| CPC G01R 31/367 (2019.01) [G01R 31/3648 (2013.01); G01R 31/3842 (2019.01); G01R 31/396 (2019.01)] | 18 Claims |

|
1. A system for determining a total chargeable/dischargeable energy of a subsystem of a battery energy storage system (BESS), the subsystem comprising battery cells, comprising:
one or more controllers comprising one or more processing modules and one or more non-transitory memory storage modules storing computing instructions which when executed by the one or more processing modules is configured to:
execute an iterative process over a dynamic time period, wherein the dynamic time period is divided into iterations, by using a neural network model comprising an energy prediction sub-model and a state prediction sub-model, wherein for each iteration of the iterations, the controller is configured to:
(1) input into the energy prediction sub-model: a voltage of the subsystem for a current iteration of the iterations, a charge rate of the subsystem for the current iteration, and a maximum temperature of the subsystem for the current iteration;
wherein the energy prediction sub-model is configured to output a chargeable/dischargeable energy of the subsystem for the current iteration; and
(2) input into the state prediction sub-model: the voltage of the subsystem for the current iteration, the charge rate of the subsystem for the current iteration, the maximum temperature of the subsystem for the current iteration, and a charge rate difference for the current iteration;
wherein the charge rate difference for the current iteration is the charge rate of the subsystem for the current iteration minus the charge rate of the subsystem for a previous iteration of the iterations;
wherein the state prediction sub-model is configured to output a voltage of the subsystem for a next iteration of the iterations, the charge rate of the subsystem for the next iteration, the maximum temperature of the subsystem for the next iteration, and a charge rate difference for the next iteration;
(3) repeat steps (1) and (2) until a last iteration of the iterative process is executed; and
(4) determine the total chargeable/dischargeable energy of the subsystem of the BESS over the dynamic time period by summing the chargeable/dischargeable energy outputted by the energy prediction sub-model for each iteration;
(5) manage a timing and an amount of energy for charging and discharging the BESS based at least partially on the determined total chargeable/dischargeable energy of the subsystem of the BESS.
|