Abstract
This letter investigates a Branching Dueling Q-Network (BDQ) based online operation strategy for a microgrid with distributed battery energy storage systems (BESSs) operating under uncertainties. The developed deep reinforcement learning (DRL) based microgrid online optimization strategy can achieve a linear increase in the number of neural network outputs with the number of distributed BESSs, which overcomes the curse of dimensionality caused by the charge and discharge decisions of multiple BESSs. Numerical simulations validate the effectiveness of the proposed method.
| Original language | English |
|---|---|
| Pages (from-to) | 5479-5482 |
| Number of pages | 4 |
| Journal | IEEE Transactions on Smart Grid |
| Volume | 12 |
| Issue number | 6 |
| DOIs | |
| State | Published - Nov 1 2021 |
Funding
This work was supported in part by the U.S. National Science Foundation (NSF) ECCS Awards under Grant 1809458 and Grant 2033910; in part by the CURENT which is an Engineering Research Center funded by NSF and U.S. Department of Energy (DOE) through NSF Award under Grant EEC-1041877; and in part by the U.S. DOE, Office of Energy Efficiency and Renewable Energy and Office of Electricity under Contract DE-AC05-00OR22725.
| Funders | Funder number |
|---|---|
| National Science Foundation | 2033910 |
| U.S. Department of Energy | EEC-1041877 |
| Directorate for Engineering | 1809458 |
| Office of Energy Efficiency and Renewable Energy | |
| Office of Electricity | DE-AC05-00OR22725 |
Keywords
- Deep reinforcement learning (DRL)
- distributed energy storage
- microgrid optimization
- uncertainty