David Cole

Marena Trujillo, David Cole, Bri-Mathias Hodge

In modern power systems with high shares of renewable, inverter-based resources (IBRs), frequency stability becomes more complex due to the fast dynamics of IBRs and frequency trajectories that vary significantly from bus to bus. In this paper, we present an optimization framework for unit commitment and economic dispatch with endogenous frequency stability constraints at each bus. Two approaches for mitigating excessively low instantaneous frequency values in the event of the largest generator contingency are proposed: 1) by introducing a constraint requiring more thermal generation, and 2) by constraining the maximum power output of the generator that had the largest power output in the incumbent solution. Both approaches proved effective in eliminating dispatch scenarios that resulted in instantaneous frequencies below 58 Hz, while the second approach minimized the difference in production cost values from the non-stability-constrained case. Overall, the results indicate that the proposed optimization framework is a more effective alternative to frequency stability-constrained unit commitment and economic dispatch (UC & ED) than those based on the center-of-inertia (COI) principle.

David Cole, Himanshu Sharma, Wei Wang

We propose a framework for applying reinforcement learning to contextual two-stage stochastic optimization and apply this framework to the problem of energy market bidding of an off-shore wind farm. Reinforcement learning could potentially be used to learn close to optimal solutions for first stage variables of a two-stage stochastic program under different contexts. Under the proposed framework, these solutions would be learned without having to solve the full two-stage stochastic program. We present initial results of training using the DDPG algorithm and present intended future steps to improve performance.