Automated optimized instruction of energy and load resource networks

1 . A computer-implemented method executed using a global energy management system computer in an energy and load resource network, the energy and load resource network comprising a plurality of energy generating resources, a plurality of load resources, a plurality of energy storage resources, and a plurality of virtual energy resources, the computer-implemented method comprising:

receiving a plurality of energy market data and a plurality of capacity market data items;

creating and storing a long-term forecast of one or more of energy supply, energy demand, resource topology, and market trends; using the long-term forecast, creating and storing a day-ahead forecast of one or more of energy supply, energy demand, resource topology, system conditions, and outages; using the day-ahead forecast, creating and storing a real-time forecast of one or more of a change in energy supply, energy demand, system conditions, and outages;

executing an inference stage of a trained machine learning model over the plurality of energy market data and the plurality of capacity market data items to output predictions of generating capacity and load requirements;

executing an optimization algorithm over the predictions of generating capacity and load requirements to output a plurality of optimized generating capacity and load requirements;

forming a plurality of operational instructions for a plurality of the resources in the energy and load resource network, the plurality of operational instructions being formatted to cause the plurality of the resources in the energy and load resource network to conform to the plurality of optimized generating capacity and load requirements;

executing a real-time optimizer for the plurality of the resources in the energy and load resource network, the real-time optimizer being programmed to maximize one or more of arbitrage and regulation dispatch revenue against a plurality of constraints comprising meeting day-ahead commitments within resource limits;

transmitting the plurality of operational instructions to a plurality of local energy management systems respectively associated with the plurality of the resources in the energy and load resource network; and

transmitting the plurality of operational instructions to the plurality of the resources in the energy and load resource network to instruct the plurality of the resources in the energy and load resource network to conform to the plurality of optimized generating capacity and load requirements.

2 . The computer-implemented method of claim 1 , further comprising:

executing the optimization algorithm by receiving long-term market data representing one or more of long-term energy prices and ancillary prices, executing a site resource optimization for multiple sites of nodes in the energy and load resource network, multiple resources among the plurality of energy generating resources, the plurality of load resources, the plurality of energy storage resources, and the plurality of virtual energy resources, including site-resource co-optimization, and outputting a site-resource plan.

3 . The computer-implemented method of claim 1 , further comprising:

receiving price forecast data representing one or more of energy prices and ancillary prices;

executing a network optimization for multiple energy resource assets, multiple energy markets, and probabilistic price forecasts; and

outputting a day-ahead plan for use of the multiple energy resource assets.

4 . The computer-implemented method of claim 1 , further comprising:

receiving updated operating plan data representing then-current ancillary services commitments, ancillary service deployment data, stage of charge data, resource limit data, and the real-time forecast; and

transmitting adjusted telemetry data to a grid regulator.

5 . One or more non-transitory computer-readable storage media storing one or more sequences of instructions which, when executed using one or more processors, cause the one or more processors to execute:

a computer-implemented method executed using a global energy management system computer in an energy and load resource network, the energy and load resource network comprising a plurality of energy generating resources, a plurality of load resources, a plurality of energy storage resources, and a plurality of virtual energy resources, the computer-implemented method comprising:

receiving a plurality of energy market data and a plurality of capacity market data items;

creating and storing a long-term forecast of one or more of energy supply, energy demand, resource topology, and market trends; using the long-term forecast, creating and storing a day-ahead forecast of one or more of energy supply, energy demand, resource topology, system conditions, and outages; using the day-ahead forecast, creating and storing a real-time forecast of one or more of a change in energy supply, energy demand, system conditions, and outages;

executing an inference stage of a trained machine learning model over the plurality of energy market data and the plurality of capacity market data items to output predictions of generating capacity and load requirements;

executing an optimization algorithm over the predictions of generating capacity and load requirements to output a plurality of optimized generating capacity and load requirements;

forming a plurality of operational instructions for a plurality of the resources in the energy and load resource network, the plurality of operational instructions being formatted to cause the plurality of the resources in the energy and load resource network to conform to the plurality of optimized generating capacity and load requirements;

executing a real-time optimizer for the plurality of the resources in the energy and load resource network, the real-time optimizer being programmed to maximize one or more of arbitrage and regulation dispatch revenue against a plurality of constraints comprising meeting day-ahead commitments within resource limits;

transmitting the plurality of operational instructions to a plurality of local energy management systems respectively associated with the plurality of the resources in the energy and load resource network; and

transmitting the plurality of operational instructions to the plurality of the resources in the energy and load resource network to instruct the plurality of the resources in the energy and load resource network to conform to the plurality of optimized generating capacity and load requirements.

6 . The one or more non-transitory computer-readable storage media of claim 5 , further comprising:

executing the optimization algorithm by receiving long-term market data representing one or more of long-term energy prices and ancillary prices, executing a site resource optimization for multiple sites of nodes in the energy and load resource network, multiple resources among the plurality of energy generating resources, the plurality of load resources, the plurality of energy storage resources, and the plurality of virtual energy resources, including site-resource co-optimization, and outputting a site-resource plan.

7 . The one or more non-transitory computer-readable storage media of claim 5 , further comprising:

receiving price forecast data representing one or more of energy prices and ancillary prices;

executing a network optimization for multiple energy resource assets, multiple energy markets, and probabilistic price forecasts; and

outputting a day-ahead plan for use of the multiple energy resource assets.

8 . The one or more non-transitory computer-readable storage media of claim 5 , further comprising:

receiving updated operating plan data representing then-current ancillary services commitments, ancillary service deployment data, stage of charge data, resource limit data, and the real-time forecast; and

transmitting adjusted telemetry data to a grid regulator.