SLS Blog
Perspectives on renewable bidding, probabilistic forecasting, and trading in US wholesale electricity markets.
June 30, 2026
Most renewable plants bid their median production forecast into the day-ahead market. That is almost never the optimal bid. The right commitment is a quantile chosen by the expected DA-RT spread and the asymmetry of real-time settlement.
May 19, 2026
The RL literature on electricity market bidding is large and growing, yet production bidding still runs on mathematical optimization. Here is why, and where RL credibly fits.
March 10, 2026
I trace a single grid battery trade through CAISO, from bid construction through day-ahead clearing, five-minute dispatch, and settlement. The surprise is how much of the engineering lives outside the forecasting model.
January 13, 2026
Why rolling-horizon LP/MILP over coherent scenarios, with CVaR and hard market-rule constraints inside the optimizer, remains the most defensible way to bid flexible assets, and why pure expected value fails in fat-tailed power markets.
November 4, 2025
Power-market backtests fail in ways equity backtests rarely do: revised forecasts, shifting grid topology, uplift charges, and fills that never would have happened. Point-in-time discipline and honest baselines are the actual deliverable of a quant research effort.
August 26, 2025
Point forecasts are insufficient for most high-value bidding decisions. Calibrated distributions and coherent scenarios, with tails and dependence intact, are what optimization actually consumes.
June 17, 2025
In US wholesale power markets, prices come out of a security-constrained optimization, not a learned model. That changes what 'AI for energy trading' should mean: forecast the optimizer's outputs instead of trying to rebuild the optimizer.
