Abstract
The present disclosure is directed to identifying daily key predictive features through a high-fidelity, counterfactual grid simulation of the Electric Reliability Council of Texas (ERCOT) market to evaluate the impact of various load-shaping strategies on CO2 emissions and energy costs. Key predictive features may include seasonality data expressed as grid net demand (GND) and the daily minimum locational marginal price (LMP), which determine a strategy's effectiveness. Based on these features, a system can determine a rule-based algorithm that selects the optimal load-shaping strategy for the upcoming day based on predicted grid conditions. The approach can significantly reduce CO2 emissions while also lowering electricity costs, thereby providing an implementable, high-impact approach for flexible loads like data centers and electric vehicle charging to contribute effectively to grid decarbonization.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
N/A, "Load Shaping For The Reduced Grid CO2 Emissions And Energy Market Cost", Technical Disclosure Commons, (December 18, 2025)
https://www.tdcommons.org/dpubs_series/9062