Datasets

All Synthetic Challenge 3 datasets are available on this page. Industry datasets will not be posted.

The intervals for each Division are not the same.

  • Division 1: Real-Time Market with 8-hour look ahead -- 8 0.25-hour periods, 8 0.5-hour periods, 2 1-hour periods
  • Division 2: Day-Ahead Market with 48-hour look ahead -- 48 1-hour periods
  • Division 3: Week-Ahead Advisory with 7-day (168-hour) look ahead -- 42 4-hour periods.

All time periods are given in hours. 

C3_Sandbox

Sandbox submissions are now closed. It will open for approved teams after Event submissions are evaluated. We encourage entrants to use the Sandbox to verify all the runtime settings necessary to use the Evaluation Platform for upcoming Events are in place. The Submission button on this page will only be on for Events.

S0

Download the revised (12/8/2022) S0 Sandbox datasets (3.1 MB). It contains 4 network models consisting of  3-, 14-, 37- and 73-buses. Each S0 network model in this set consists one scenario with 4 JSON files for each division as follows:

  1. scenario_nnn.json contains the problem input data,
  2. scenario_nnn_summary.json contains information about the problem input data, including the length and number of periods as in the table below,
  3. scenario_nnn_solution.json contains a feasible solution file produced by the Benchmark program for this scenario, and
  4. scenario_nnn_evaluation.json, the output from the Evaluation program that calculates the objective ("z") from the solution file. This will be the score for the scenario.
S0 datasets released December 8, 2022
Division network model scenario buses ac lines dc lines transformers  shunts simple
dispatchable
devices		 producing
devices		 consuming
devices		 real power
reserve zones		 reactive power
reserve zones		 intervals contingencies hours
duration		 Objective "z"
from (feasible)
Benchmark
solution
1 C3S0N00003 3 3 2 0 2 2 3 2 1 1 1 18 2 8 143,164.98
2 C3S0N00003 3 3 2 0 2 2 3 2 1 1 1 48 2 48 907,176.92
3 C3S0N00003 3 3 2 0 2 2 3 2 1 1 1 42 2 168 2,943,776.23
1 C3S0N00014 3 14 17 0 3 1 17 6 11 2 2 18 12 8 369,670.34
2 C3S0N00014 3 14 17 0 20 1 17 6 11 2 2 48 12 48 2,231,247.62
3 C3S0N00014 3 14 17 0 3 1 17 6 11 2 2 42 12 168 7,808,744.45
1 C3S0N00037 3 37 43 0 14 8 34 8 26 2 2 18 40 8 1,787,896.16
2 C3S0N00037 3 37 43 0 14 8 34 8 26 2 2 48 40 48 10,697,172.61
3 C3S0N00037 3 37 43 0 14 8 34 8 26 2 2 42 40 168 37,469,492.15
1 C3S0N00073 2 73 105 1 15 73 208 157 51 1 1 18 2 8 1,218,124.58
2 C3S0N00073 2 73 105 1 15 73 208 157 51 1 1 48 2 48 55,569,951.09
3 C3S0N00073 2 73 105 1 15 73 208 157 51 1 1 42 2 168 195,862,934.29

These small datasets are intended to help entrants create solvers that can correctly handle Challenge 3 data formats. The solutions produced by the Benchmark are not intended to be anywhere near optimal. Their purpose is to demonstrate that feasible solutions do exist and what a valid solution file would look like. These network models will not be used in any Event.

S1

Download S1 Sandbox datasets (55.5 MB) released December 22, 2022. It contains 4 network models consisting of  600-, 1576-, 4200- and 6049-buses. Each S1 network model in this set consists one scenario with 3 JSON files for each division as follows:

  1. scenario_nnn.json contains the problem input data,
  2. scenario_nnn_pop_solution.json contains a feasible solution file produced by the POP (Prior Operating Point) program for this scenario, and
  3. scenario_nnn_pop_eval_summary.json, the output from the Evaluation program that calculates the objective ("z") from the solution file. This will be the score for the scenario.
S1 datasets released December 22,2022
network model scenario buses ac lines dc lines transformers  shunts simple
dispatchable
devices		 producing
devices		 consuming
devices		 real power
reserve zones		 reactive power
reserve zones		 intervals contingencies hours
duration		 Objective "z"
from (feasible)
Benchmark
solution 1/24/23
C3S1N00600D1 1 617 723 0 130 22 499 94 405 10 10 18 562 8 42,226,325
C3S1N00600D2 1 617 723 0 130 22 499 94 405 10 10 48 562 48 272,379,900
C3S1N00600D3 1 617 723 0 130 22 499 94 405 10 10 42 562 168 956,326,855
                               
C3S1N01576D1 1 1576 2227 0 144 68 2064 615 1449 2 2 18 219 8 1,611,632
C3S1N01576D2 1 1576 2227 0 144 68 2064 615 1449 2 2 48 219 48 8,868,527
C3S1N01576D3 1 1576 2227 0 144 68 2064 615 1449 2 2 42 219 168 30,371,197
                               
C3S1N04200D1 1 4224 2605 0 2325 436 2151 478 1673 2 2 18 2313 8 256,604,444
C3S1N04200D2 1 4224 2605 0 2325 436 2151 478 1673 2 2 48 2313 48 1,619,066,741
C3S1N04200D3 1 4224 2605 0 2325 436 2151 478 1673 2 2 42 2313 168 5,381,415,727
                               
C3S1N06049D1 1 6049 4920 0 3086 236 3836 468 3368 6 6 18 3884 8 214,346,894
C3S1N06049D2 1 6049 4920 0 3086 236 3836 468 3368 6 6 48 3884 48 1,369,855,103
C3S1N06049D3 1 6049 4920 0 3086 236 3836 468 3368 6 6 42 3884 168 4,798,688,125

 

Event 1 will consist of datasets using these same 4 network models, from the S0 datasets and from one industry network model, 3 scenarios, one for each division, that will not be publicly released.

The solutions produced by the Prior Operating Point (POP) program are not intended to be anywhere near optimal. Their purpose is to demonstrate that feasible solutions do exist and what a valid solution file would look like. The Benchmark program now demonstrates that positive feasible solutions are possible.