Collaborative Research: CyberTraining: Implementation: Small: Multi-disciplinary Training of Learning, Optimization and Communications for Next Generation Power Engineers

协作研究：网络培训：实施：小型：下一代电力工程师的学习、优化和通信多学科培训

• 批准号: 1949921
• 负责人: Zhen Ni
• 金额: $ 29.99万
• 依托单位: Florida Atlantic University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-10 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1949921&HistoricalAwards=false
• 关键词: Collaborative; Research; CyberTraining; Implementation; Small

With the increasing adoption of interconnected power/micro grid infrastructures, today's power engineering research professionals require broader knowledge and a more diverse skillset. This project provides undergraduate and graduate students in the Northern Plains region with access and opportunity to learn using state-of-the-art smart grid cyberinfrastructure. The Northern Plains region sees increasing use and potential in renewable energy, in addition to energy exports to other areas, solidifying the importance of advanced training in power engineering. The project thus serves the national interest, as stated by NSF's mission: to promote the progress of science and to secure the national defense. The resulting curriculum and instructional materials integrate advanced skills from multiple areas into power engineering infrastructure education. Students practice the multi-disciplinary skillsets needed for the power industry using a unique, remotely connected smart grid cyberinfrastructure. They extend their academic and research portfolios and strengthen their career competitiveness as smart grid cyberinfrastructure professionals and cyberinfrastructure users for regional and national levels. The cyber training model leverages resources for underrepresented minority schools and schools with limited research cyberinfrastructure to participate, either remotely or on-site. The mobile microgrid laboratory demonstrations introduce K-12 teachers and students to Science, Technology, Engineering and Mathematics majors.This project establishes a new, remotely-connected smart grid cyberinfrastructure platform between the collaborative institutes using a real-time digital simulator, and sharing software licenses and hardware resources. This project promotes the application of advanced cyberinfrastructure techniques in power system monitoring, planning, operation and control, and prepares the next-generation power engineers to face challenges in modern power systems. This remotely connected power cyberinfrastructure provides an ideal platform for interdisciplinary research and education of computational intelligence, machine learning, control, communications, and data analytics in the smart grid area. The project team collects heterogeneous smart grid measurement data from this new cyberinfrastructure to conduct real-time learning, event-detection and data integrity, online optimization and multi-level decision-making process of intelligent systems. The project team integrates results into existing undergraduate courses and expand graduate courses from a frontier interdisciplinary viewpoint. The project team also creates replicable project templates/demos with designated benchmark data so other schools can easily adopt this new educational model with or without specific resources. Feedback from an independent evaluator, institutional stakeholders, national laboratory scientists and local industry partners supports periodic improvement of the educational model and materials. This project is funded by the Office of Advanced Cyberinfrastructure in the Directorate for Computer and Information Science and Engineering and the Division of Electrical, Communications and Cyber Systems in the Directorate for Engineering.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.

随着互联电力/微电网基础设施的日益普及，当今的电力工程研究专业人员需要更广泛的知识和更多样化的技能。该项目为北部平原地区的本科生和研究生提供了使用最先进的智能电网网络基础设施学习的机会。除了向其他地区出口能源外，北部平原地区可再生能源的使用和潜力也在增加，这巩固了电力工程高级培训的重要性。因此，该项目符合国家利益，正如NSF的使命所述：促进科学进步，确保国防安全。由此产生的课程和教学材料将多个领域的先进技能整合到电力工程基础设施教育中。学生使用独特的远程连接智能电网网络基础设施，练习电力行业所需的多学科技能。他们扩展了他们的学术和研究组合，并加强了他们作为区域和国家层面的智能电网网络基础设施专业人员和网络基础设施用户的职业竞争力。网络培训模式利用资源，使代表性不足的少数民族学校和研究网络基础设施有限的学校能够远程或现场参与。移动微电网实验室演示向K-12教师和学生介绍科学、技术、工程和数学专业。该项目使用实时数字模拟器在合作机构之间建立了一个新的远程连接的智能电网网络基础设施平台，并共享软件许可证和硬件资源。该项目将推动先进的网络基础设施技术在电力系统监测、规划、运行和控制方面的应用，为下一代电力工程师应对现代电力系统的挑战做好准备。这种远程连接的电力网络基础设施为智能电网领域的计算智能、机器学习、控制、通信和数据分析的跨学科研究和教育提供了理想的平台。项目组从这个新的网络基础设施中收集异构智能电网测量数据，进行智能系统的实时学习、事件检测和数据完整性、在线优化和多层次决策过程。项目团队将成果整合到现有的本科课程中，并从前沿跨学科的角度拓展研究生课程。项目团队还使用指定的基准数据创建可复制的项目模板/演示，以便其他学校可以轻松地采用这种新的教育模式，无论是否有特定的资源。来自独立评估者、机构利益相关者、国家实验室科学家和当地行业合作伙伴的反馈支持对教育模式和材料的定期改进。该项目由计算机和信息科学与工程理事会的先进网络基础设施办公室以及工程理事会的电气、通信和网络系统司资助。该奖项反映了美国国家科学基金会的法定使命，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

Aggregating Learning Agents for Microgrid Energy Scheduling During Extreme Weather Events

• DOI: 10.1109/pesgm46819.2021.9637949
• 发表时间: 2021-07
• 期刊: 2021 IEEE Power & Energy Society General Meeting (PESGM)
• 作者: Avijit Das;Z. Ni;Xiangnan Zhong

An Efficient Distributed Reinforcement Learning for Enhanced Multi-Microgrid Management

• DOI: 10.1109/ijcnn55064.2022.9892754
• 发表时间: 2022-07
• 期刊: 2022 International Joint Conference on Neural Networks (IJCNN)
• 作者: Avijit Das;Z. Ni;Di Wu

A Novel Fitted Rolling Horizon Control Approach for Real-Time Policy Making in Microgrid

• DOI: 10.1109/tsg.2020.2966931
• 发表时间: 2020-07-01
• 期刊: IEEE TRANSACTIONS ON SMART GRID
• 影响因子: 9.6
• 作者: Das, Avijit;Ni, Zhen
• 通讯作者: Ni, Zhen

Experimental Validation of Approximate Dynamic Programming Based optimization and Convergence on Microgrid Applications

• DOI: 10.1109/pesgm41954.2020.9281629
• 发表时间: 2020-08
• 期刊: 2020 IEEE Power & Energy Society General Meeting (PESGM)
• 作者: Avijit Das;Z. Ni;Xiangnan Zhong;Di Wu

Cooperative Differential Game-Based Optimal Control and Its Application to Power Systems

• DOI: 10.1109/tii.2019.2955966
• 发表时间: 2020-08
• 期刊: IEEE Transactions on Industrial Informatics
• 影响因子: 12.3
• 作者: C. Mu;Ke Wang;Z. Ni;Changyin Sun