Power grid aware machine learning device

1. A computer implemented method of managing operation of electrical devices, comprising:

monitoring status of at least one source of electrical power to one or more electrical devices;

monitoring electrical usage at each of the one or more electrical devices that receive electricity from the at least one source of electrical power;

receiving control parameters for optimization of operation of each of the one or more electrical devices; and

managing electrical power usage by each of the one or more electrical devices using a machine learning model that forecasts status of the at least one source of electrical power and generates operational rules for each of the one or more electrical devices from historical values of the control parameters, the status of the at least one source of electrical power, and the electrical usage of each of the one or more electrical devices.

2. The method of claim 1 , wherein managing electrical power usage comprises generating instructions based on a predictive machine learning model for managing the at least one source of electrical power and the electrical devices, the predictive machine learning model forecasting status of the at least one source of electrical power; predicting demands by the one or more electrical devices for the electrical power, and predicting availability of the electrical power at the times the electrical power is demanded by the one or more electrical devices.

3. The method of claim 2 , wherein the predictive machine learning model comprises a long short-term memory machine learning based prediction model that forecasts demand on the at least one source of electrical power by the one or more electrical devices from historical data.

4. The method of claim 2 , further comprising transferring learned rules from the predictive machine learning model to a newly connected electrical device.

5. The method of claim 1 , further comprising communicating at least one of status data of the at least one source of electrical power and electrical usage data of one electrical device to at least one of another electrical device and a cloud server.

6. The method of claim 1 , therein monitoring electrical usage comprises passively monitoring a status of at least one of a neighboring electrical device, a household electrical circuit, a neighborhood, a substation, and a power grid.

7. The method of claim 1 , further comprising scheduling at least one of electrical charge and discharge functions and energy storage functions of the one or more electrical devices based on at least one of the status of the at least one source of electrical power, the electrical usage of the one or more electrical devices, and the operational rules.

8. The method of claim 1 , further comprising using at least one of reinforcement learning, online machine learning, and transfer learning methods to update operational rules established using the control parameters over time based on changes in the status data of the at least one source of electrical power and electrical usage data of the one or more electrical devices over time.

9. The method of claim 1 , further comprising notifying an electrical grid operator of detection of an anomaly in the electrical grid upon detection of at least one of a faulty transmission line, a faulty transformer, and a faulty substation or an anomaly in status data of the at least one source of electrical power.

10. The method of claim 1 , wherein managing the electrical power usage includes selecting the control parameters to optimize at least one of renewable energy utilization, power grid stabilization, smoothing out of transient irregularities in the at least one source of electrical power, cost of electrical power usage by the one or more electrical devices, and a user-specified optimization goal.

11. A control module for managing operation of one or more associated electrical devices, comprising:

a first input that receives status data including control parameters relating to performance of the one or more associated electrical devices in relation to user-defined rules;

a second input that receives optimization settings and the user-defined rules for optimizing at least one of power generation, power usage, and power storage of the one or more associated electrical devices based on user-defined priorities; and

a processor that executes instructions to manage at least one of power generation, power usage, and power storage by the one or more associated electrical devices using a machine learning model that generates operational rules for the one or more electrical devices from historical values of the control parameters and the optimization settings to optimize at least one of power generation, power usage, and power storage by the one or more associated electrical devices according to the user-defined rules.

12. The control module of claim 11 , wherein the processor executes the instructions based on a predictive machine learning model that forecasts status of at least one source of electrical power, predicts demands by the one or more associated electrical devices for the electrical power, and predicts availability of the electrical power at the times the electrical power is demanded by the one or more associated electrical devices.

13. The control module of claim 12 , wherein the predictive machine learning model comprises a long short-term memory machine learning based prediction model that forecasts demand on the at least one source of electrical power by the one or more associated electrical devices from historical data.

14. The control module of claim 12 , wherein the processor further executes the instructions to transfer learned rules from the predictive machine learning model to a newly connected electrical device.

15. The control module of claim 12 , wherein the processor further executes the instructions to communicate status data of the at least one source of electrical power and the one or more associated electrical devices to at least one of another control module and a cloud server.

16. The control module of claim 12 , wherein the processor monitors power usage by passively monitoring a status of at least one of a neighboring electrical device, a household electrical circuit, a neighborhood, a substation, and a power grid.

17. The control module of claim 12 , wherein the processor further executes the instructions to schedule at least one of electrical charge and discharge functions and energy storage functions of the one or more associated electrical devices based on at least one of the status of the at least one source of electrical power, the electrical usage of the one or more associated electrical devices, and operational rules.

18. The control module of claim 12 , wherein the processor further executes the instructions to use at least one of reinforcement learning, online machine learning, and transfer learning methods to update operational rules established using the control parameters over time based on changes in the status data of the at least one source of electrical power and electrical usage data of the one or more associated electrical devices over time.

19. The control module of claim 12 , wherein the processor further executes the instructions to notify an electrical grid operator of detection of an anomaly in the electrical grid upon detection of at least one of a faulty transmission line, a faulty transformer, and a faulty substation or an anomaly in status data of the at least one source of electrical power.

20. The control module of claim 12 , wherein the processor further executes the instructions to select the control parameters to optimize at least one of renewable energy utilization, power grid stabilization, smoothing out of transient irregularities in the at least one source of electrical power, cost of electrical power usage by the one or more associated electrical devices, and a user-specified optimization goal.