S5 BIG DATA MANAGEMENT AND ANALYTICS

Symposium Co-Chairs

  • Hamed Mohsenian-Rad, University of California, Riverside, CA, USA
  • Sebastian Lehnhoff, OFFIS – Institute for Information Technology, Germany
  • Emre Can Kara, SLAC National Accelerator Laboratory, Menlo Park, CA, USA
     

Scope and Motivation

Data has traditionally been a lesser concern for utilities and grid operators. Until recently, the most data-intensive elements---aside from supervisory control in energy management systems (SCADA/EMS)---within the energy industry tended to be in customer-related fields such as billing. Here, the level of complexity was average-to-low compared to that seen in other sectors, such as financial services or telecommunications. This made it possible to handle the requirements of the business with moderate means of information technology (IT) investment and skill. The ongoing digitalization, e.g. deployment of advanced metering infrastructure (AMI) and phasor measurement units (PMUs) as well as intelligent automation systems  is drastically increasing the amount, quality, and variety of data that utilities and grid operators are collecting on supply, transmission, distribution, and demand.  Major challenges facing the use of these new data streams by utilities and grid operators are: how to handle and cope with the complex data-streams (e.g. processing data from numerous and spatially diffuse PMUs and/or smart-meters), how to persist relevant information in big data volumes and maintain availability (e.g. requirements for communication, storage and computational systems ensuring speedy, secure, and reliable access), what can be done with this data to meet sustainability objectives, how to generate a return on investments?
 
 

Topics of Particular Interest

This symposium is focused on big data management and smart grid data analytics to operate  large-scale electricity transmission and distribution networks and to manage the associated energy trade. Topics of interest include, but are not limited to the following:
 
•  Data management strategies:
- Strategies for wide-area monitoring and visualization
- software/cloud architectures
- reliable and privacy-preserving data storage
- reliable and privacy-preserving data communications

•  Big Data Analytics:
- data mining
- machine learning
- privacy-preserving analytics
- visualization
- semantic techniques
- real-time data analysis and decision making

•  Application of data management and analytics to:
- power-grid transmission system automation
- power-grid distribution system automation
- state estimation
- energy trade
- resource aggregation (renewables, electric vehicles, flexible demand, etc.)
- managing smart buildings/houses at scale

The organizers particularly welcome case studies based on real-world data.