US-12625474-B2 - Automated asset strategy selection for an asset via cloud-based supervisory control

US12625474B2US 12625474 B2US12625474 B2US 12625474B2US-12625474-B2

Abstract

Various embodiments described herein relate to automated asset strategy selection for assets via cloud-based supervisory control. In this regard, one or more baselines for asset strategy data related to an asset is estimated based on a regression analysis process associated with the asset. Additionally, a maximum uncertainty level for the one or more baselines is determined, one or more conditions related to energy optimization for an environment associated with the asset is estimated for a future period of time, and a predicted uncertainty level for the one or more conditions related to the energy optimization is determined. Based on a comparison between the maximum uncertainty level and the predicted uncertainty level, a predetermined asset strategy or an energy optimization asset strategy for the future period of time is then selected.

Inventors

Petr Endel
MICHAL VRANA
Karel Marik
Raman Samusevich
Vaclav Slimacek

Assignees

HONEYWELL INTERNATIONAL INC.

Dates

Publication Date: 20260512
Application Date: 20220824

Claims (15)

1 . A system, comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs comprising instructions configured to: estimate one or more baselines for asset strategy data related to an asset based on a regression analysis process associated with historical operational performance data of the asset; determine a maximum uncertainty level for the one or more baselines; estimate, for a future period of time, one or more conditions related to energy optimization for an environment associated with the asset; determine a predicted uncertainty level for the one or more conditions related to the energy optimization; compare the maximum uncertainty level for the one or more baselines and the predicted uncertainty level for the one or more conditions, wherein the maximum uncertainty level and the predicted uncertainty level are both determined using the regression analysis process; based on a comparison between the maximum uncertainty level and the predicted uncertainty level, select a predetermined asset strategy or an energy optimization asset strategy for the future period of time; execute the selected asset strategy by transmitting control signals to a control device associated with the asset to perform one or more operational changes, wherein the asset comprises at least a Heating, Ventilation, and Air Conditioning (HVAC) system, and wherein the control signals to the control device associated with the asset adjust at least one control parameter comprising a temperature setpoint, a supply air flow rate, a damper position, and a fan speed; and update the selected asset strategy based on operational data received from the asset, wherein the operational data comprises real-time sensor measurements of attributes of a current performance state of the asset, and wherein the update comprises modifying the selected asset strategy by dynamically adjusting at least one control parameter and transmitting updated control signals to the asset, based on a comparison between a predicted value of an operational attribute and a real-time sensor measurement of the operational attribute, using a feedback loop that applies corrective adjustments to the control signals until a deviation between the predicted value and the real-time sensor measurement falls below a threshold.
2 . The system of claim 1 , the one or more programs further comprising instructions configured to: estimate the one or more baselines based on a Gaussian process regression associated with the asset.
3 . The system of claim 2 , the one or more programs further comprising instructions configured to: determine the maximum uncertainty level at respective training points associated with the Gaussian process regression.
4 . The system of claim 1 , the one or more programs further comprising instructions configured to: in response to selecting the predetermined asset strategy for the asset, re-estimate the one or more baselines for the asset strategy data based on the regression analysis process.
5 . The system of claim 1 , the one or more programs further comprising instructions configured to: in response to selecting the predetermined asset strategy for the asset, re-estimate the one or more baselines for the asset strategy data based on a Gaussian process regression associated with the asset.
6 . The system of claim 1 , the one or more programs further comprising instructions configured to: apply the predetermined asset strategy for the asset in response to a determination that the predicted uncertainty level is greater than the maximum uncertainty level.
7 . The system of claim 1 , the one or more programs further comprising instructions configured to: re-estimate the one or more baselines for the asset strategy data in response to applying the predetermined asset strategy for the asset.
8 . The system of claim 1 , the one or more programs further comprising instructions configured to: update the maximum uncertainty level in response to applying the predetermined asset strategy for the asset.
9 . The system of claim 1 , the one or more programs further comprising instructions configured to: apply the energy optimization asset strategy for the asset in response to a determination that the predicted uncertainty level is less than the maximum uncertainty level.
10 . A method, comprising: at a device with one or more processors and a memory: estimating one or more baselines for asset strategy data related to an asset based on a regression analysis process associated with historical operational performance data of the asset; determining a maximum uncertainty level for the one or more baselines; estimating, for a future period of time, one or more conditions related to energy optimization for an environment associated with the asset; determining a predicted uncertainty level for the one or more conditions related to the energy optimization; comparing the maximum uncertainty level for the one or more baselines and the predicted uncertainty level for the one or more conditions, wherein the maximum uncertainty level and the predicted uncertainty level are both determined using the regression analysis process; based on a comparison between the maximum uncertainty level and the predicted uncertainty level, selecting a predetermined asset strategy or an energy optimization asset strategy for the future period of time; executing the selected asset strategy by transmitting control signals to a control device associated with the asset to perform one or more operational changes, wherein the asset comprises at least a Heating, Ventilation, and Air Conditioning (HVAC) system, and wherein the control signals to the control device associated with the asset adjust at least one control parameter comprising a temperature setpoint, a supply air flow rate, a damper position, and a fan speed; and updating the selected asset strategy based on operational data received from the asset, wherein the operational data comprises real-time sensor measurements of attributes of a current performance state of the asset, and wherein the update comprises modifying the selected asset strategy by dynamically adjusting at least one control parameter and transmitting updated control signals to the asset, based on a comparison between a predicted value of an operational attribute and a real-time sensor measurement of the operational attribute, using a feedback loop that applies corrective adjustments to the control signals until a deviation between the predicted value and the real-time sensor measurement falls below a threshold.
11 . The method of claim 10 , the estimating the one or more baselines comprising estimating the one or more baselines based on a Gaussian process regression associated with the asset.
12 . The method of claim 11 , the determining the maximum uncertainty level for the one or more baselines comprising determining the maximum uncertainty level at respective training points associated with the Gaussian process regression.
13 . The method of claim 10 , further comprising: in response to selecting the predetermined asset strategy for the asset, re-estimating the one or more baselines for the asset strategy data based on the regression analysis process.
14 . The method of claim 10 , further comprising: in response to selecting the predetermined asset strategy for the asset, re-estimating the one or more baselines for the asset strategy data based on a Gaussian process regression associated with the asset.
15 . The method of claim 10 , further comprising: applying the predetermined asset strategy for the asset in response to a determination that the predicted uncertainty level is greater than the maximum uncertainty level.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application is a divisional of and claims priority to U.S. application Ser. No. 17/893,932, titled “AUTOMATED SETPOINT GENERATION FOR AN ASSET VIA CLOUD-BASED SUPERVISORY CONTROL,” and filed Aug. 23, 2022, which claims the benefit of U.S. Provisional Patent Application No. 63/236,271, titled “AUTOMATED SETPOINT GENERATION FOR AN ASSET VIA CLOUD-BASED SUPERVISORY CONTROL,” and filed on Aug. 24, 2021, the contents of which are hereby incorporated by reference in their entirety. TECHNICAL FIELD The present disclosure relates generally to performance management related to assets, and more particularly to automated setpoint generation for assets via cloud-based supervisory control. BACKGROUND Asset settings for an asset are generally configured by a user based on user knowledge or written instructions. For example, settings for a heating, ventilation and air conditioning (HVAC) system are generally configured by a user based on user knowledge or written instructions with respect to the HVAC system. However, asset settings configured based on user knowledge or written instructions with respect to an asset generally results in inefficiencies and/or decreased performance for the asset. SUMMARY The details of some embodiments of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims. In an embodiment, a system comprises one or more processors, a memory, and one or more programs stored in the memory. The one or more programs comprise instructions configured to receive a request to perform supervisory control with respect to an asset. In one or more embodiments, the request comprises an asset identifier indicating an identity of the asset. In response to the request, the one or more programs comprise instructions configured to determine one or more setpoints for the asset based on the asset identifier. In response to the request, the one or more programs also comprise instructions configured to determine, based on the asset identifier, comfort constraint data indicative of one or more comfort constraints for an environment associated with the asset. Additionally, in response to the request, the one or more programs comprise instructions configured to adjust the one or more setpoints for the asset based on the comfort constraint data. In another embodiment, a method comprises, at a device with one or more processors and a memory, receiving a request to perform supervisory control with respect to an asset. In one or more embodiments, the request comprises an asset identifier indicating an identity of the asset. In response to the request, the method comprises determining one or more setpoints for the asset based on the asset identifier. In response to the request, the method also comprises determining, based on the asset identifier, comfort constraint data indicative of one or more comfort constraints for an environment associated with the asset. Additionally, in response to the request, the method comprises adjusting the one or more setpoints for the asset based on the comfort constraint data. In yet another embodiment, a non-transitory computer-readable storage medium comprises one or more programs for execution by one or more processors of a device. The one or more programs comprise instructions which, when executed by the one or more processors, cause the device to receive a request to perform supervisory control with respect to an asset. In one or more embodiments, the request comprises an asset identifier indicating an identity of the asset. The one or more programs comprise instructions which, when executed by the one or more processors and in response to the request, cause the device to determine one or more setpoints for the asset based on the asset identifier. The one or more programs also comprise instructions which, when executed by the one or more processors and in response to the request, cause the device to determine, based on the asset identifier, comfort constraint data indicative of one or more comfort constraints for an environment associated with the asset. Additionally, one or more programs comprise instructions which, when executed by the one or more processors and in response to the request, cause the device to adjust the one or more setpoints for the asset based on the comfort constraint data. In another embodiment, a system comprises one or more processors, a memory, and one or more programs stored in the memory. The one or more programs comprise instructions configured to estimate one or more baselines for asset strategy data related to an asset based on a regression analysis process associated with the asset. The one or more programs also comprise instructions configured to determine a maximum uncertainty level for the one or more baselines. The one or