List view
Agents consistently mispredict dispatch results at the 3-year deterministic crossover point. This misprediction seems to be more severe than would be anticipated based on limitations of the decision algorithm. I need to: * Verify that the misprediction is real (rather than a postprocessing limitation) by saving interim agent forecasts of generation unit financial results * Identify possible causes of the issue and investigate each one * Develop a test case to conclusively identify when the issue has been fixed
Overdue by 6 month(s)•Due by October 10, 2025•11/11 issues closedDefine a sensible set of two-factor tests based on the single-factor results, run the initial set, and characterize the results
Overdue by 4 month(s)•Due by November 28, 2025•0/1 issues closedRun a complete initial set of single-factor tests, review the results in detail, and determine that all behaviors are explainable. Set of single-factor tests will be described in individual issues and tagged to this milestone.
Overdue by 5 month(s)•Due by October 31, 2025•6/6 issues closed