# US 2025/0085758 A1 · Powered Device Electrical Data Modeling And Intelligence > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0085758 A1 - Document ID: US20250085758A1 - Status: Published application - Kind: A1 - Application number: 18/894,409 - Filed: 2024-09-24 - Published: 2025-03-13 - Earliest claimed: 2020-07-10 - Assignees: Sapient Industries, Inc. - Applicants: Sapient Industries, Inc. - Inventors: Samuel M. Parks; Derek Horkel - Web page: https://patentgrep.com/patent/US20250085758A1 ## CPC - G06F 1/266: {Arrangements to supply power to external peripherals either directly from the computer or under computer control, e.g. supply of power through the communication port, computer controlled power-strips} - G06F 1/28: Supervision thereof, e.g. detecting power-supply failure by out of limits supervision - G06F 1/3206: Monitoring of events, devices or parameters that trigger a change in power modality - G06F 1/3287: by switching off individual functional units in the computer system - Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE ## Abstract A powered device electrical data modeling and intelligence system is used to monitor electrical data of powered devices to determine in-use activity thereof. A number of network-enabled electric plugs are deployed in a region, for example, within certain areas of a floor of a building or within certain floors of a building. Each of the network-enabled electric plugs is configured to deliver electricity from an electricity source to one or more powered devices located in the region. A server runs a web application used to monitor electrical data for the region based on electricity drawn by each of the one or more powered devices. The web application computes usage metrics for the powered devices by modeling electrical data for the powered devices into clusters representative of device operational states. The web application may then determine an operational state of a powered device according to the usage metrics. ## Claims ### Claim 1 A method, comprising: determining common values of electrical data collected for a powered device; identifying a first cluster representing a lowest value of the common values of the electrical data, wherein the first cluster corresponds to a first operational state of the powered device; identifying a second cluster representing another value of the common values of the electrical data, wherein the second cluster corresponds to a second operational state of the powered device; determining usage metrics representing usage activity of the powered device based on the first cluster and the second cluster; and outputting the usage metrics for storage or further processing. ### Claim 2 (depends on 1) The method of claim 1, wherein the first operational state of the powered device is an off operational state, wherein, when the common values of the electrical data includes two values, the second operational state of the powered device is an on and in-use operational state, and wherein, when the common values of the electrical data includes three or more values: the second cluster represents a next lowest value of the common values of the electrical data and the second operational state of the powered device is an on but not in-use operational state, and a third cluster representing a third value of the common values of the electrical data higher than the lowest value and the next lowest value corresponds to a third operational state of the powered device, wherein the third operational state of the powered device is an on and in-use operational state. ### Claim 3 (depends on 1) The method of claim 1, wherein the electrical data collected for the powered device includes time series data indicating electrical usage measurements and timestamps indicative of the electrical usage measurements, and wherein determining the common values of the electrical data collected for the powered device comprises: determining average electrical data values over a period of time based on the time series data; and smoothing the electrical data values using one or more filters to eliminate spikes misrepresenting the average electrical data values. ### Claim 4 (depends on 3) The method of claim 3, wherein the first cluster and the second cluster are identified by processing the smoothed electrical data values using a kernel density function. ### Claim 5 (depends on 1) The method of claim 1, wherein the electrical data is collected for the powered device at a first time, the method comprising: processing second electrical data based on the usage metrics to infer an operational state of the powered device at a second time after the first time. ### Claim 6 (depends on 5) The method of claim 5, the method comprising: populating a truth table with information indicating the common values of the electrical data collected for the powered device associated with the first cluster and the second cluster, wherein the second electrical data is processed based on the usage metrics to infer the operational state of the powered device at the second time by comparing values of the second electrical data against the information within the truth table. ### Claim 7 (depends on 1) The method of claim 1, the method comprising: determining a device type of the powered device based on power amount inferences according to the usage metrics; and responsive to second electrical data collected for a second powered device of the device type, automatically labeling the second powered device with the device type. ### Claim 8 (depends on 1) The method of claim 1, the method comprising: determining a forecast of electricity usage for the powered device over a period of time based on the usage metrics. ### Claim 9 (depends on 1) The method of claim 1, the method comprising: generating a rule for selectively controlling a delivery of electricity to the powered device according to the usage metrics by inferring usage patterns representative of patterns of operational states of the powered device over time. ### Claim 10 (depends on 1) The method of claim 1, wherein the electrical data is collected for the powered device using a web application configured to communicate with a network-enabled electric plug coupled to the powered device in a region defined at the web application. ### Claim 11 (depends on 10) The method of claim 10, wherein a plurality of network-enabled electric plugs are deployed within the region, wherein each network-enabled electric plug of the plurality of network-enabled electric plugs is coupled to one or more powered devices within the region, and wherein the web application is configured to collect electrical data for each of the one or more powered devices coupled to each network-enabled electric plug of the plurality of network-enabled electric plugs. ### Claim 12 (depends on 10) The method of claim 10, wherein the region includes one or more floors of a building or one or more areas of the one or more floors of the building. ### Claim 13 A system, comprising: a network-enabled electric plug configured to deliver electricity from an electricity source to a powered device; and a server device running a web application in communication with the network-enabled electric plug and configured to: determine common values of electrical data collected for the powered device; determine two or more clusters corresponding to operational states of the powered device based on the common values; determine usage metrics representing usage activity of the powered device based on the two or more clusters; and output the usage metrics for storage or further processing. ### Claim 14 (depends on 13) The system of claim 13, wherein, to determine the two or more clusters corresponding to the operational states of the powered device based on the common values, the web application is configured to: identify a first cluster representing a lowest value of the common values of the electrical data, wherein the first cluster corresponds to a first operational state of the powered device; and identify a second cluster representing another value of the common values of the electrical data, wherein the second cluster corresponds to a second operational state of the powered device. ### Claim 15 (depends on 14) The system of claim 14, wherein the first operational state of the powered device is an off operational state, wherein, when the common values of the electrical data includes two values, the second operational state of the powered device is an on and in-use operational state, and wherein, when the common values of the electrical data includes three or more values: the second cluster represents a next lowest value of the common values of the electrical data and the second operational state of the powered device is an on but not in-use operational state, and a third cluster representing a third value of the common values of the electrical data higher than the lowest value and the next lowest value corresponds to a third operational state of the powered device, wherein the third operational state of the powered device is an on and in-use operational state. ### Claim 16 (depends on 13) The system of claim 13, wherein the web application is configured to: determine a device type of the powered device based on power amount inferences according to the usage metrics; and responsive to second electrical data collected for a second powered device of the device type, automatically label the second powered device with the device type. ### Claim 17 (depends on 13) The system of claim 13, wherein the web application is configured to: generate a rule for selectively controlling the delivery of electricity by the network-enabled electric plug to the powered device according to the usage metrics by inferring usage patterns representative of patterns of the operational states of the powered device over time. ### Claim 18 A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations, the operations comprising: determining two or more clusters corresponding to operational states of a powered device based on common values of electrical data collected for the powered device; and outputting usage metrics representing usage activity of the powered device and determined based on the two or more clusters for storage or further processing. ### Claim 19 (depends on 18) The non-transitory computer readable medium of claim 18, wherein the two or more clusters include at least a first cluster representing a lowest value of the common values of the electrical data and a second cluster representing another value of the common values of the electrical data, wherein the first cluster corresponds to a first operational state of the powered device and the second cluster corresponds to a second operational state of the powered device, wherein the first operational state of the powered device is an off operational state, wherein, when the common values of the electrical data includes two values, the second operational state of the powered device is an on and in-use operational state, and wherein, when the common values of the electrical data includes three or more values: the second cluster represents a next lowest value of the common values of the electrical data and the second operational state of the powered device is an on but not in-use operational state, and a third cluster representing a third value of the common values of the electrical data higher than the lowest value and the next lowest value corresponds to a third operational state of the powered device, wherein the third operational state of the powered device is an on and in-use operational state. ### Claim 20 (depends on 18) The non-transitory computer readable medium of claim 18, wherein the electrical data is collected for the powered device at a first time, the operations comprising: processing second electrical data based on the usage metrics to infer an operational state of the powered device at a second time after the first time.