BD Spokes: SPOKE: SOUTH: Collaborative: Smart Grids Big Data

BD Spokes：SPOKE：SOUTH：协作：智能电网大数据

• 批准号: 1636772
• 负责人: Mladen Kezunovic
• 金额: $ 66.7万
• 依托单位: Texas A&M Engineering Experiment Station
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1636772&HistoricalAwards=false
• 关键词: BD; Spokes; SPOKE; SOUTH; Collaborative

An inherent feature of the modernization of America's electrical power grid is a rapidly emerging Big Data (BD) presence. The American Recovery and Reinvestment Act (ARRA) of 2009 allocated over $4 billion to deployment of new technology for grid monitoring, control and infrastructure protection. This led to a dramatic proliferation in the use of Big Data across multiple operational domains such as generation, transmission and distribution, customers, services, and markets. A challenging goal is to convert Big Data in smart grids, which is overwhelmingly abundant and yet grossly underutilized, into new knowledge that can offer major improvements in the above mentioned domains of smart grid operation, including management of almost a trillion dollars in grid infrastructure annually and an increase in building energy efficiency by at least 20% by 2020. The Smart Grids BD (SGBD) Spoke will build an action-oriented organization focused on developing the fundamental framework for BD integration and knowledge extraction for power system applications. This will enable the South Big Data Hub to meet the societal grand challenge of creating technological solutions that can fulfill the economic potential inherent in Big Data analytics in the electric utility industry, expected to reach an annual value of close to $4 billion by 2020. The Project mission is to complement, strengthen, and serve the South Hub regional priority areas. Moreover, the services of the Spoke will benefit and complement the other Hub regional priority areas dependent on a smart grid backbone for operational assurance and resilience, specifically the areas of Oil and Gas Production and Distribution, National Hazards (Coastal and Other Hazards), Materials and Manufacturing, Habitat Planning (Smart and Connected Communities, Transportation, Urban Infrastructure and Sustainability) and Education and Training. The significance of Smart Grids Big Data is in the diversity of its sources, growth rate, and spatiotemporal characteristics. Developing a fundamental framework for Big Data integration and knowledge extraction is a grand challenge since the science and technology are yet to be discovered and the theoretical framework established. The main objective is to create an organization that brings together a cross disciplinary capability from academia, industry, and government, thereby (a) bringing talent and resources from diverse Big Data areas to create an open access Big Data infrastructure that enables collaboration and innovation; (b) engaging industry to define its challenges and implement new Big Data technologies for cost-effective computational, analytical, and data management solutions needed to get the full benefits of smart grids; and (c) establishing close collaboration with the South Hub to find the most effective way to develop outreach, education, and training, thereby assuring the SGBD SPOKE domain integrates synergistically with the other Hub domains to advance fundamental data science and its impacts. Achieving the knowledge extraction from Smart Grids Big Data will result in the advancement of fundamental sciences in multiple disciplinary domains related to Big Data analytics. It will also increase our understanding of merged data collected from the physical systems, thereby helping us better understand the flow of energy in the smart grids, and how this understanding can prevent emergencies, improve asset management, and increase energy efficiency. It will also provide a more illuminated understanding of behavioral analytics that addresses the human interface with smart electricity systems. The expected transformational outcomes are: (a) solutions to decreasing the grid outages, improving energy and market efficiency, reducing carbon emissions, and engaging industry and customers in new business models to ensure industry growth, operational resiliency, and customer value, (b) a cross cutting research community focused on solving practical problems while concurrently advancing the fundamental understanding of Big Data issues; and (c) engaging novel instructional paradigms for educating and training the next generation of Big Data experts nationally and globally.

美国电网现代化的一个固有特征是快速兴起的大数据 (BD)。 2009 年的美国复苏和再投资法案 (ARRA) 拨款超过 40 亿美元用于部署电网监测、控制和基础设施保护新技术。 这导致大数据在发电、输电和配电、客户、服务和市场等多个运营领域的使用急剧增加。一个具有挑战性的目标是将智能电网中极其丰富但未得到充分利用的大数据转化为新知识，可以为上述智能电网运营领域提供重大改进，包括每年管理近万亿美元的电网基础设施到 2020 年，建筑能源效率至少提高 20%。智能电网 BD (SGBD) Spoke 将建立一个以行动为导向的组织，专注于开发 BD 集成和电力系统应用知识提取的基本框架。这将使南方大数据中心能够应对创建技术解决方案的巨大社会挑战，这些解决方案能够发挥电力行业大数据分析固有的经济潜力，预计到 2020 年年产值将达到近 40 亿美元。项目使命是补充、加强和服务南部枢纽区域优先领域。此外，Spoke 的服务将有利于并补充依赖于智能电网骨干网络来提供运营保证和恢复力的其他中心区域优先领域，特别是石油和天然气生产和分配、国家灾害（沿海和其他灾害）、材料等领域制造、人居规划（智能和互联社区、交通、城市基础设施和可持续发展）以及教育和培训。 智能电网大数据的重要性在于其来源、增长率和时空特征的多样性。由于科学技术尚未被发现，理论框架尚未建立，因此开发大数据集成和知识提取的基本框架是一项巨大的挑战。主要目标是创建一个汇集学术界、工业界和政府跨学科能力的组织，从而 (a) 汇集来自不同大数据领域的人才和资源，创建一个开放访问的大数据基础设施，以实现协作和创新； (b) 让行业参与定义其挑战并实施新的大数据技术，以获得获得智能电网的全部好处所需的具有成本效益的计算、分析和数据管理解决方案； (c) 与南方中心建立密切合作，寻找最有效的方式来发展外展、教育和培训，从而确保 SGBD SPOKE 领域与其他中心领域协同整合，以推进基础数据科学及其影响。 实现从智能电网大数据中提取知识将促进与大数据分析相关的多个学科领域的基础科学的进步。它还将增加我们对从物理系统收集的合并数据的理解，从而帮助我们更好地理解智能电网中的能量流动，以及这种理解如何能够预防紧急情况、改善资产管理和提高能源效率。它还将为行为分析提供更清晰的理解，以解决人机交互与智能电力系统的问题。预期的转型成果是：(a) 减少电网停电、提高能源和市场效率、减少碳排放以及让行业和客户参与新业务模式的解决方案，以确保行业增长、运营弹性和客户价值，(b)一个跨领域的研究社区，专注于解决实际问题，同时增进对大数据问题的基本理解； (c) 采用新颖的教学范式来教育和培训国内和全球的下一代大数据专家。

项目成果

A Data-Driven Framework for Optimal Placement of Grid-Connected Solar Generation

用于优化并网太阳能发电布局的数据驱动框架

• 发表时间: 2019-01
• 期刊: 2019
• 作者: A. M. Ospina; M. Kezunovic
• 通讯作者: M. Kezunovic

Resiliency Assessment in Distribution Networks Using GIS Based Predictive Risk Analytics

使用基于 GIS 的预测风险分析进行配电网弹性评估

• DOI: 10.1109/tpwrs.2019.2913090
• 发表时间: 2019-01
• 期刊: IEEE Transactions on Power Systems
• 影响因子: 6.6
• 作者: Leite, Jonatas Boas;Mantovani, Jose Roberto;Dokic, Tatjana;Yan, Qin;Chen, Po;Kezunovic, Mladen
• 通讯作者: Kezunovic, Mladen

Spatially Aware Ensemble-Based Learning to Predict Weather-Related Outages in Transmission

基于空间感知的集成学习来预测与天气相关的传输中断

• 发表时间: 2019-01
• 期刊: January 2019
• 作者: T. Dokic; M. Pavlovski
• 通讯作者: M. Pavlovski

Predictive Risk Management for Dynamic Tree Trimming Scheduling for Distribution Networks

配电网动态树木修剪调度的预测风险管理

• DOI: 10.1109/tsg.2018.2868457
• 发表时间: 2019-09
• 期刊: IEEE Transactions on Smart Grid
• 影响因子: 9.6
• 作者: Dokic, Tatjana;Kezunovic, Mladen
• 通讯作者: Kezunovic, Mladen

Scenario-based Economic Dispatch with Tunable Risk Levels in High-renewable Power Systems

高可再生电力系统中风险水平可调的基于情景的经济调度

• DOI: 10.1109/tpwrs.2018.2874464
• 发表时间: 2018-01
• 期刊: IEEE Transactions on Power Systems
• 影响因子: 6.6
• 作者: Modarresi, M. Sadegh;Xie, Le;Campi, Marco;Garatti, Simone;Care, Algo;Thatte, Anupam;Kumar, P. R.
• 通讯作者: Kumar, P. R.