CAREER: Data-Driven Network Resource Management Systems

职业：数据驱动的网络资源管理系统

• 批准号: 1751009
• 负责人: Mohammad Alizadeh
• 金额: $ 62.8万
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-05-15 至 2024-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1751009&HistoricalAwards=false
• 关键词: CAREER; Data; Driven; Network; Resource

Modern networks require sophisticated systems and algorithms to manage resources efficiently and deliver high quality of experience to users. These systems are critical to services society has come to rely on, from video streaming to social networks to AI applications. Video streaming, for example, involves numerous systems that control everything from the resolution of the video to the network path and the video download speed based on dynamic network conditions. As networks and applications have become more complex, existing approaches have become inadequate and designing algorithms that deliver high performance in all conditions has become exceedingly difficult. The goal of this research is to address this challenge by developing network systems that learn to manage resources automatically through experience by applying new machine learning techniques. This new paradigm, if successful, will make networks simpler to design, more efficient and cost effective, and able to deliver better services to businesses and consumers. This project's goal is to develop the algorithmic and systems foundations for designing resource management systems that use modern reinforcement learning and other predictive control techniques to achieve strong performance across heterogeneous networks and applications. To this end, the researchers plan to build a series of practical systems for important applications, including schedulers for cluster computing systems (e.g., for data-parallel analytics workloads), and context-aware network control protocols (e.g., for adaptive streaming of 360 virtual reality video). In building these systems, the researchers will tackle fundamental challenges that confront data-driven network resource management, including (i) techniques to represent workloads (e.g., graph-structured jobs) and networks (e.g., topologies, queues, flows) to facilitate learning using neural networks; (ii) techniques to handle challenging resource management problems with large and deep action spaces; (iii) techniques to efficiently collect data across a myriad of devices for learning control models; and (iv) techniques to bootstrap learning models from data collected offline and continually train models safely after deploymentThis 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.

现代网络需要复杂的系统和算法来有效管理资源并为用户提供高质量的体验。这些系统对于社会所依赖的服务至关重要，从视频流到社交网络再到人工智能应用。例如，视频流涉及许多系统，这些系统根据动态网络条件控制从视频分辨率到网络路径以及视频下载速度的所有内容。随着网络和应用程序变得更加复杂，现有的方法已经变得不够充分，设计在所有条件下提供高性能的算法变得极其困难。这项研究的目标是通过开发网络系统来应对这一挑战，该系统通过应用新的机器学习技术，通过经验学习自动管理资源。这种新模式如果成功，将使网络设计更简单、更高效、更具成本效益，并能够为企业和消费者提供更好的服务。该项目的目标是开发用于设计资源管理系统的算法和系统基础，该系统使用现代强化学习和其他预测控制技术来跨异构网络和应用程序实现强大的性能。为此，研究人员计划为重要应用构建一系列实用系统，包括集群计算系统的调度程序（例如，用于数据并行分析工作负载）和上下文感知网络控制协议（例如，用于 360 度视频流的自适应流）虚拟现实视频）。在构建这些系统时，研究人员将解决数据驱动的网络资源管理面临的基本挑战，包括（i）表示工作负载（例如图结构作业）和网络（例如拓扑、队列、流）的技术以促进学习使用神经网络； (ii) 处理具有大而深的行动空间的具有挑战性的资源管理问题的技术； (iii) 跨多种设备有效收集数据以学习控制模型的技术； (iv) 从离线收集的数据中引导学习模型并在部署后持续安全地训练模型的技术该奖项反映了 NSF 的法定使命，并通过使用基金会的智力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

Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning

• 发表时间: 2019-06
• 作者: Ravichandra Addanki;S. Venkatakrishnan;Shreyan Gupta;Hongzi Mao;Mohammad Alizadeh

Real-Time Video Inference on Edge Devices via Adaptive Model Streaming

• DOI: 10.1109/iccv48922.2021.00453
• 发表时间: 2020-06
• 期刊: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: Mehrdad Khani Shirkoohi;Pouya Hamadanian;Arash Nasr-Esfahany;Mohammad Alizadeh

RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics

RECL：视频分析的响应式资源高效持续学习

• 发表时间: 2023
• 期刊: 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23
• 作者: Khani, Mehrdad;Ananthanarayanan, Ganesh;Hsieh, Kevin;Jiang, Junchen;Netravali, Ravi;Shu, Yuanchao;Alizadeh, Mohammad;Bahl, Victor
• 通讯作者: Bahl, Victor

Adaptive Neural Signal Detection for Massive MIMO

• DOI: 10.1109/twc.2020.2996144
• 发表时间: 2020-08-01
• 期刊: IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
• 影响因子: 10.4
• 作者: Khani, Mehrdad;Alizadeh, Mohammad;Fleming, Phil
• 通讯作者: Fleming, Phil

Robust Query Driven Cardinality Estimation under Changing Workloads

不断变化的工作负载下鲁棒查询驱动的基数估计

• DOI: 10.14778/3583140.3583164
• 发表时间: 2023
• 期刊: Proceedings of the VLDB Endowment
• 影响因子: 2.5
• 作者: Negi, Parimarjan;Wu, Ziniu;Kipf, Andreas;Tatbul, Nesime;Marcus, Ryan;Madden, Sam;Kraska, Tim;Alizadeh, Mohammad
• 通讯作者: Alizadeh, Mohammad