It is arguable that the term "big data" is not applicable to power grid control, operations, and planning - particularly in comparison to remote sensing and cyber applications. However, power grid applications should still be of significant interest to the data science community, due to the potential and largely differentiating linkages between diverse spatio-temporal data sources (e.g., forecasted and realized renewables output) and control algorithms used to operate power grids worldwide. In particular, the outputs of data science analyses can both directly impact existing power grid operational paradigms and inform the design of novel control architectures and investment plans, ultimately improving cost-effectiveness, reliability, and resiliency.
In this talk, I will introduce various exemplars of existing, on-going research projects that lie firmly at the data-science/power-grid intersection. These projects range from being loosely to tightly coupled with power grid control and planning paradigms, and range from (physics) "model-free" approaches to more complex applications that directly couple data science outputs with control models and algorithms. Typically, such projects are staffed almost exclusively by engineers and operations researchers - including the speaker, who have leveraged and developed a range of heterogeneous and often ad-hoc approaches to dealing with the requisite data analyses. Direct engagement with the data science community has the potential to dramatically improve the fidelity and rigor of data modeling tasks (e.g., projecting hurricane impacts) and the effectiveness of control architectures (e.g., operations models based on probabilistic forecasts of renewables generation). Further, I argue that major impediments to deploying advanced control technologies in the power grid often center around data science questions - for which we often have poor or inadequate answers.