# US 2013/0158908 A1 · Method for Unsupervised Non-Intrusive Load Monitoring > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2013/0158908 A1 - Document ID: US20130158908A1 - Status: Published application - Kind: A1 - Application number: 13/331,822 - Filed: 2011-12-20 - Published: 2013-06-20 - Earliest claimed: 2011-12-20 - Assignees: Robert Bosch GmbH - Inventors: Naveen Ramakrishnan; Diego Benitez - Web page: https://patentgrep.com/patent/US20130158908A1 ## CPC - G01D 4/002: {Remote reading of utility meters} - G01D 2204/14: Displaying of utility usage with respect to time, e.g. for monitoring evolution of usage or with respect to weather conditions - 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) - Y04S 20/242: Home appliances - Y04S 20/30: Smart metering, e.g. specially adapted for remote reading - G01D: MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR - Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS - 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 A method distinguishes electrical signals corresponding to an activation or deactivation of a single electrical power consuming device from an electrical signal that supplies electricity to multiple electrical power consuming devices has been developed. The method includes generating signatures corresponding to activation and deactivation of a plurality of electrical devices from a transformation of an electrical power signal using sparse deconvolution to cluster and then identify the activation and deactivation of one of the plurality of electrical devices. ## Claims ### Claim 1 A method for monitoring electrical power consumption comprising: identifying a plurality of electrical events corresponding to activation or deactivation of one of a predetermined number of electrical devices in a transformation of a time varying electrical power signal over a predetermined time period, the time varying electrical power signal supplying power to the predetermined number of electrical devices; deconvolving the identified plurality of electrical events in the transformation of the time varying electrical power signal to generate a first plurality of signatures, each signature in the first plurality of signatures corresponding to activation of one electrical device in the predetermined number of electrical devices, and to generate a second plurality of signatures, each signature in the second plurality of signatures corresponding to deactivation of one electrical device in the predetermined number of electrical devices; clustering the first plurality of signatures and second plurality of signatures to identify activations and deactivations of each electrical device in the predetermined number of electrical devices; and identifying one electrical device in the predetermined number of electrical devices corresponding to one signature in the first clustered plurality of signatures and one signature in the second clustered plurality of signatures. ### Claim 2 (depends on 1) The method of claim 1, the transformation of the time varying electrical signal being a first derivative of the time varying electrical power signal. ### Claim 3 (depends on 1) The method of claim 1 further comprising: identifying a signature that is generated with the deconvolution is in the first plurality of signatures in response to the signature having a positive value. ### Claim 4 (depends on 1) The method of claim 1 further comprising: identifying a signature that is generated with the deconvolution is in the second plurality of signatures in response to the signature having a negative value. ### Claim 5 (depends on 1) The method of claim 1, wherein the deconvolution includes a penalty optimization to identify the first plurality of signatures and the second plurality of signatures. ### Claim 6 (depends on 4) The method of claim 4, wherein the penalty optimization includes a sparsity penalty term. ### Claim 7 (depends on 1) The method of claim 1, wherein the clustering of the first plurality of signatures and the second plurality of signatures is made with respect to a plurality of times at which each electrical device in the predetermined number of electrical devices is activated and deactivated. ### Claim 8 (depends on 1) The method of claim 1, wherein the clustering of the first plurality of signatures and the second plurality of signatures is made with respect to a frequency at which each electrical device in the predetermined number of electrical devices is activated and deactivated. ### Claim 9 A system for monitoring electrical power consumption comprising: an electrical power meter configured to measure a time varying electrical power signal that supplies power to a predetermined number of electrical devices; and a processor operatively connected to the electrical power meter and configured to store data generated by the electrical power meter corresponding to the time varying electrical power signal in a memory, the processor being further configured to: generate a transformation of the time varying electrical power signal with reference to the data stored in the memory corresponding to the time varying electrical power signal over a predetermined time period; identify a plurality of electrical events corresponding to activation or deactivation of one of the predetermined number of electrical devices in the transformation of the time varying electrical power signal; deconvolve the identified plurality of electrical events in the transformation of the time varying electrical power signal to generate a first plurality of signatures, each signature in the first plurality of signatures corresponding to activation of one electrical device in the predetermined number of electrical devices, and to generate a second plurality of signatures, each signature in the second plurality of signatures corresponding to deactivation of one electrical device in the predetermined number of electrical devices; cluster the first plurality of signatures and second plurality of signatures to identify activations and deactivations of each electrical device in the predetermined number of electrical devices; and identify one electrical device in the predetermined number of electrical devices corresponding to one signature in the first clustered plurality of signatures and one signature in the second clustered plurality of signatures. ### Claim 10 (depends on 9) The system of claim 9, the processor being further configured to: generate the transformation of the time varying electrical power signal as a first derivative of the data stored in the memory corresponding to the time varying electrical power signal over the predetermined time period. ### Claim 11 (depends on 9) The system of claim 9, the processor being further configured to: identify a signature that is generated with the deconvolution is in the first plurality of signatures in response to the signature having a positive value. ### Claim 12 (depends on 9) The system of claim 9, the processor being further configured to: identify a signature that is generated with the deconvolution is in the second plurality of signatures in response to the signature having a negative value. ### Claim 13 (depends on 9) The system of claim 9, wherein the deconvolution includes a penalty optimization to identify the first plurality of signatures and the second plurality of signatures. ### Claim 14 (depends on 13) The system of claim 13, wherein the penalty optimization includes a sparsity penalty term. ### Claim 15 (depends on 9) The system of claim 9, wherein the processor clusters the first plurality of signatures and the second plurality of signatures with respect to a plurality of times at which each electrical device in the predetermined number of electrical devices is activated and deactivated. ### Claim 16 (depends on 9) The system of claim 9, wherein the processor clusters the first plurality of signatures and the second plurality of signatures with respect to a frequency at which each electrical device in the predetermined number of electrical devices is activated and deactivated. ### Claim 17 (depends on 9) The system of claim 9, wherein the time varying electrical power signal is an alternating current (AC) signal and the electrical power meter is further configured to measure a real component and a reactive component of the time varying electrical power signal. ### Claim 18 (depends on 17) The system of claim 17, wherein the processor is configured to generate the transformation of the data stored in the memory corresponding to the time varying electrical power signal with reference to a root mean square valuation of the real component and the reactive component of the time varying electrical power signal. ### Claim 19 (depends on 17) The system of claim 17, the processor being further configured to: store the one signature in the first clustered plurality of signatures and the one signature in the second clustered plurality of signatures corresponding to the identified electrical device in the memory; and identify at least one additional activation and deactivation of the identified electrical device that occurs after the predetermined time period with reference to the signatures stored in the memory.