CAREER: Orchestrating Edge Infrastructures and Mobile Devices under Uncertainty to Provision Edge AI as a Service
CAREER: Orchestrating Edge Infrastructures and Mobile Devices under Uncertainty to Provision Edge AI as a Service
批准号:
2047719
负责人:
Lei Jiao
金额:
$51.08万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2021
资助国家:
美国
项目状态:
未结题
起止时间:
2021-07-01 至 2026-06-30
中文摘要
人工智能(AI)通常首先通过数据进行训练,然后用于对可能从未见过的数据进行推理。今天的人工智能服务大多在远程数据中心进行培训,并通过互联网访问。然而,随着最终用户生成大量训练数据,并且推理任务也在内部执行,人工智能需要移动到更接近用户的网络边缘。该项目的目标是通过编排分布式计算和网络基础设施,并从网络边缘提供AI即服务,以服务于不同位置的大量用户,来应对这一新兴的范式转变。该项目将定义优化问题,设计控制算法,并开发可部署的实现,以便在云边缘网络和移动的设备上运营AI即服务。该项目以系统动力学和不确定性为中心,包括多个研究方向。首先,该项目将通过在参与者选择、模型放置、聚合控制和请求调度方面做出明智的决策来优化人工智能的训练和推理,并将产生以在线方式运行的基于时间的算法,这些算法具有可证明的性能保证。第二,从经济学的角度研究人工智能服务生态系统中各方的互动关系,并设计激励机制,以实现上级资源利用率和最佳社会福利,并具有预期的经济属性。第三,该项目将通过模拟、测量和实施,结合真实世界的数据跟踪和现实的实验设置,全面评估和验证模型、算法和系统。该项目将通过为电信运营商、网络运营商、和服务提供商提供一套关键技术,使他们能够在分布式基础设施上提供和运营专用或增值的边缘AI服务。此外,该项目将基于优化,控制,学习和机制设计的数学设计新的理论和算法,并且可以独立感兴趣,并扩展应用于其他相关领域也面临动态和不确定输入的问题。最后,除了为本科生和研究生提供教材外,该项目还将实施教育计划,重点是通过培训教师来促进K-12教育,并以道德的方式为学生提供人工智能知识和经验。该项目的交付成果,包括但不限于论文,数据和代码,将在以下网站公开:https://github.com/ai-at-edge。本网站将在项目期间及时更新,并在项目结束后在线维护。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。
英文摘要
Artificial Intelligence (AI) is often trained by data first, and then used to perform inference upon data which may have never been seen. Today's AI services are mostly trained in remote data centers and accessed via the Internet. However, increasingly, as large volumes of training data are generated by end users and inference tasks are also performed on premises, AI needs to be moved to the network edge in closer proximity to users. The objective of this project is to address this emerging paradigm shift by orchestrating the distributed computing and networking infrastructures and provisioning AI as a service from the network edge to serve large numbers of users at different locations.This project will define the optimization problems, design the control algorithms, and develop the deployable implementations for operating AI as a service across cloud-edge networks and mobile devices. Centered on system dynamics and uncertainty, the project consists of multiple research thrusts. First, the project will optimize the training and the inference of AI through making smart decisions on participant selection, model placement, aggregation control, and request dispatching, and will produce time-based algorithms running in an online manner with provable performance guarantees. Second, the project will investigate the interactions among different parties in the AI service ecosystem from an economics perspective, and will devise incentive mechanisms towards superior resource utilization and optimal social welfare with desired economic properties. Third, the project will conduct a combination of simulations, measurements, and implementations with real-world data traces and realistic experimental settings to comprehensively evaluate and validate the models, algorithms, and systems.This project will impact the industry by providing telecom carriers, network operators, and service providers with a critical set of techniques to enable them to provision and operate dedicated or value-added edge-AI services upon distributed infrastructures. Further, the project will devise novel theories and algorithms based on the mathematics of optimization, control, learning, and mechanism design, and could be of independent interest and have extended applications to problems in other related fields that also face dynamic and uncertain inputs. Finally, besides contributing to undergraduate and graduate course materials, the project will execute the education plan that focuses on facilitating K-12 education via training teachers and also equipping students with AI knowledge and experiences in an ethical manner.The deliverables of this project, which include but are not limited to papers, data, and codes, will be made publicly available at the following website: https://github.com/ai-at-edge. This website will be updated in time for the duration of this project and maintained online thereafter.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.
期刊论文(15)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
DOI:
10.1109/infocom53939.2023.10229102
发表时间:
2023-05
期刊:
IEEE INFOCOM 2023 - IEEE Conference on Computer Communications
影响因子:
--
作者:
[Biao Hou;Song Yang;F. Kuipers;Lei Jiao;Xiao-Hui Fu]
通讯作者:
Biao Hou;Song Yang;F. Kuipers;Lei Jiao;Xiao-Hui Fu
DOI:
10.1109/twc.2021.3137024
发表时间:
2022-07
期刊:
IEEE Transactions on Wireless Communications
影响因子:
10.4
作者:
[Yulan Yuan;Lei Jiao;Konglin Zhu;Lin Zhang]
通讯作者:
Yulan Yuan;Lei Jiao;Konglin Zhu;Lin Zhang
DOI:
10.1109/iwqos57198.2023.10188789
发表时间:
2023-05
期刊:
2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS)
影响因子:
--
作者:
[Xinjing Yuan;Lingjun Pu;Lei Jiao;Xiaofei Wang;Mei Yang;Jingdong Xu]
通讯作者:
Xinjing Yuan;Lingjun Pu;Lei Jiao;Xiaofei Wang;Mei Yang;Jingdong Xu
Power-of-2-arms for bandit learning with switching costs
用于强盗学习的 2 臂力量(Power-of-2-arms),具有转换成本
DOI:
10.1145/3492866.3549720
发表时间:
2022
期刊:
and Protocol Design for Mobile Networks and Mobile Computing
影响因子:
--
作者:
[Shi, Ming, Lin, Xiaojun, Jiao, Lei]
通讯作者:
Jiao, Lei
DOI:
10.1109/infocom48880.2022.9796779
发表时间:
2022-05
期刊:
IEEE INFOCOM 2022 - IEEE Conference on Computer Communications
影响因子:
--
作者:
[Yulan Yuan;Lei Jiao;Konglin Zhu;Xiaojun Lin;Lin Zhang]
通讯作者:
Yulan Yuan;Lei Jiao;Konglin Zhu;Xiaojun Lin;Lin Zhang
共 14 条
Collaborative Research: CNS Core: Small: Edge AI with Streaming Data: Algorithmic Foundations for Online Learning and Control
-
批准号:2225949
-
项目类别:Standard Grant
-
资助金额:$29.99万
-
财政年份:2022
-
负责人:Lei Jiao
-
依托单位:
海外基金