ELECTRICAL LOAD VALIDATION FOR A SMART SPACE IN A BUILDING
A method/system monitors and controls operational aspects of devices in a space, for example a living, office or other human-occupied space or storage space, in a building, such as turning lights on/off, raising/lowering blinds, maintaining or changing temperature, and other operational aspects. Sensors monitor energy usage of the devices in the space, and a controller/engine compares the monitored energy usage with reference energy usage to validate whether the devices are performing as expected. A temperate set-versus-anomaly detection technique may use temperature set point adjustments by a user (during a timeframe) to determine whether an anomaly exists that requires changes in the central plant of the building.
1 . (canceled)
2 . A method to monitor and control operational aspects associated with a space in a building, the method comprising:
storing reference data associated with at least one device located in the space;
receiving, from a user device of a user of the space, a request to perform a first action directed towards remotely controlling the at least one device, wherein the user is absent from the space at a time that the request to perform the first action is received;
obtaining data from at least one sensor, including either or both an audio sensor and an image sensor, located in the space;
comparing the obtained data with the stored reference data to determine whether the obtained data matches the stored reference data with respect to the first action;
in response to determining that the obtained data matches the stored reference data, validating that the first action has been performed successfully; and
in response to determining that there is a mismatch between the obtained data and the stored reference data, generating an alert to inform the user that the first action is unsuccessful.
3 . The method of claim 2 , wherein:
the at least one device includes one or more light bulbs, and
the first action turns the one or more light bulbs ON or OFF.
4 . The method of claim 2 , wherein comparing the obtained data with the stored reference data comprises using a machine learning technique to determine whether the obtained data matches the stored reference data.
5 . The method of claim 2 , further comprising using a machine learning technique to collect data that pertains to the space and to update the reference data with the collected data.
6 . The method of claim 2 , wherein comparing the obtained data with the stored reference data to determine whether the obtained data matches the stored reference data with respect to the first action comprises:
identifying a portion of the obtained data that corresponds to the time that the request to perform the first action is received;
selecting a portion of the stored reference data that corresponds to the first action; and
determining whether the identified portion of the obtained data and the selected portion of the stored reference data match.
7 . The method of claim 2 , wherein comparing the obtained data with the stored reference data to determine whether the obtained data matches the stored reference data with respect to the first action comprises:
identifying a portion of the obtained data that corresponds to a time before the request to perform the first action is received;
identifying a portion of the obtained data that corresponds to a time after the request to perform the first action is received;
calculating an actual change between the portion of the obtained data that corresponds to the time before the request to perform the first action is received and the portion of the obtained data that corresponds to the time after the request to perform the first action is received;
determining a reference change from the stored reference data; and
comparing the actual change with the reference change to determine whether the actual change matches the reference change.
8 . The method of claim 2 , wherein in response to determining that there is the mismatch between the obtained data and the stored reference data, generating the alert comprises:
performing a retry of the first action; and
generating the alert, if the retry indicates that the first action is unsuccessfully performed.
9 . The method of claim 2 , wherein in response to determining that the obtained data matches the stored reference data, validating that the first action has been performed successfully comprises:
checking for a steady state status of the at least one device, before validating that the first action has been performed successfully; and
validating that the first action has been performed successfully, after the steady state status of the at least one device is confirmed.
10 . A method to monitor and control operational aspects associated with a space in a building, the method comprising:
sending, from a user device to head-end equipment at the building, a request to perform a first action directed towards remotely controlling at least one device located in the space, wherein the user device is absent from the space at a time that the request to perform the first action is sent;
receiving, by the user device from the head-end equipment, data from at least one sensor, including either or both an audio sensor and an image sensor, located in the space;
based at least in part on the received data, determining whether the first action has been performed successfully; and
presenting, by the user device, an alert in response to determining that the first action has been performed unsuccessfully.
11 . The method of claim 10 , wherein determining whether the first action has been performed successfully comprises:
comparing the received data with stored reference data associated with the at least one device to determine whether the received data matches the stored reference data with respect to the first action;
in response to determining that the received data matches the stored reference data, validating that the first action has been performed successfully; and
in response to determining that there is a mismatch between the received data and the stored reference data, determining that the first action has not been performed successfully.
12 . The method of claim 10 , wherein:
the at least one device includes utility equipment, and
the first action changes an operational state of the utility equipment.
13 . The method of claim 10 , wherein determining whether the first action has been performed successfully comprises using a machine learning technique to determine a match between the received data and stored reference data associated with the at least one device.
14 . The method of claim 13 , further comprising using the machine learning technique to collect data that pertains to the space and to update the reference data with the collected data.
15 . The method of claim 10 , wherein determining whether the first action has been performed successfully comprises:
identifying a portion of the received data that corresponds to the time that the request to perform the first action is sent;
selecting stored reference data that corresponds to the first action; and
comparing the identified portion of the received data with the selected reference data to determine whether the identified portion of the received data matches the selected reference data.
16 . The method of claim 10 , wherein determining whether the first action has been performed successfully comprises:
identifying a portion of the received data that corresponds to a time before the request to perform the first action is sent;
identifying a portion of the received data that corresponds to a time after the request to perform the first action is sent;
calculating an actual change between the portion of the received data that corresponds to the time before the request to perform the first action is sent and the portion of the received data that corresponds to the time after the request to perform the first action is sent;
determining a reference change from stored reference data; and
comparing the actual change with the reference change to determine whether the actual change matches the reference change.
17 . A non-transitory computer-readable medium having instructions stored thereon, which in response to execution by a processor, cause the processor to perform or control performance of operations that comprise:
sending, from a user device to head-end equipment in a building, a request to perform a first action directed towards remotely controlling at least one device located in a space in the building, wherein the user device is absent from the space at a time that the request to perform the first action is sent and wherein the user device is configured to access the head-end equipment in the building;
receiving, by the user device from the head-end equipment, data from at least one sensor, including either or both an audio sensor and an image sensor, located in the space;
based at least in part on the received data, determining whether the first action has been performed successfully; and
presenting, by the user device, an alert in response to determining that the first action has been performed unsuccessfully.
18 . The non-transitory computer-readable medium of claim 17 , wherein determining whether the first action has been performed successfully comprises:
comparing the received data with stored reference data associated with the at least one device to determine whether the received data matches the stored reference data with respect to the first action;
in response to determining that the received data matches the stored reference data, validating that the first action has been performed successfully; and
in response to determining that there is a mismatch between the received data and the stored reference data, determining that the first action has been performed unsuccessfully.
19 . The non-transitory computer-readable medium of claim 17 , wherein determining whether the first action has been performed successfully comprises using a machine learning technique to compare the received data with stored reference data associated with the at least one device.
20 . The non-transitory computer-readable medium of claim 19 , wherein the operations further comprise using the machine learning technique to collect data that pertains to the space and to update the reference data with the collected data.
21 . The non-transitory computer-readable medium of claim 17 , wherein determining whether the first action has been performed successfully comprises:
identifying a portion of the received data that corresponds to a time before the request to perform the first action is sent;
identifying a portion of the received data that corresponds to a time after the request to perform the first action is sent;
calculating an actual change between the portion of the received data that corresponds to the time before the request to perform the first action is sent and the portion of the received data that corresponds to the time after the request to perform the first action is sent;
determining a reference change from stored reference data; and
comparing the actual change with the reference change to determine whether the actual change matches the reference change.