Skip to main content

Data-Driven Unit Commitment Refinement - a Scalable Approach for Complex Modern Power Grids

by Timothy A Holt, Shrirang Abhyankar, Phani Teja V Kuruganti, Olaf Schenk, Slaven Peles
Publication Type
Conference Paper
Book Title
Proceedings of the 57th Hawaii International Conference on System Sciences
Publication Date
Page Numbers
3082 to 3091
Policy, Ma
Publisher Location
Hawaii, United States of America
Conference Name
Hawaii International Conference on System Sciences (HICSS)
Conference Location
Waikiki, Hawaii, United States of America
Conference Sponsor
University of Hawaii at Manoa
Conference Date

Integration of renewable generation, which is often intermittent and decentralized, substantially increases the stochasticity and complexity of power grid operations. Future power systems planning will require significant computational capability to evaluate balance between demand and supply under varying conditions, both temporally and spatially. The standard approach for generation unit commitment is to use mixed-integer linear programming to find the optimal generation schedule considering ramping and generator constraints. In the future grid this poses computational scalability challenges because generation and demand are not known with certainty due to stochasticity in weather and complexity of the grid. To address this challenge, we present a data-driven unit commitment approach that can efficiently include stochastic weather impacts and contingency considerations to improve unit commitment. Our approach uses graph-based data analytics techniques on solutions to the security constrained (and possibly stochastic) economic dispatch problem to identify potential improvements to a given unit commitment. Recent breakthroughs in fully-parallel stochastic economic dispatch software allow this approach to be scalably deployed. Simulations on synthetic South Carolina and Texas grids show this method can improve grid reliability with security constraints over a set of contingencies, while also meaningfully lowering total generation cost.