Datacenter stabilization of regional power grids

1. A computer-implemented method of using a battery to stabilize a regional power grid, comprising:

monitoring a frequency regulation signal from the regional power grid and market conditions for obtaining power from the regional power grid;

predicting from the frequency regulation signal and market conditions a future period when the battery may be exposed to the regional power grid to at least one of charge or discharge power in accordance with a future frequency regulation signal to stabilize the regional power grid through participation in the regulation of the regional power grid;

calculating a regulation control signal that tracks the future frequency regulation signal during the future period; and

during the future period, at least one of charging or discharging the battery in response to the regulation control signal.

2. The method of claim 1 , wherein the market conditions comprise at least one of (1) a discrepancy between available power from the regional power grid and a load on the regional power grid, or (2) a performance score that measures how well a participant in regulation of the regional power grid performs frequency regulation services.

3. The method of claim 1 , wherein the battery comprises backup batteries of a datacenter.

4. The method of claim 3 , further comprising during the future period, in response to the regulation control signal, performing at least one of adjusting power usage of a backup generator, adjusting cooling and ambient temperatures of the datacenter, and adjusting load balancing of computing operations of the datacenter.

5. The method of claim 3 , wherein predicting the future period comprises predicting a benefit of participation in regulation of the regional power grid during a prospective participation period relative to costs of participation in regulation of the regional power grid during the prospective participation period.

6. The method of claim 5 , wherein the costs of participation in regulation of the regional power grid during the prospective participation period include predicted battery degradation due to charging and discharging of the battery as determined using a battery degradation cost model.

7. The method of claim 5 , wherein predicting the future period comprises predicting at least one of a black-out event and a grid equipment failure event.

8. The method of claim 1 , further comprising providing a dashboard that displays to a user at least the predicted future period for participation in regulation of the regional power grid and actual market payout for participation in regulation of the regional power grid during a prior participation period.

9. The method of claim 1 , wherein predicting the future period comprises using a machine learning prediction model to forecast energy-market stability of the regional power grid from at least the market conditions.

10. The method of claim 9 , wherein the prediction model comprises a long short-term memory machine learning based prediction model that forecasts regulation service payout from energy market-specific historical data.

11. A system for regulating the charge and discharge of a battery to stabilize a regional power grid, comprising:

a battery;

a regulation control module that monitors a frequency regulation signal from the regional power grid and market conditions for obtaining power from the regional power grid,

the regulation control module including a machine learning module that predicts from the frequency regulation signal and market conditions a future period when the battery may be exposed to the regional power grid to at least one of charge or discharge power in accordance with a future frequency regulation signal to stabilize the regional power grid through participation in the regulation of the regional power grid,

the regulation control module further comprising a machine learning module that calculates a regulation control signal that tracks the future frequency regulation signal during the future period and that outputs the regulation control signal during the future period to manage charging and discharging of the battery; and

at least one battery control module that manages at least one of the charging or discharging of the battery in response to the regulation control signal to selectively withdraw power from or apply power to the regional power grid.

12. The system of claim 11 , wherein the market conditions comprise at least one of (1) a discrepancy between available power from the regional power grid and a load on the regional power grid, or (2) a performance score that measures how well a participant in regulation of the regional power grid performs frequency regulation services.

13. The system of claim 11 , wherein the battery comprises backup batteries of a datacenter.

14. The system of claim 13 , wherein the regulation control module further adjusts at least one of power usage of a backup generator, cooling and ambient temperatures of the datacenter, and load balancing of computing operations of the datacenter during the future period in response to the regulation control signal.

15. The system of claim 13 , wherein the machine learning module that predicts the future period predicts a benefit of participation in regulation of the regional power grid during a prospective participation period relative to costs of participation in regulation of the regional power grid during the prospective participation period.

16. The system of claim 15 , wherein the machine learning module that predicts the future period calculates the costs of participation in regulation of the regional power grid during the prospective participation period by using a battery degradation cost model to predict battery degradation due to charging and discharging of the battery during the prospective participation period.

17. The system of claim 15 , wherein the machine learning module that predicts the future period predicts at least one of a black-out event and a grid equipment failure event.

18. The system of claim 11 , further comprising a dashboard display 1 that displays to a user at least the predicted future period for participation in a regulation service of the regional power grid and actual market payout for participation in the regulation service of the regional power grid after a participation period.

19. The system of claim 11 , wherein the machine learning module that predicts the future period comprises a long short-term memory machine learning based prediction model that forecasts regulation service payout from energy market-specific historical data.

20. A non-transitory computer readable medium having instructions stored thereon that when executed by one or more processors implements a method of using a battery to stabilize a regional power grid, comprising:

instructions for monitoring a frequency regulation signal from the regional power grid and market conditions for obtaining power from the regional power grid;

instructions for calculating battery degradation costs using a battery degradation cost model for at least one of charging or discharging the battery during a future period;

instructions for calculating a payout prediction from the frequency regulation signal and market conditions for participation in stabilizing the regional power grid through participation in the regulation of the regional power grid during the future period;

instructions for determining when the payout prediction exceeds the battery degradation costs during the future period;

instructions for calculating a regulation control signal that tracks a future frequency regulation signal during the future period; and

instructions for dispatching battery regulation signals to the battery during the future period for at least one of charging or discharging the battery from or to the regional power grid in response to the calculated regulation control signal.