waseda Univ Grad Sch Informat Prod & Syst Kitakyushu 8080135 Japan

Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.

关键词： optical thin-film design reinforcement learning neural combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing Systems

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第7期23卷 8704-8714页

作者： Bogyrbayeva, Aigerim Jang, Sungwook Shah, Ankit Jang, Young Jae Kwon, Changhyun Univ S Florida Dept Ind & Management Syst Engn Tampa FL 33620 USA Korea Adv Inst Sci & Technol Dept Ind & Syst Engn Daejeon 34141 South Korea

This paper proposes a reinforcement learning approach for nightly offline rebalancing operations in free-floating electric vehicle sharing systems (FFEVSS). Due to sparse demand in a network, FFEVSS requires relocation of electrical vehicles (EVs) to charging stations and demander nodes, which is typically done by a group of drivers. A shuttle is used to pick up and drop off drivers throughout the network. The objective of this study is to solve the shuttle routing problem to finish the rebalancing work in minimal time. We consider a reinforcement learning framework for the problem, in which a central controller determines the routing policies of a fleet of multiple shuttles. We deploy a policy gradient method for training recurrent neural networks and compare the obtained policy results with heuristic solutions. Our numerical studies show that unlike the existing solutions in the literature, the proposed methods allow solving the general version of the problem with no restrictions on the urban EV network structure and charging requirements of EVs. Moreover, the learned policies offer a wide range of flexibility, resulting in a significant reduction in the time needed to rebalance the network.

关键词： Shared mobility reinforcement learning neural combinatorial optimization vehicle routing

来源：评论

学校读者我要写书评

暂无评论

Simultaneous task and energy planning using deep reinforcement learning

引用

INFORMATION SCIENCES 2022年 607卷 931-946页

作者： Wang, Di Hu, Mengqi Weir, Jeffery D. Univ Illinois Dept Mech & Ind Engn Chicago IL 60607 USA Air Force Inst Technol Dept Operat Sci Wright Patterson AFB OH 45433 USA

To improve energy awareness of unmanned autonomous vehicles, it is critical to co optimize task planning and energy scheduling. To the best of our knowledge, most of the existing task planning algorithms either ignore energy constraints or make energy scheduling decisions based on simple rules. To bridge these research gaps, we propose a combinatorial optimization model for the simultaneous task and energy planning (STEP) problem. In this paper, we propose three variants of STEP problems (i) the vehicle can visit stationary charging stations multiple times at various locations;(ii) the vehicle can efficiently coordinate with mobile charging stations to achieve zero waiting time for recharging, and (iii) the vehicle can maximally harvest solar energy by considering time variance in solar irradiance. Besides, in order to obtain fast and reliable solutions to STEP problems, we propose a neural combinatorial optimizer using the deep reinforcement learning algorithm with a proposed link information filter. The near-optimal solutions can be obtained very fast without solving the problem from scratch when environments change. Our simulation results demonstrate that (i) our proposed neural optimizer can find solutions close to the optimum and outperform the exact and heuristic algorithms in terms of computational cost;(ii) the end-to-end learning (directly mapping from perceptions to control) model outperforms the traditional learning (mapping from perception to prediction to control) model. (c) 2022 Elsevier Inc. All rights reserved.

关键词： Simultaneous task and energy planning neural combinatorial optimization Deep reinforcement learning End-to-end learning Sequence-to-sequence decision

来源：评论

学校读者我要写书评

暂无评论

D2A: Operating a Service Function Chain Platform With Data-Driven Scheduling Policies

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2022年第3期19卷 2839-2853页

作者： Kraemer, Patrick Diederich, Philip Kraemer, Corinna Pries, Rastin Kellerer, Wolfgang Blenk, Andreas Tech Univ Munich Chair Commun Networks D-80333 Munich Germany Deutsch Sparkassenverlag GmbH D-70563 Stuttgart Germany Nokia Bell Labs Nokia Strategy & Technol D-81541 Munich Germany Siemens AG Corp Technol D-80333 Munich Germany

Realizing Service Function Chaining with a micro-service-based architecture results in an increased number of computationally cheap Virtual Network Functions (VNFs). Pinning cheap VNFs to dedicated CPU cores can waste resources since not every VNF fully utilizes its core. Thus, cheap VNFs should share CPU cores to improve resource utilization. However, sharing cores can result in degraded performance due to interference between VNFs, even in mildly loaded scenarios. We propose D(2)A, a system that combines neural combinatorial optimization, Machine Learning (ML)-based Digital Twins (DTs), and Game Theory to optimize VNF assignments. Measurements in a testbed show that D(2)A increases throughput by up to 46% and reduces latency by up to 93%, compared to three baseline algorithms. Using an ML-based DT to model VNF interference increases throughput by up to 11%, and reduces latency by up to 90% compared to an analytical model of the system.

关键词： Behavioral sciences Noise measurement Kernel Interference Task analysis Scheduling Throughput Reinforcement learning network virtualization game theory neural combinatorial optimization digital twin graph neural networks service function chaining

来源：评论

学校读者我要写书评

暂无评论

Graph Q-learning Assisted Ant Colony optimization for Vehicle Routing Problems with Time Windows

Graph Q-learning Assisted Ant Colony Optimization for Vehicl...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Yue, Peng Liu, Shiqing Jin, Yaochu Northeastern Univ Shenyang Liaoning Peoples R China Bielefeld Univ Bielefeld Germany

ISBN: (纸本)9798400701207

Vehicle routing problem with time windows (VRPTW) is a typical class of constrained path planning problems in the field of combinatorial optimization. VRPTW considers a delivery task for a given set of customers with time windows, and the target is to find optimal routes for a group of vehicles that can minimize the total transportation cost. The traditional heuristics suffer from several limitations when solving VRPTW, such as poor scalability, sensitivity to hyperparameters and difficulty in handling complex constraints. Recent advance in machine learning makes it possible to enhance heuristic approaches via learned knowledge. In this paper, we propose a graph Q-learning assisted ant colony optimization algorithm named GQL-ACO to solve VRPTW. Compared to vanilla ant colony optimization (ACO), our proposed method first employs the learned heuristic values by using graph Q learning, instead of handcrafted ones, to define the hyperparameters of ACO. Second, we design a collaborative search strategy by combining ACO and Q-learning effectively, which can adaptively adjust the hyperparameters of ACO based on the search experiences.

关键词： Ant Colony optimization Deep Q-Learning Graph neural Network neural combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

An edge-aware graph autoencoder trained on scale-imbalanced data for traveling salesman problems

引用

KNOWLEDGE-BASED SYSTEMS 2024年 291卷

作者： Liu, Shiqing Yan, Xueming Jin, Yaochu Bielefeld Univ Fac Technol Nat Inspired Comp & Engn D-33619 Bielefeld Germany Guangdong Univ Foreign Studies Sch Informat Sci & Technol Guangzhou 510006 Peoples R China Westlake Univ Sch Engn Hangzhou 310030 Peoples R China

In recent years, there has been a notable surge in research on machine learning techniques for combinatorial optimization. It has been shown that learning -based methods outperform traditional heuristics and mathematical solvers on the Traveling Salesman Problem (TSP) in terms of both performance and computational efficiency. However, most learning -based TSP solvers are primarily designed for fixed -scale TSP instances, and also require a large number of training samples to achieve optimal performance. To fill this gap, this work proposes a data -driven graph representation learning method for solving TSPs with various numbers of cities. Specifically, we formulate the TSP as a link prediction task and propose an edge -aware graph autoencoder (EdgeGAE) model that can solve TSPs by learning from various -scale samples with an imbalanced distribution. A residual gated encoder is trained to learn latent edge embeddings, followed by an edge -centered decoder to output link predictions in an end -to -end manner. Furthermore, we introduce an active sampling strategy into the training process to improve the model's generalization capability in large-scale scenarios. To investigate the model's practical applicability, we generate a scale-imbalanced dataset comprising 50,000 TSP instances ranging from 50 to 500 cities. The experimental results demonstrate that the proposed edge -aware graph autoencoder model achieves a highly competitive performance among state-of-the-art graph learning -based approaches in solving TSPs with various scales, implying its remarkable potential in dealing with practical optimization challenges.

关键词： Traveling salesman problem Graph neural network Link prediction neural combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

neural Order-First Split-Second Algorithm for the Capacitated Vehicle Routing Problem 5th

Neural Order-First Split-Second Algorithm for the Capacitate...

引用

4th International Conference on optimization and Learning (OLA)

作者： Yaddaden, Ali Harispe, Sebastien Vasquez, Michel Univ Montpellier IMT Mines Ales EuroMov Digital Hlth Mot Ales France

ISBN: (纸本)9783031220388;9783031220395

Modern machine learning, including deep learning models and reinforcement learning techniques, have proven effective for solving difficult combinatorial optimization problems without relying on handcrafted heuristics. In this work, we present NOFSS, a neural Order-First Split-Second deep reinforcement learning approach for the Capacity Constrained Vehicle Routing Problem (CVRP). NOFSS consists of a hybridization between a deep neural network model and a dynamic programming shortest path algorithm (Split). Our results, based on intensive experiments with several neural network model architectures, show that such a two-step hybridization enables learning of implicit algorithms (i.e. policies) producing competitive solutions for the CVRP.

关键词： neural combinatorial optimization Capacitated vehicle routing problem Order-first split-second Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Container Cluster Placement Strategy in Edge Computing Environment

Deep Reinforcement Learning Based Container Cluster Placemen...

引用

IEEE Global Communications Conference (GLOBECOM)

作者： Chen, Zhuo Zhu, Bowen Chongqing Univ Technol Coll Comp Sci & Engn Chongqing Peoples R China

ISBN: (纸本)9781665435406

Container-based virtualization technology has been increasingly used in edge clouds recently due to its advantages of lighter resource occupation, faster startup capability, and better resource utilization efficiency. For a task request, it is usually necessary to interconnect multiple containers to build a Container Cluster (CC), and then deploy it to edge service nodes with relatively limited resources. However, the increasingly complex and time-varying nature of tasks brings great challenges to optimally deploying CC on edge nodes. From the perspective of edge service provider, this paper regards the charges for various resources occupied by providing services as revenue, and regards the service efficiency and energy consumption generated by providing services as cost, then formulate an integer optimization model to describe the optimal deployment of CC on distributed edge nodes. Different from the heuristic-based methods adopted in existing works, we introduce Graph Convolutional Network (GCN) to extract features from the logical topological link relationships among containers in CCs and use them as the input of the solution framework to improve the solution quality. Compared with other related algorithms, the results show that the method proposed in this paper can obtain better solution quality and maintain acceptable solution efficiency under the same edge cloud environment. The improved system revenue for edge service provider can be further obtained.

关键词： Edge computing Network virtualization Cloud container cluster neural combinatorial optimization Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

An integrated neural combinatorial Tabu Search for optimizing school bus scheduling with bell time

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2024年 164卷

作者： Qian, Leren Melachrinoudis, Emanuel Northeastern Univ Dept Mech & Ind Engn Boston MA 02115 USA

Maintaining a fleet of buses to transport students to school is a major expense for school districts. An efficient bus routing system can greatly reduce the time and cost associated with transportation, while also ensuring the safety and comfort of students. The School Bus Routing Problem (SBRP) is a comprehensive real-world problem that has been studied over decades while the neural combinatorial optimization technique is only developed and caught researchers' attention in recent years. optimization on large-scale SBRP instances is challenging due to the huge number of variables and constraints involved. In this paper, we integrate the school bell time decisions with bus scheduling decisions in a multi-criteria optimization model under single load assumption for both heterogeneous and homogeneous bus fleet scenarios. A Tabu Search heuristic, incorporating a deep neural network that is trained through reinforcement learning, is designed to deal with large-scale bell time and bus scheduling optimization. Numerical experiments show that our solution approach outperformed existing heuristics and a state-of-the-art commercial solver with respect to solution quality for a given execution time. The tests on real-world cases demonstrate that adjusting the school bell time in school districts can result in an improvement in terms of deadhead travel distances from 15% to 55% (average 20%-30%), depending on the original bell time allocation, and the proposed bell time policy.

关键词： School bus routing School bell optimization neural combinatorial optimization Tabu search Deep reinforcement learning

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：