| CPC H02J 13/00002 (2020.01) [G06Q 30/0206 (2013.01); G06Q 50/06 (2013.01); H02J 7/0047 (2013.01); H02J 2203/10 (2020.01)] | 16 Claims |
|
1. A system for management and control of battery energy storage systems, comprising:
a computer system comprising a memory and a processor;
a central controller comprising a first plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive or retrieve data of a plurality of the following types: market-related data, EV charging data, system telemetry data, and grid status data;
send the received or retrieved data to two or more of a plurality of other agents;
receive one or more directives from a coordinator agent; and
implement the directives by operating one or more hardware components;
the coordinator agent comprising:
a coordinator agent learning environment comprising coordinator environment data;
a second plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive a prediction, or a recommendation, or both, from the two or more of the plurality of other agents;
process the prediction, or recommendation, or both, by applying a first machine learning algorithm to the prediction, or recommendation, or both, in conjunction with the coordinator agent learning environment to generate the one or more directives for operation of hardware components; and
forward the one or more directives to the central coordinator for implementation;
the two or more of the plurality of other agents drawn from the following list of other agents:
an energy arbitrage agent comprising:
an energy arbitrage agent learning environment comprising energy arbitrage environment data;
a third plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive the market-related data from the central coordinator;
process the market-related data by applying a second machine learning algorithm to the energy arbitrage agent learning environment and the market-related data to obtain an energy arbitrage prediction or recommendation; and
forward the energy arbitrage prediction or recommendation to the coordinator agent;
an EV scheduling agent comprising:
an EV scheduling agent learning environment comprising EV charging environment data;
a fourth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive the EV charging data from the central coordinator;
process the EV charging data by applying a third machine learning algorithm to the EV charging agent learning environment and the EV charging data to obtain an EV charging prediction or recommendation; and
forward the EV charging prediction or recommendation to the coordinator agent;
a battery management system agent comprising:
a battery management system agent learning environment comprising battery management system data;
a fifth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive the system telemetry data from the central coordinator;
process the system telemetry data by applying a fourth machine learning algorithm to the battery management system agent learning environment and the system telemetry data to obtain a battery management prediction or recommendation; and
forward the battery management prediction or recommendation to the coordinator agent; and
a battery management system agent comprising:
a backup power agent learning environment comprising backup power environment data;
a sixth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive the grid status data from the central coordinator;
process the grid status data by applying a fifth machine learning algorithm to the backup power agent learning environment and the grid status data to obtain a backup power prediction or recommendation; and
forward the backup power prediction or recommendation to the coordinator agent.
|