Bayesian Inference for Estimating Generation Costs in Electricity Markets
Abstract
We model the relationship between generation costs and production schedules with a latent variable model, and estimate generation costs from observed schedules by Bayesian inference with balanced neural posterior estimation. On the IEEE RTS-96 test system, marginal costs are recovered with narrow credible intervals, while start-up costs remain largely unidentifiable from schedules alone.
Date
Jun 11, 2026
Event
24th Power Systems Computation Conference (PSCC 2026)
Location
Limassol, Cyprus
