# US 10,312,681 B2 · Automatic network device electrical phase identification > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,312,681 B2 - Document ID: US10312681B2 - Status: Granted - Kind: B2 - Application number: 15/058,112 - Filed: 2016-03-01 - Published: 2016-12-01 - Granted: 2019-06-04 - Earliest claimed: 2015-05-28 - Assignees: Itron, Inc. - Applicants: Itron, Inc. - Inventors: Roberto Aiello; Patrick Amihood - Web page: https://patentgrep.com/patent/US10312681B2 ## CPC - H02J 13/333: the equipment forming part of substations - G01R 19/2513: {Arrangements for monitoring electric power systems, e.g. power lines or loads; Logging} - G01R 29/18: Indicating phase sequence; Indicating synchronism - G05B 13/0265: {the criterion being a learning criterion} - H02J 3/00: Circuit arrangements for AC mains or AC distribution networks - H02J 3/12: Arrangements for adjusting voltage in AC networks by changing a characteristic of the network load - H02J 3/26: Arrangements for eliminating or reducing asymmetry in polyphase networks - H02J 13/10: characterised by displaying of information or by user interaction, e.g. supervisory control and data acquisition [SCADA] systems - H02J 13/12: Monitoring network conditions, e.g. electrical magnitudes or operational status - H02J 13/1331: {using wireless data transmission} - H02J 13/182: the equipment comprising loads connected to the power network - H02J 3/34: Arrangements for transfer of electric power between networks of substantially different frequency - Y02B 70/30: Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level - Y02B 90/20: Smart grids as enabling technology in buildings sector (smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00) - Y02E 60/00: Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation - Y04S 10/30: State monitoring, e.g. fault, temperature monitoring, insulator monitoring, corona discharge - Y04S 10/40: Display of information, e.g. of data or controls - Y04S 20/00: Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof - Y04S 20/242: Home appliances - Y04S 40/126: using wireless data transmission - H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) - 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) - Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS - Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION - Y04S: SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS ## Abstract Techniques detect an electrical phase used by electrical network devices (e.g., a transformer, electrical meter, etc.). Voltage measurement data is obtained, such as from electrical meters. The voltage measurement data may be associated with a timestamp, and may be made at intervals over a period of time. Voltage changes may be calculated using the voltage measurement data. In an example, the voltage change is a difference determined between sequential voltage measurements. In some instances, voltage changes data is removed if it exceeds a threshold. An initial classification of network devices (e.g., randomly or by assumed electrical phase) is determined. A clustering technique (e.g., k-means) is applied, wherein the classification is updated in a manner that segregates the network devices according to actual electrical phase. ## Claims ### Claim 1 A method, comprising: under control of one or more processors configured with executable instructions: obtaining voltage measurement data, wherein the voltage measurement data comprises voltage measurements made at a plurality of meters, wherein each meter is connected to a transformer, and wherein each transformer is connected to a phase of a feeder line; calculating voltage change data for each meter using the obtained voltage measurement data, wherein the calculated voltage change data of each meter is based at least in part changing voltages of a phase of the feeder line to which the meter is connected, and wherein voltage measurements are made less than two hours apart by a same network device to calculate a voltage change; excluding voltage change data having a magnitude greater than a threshold value; configuring an initial classification of network devices; and updating the initial classification according to a clustering technique acting on the calculated voltage change data, thereby segregating the network devices according to electrical phase, wherein the updating of the initial classification is based at least in part on: the calculated voltage change data of each meter; connectivity of meters to a respective transformer; and connectivity of each transformer to a phase of the feeder line. ### Claim 2 (depends on 1) The method of claim 1, wherein the updating comprises: reclassifying at least some network devices based on the calculated voltage change data, to thereby cluster network devices having similar calculated voltage changes at similar times. ### Claim 3 (depends on 1) The method of claim 1, wherein the updating comprises: reclassifying the network devices to minimize a distance function as applied to the calculated voltage change data. ### Claim 4 (depends on 1) The method of claim 1, wherein the updating comprises: operating k-means clustering techniques to segregate the network devices according to electrical phase. ### Claim 5 (depends on 1) The method of claim 1, wherein obtaining voltage measurement data comprises: obtaining at least 48 measurements over at least two days. ### Claim 6 (depends on 1) The method of claim 1, wherein excluding of the voltage change data comprises: setting voltage change data to approximately zero, when the magnitude of the voltage change data exceeds the threshold value. ### Claim 7 (depends on 1) The method of claim 1, additionally comprising: connecting at least one network device, from among the network devices, to a different phase based at least in part on the update. ### Claim 8 (depends on 1) The method of claim 1, additionally comprising: excluding data from network devices for which insufficient or incomplete data exists. ### Claim 9 One or more computer-readable media storing computer-executable instructions that, when executed, cause one or more processors to perform acts comprising: obtaining voltage measurement data, wherein the voltage measurement data comprises voltage measurements made at a plurality of network devices, wherein each network device is connected to a transformer, and wherein each transformer is connected to a phase of a feeder line; calculating voltage change data for a plurality of network devices, wherein the calculated voltage change data of each of the plurality of network devices is based at least in part changing voltages of a phase of the feeder line to which the network device is connected, wherein calculating the voltage change data comprises calculating a voltage change vector for each of the plurality of network devices, and wherein each voltage change vector comprises paired time and voltage change values; classifying meters according to an initial classification to prepare for application of a clustering technique to the voltage change data; clustering the meters according to voltage changes over time, in an iterative manner to update the initial classification and to thereby cluster meters by electrical phase; and providing information about an electrical service associated with at least one network device from among the plurality of network devices, the information sufficient to indicate an electrical load to be moved from a first phase to a second phase. ### Claim 10 (depends on 9) One or more computer-readable media as recited in claim 9, wherein the acts additionally comprise: setting to zero voltage change data having a magnitude greater than a threshold value. ### Claim 11 (depends on 9) One or more computer-readable media as recited in claim 9, wherein clustering the meters comprises: minimizing a distance function between the meters. ### Claim 12 (depends on 9) One or more computer-readable media as recited in claim 9, wherein providing information comprises: reconnecting a load measured by a first network device from a first phase to a second phase. ### Claim 13 A computing device, comprising: a processing unit; memory, accessible by the processing unit; a data module, defined in the memory and executed by the processing unit, to gather voltage measurement data of a plurality of network devices, wherein the voltage measurement data comprises voltage measurements made at a plurality of network devices, wherein each network device is connected to a transformer, and wherein each transformer is connected to a phase of a feeder line; a voltage change calculation module, defined in the memory and executed by the processing unit, to calculate voltage change data for each of the plurality of network devices, wherein the calculated voltage change data of each of the plurality of network devices is based at least in part changing voltages of a phase of the feeder line to which the network device is connected, wherein calculating the voltage change data comprises calculating a voltage change vector for each of the plurality of network devices, and wherein each voltage change vector comprises paired time and voltage change values; and a clustering module, defined in the memory and executed by the processing unit, to determine a phase to which a network device from among the plurality of network devices is associated based at least in part on the changes in voltage determined by the voltage change calculation module, wherein the clustering module is configured to utilize k-means techniques to cluster network devices having similar calculated voltage changes at similar times. ### Claim 14 (depends on 13) The computing device as recited in claim 13, additionally comprising: a phase-switching module, defined in the memory and executed by the processing unit, and configured to cause a load of one of the plurality of network devices to be switched from one phase to another phase. ### Claim 15 (depends on 13) The computing device as recited in claim 13, wherein the data module is configured to: obtain data over a period of at least 24 hours; and obtain measurements separated by 2 hours or less. ### Claim 16 (depends on 13) The computing device as recited in claim 13, additionally comprising: a data threshold module configured to set voltage change data to approximately zero, when the voltage change data exceeds a threshold; and a data cleaning module configured to remove voltage data associated with network devices for which the gathered voltage measurement data is incomplete. ### Claim 17 (depends on 13) The computing device as recited in claim 13, wherein the clustering module is configured to perform: an iterative process by which convergence is indicated by minimizing a distance function.