Patent · US Active

Optimal charging and discharging control for hybrid energy storage system based on reinforcement learning

US10985572B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 22, 2019
Grant dateApr 20, 2021
Priority date
Expiry dateJul 22, 2039

Classification

  • Technology area (CPC Y)Emerging Cross-Sectional Technologies
  • CPC primaryY02E40/40
  • WIPO fieldElectrical machinery, apparatus, energy
  • WIPO sectorElectrical engineering

Abstract

Systems and methods are disclosed to manage a microgrid with a hybrid energy storage system (HESS) includes deriving a dynamic model of a bidirectional-power-converter (BPC)-interfaced HESS; applying a first neural network (NN) to estimate a system dynamic; and applying a second NN to calculate an optimal control input for the HESS through online learning based on the estimated system dynamics.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.