# US 2025/0085013 A1 · Method and Apparatus for Optimizing Control Parameters

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

- Number: US 2025/0085013 A1
- Document ID: US20250085013A1
- Status: Published application
- Kind: A1
- Application number: 18/728,325
- Filed: 2022-01-25
- Published: 2025-03-13
- Earliest claimed: 2022-01-25
- Assignees: Siemens Schweiz AG
- Applicants: Siemens Schweiz AG
- Inventors: Jin Yan Guan; Ying Qu; Cheng Feng; Xiao Nan Liu
- Web page: https://patentgrep.com/patent/US20250085013A1

## CPC

- F24F 11/64: using pre-stored data
- F24F 11/47: Responding to energy costs
- F24F 11/62: characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- G05B 13/042: {in which a parameter or coefficient is automatically adjusted to optimise the performance}
- G05B 13/048: {using a predictor}
- G05B 15/02: electric
- F24F 2130/10: Weather information or forecasts
- G05B 2219/2614: HVAC, heating, ventillation, climate control
- 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

Embodiments of this application relate to control parameter optimization technologies. Various embodiments include methods and apparatus for optimizing control parameters. At least one group of initial control parameters within a preset range is randomly generated, to obtain a group of current control parameters; it is determined whether a number of updates has exceeded a preset threshold, referring to a total number of times that the current control parameters have been changed; the group of current control parameters is changed when the number of updates does not reach the preset threshold; and air conditioning control parameters are optimized according to control parameters corresponding to a comprehensive score of a combination when the number of updates reaches the preset threshold.

## Claims

### Claim 1

A method for optimizing control parameters, the method comprising:
randomly generating a group of initial control parameters within a preset range to obtain a group of current control parameters;
determining whether a number of updates has exceeded a preset threshold, wherein the number of updates represents a total number of times that the current control parameters have been changed;
when the number of updating does not reach the preset threshold:
entering the group of current control parameters, a current indoor condition value, and a future weather condition value to an energy consumption prediction model and an indoor condition prediction model;
receiving a combination comprising: future energy consumption generated by the energy consumption prediction model and a future indoor condition generated by the indoor prediction model;
scoring the combination to obtain a consumption cost and indoor condition cost of the combination, wherein the indoor condition cost reflects a deviation of the future indoor condition from a target indoor condition;
calculating a comprehensive score for each group according to the consumption cost and the indoor condition cost of the respective, wherein the comprehensive score reflects a comprehensive cost of the consumption cost and the indoor condition cost;
changing the group of current control parameters, and incrementing the number of updates;
and
optimizing a set of air conditioning control parameters using control parameters corresponding to the comprehensive score of the combination when the number of updates reaches the preset threshold.

### Claim 2 (depends on 1)

The method according to claim 1, wherein changing the group of current control parameters comprises
changing the group of current control parameters using an evolutionary multi-objective optimization incorporating the consumption cost and the indoor condition cost of each combination.

### Claim 3 (depends on 1)

The method according to claim 1, wherein randomly generating a group of initial control parameters comprises
generating a group of initial control parameters in next N hours, wherein N≤24.

### Claim 4 (depends on 1)

The method according to claim 1, wherein calculating a comprehensive score of each group according to the consumption cost and the indoor condition cost of each combination comprises
calculating the comprehensive score of each combination by combining the consumption cost and the indoor condition cost of each combination with preset weights.

### Claim 5 (depends on 1)

The method according to claim 1, further comprising, after calculating a comprehensive score of each combination, ranking the comprehensive score of each combination in an ascending order, and recording control parameters corresponding to top K comprehensive scores, wherein K≥1.

### Claim 6 (depends on 1)

The method according to claim 1, wherein:
the consumption cost comprises a cost of average energy consumption; and
the indoor condition cost comprises a cost of average indoor condition.

### Claim 7 (depends on 1)

The method according to claim 1, wherein:
the consumption cost comprises a cost of average energy consumption and cost of the uncertainty in energy consumption; and
the indoor condition cost comprises a cost of an average indoor condition and cost of the uncertainty in indoor condition.

### Claim 8 (depends on 1)

The method according to claim 1, wherein:
an offline training method for the energy consumption prediction model comprises
providing historical weather data, historical energy consumption data, historical indoor condition data and a historical control parameter to the energy consumption prediction model for training; and
an offline training method for the indoor condition prediction model comprises
providing a historical weather data, historical energy consumption data, historical indoor condition data and a historical control parameter to the indoor condition prediction model for training.

### Claim 9

(canceled)

### Claim 10

An electronic device comprising:
a processor; and
a memory storing a computer-readable instructions;
wherein the computer-readable instruction, when executed by the processor, cause the processor to:
generate a group of initial control parameters within a preset range to obtain at least one group of current control parameters;
determine whether a number of updates in an updating module has exceeded preset threshold, wherein the number of updates represents a total number of times that the current control parameters have been changed;
change the group of current control parameters when the number of updates has not reached the preset threshold and update the number of updates;
provide the group of current control parameters, a current indoor condition value, and a future weather condition value to an energy consumption prediction model and an indoor condition prediction model; receive a combination including: future energy consumption generated by the energy consumption prediction model and a future indoor condition generated by the indoor prediction model; score the combination to obtain consumption cost and indoor condition cost of the combination, wherein the indoor condition cost reflects a deviation of the generated future indoor condition from a tar et indoor condition; calculate a comprehensive score of each combination according to the consumption cost and the indoor condition cost of each combination respectively, wherein the Comprehensive score reflects a comprehensive cost of the consumption cost and the indoor condition cost; and
optimize air conditioning control parameters using the control parameters corresponding to the comprehensive score of the combination when the number of updates reaches the preset threshold.

### Claim 11

(canceled)