Collaborative Research: CNS CORE: Small: RUI: Hierarchical Deep Reinforcement Learning for Routing in Mobile Wireless Networks
合作研究:CNS CORE:小型:RUI:移动无线网络中路由的分层深度强化学习
基本信息
- 批准号:2154191
- 负责人:
- 金额:$ 27.3万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-04-15 至 2025-03-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
The use of multi-hop routing in mobile wireless networks is becoming more prevalent, just as these networks are becoming more dense, dynamic, and heterogeneous. Designing a universal multi-hop routing strategy for mobile wireless networks is challenging, however, due to the need to seamlessly adapt routing behavior to spatially diverse and temporally changing network conditions. An alternative to using hand-crafted routing strategies is to use Reinforcement Learning (RL) to learn adaptive multi-hop routing strategies automatically. RL focuses on the design of intelligent agents: an RL agent interacts with its environment to learn a policy, i.e., which actions to take in different environmental states. By using function approximation like deep neural networks (DNNs) as in deep reinforcement learning (DeepRL) to approximate the policy, the RL agent can learn to generalize from its training experience to unseen network conditions and scale the learned routing strategy to larger networks. The PIs will continue their current practice of involving under-represented groups in research, and will use the project research to promote teaching and training through postdoctoral mentoring, course development, and outreach activities.The goal of this project is to use DeepRL to develop a universal multi-hop routing strategy for mobile wireless networks that is scalable, generalizable, and adaptive. Specifically, this project will build a novel routing framework that uses hierarchical DeepRL to design an option hierarchy, comprised of multiple layers of routing decisions working together to achieve the overall goals of the network. To enable the same routing strategy to be used at different devices and in unseen network scenarios, the framework will use relational features combined with novel neural network models to handle mobility and perform feature estimation. To further enhance generalizability, the framework will use continual learning to ensure that the routing behaviors learned for more recently seen network scenarios do not dominate the learned routing policy. The developed routing strategies will be thoroughly evaluated using both simulation and experimental testbeds. Through the use of hierarchical DeepRL, this project will provide a significant step forward in developing RL-based routing strategies, and will facilitate development of adaptive strategies for a wide range of mobile wireless networks.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
在移动的无线网络中使用多跳路由正变得越来越普遍,正如这些网络正变得越来越密集、动态和异构。然而,由于需要使路由行为无缝地适应空间多样和时间变化的网络条件,因此为移动的无线网络设计通用的多跳路由策略是具有挑战性的。使用手工制作的路由策略的替代方案是使用强化学习(RL)来自动学习自适应多跳路由策略。RL专注于智能代理的设计:RL代理与其环境交互以学习策略,即,在不同的环境状态下采取什么行动。通过使用像深度强化学习(DeepRL)中的深度神经网络(DNN)这样的函数近似来近似策略,RL代理可以学习从其训练经验推广到看不见的网络条件,并将学习的路由策略扩展到更大的网络。 PI将继续他们目前的做法,让代表性不足的群体参与研究,并将利用项目研究,通过博士后指导,课程开发和推广活动来促进教学和培训。该项目的目标是使用DeepRL为移动的无线网络开发一个通用的多跳路由策略,该策略具有可扩展性,可推广性和自适应性。 具体来说,该项目将构建一个新的路由框架,该框架使用分层DeepRL来设计一个选项层次结构,由多层路由决策组成,共同实现网络的总体目标。为了使相同的路由策略能够在不同的设备和看不见的网络场景中使用,该框架将使用与新型神经网络模型相结合的关系特征来处理移动性并执行特征估计。为了进一步增强可推广性,该框架将使用持续学习来确保针对最近看到的网络场景学习的路由行为不会主导学习的路由策略。开发的路由策略将使用仿真和实验测试平台进行彻底评估。通过使用分层DeepRL,该项目将在开发基于RL的路由策略方面向前迈出重要一步,并将促进为各种移动的无线网络开发自适应策略。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Ricci Curvature-Based Graph Sparsification for Continual Graph Representation Learning
用于连续图表示学习的基于 Ricci 曲率的图稀疏化
- DOI:10.1109/tnnls.2023.3303454
- 发表时间:2024
- 期刊:
- 影响因子:10.4
- 作者:Zhang, Xikun;Song, Dongjin;Tao, Dacheng
- 通讯作者:Tao, Dacheng
Hierarchical Prototype Networks for Continual Graph Representation Learning
- DOI:10.1109/tpami.2022.3186909
- 发表时间:2021-11
- 期刊:
- 影响因子:23.6
- 作者:Xikun Zhang;Dongjin Song;D. Tao
- 通讯作者:Xikun Zhang;Dongjin Song;D. Tao
Sparsified Subgraph Memory for Continual Graph Representation Learning
- DOI:10.1109/icdm54844.2022.00177
- 发表时间:2022-11
- 期刊:
- 影响因子:0
- 作者:Xikun Zhang;Dongjin Song;D. Tao
- 通讯作者:Xikun Zhang;Dongjin Song;D. Tao
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Bing Wang其他文献
Exploring Th17-related inflammation in AP1B1-associated KIDAR syndrome and potential therapeutic implications of secukinumab.
探索 AP1B1 相关 KIDAR 综合征中 Th17 相关炎症以及苏金单抗的潜在治疗意义。
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:9.2
- 作者:
C. Pan;Hongsong Ge;Luyao Zheng;Q. Cao;Cheng Zhang;Yumeng Wang;A. Zhao;Wei He;Guofang Li;Haifei Liu;Yijun Yang;Ruoqu Wei;Haoyu Wang;Yidong Tan;Bing Wang;Wenjie Cheng;Zhe Sun;Xiaoxiao Wang;Ming Li - 通讯作者:
Ming Li
The Effect of Alloying Elements on the Structural Stability, Mechanical Properties, and Debye Temperature of Al₃Li: A First-Principles Study
合金元素对 Al-Li 结构稳定性、力学性能和德拜温度的影响:第一性原理研究
- DOI:
- 发表时间:
2018 - 期刊:
- 影响因子:3.4
- 作者:
Jinzhong Tian;Yuhong Zhao;Hua Hou;Bing Wang - 通讯作者:
Bing Wang
Abstract Next Subvolume Method: A logical process-based approach for spatial stochastic simulation of chemical reactions
Abstract Next Subvolume Method:一种基于逻辑过程的化学反应空间随机模拟方法
- DOI:
10.1016/j.compbiolchem.2011.05.001 - 发表时间:
2011-06 - 期刊:
- 影响因子:3.1
- 作者:
Bing Wang;Bonan Hou;Fei Xing;Yiping Yao - 通讯作者:
Yiping Yao
yntheses of Ferrocene-Functionalized Indium-based Metal-Organic Frameworks for Third Order Nonlinear Optical Application
用于三阶非线性光学应用的二茂铁功能化铟基金属有机框架的合成
- DOI:
10.1039/d2qi01949c - 发表时间:
2022 - 期刊:
- 影响因子:7
- 作者:
Rong Zhang;Bing Wang;Fei Wang;Shumei Chen;Jian Zhang - 通讯作者:
Jian Zhang
Ohmic Contact Characteristics of AlGaN-based Deep-ultraviolet Light-emitting-diodes with NiAu Transparent Electrode
NiAu透明电极AlGaN基深紫外发光二极管的欧姆接触特性
- DOI:
10.37188/cjl.20220385 - 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
X. Wang;N. Liu;Bing Wang;Yanan Guo;Xiaona Zhang;Kai Guo;Yongqiang Li;Tong Zhang;Jianchang Yan;Jinmin Li - 通讯作者:
Jinmin Li
Bing Wang的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Bing Wang', 18)}}的其他基金
IMR: MM-1B: Longitudinal End-device based Performance Measurement of Cellular Networks with Provable Privacy
IMR:MM-1B:具有可证明隐私的蜂窝网络基于纵向终端设备的性能测量
- 批准号:
2319277 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant
CyberTraining: Pilot: Cyberinfrastructure Training in Computer Science and Geoscience
网络培训:试点:计算机科学和地球科学的网络基础设施培训
- 批准号:
2118102 - 财政年份:2021
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
REU Site: Trustable Embedded Systems Security Research
REU 网站:可信嵌入式系统安全研究
- 批准号:
1659764 - 财政年份:2017
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
EAGER: US Ignite: Enabling Highly Resilient and Efficient Microgrids through Ultra-Fast Programmable Networks
EAGER:US Ignite:通过超快可编程网络实现高弹性和高效的微电网
- 批准号:
1419076 - 财政年份:2014
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
SCH: EXP: LifeRhythm: A Framework for Automatic and Pervasive Depression Screening Using Smartphones
SCH:EXP:LifeRhythm:使用智能手机进行自动和普遍抑郁症筛查的框架
- 批准号:
1407205 - 财政年份:2014
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
CC-NIE Network Infrastructure: Enabling Data-Intensive Research at the University of Connecticut Through Science DMZ
CC-NIE 网络基础设施:通过 Science DMZ 实现康涅狄格大学的数据密集型研究
- 批准号:
1341003 - 财政年份:2013
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Investigation of Ricci Flows with Bounded Scalar Curvature
具有有界标量曲率的 Ricci 流研究
- 批准号:
1312836 - 财政年份:2012
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant
Investigation of Ricci Flows with Bounded Scalar Curvature
具有有界标量曲率的 Ricci 流研究
- 批准号:
1221330 - 财政年份:2011
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant
Investigation of Ricci Flows with Bounded Scalar Curvature
具有有界标量曲率的 Ricci 流研究
- 批准号:
1006518 - 财政年份:2010
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant
CAREER: Automating Wireless Network Management: Lessons from Managing Wireless LANs and Sensor Networks
职业:自动化无线网络管理:管理无线局域网和传感器网络的经验教训
- 批准号:
0746841 - 财政年份:2008
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant
相似国自然基金
Research on Quantum Field Theory without a Lagrangian Description
- 批准号:24ZR1403900
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
Cell Research
- 批准号:31224802
- 批准年份:2012
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research
- 批准号:31024804
- 批准年份:2010
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research (细胞研究)
- 批准号:30824808
- 批准年份:2008
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
- 批准号:10774081
- 批准年份:2007
- 资助金额:45.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: CNS Core: Medium: Reconfigurable Kernel Datapaths with Adaptive Optimizations
协作研究:CNS 核心:中:具有自适应优化的可重构内核数据路径
- 批准号:
2345339 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Small: A Compilation System for Mapping Deep Learning Models to Tensorized Instructions (DELITE)
合作研究:CNS Core:Small:将深度学习模型映射到张量化指令的编译系统(DELITE)
- 批准号:
2230945 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: NSF-AoF: CNS Core: Small: Towards Scalable and Al-based Solutions for Beyond-5G Radio Access Networks
合作研究:NSF-AoF:CNS 核心:小型:面向超 5G 无线接入网络的可扩展和基于人工智能的解决方案
- 批准号:
2225578 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Medium: Movement of Computation and Data in Splitkernel-disaggregated, Data-intensive Systems
合作研究:CNS 核心:媒介:Splitkernel 分解的数据密集型系统中的计算和数据移动
- 批准号:
2406598 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant
Collaborative Research: CNS Core: Small: SmartSight: an AI-Based Computing Platform to Assist Blind and Visually Impaired People
合作研究:中枢神经系统核心:小型:SmartSight:基于人工智能的计算平台,帮助盲人和视障人士
- 批准号:
2418188 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Small: Creating An Extensible Internet Through Interposition
合作研究:CNS核心:小:通过介入创建可扩展的互联网
- 批准号:
2242503 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Small: Adaptive Smart Surfaces for Wireless Channel Morphing to Enable Full Multiplexing and Multi-user Gains
合作研究:CNS 核心:小型:用于无线信道变形的自适应智能表面,以实现完全复用和多用户增益
- 批准号:
2343959 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Small: Efficient Ways to Enlarge Practical DNA Storage Capacity by Integrating Bio-Computer Technologies
合作研究:中枢神经系统核心:小型:通过集成生物计算机技术扩大实用 DNA 存储容量的有效方法
- 批准号:
2343863 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Small: A Compilation System for Mapping Deep Learning Models to Tensorized Instructions (DELITE)
合作研究:CNS Core:Small:将深度学习模型映射到张量化指令的编译系统(DELITE)
- 批准号:
2341378 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Medium: Innovating Volumetric Video Streaming with Motion Forecasting, Intelligent Upsampling, and QoE Modeling
合作研究:CNS 核心:中:通过运动预测、智能上采样和 QoE 建模创新体积视频流
- 批准号:
2409008 - 财政年份:2023
- 资助金额:
$ 27.3万 - 项目类别:
Continuing Grant