# US 2021/0281077 A1 · Micro-grid site predictive control for multi-power resource management with machine learning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0281077 A1
- Document ID: US20210281077A1
- Status: Published application
- Kind: A1
- Application number: 16/808,181
- Filed: 2020-03-03
- Published: 2021-09-09
- Earliest claimed: 2020-03-03
- Assignees: Caterpillar Inc.
- Applicants: Caterpillar Inc.
- Inventors: Zhijun CAI; Yanchai ZHANG
- Web page: https://patentgrep.com/patent/US20210281077A1

## CPC

- H02J 3/381: {Dispersed generators}
- G05B 13/0265: {the criterion being a learning criterion}
- G05B 13/048: {using a predictor}
- G06Q 50/06: Energy or water supply
- H02J 3/004: {Generation forecast, e.g. methods or systems for forecasting future energy generation}
- H02J 3/32: using batteries or super capacitors with converting means
- G01W 1/10: Devices for predicting weather conditions (computers per se G06; display devices G09)
- H02J 3/388: Arrangements for the handling of islanding, e.g. for disconnection or for avoiding the disconnection of power
- H02J 3/46: Controlling the sharing of generated power between the generators, sources or networks
- H02J 2101/24: Photovoltaics
- H02J 2103/30: Simulating, planning, modelling, reliability check or computer assisted design [CAD] of electric power networks
- Y02A 30/00: Adapting or protecting infrastructure or their operation
- Y02B 10/10: Photovoltaic [PV]
- Y02E 10/56: Power conversion systems, e.g. maximum power point trackers
- Y02E 70/30: Systems combining energy storage with energy generation of non-fossil origin
- Y04S 10/50: Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G01W: METEOROLOGY (radar, sonar, lidar or analogous systems, designed for meteorological use G01S13/95, G01S15/88, G01S17/95)
- Y02A: TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y04S: SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS

## Abstract

A device may receive a power demand for a load and a weather forecast for a time period. The device may determine a first supply of power available from a photo-voltaic (PV) installation for the time period based on the weather forecast. The device may determine a power deficit for the time period based on the power demand and the first supply of power. The device may determine a first cost associated with utilizing a second supply of power available from a battery and a second cost associated with utilizing a third supply of power available from an engine for the time period. The device may determine a power source to overcome the power deficit based on the first cost and the second cost and may cause the PV installation and the power source to supply power to satisfy the power demand for the load.

## Claims

### Claim 1

A method of determining a power source, comprising:
receiving, by an optimizer of a power control system, a power demand for a load;
receiving, by the optimizer a weather forecast for a time period;
determining, by the optimizer, whether a first power supply is available from a photo voltaic (PV) installation for the time period based on the weather forecast;
determining, by the optimizer, a power deficit for the time period based on the power demand and the first supply of power;
determining, by the optimizer, a first cost associated with utilizing a second supply of power available from a battery for the time period;
determining, by the optimizer, a second cost associated with utilizing a third supply of power available from an engine for the time period;
determining, by the optimizer, a power source to reduce the power deficit based on the first cost and the second cost,
wherein the power source includes at least one of the battery or the engine; and
sending, by the power control system, a request to the PV installation and the power source to cause the PV installation and the power source to supply power to satisfy the power demand for the load.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the first power supply includes:
utilizing machine learning to determine the first power supply.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the first power supply includes:
obtaining a plurality of historical weather data;
generating a model for determining the first power supply; and
processing, using the model, the historical weather data to determine the first power supply.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
performing a training operation when generating the model by portioning the historical weather data into a training set, a validation set, and a test set,
wherein performing the training operation comprises:
using the training set to fit the model,
using the validation set to provide an evaluation of a fit of the model, and
using the test set to provide an evaluation of the model on the training set.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining the first cost includes at least one of:
determining a cost associated with charging the battery; or
determining a cost associated with a bi-directional loss associated with utilizing the battery as a power resource.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the first cost includes at least one of:
determining a first degradation factor associated with an age of the battery;
determining a second degradation factor associated with a state of charge for the battery; or
determining a third degradation factor associated with a cycle count associated with the battery.

### Claim 7 (depends on 1)

The method of claim 1, wherein determining the second cost includes:
determining a cost of a type of fuel utilized by the engine.

### Claim 8

A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
receive a power demand for a load;
receive a weather forecast for a time period;
determine a first power supply available from a photo voltaic (PV) installation for the time period based on the weather forecast;
determine a power deficit for the time period based on the power demand and the first power supply;
determine a first cost associated with utilizing a second power supply available from a battery for the time period;
determine a second cost associated with utilizing a third power supply available from an engine for the time period;
determine a power source to overcome the power deficit based on the first cost and the second cost,
wherein the power source includes at least one of the battery or the engine; and
send a request to the PV installation and the power source to cause the PV installation and the power source to supply power to satisfy the power demand for the load.

### Claim 9 (depends on 8)

The device of claim 8, wherein determining the power source includes:
utilize machine learning to determine the power source.

### Claim 10 (depends on 8)

The device of claim 8, wherein determining power source includes:
obtain a plurality of historical load profiles;
generate a model for determining the power source;
process, using the model, the historical load profiles to determine a predicted load profile; and
determining the power source based on the predicted load profile and the first power supply.

### Claim 11 (depends on 10)

The device of claim 10, wherein the one or more processors are further configured to:
perform a training operation when generating the model by portioning the historical load profiles into a training set, a validation set, and a test set,
wherein the one or more processors, when perform the training operation, are configured to:
use the training set to fit the model,
use the validation set to provide an evaluation of a fit of the model, and
use the test set to provide an evaluation of the model on the training set.

### Claim 12 (depends on 8)

The device of claim 8, wherein determining the first cost includes at least one of:
determine a cost associated with charging the battery; or
determine a cost associated with a bi-directional loss associated with utilizing the battery as a power resource.

### Claim 13 (depends on 8)

The device of claim 8, wherein determining the first cost includes at least one of:
determine a first degradation factor associated with an age of the battery;
determine a second degradation factor associated with a state of charge for the battery; or
determine a third degradation factor associated with a cycle count associated with the battery.

### Claim 14 (depends on 8)

The device of claim 8, wherein determining the second cost includes:
determine a cost of a type of fuel utilized by the engine.

### Claim 15

A system comprising:
a plurality of power resources; and
a power control device configured to:
receive a power demand;
receive a first weather forecast for a first time period and a second weather forecast for second time period,
wherein the second time period is after the first time period;
determine a first power supply available from a first power resource, of the plurality of power resources, over the first time period based on the first weather forecast and a second power supply available from the first power resource over the second time period based on the second weather forecast;
determine a power deficit for the first time period based on the power demand and the first power supply;
determine a cost associated with utilizing a third power supply from a second power resource, of the plurality of power resources, over the first time period;
determine a cost associated with utilizing a fourth power supply from a third power resource, of the plurality of power resources, over the first time period;
select one or more of the second power resource or the third power resource, as a selected power source, to satisfy the power deficit based on the second power supply, the cost associated with utilizing the third power supply, and the cost associated with utilizing the fourth power supply; and
transmit a request to the first power resource and the selected power resource to cause the first power resource and the selected power resource to supply power to satisfy the power demand.

### Claim 16 (depends on 15)

The system of claim 15, wherein when determining the first power supply, the power control device is configured further to:
utilize machine learning to determine the first power supply.

### Claim 17 (depends on 15)

The system of claim 15, wherein when determining the first power supply, the power control device is configured further to:
obtain a plurality of historical weather data;
generate a model for determining the first power supply; and
process, using the model, the historical weather data to determine the first power supply.

### Claim 18 (depends on 17)

The system of claim 17, wherein the power control device is configured further to:
perform a training operation when generating the model by portioning the historical weather data into a training set, a validation set, and a test set,
wherein when performing the training operation, the power control device is configured further to:
use the training set to fit the model,
use the validation set to provide an evaluation of a fit of the model, and
use the test set to provide an evaluation of the model on the training set.

### Claim 19 (depends on 15)

The system of claim 15, wherein, when determining the cost associated with utilizing the second power resource, the power control device is configured to determine at least one of:
a cost associated with charging a battery; or
a cost associated with a bi-directional loss associated with utilizing the battery as a power resource.

### Claim 20 (depends on 15)

The system of claim 15, wherein, when determining the cost associated with utilizing the second power resource, the power control device is configured to determine at least one of:
a first degradation factor associated with an age of a battery;
a second degradation factor associated with a state of charge for the battery; or
a third degradation factor associated with a depth of a cycle associated with the battery.
