Predictive control system for electrical energy grids
Automatically managing surplus and deficiencies on an electrical distribution network comprises sending and receiving information from a connected control point of a computer-based grid controller, and operating the control point, including: monitoring the energy surplus and deficiency state of the electrical distribution network to predict the energy surplus and deficiencies on the electrical distribution network. Locally trained machine learning models are run against collected data corresponding to an electrical distribution network to generate predictions of energy consumption and generation at one or more sites that each include at least one locally controlled energy management system.
1 . A system for automatically managing surplus and deficiencies on an electrical distribution or transmission network, comprising:
a computer-based grid controller, configured and operable to send information to and receive information from a connected control point, the computer-based grid controller further configured to classify the connected control point on the basis of its level and speed of compliance and to calculate one more metrics associated with compliance, and
at least one computer-based electrical controller, operably connected to the computer-based grid controller, which operates the connected control point to locally train machine learning models using a combination of one or more of distributed and local data sets, the locally trained machine learning models for running against collected data corresponding to an electrical distribution or transmission network to generate predictions of energy consumption and generation at one or more sites that each include at least one locally controlled energy management system,
the computer-based grid controller including at least one processor configured to perform operations comprising:
monitoring an energy surplus and deficiency state of the electrical distribution or transmission network, to predict energy surplus and deficiencies on the electrical distribution or transmission network,
selecting a set of electrical controllers to manage the energy surplus and deficiencies with, and
generate instructions to change energy usage/generation controlled by one or more of the at least one computer-based electrical controller, the instructions configured to cause the one or more of the at least one computer-based electrical controller(s) to
either provide additional electrical energy to the electrical distribution or transmission network, or curtail electrical energy load on the electrical distribution or transmission network,
monitor energy usage/generation of the one or more of the at least one computer-based electrical controller(s) to determine actual electrical energy used/generated for a defined period of time, and
generate additional instructions to change the energy usage/generation controlled by the one or more of the at least one computer-based electrical controllers.
2 . The system of claim 1 , wherein the computer-based grid controller is further configured to predict contribution controlled by each computer-based electrical controller to the electrical distribution or transmission network.
3 . The system of claim 1 , wherein the computer-based grid controller is further configured to predict the compliance in response of an electrical controller to an instruction from the computer-based grid controller.
4 . The system of claim 1 , wherein the additional instructions are provided to a different set of electrical controllers than the originally selected set of computer-based electrical controllers.
5 . The system of claim 1 , wherein the additional instructions are provided to a set of computer-based electrical controllers that did not comply with initial instructions.
6 . The system of claim 1 , wherein the defined period of time is less than 5 minutes.
7 . The system of claim 1 , wherein the defined period of time is less than 15 minutes.
8 . The system of claim 1 , wherein the defined period of time is less than 1 hour.
9 . The system of claim 1 , wherein the prediction is based in part upon extrinsic weather, market data, grid data or other collected information.
10 . The system of claim 1 , wherein the prediction is based in part upon performance by one or more electrical controllers in comparison to a previous prediction.
11 . The system of claim 1 , wherein the computer-based grid controller is further configured to predict the compliance and find an optimal path to minimize cost of service being provided to a stabilized distribution or transmission network in response of an electrical controller to an instruction from the computer-based grid controller.
12 . The system of claim 1 wherein the computer-based grid controller is further configured to provide optimal utilization of individual assets to minimize incurred cost, which provides space for lower costs of grid stabilization/resiliency.
13 . A method for automatically managing surplus and deficiencies on an electrical distribution or transmission network, comprising:
sending and receiving information from a connected control point of a computer-based grid controller, and
operating the connected control point, including:
monitoring an energy surplus and deficiency state of the electrical distribution or transmission network to predict the energy surplus and deficiencies on the electrical distribution or transmission network,
selecting a set of computer-based electrical controllers to manage the energy surplus and deficiencies with,
classifying the connected control point on the basis of its level and speed of compliance and to calculate one more metrics associated with compliance,
locally train machine learning models using a combination of one or more of distributed and local data sets, and running the locally trained machine learning models against collected data corresponding to the electrical distribution or transmission network to generate predictions of energy consumption and generation at one or more sites that each include at least one locally controlled energy management system, and
generating instructions to change energy usage/generation controlled by one or more computer-based electrical controllers, the instructions configured to cause the one or more computer-based electrical controllers to
either provide additional electrical energy to the distribution or transmission network, or curtail electrical energy load on the distribution or transmission network,
monitor the energy usage/generation of the instructed one or more computer-based electrical controller(s) to determine actual electrical energy used/generated for a defined period of time, and
generate additional instructions to change the energy usage/generation controlled by the one or more computer-based electrical controllers.
14 . The method of claim 13 , further including predicting contribution controlled by each computer-based electrical controller to the electrical distribution or transmission network.
15 . The method of claim 13 , further including predicting the compliance in response of a computer-based electrical controller to an instruction from the computer-based grid controller.
16 . The method of claim 13 , further including providing the additional instructions to a different set of computer-based electrical controllers than the originally selected set of computer-based electrical controllers.
17 . The method of claim 13 , further including providing the additional instructions to the set of computer-based electrical controllers that did not comply with initial instructions.
18 . The method of claim 13 , wherein the defined period of time is less than 1 hour or preferably less than 15 minutes or preferably less than 5 minutes.
19 . The method of claim 13 , where the prediction is based in part upon extrinsic weather, market data, grid data or other information collected by the computer-based grid controller and/or based upon performance by one or more computer-based electrical controllers in comparison to a previous prediction.
20 . The method of claim 13 , further including predicting the compliance and finding optimal path to minimize cost of service being provided to stabilized distribution network in response of a computer-based electrical controller to an instruction from the computer-based grid controller.
21 . The method of claim 13 further including providing optimal utilization of individual assets to minimize incurred cost, and providing space for lower costs of grid stabilization/resiliency.