Georgia Tech Research Corporation

The increasing use of renewable energy resources challenges grid operations, which have traditionally relied on highly predictable load and generation. Future grid operators must balance generation costs and system-level risk, shifting from deterministic to stochastic optimization and risk management. Georgia Tech’s Risk-Aware Market Clearing (RAMC) project will provide a blueprint for an end-to-end, data-driven approach where risk is explicitly modeled, quantified, and optimized, striking a tradeoff between cost and system-level risk minimization. The RAMC project focuses on challenges arising from increased stochasticity in generation, load, flow interchanges with adjacent markets, and extreme weather. RAMC addresses these challenges through innovations in machine learning, sampling, and optimization. RAMC quantifies the risk of individual assets from historical data and learns the correlations among assets. It quantifies the system-level risk and learns fast and accurate approximations of multi-stage stochastic optimization algorithms for the day-ahead security-constrained unit commitment, the day-ahead forward reliability assessment commitment, the look-ahead commitment, and the real-time security constrained economic dispatch. RAMC performs real-world, multi-year validations of the proposed approach to balance cost and risk.

PERFORM projects will design methods and risk scores to clearly communicate the physical delivery risk of an energy asset’s offer and design grid management systems that organically capture uncertainty. These management systems will evaluate and hedge the system risk position to meet or exceed a baseline system risk index. This pursuit will achieve the following area impacts: