Reinforcement Learning on OPF with Battery Energy Storage
42.971Episode RewardRPO-DDPG
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| RPO-DDPG2023.10 | 42.971 | 0.0002 | 0.0001 | 0 | 0.0003 | |
| RPO-SAC2023.10 | 42.0764 | 0.0003 | 0 | 0 | 0.0002 | |
| CUP2023.10 | -5.8377 | 0 | 0.4866 | 0 | 0.6827 | |
| CPO2023.10 | -10.3469 | 0 | 0.4413 | 0 | 0.6821 | |
| SAC-Ltype=abridged version2023.10 | -19.4738 | 0 | 0.1908 | 0.0094 | 0.3994 | |
| DDPG-Ltype=abridged version2023.10 | -22.0649 | 0 | 0.1348 | 0.0042 | 0.2845 | |
| Safety Layer2023.10 | -24.1147 | 0 | 11.4698 | 0 | 69.9568 |