SYSTEM AND METHOD FOR DYNAMIC ENERGY STORAGE SYSTEM CONTROL

• US 20190312457A1
• Filed: 11/29/2017
• Published: 10/10/2019
• Est. Priority Date: 11/29/2016
• Status: Active Grant

• Current Assignee: Peak Power Inc.
• Original Assignee: Peak Power Inc.
• Inventors: LI, Yiran, HU, Peisen, SOO, Derek Lim, SACHS, Matthew
• Granted Patent: US 10,873,209 B2
• Time in Patent Office: Days
• CPC Class Codes: G05B 13/029 using neural networks and expert systems
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: H02J 13/00 Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
• CPC Class Codes: H02J 13/00034 the elements or equipment being or involving an electric power substation
• CPC Class Codes: H02J 2203/20 Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
• CPC Class Codes: H02J 3/003 Load forecast, e.g. methods or systems for forecasting future load demand
• CPC Class Codes: H02J 3/32 using batteries with converting means
• CPC Class Codes: Y02B 90/20 Smart grids as enabling technology in buildings sector smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00
• CPC Class Codes: Y02P 90/50 Energy storage in industry with an added climate change mitigation effect
• CPC Class Codes: Y04S 10/14 Energy storage units
• CPC Class Codes: Y04S 20/00 Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof

Abstract

A control system for controlling an energy storage system includes a controller including a plurality of layered nodes configured to form an artificial neural network trained to generate a forecasted transmission level load and confidence value for an entire jurisdiction of a utility distribution system. The controller includes at least one memory and at least one processor configured for: identifying a potential coincident peak for the utility distribution system based on the forecasted transmission level load and confidence value generated by the artificial neural network; and upon identifying a potential coincident peak, transmitting signals to cause the electrical infrastructure to consume energy stored at the energy storage system thereby reducing the energy drawn from the utility distribution system during the identified potential coincident peak.

Claims

1. A control system for controlling an energy storage system, the control system comprising:

a meter interface for receiving meter data from at least one metering device positioned to track energy drawn by an electrical infrastructure from a utility distribution system;

an energy storage system interface for communicating with an energy storage system connected to the electrical infrastructure, the energy storage system having an energy capacity and an output power rating; and

a controller including a plurality of layered nodes configured to form an artificial neural network trained to generate a forecasted transmission level load and confidence value for an entire jurisdiction of the utility distribution system;

the controller comprising;

at least one memory and at least one processor configured for;

identifying a potential coincident peak for the utility distribution system based on the forecasted transmission level load and confidence value generated by the artificial neural network; and

upon identifying a potential coincident peak, transmitting signals to cause the electrical infrastructure to consume energy stored at the energy storage system thereby reducing the energy drawn from the utility distribution system during the identified potential coincident peak.

2. The control system of claim 1, wherein the transmitted signals cause the electrical infrastructure to consume energy stored at the energy storage system during time periods selected at least in part based on the energy capacity and output power rating of the energy storage system.

3. The control system of claim 1, wherein the plurality of layered nodes are configured to form the artificial neural network based on a forecasting target defined at least in part on load side resources in the jurisdiction of the utility distribution system, and outputs of generators in the jurisdiction of the utility distribution system.

4. The control system of claim 1, wherein the artificial neural network generates a matrix of forecasted transmission level loads for a defined number of upcoming hours.

5. The control system of claim 1, wherein the controller is configured to update parameters of the artificial neural network based on a reinforcement learning model.

6. The control system of claim 5, wherein updating the parameters of the artificial neural network comprises:

executing a discrete tabu search of a plurality of time periods with the parameters of the artificial neural network; and

updating the parameters of the artificial neural network to minimize an error between forecasted transmission level loads for the discrete tabu search time periods and an actual forecasted transmission level load for the time period.

7. The control system of claim 1, wherein the energy storage system is configured to have one or more energy storage devices to provide the energy capacity and output power rating of the energy storage system based on historical coincident peak data and energy consumption rates of the electrical infrastructure.

8. The control system of claim 1, wherein the controller is configured to transmit the signals to cause the electrical infrastructure to consume energy stored at the energy storage system based on a predicted load of the electrical infrastructure.

9. The control system of claim 1, wherein the artificial neural network has inputs relating to previous and current conditions which affect load side resources and generators.

10. The control system of claim 1, wherein the artificial neural network is trained with data preprocessed through spectral analysis to account for at least one of:

frequency, relative correlation or variance of electricity consumption and generation data.

11. A method for controlling an energy storage system, the method comprising:

receiving meter data from at least one metering device positioned between a utility distribution system and an electrical infrastructure, the at least one metering device for tracking energy drawn from the utility distribution system;

using real-time or near real-time historical and current electricity consumption and generator data with a plurality of layered nodes configured to form an artificial neural network, generating a forecasted transmission level load and confidence value for an entire jurisdiction of the utility distribution system;

identifying a potential coincident peak for the utility distribution system based on the forecasted transmission level load and confidence value generated by the artificial neural network; and

upon identifying a potential coincident peak, transmitting signals to cause the electrical infrastructure to consume energy stored at the energy storage system thereby reducing the energy drawn from the utility distribution system during the identified potential coincident peak.

12. The method of claim 11, wherein the transmitted signals cause the electrical infrastructure to consume energy stored at the energy storage system during time periods selected at least in part based on the energy capacity and output power rating of the energy storage system.

13. The method of claim 11, wherein the plurality of layered nodes are configured to form the artificial neural network based on a forecasting target defined at least in part on load side resources in the jurisdiction of the utility distribution system, and outputs of generators in the jurisdiction of the utility distribution system.

14. The method of claim 11, wherein the artificial neural network generates a matrix of forecasted transmission level loads for a defined number of upcoming hours.

15. The method of claim 11, comprising:

updating parameters of the artificial neural network based on a reinforcement learning model.

16. The method of claim 15, wherein updating the parameters of the artificial neural network comprises:

executing a discrete tabu search of a plurality of time periods with the parameters of the artificial neural network; and

updating the parameters of the artificial neural network to minimize an error between forecasted transmission level loads for the discrete tabu search time periods and an actual forecasted transmission level load for the time period.

17. The method of claim 11, comprising transmitting the signals to cause the electrical infrastructure to consume energy stored at the energy storage system based on a predicted load of the electrical infrastructure.

18. The method of claim 11, wherein the artificial neural network has inputs relating to previous and current conditions which affect load side resources and generators.

19. The method of claim 11, comprising training the artificial neural network with data preprocessed through spectral analysis to account for at least one of:

frequency, relative correlation or variance of electricity consumption and generation data.

20. A device for controlling an energy storage system, the device comprising:

at least one memory and at least one processor providing a plurality of layered nodes configured to form an artificial neural network trained to generate a forecasted transmission level load and confidence value for an entire jurisdiction of the utility distribution system;

the at least one processor configured for;

identifying a potential coincident peak for the utility distribution system based on the forecasted transmission level load and confidence value generated by the artificial neural network; and

upon identifying a potential coincident peak, transmitting signals to cause the electrical infrastructure to consume energy stored at the energy storage system thereby reducing the energy drawn from the utility distribution system during the identified potential coincident peak.