# US 2025/0155151 A1 · Systems and methods for environmental control

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

- Number: US 2025/0155151 A1
- Document ID: US20250155151A1
- Status: Published application
- Kind: A1
- Application number: 18/946,817
- Filed: 2024-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-14
- Assignees: Dar Al-Handasah
- Applicants: Dar Al-Handasah
- Inventors: Faysal Shair; Dany El Feghali; Majdi Saadeddine
- Web page: https://patentgrep.com/patent/US20250155151A1

## CPC

- F24F 11/63: Electronic processing
- G05B 15/02: electric
- F24F 11/47: Responding to energy costs
- G05B 13/0265: {the criterion being a learning criterion}
- G05B 13/027: {using neural networks only}
- G05B 2219/2614: HVAC, heating, ventillation, climate control
- G05B 2219/2639: Energy management, use maximum of cheap power, keep peak load low
- G05B 2219/2642: Domotique, domestic, home control, automation, smart house
- F24F: AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING (removing dirt or fumes from areas where they are produced B08B15/00; vertical ducts for carrying away waste gases from buildings E04F17/02; tops for chimneys or ventilating shafts, terminals for flues F23L17/02)
- 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)

## Abstract

The system may utilize input data sensors to populate a digital twin of an environment. The system may predict, using machine learning models, a duration required to change an observed environmental condition to a target environmental condition using one or more environmental control devices and one or more occupancy intervals of one or more occupants of the environment. The system may calculate, using the digital twin, an estimated power consumption at the target environmental condition and optimization instructions for the environmental control devices. The system may additionally estimate, using a third machine learning model, an environment optimization parameter based on the one or more optimization instructions and the input data. The system may dynamically generate a graphical user interface comprising a graphical representation of the environment and the environment optimization parameter.

## Claims

### Claim 1

A control system for an environment comprising:
one or more sensors;
one or more controllers;
one or more processors;
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive input data from the one or more sensors;
populate a digital twin of the environment based at least in part on the input data from the one or more sensors, the digital twin comprising one or more zones;
continuously output, to the one or more controllers, environmental control instructions, wherein the environmental control instructions control an operation of one or more environmental control devices;
predict, using a first machine learning model, a duration required to change an observed environmental condition to a target environmental condition of the one or more zones based on the input data using the one or more environmental control devices;
predict, using a second machine learning model, one or more occupancy intervals of one or more occupants of the environment based on the input data;
calculate, using the digital twin, an estimated power consumption at the target environmental condition in the one or more zones based on the duration, the one or more occupancy intervals, and the input data;
generate a comparison by comparing the estimated power consumption in the one or more zones to an actual power consumption observed in the one or more zones;
generate, using the digital twin, one or more optimization instructions for the one or more of the environmental control devices to optimize energy use based on the comparison and the input data;
automatically output the one or more optimization instructions to optimize energy use for the one or more zones to the one or more controllers;
estimate, using a third machine learning model, an environment optimization parameter for the one or more zones based on the one or more optimization instructions and the input data; and
dynamically generate a graphical user interface comprising a graphical representation of the environment and the environment optimization parameter for the one or more zones.

### Claim 2 (depends on 1)

The control system for the environment of claim 1, wherein the memory stores further instructions which are configured to cause the system to:
the environmental control instructions comprise occupancy-based rules for the one or more zones based on the digital twin and input data.

### Claim 3 (depends on 2)

The control system for the environment of claim 2, wherein:
the environment optimization parameter comprises an actual cost savings estimate, and
the actual cost savings estimate is generated using the third machine learning model by simulating airflow through the one or more zones if the occupancy-based rules were not performed, and the third machine learning model is a temporal convolutional network.

### Claim 4 (depends on 1)

The control system for the environment of claim 1, wherein the environmental control devices are one or more air handling units, lights, pressure independence modules, chilled water units, or combinations thereof.

### Claim 5 (depends on 1)

The control system for the environment of claim 1, wherein the input data comprises data from an access control system, a lighting control system, internet-of-things (IoT) sensors, attendance sensors, people counters, and a building management system.

### Claim 6 (depends on 1)

The control system for the environment of claim 1, wherein the memory stores further instructions which are configured to cause the system to:
preprocess the input data to be in a common format.

### Claim 7 (depends on 1)

The control system for the environment of claim 1, wherein:
the estimated power consumption is calculated by calculating a target airflow calculation for the one or more zones based on the duration, the one or more occupancy intervals, and the input data, and
comparing the estimated power consumption to the actual power consumption for the one or more zones comprises comparing the target airflow calculation for the one or more zones to an actual airflow calculation.

### Claim 8 (depends on 1)

The control system for the environment of claim 1, wherein the memory stores further instructions which are configured to cause the system to:
dynamically transmit the graphical user interface to a user device for display;
receive, via the graphical user interface, a first request to select a specific portion of the graphical representation of the environment;
generate an updated graphical user interface displaying a magnified portion of the graphical representation of the environment according to the first request; and
transmit the updated graphical user interface to the user device.

### Claim 9 (depends on 1)

The control system for the environment of claim 1, wherein the memory stores further instructions which are configured to cause the system to:
dynamically transmit the graphical user interface to a user device for display;
receive, via the graphical user interface, a second request to display the one or more optimization instructions grouped by system and chronology;
generate an updated graphical user interface grouping the one or more optimization instructions by system and chronology according to the second request; and
transmit the updated graphical user interface to the user device.

### Claim 10

A control system for an environment comprising:
one or more sensors;
one or more controllers;
one or more processors;
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive input data from the one or more sensors;
populate a digital twin of the environment based at least in part on the input data from the one or more sensors, the digital twin comprising one or more zones;
continuously output, to the one or more controllers, environmental control instructions, wherein the environmental control instructions control an operation of one or more environmental control devices;
predict, using a first machine learning model, a duration required to change an observed environmental condition to a target environmental condition of the one or more zones based on the input data using the one or more environmental control devices;
predict, using a second machine learning model, one or more occupancy intervals of one or more occupants of the environment based on the input data;
calculate, using the digital twin, an estimated power consumption at the target environmental condition in the one or more zones based on the duration, the one or more occupancy intervals, and the input data;
generate a comparison by comparing the estimated power consumption in the one or more zones to an actual power consumption observed in the one or more zones;
generate, using the digital twin, one or more optimization instructions for one or more of the environmental control devices to optimize energy use based on the comparison and the input data;
generate a first graphical user interface displaying the one or more optimization instructions;
transmit the first graphical user interface to a user device;
receive, from the user device, a selection of the one or more optimization instructions;
output the selected optimization instructions to optimize energy use to the one or more controllers;
estimate, using a third machine learning model, a first environment optimization parameter based on the selected optimization instructions and the input data;
generate a second graphical user interface displaying the first environment optimization parameter; and
transmit the second graphical user interface to the user device.

### Claim 11 (depends on 10)

The control system for the environment of claim 10, wherein the second graphical user interface further comprises, a graphical representation of the environment.

### Claim 12 (depends on 10)

The control system for the environment of claim 10, wherein the memory stores further instructions which are configured to cause the system to:
for the one or more optimization instructions not chosen as part of the selection from the user device, calculate a second environment optimization parameter;
generate an updated second graphical user interface displaying the second environment optimization parameter; and
transmit the updated second graphical user interface to the user device.

### Claim 13 (depends on 10)

The control system for the environment of claim 10, wherein the memory stores further instructions which are configured to cause the system to:
determine occupancy-based rules for the one or more zones based on the digital twin and input data, wherein the occupancy-based rules comprise the environmental control instructions to output to one or more devices.

### Claim 14 (depends on 13)

The control system for the environment of claim 13, wherein the first environment optimization parameter is generated using the third machine learning model by simulating airflow through the one or more zones if the occupancy-based rules were not performed.

### Claim 15 (depends on 10)

The control system for the environment of claim 10, wherein outputting the selected optimization instructions to optimize energy use to one or more controllers further comprises:
transmitting, to an air handling unit controller, the environmental control instructions.

### Claim 16

A control system for an environment comprising:
one or more sensors;
one or more processors;
memory in communication with the one or more processors and storing instructions that are configured to cause the system to:
receive input data from the one or more sensors;
populate a digital twin of the environment based at least in part on the input data from the one or more sensors, the digital twin comprising one or more zones;
predict, using a first machine learning model, a duration required to change an observed environmental condition to a target environmental condition of the one or more zones based on the input data using one or more environmental control devices;
predict, using a second machine learning model, one or more occupancy intervals of one or more occupants of the environment based on the input data;
calculate, using the digital twin, an estimated power consumption at the target environmental condition in the one or more zones based on the duration, the one or more occupancy intervals, and the input data;
generate a comparison by comparing the estimated power consumption in the one or more zones to an actual power consumption observed in the one or more zones;
generate, using the digital twin, one or more optimization instructions for the one or more environmental control devices to optimize energy use based on the comparison and the input data;
automatically output the one or more optimization instructions to optimize energy use for the one or more zones;
estimate, using a third machine learning model, an environment optimization parameter for the one or more zones based on the one or more optimization instructions and the input data; and
generate a graphical user interface displaying a graphical representation of the environment and the environment optimization parameter for the one or more zones.

### Claim 17 (depends on 16)

The control system for the environment of claim 16, wherein the memory stores further instructions which are configured to cause the system to:
transmit the graphical user interface to a user device;
receive additional input data from the one or more sensors; and
train the first machine learning model with the additional input data.

### Claim 18 (depends on 16)

The control system for the environment of claim 16, wherein the optimization instructions are output to one or more devices comprising an air handling unit, a light, a pressure independence module, a chilled water unit, or combinations thereof.

### Claim 19 (depends on 16)

The control system for the environment of claim 16, wherein the memory stores further instructions which are configured to cause the system to:
determine occupancy-based rules for the one or more zones based on the digital twin and input data, wherein the occupancy-based rules comprise outputting environmental control strategies to one or more controllers, and
wherein automatically outputting the one or more optimization instructions to optimize energy use for the one or more zones further comprises outputting the environmental control strategies to the one or more controllers.

### Claim 20 (depends on 19)

The control system for the environment of claim 19, wherein the environment optimization parameter is generated using the third machine learning model by simulating airflow through the one or more zones if the occupancy-based rules were not performed.
