FIELD: computer engineering.
SUBSTANCE: invention relates to computer engineering for accounting and analysis of consumed electric power for detection of deliberate losses in electric networks. Technical result is achieved by calculating a statistical processing unit of metrics for each subscriber identifier based on time series of values in a predetermined time interval: metric P1 of average daily consumption, metric P2 of average night consumption, metric P3 of ratio of day and night consumption, metric P4 of range of values of day consumption, metric P5 of seasonal ratio; analysis by a statistical processing unit of said calculated metrics with assignment of a subscriber identifier a status corresponding to a suspicious consumption, when it is detected that the value of said metrics a predetermined number of times fell into the range of values of suspicious consumption during a predetermined time interval; analysis of data received from the statistical processing unit, and/or normalized data received from the data normalization unit, by the machine learning model unit by solving the problem of binary classification of subscribers into two groups: normal consumption and suspicious consumption, with assignment of identifiers of subscribers from the group of suspicious consumption of status corresponding to suspicious consumption.
EFFECT: higher accuracy of electric power theft detection.
15 cl, 2 dwg
Title | Year | Author | Number |
---|---|---|---|
COMPUTER APPARATUS FOR DETECTING AN UNWANTED CALL | 2021 |
|
RU2780046C1 |
SYSTEM AND METHOD FOR SUBSCRIBER DATA PROTECTION IN CASE OF AN UNWANTED CALL | 2021 |
|
RU2774054C1 |
METHOD, COMPLEX FOR PROCESSING INFORMATION ABOUT FAILURES OF DEVICES OF WIRELESS SENSOR NETWORKS FOR DATA TRANSMISSION AND RELATED NETWORKS | 2021 |
|
RU2801825C2 |
SYSTEM AND METHOD OF MACHINE TRAINING MODEL OF DETECTING MALICIOUS FILES | 2017 |
|
RU2673708C1 |
SYSTEM AND METHOD OF CLASSIFICATION OF OBJECTS | 2017 |
|
RU2679785C1 |
METHOD FOR ADJUSTING THE PARAMETERS OF A MACHINE LEARNING MODEL IN ORDER TO IDENTIFY FALSE TRIGGERING AND INFORMATION SECURITY INCIDENTS | 2020 |
|
RU2763115C1 |
METHOD FOR AUTOMATED CONTROL OF LABOUR RESOURCES BASED ON SIMULATION MODELLING | 2017 |
|
RU2697938C1 |
METHOD FOR DETECTING NORMAL REACTIONS OF COMPUTER NETWORK NODES TO NETWORK PACKETS RELATED TO UNKNOWN TRAFFIC | 2022 |
|
RU2802164C1 |
METHOD AND SYSTEM FOR RECOGNISING FACES BASED ON LIST OF PEOPLE NOT SUBJECT TO VERIFICATION | 2008 |
|
RU2381553C1 |
METHOD AND SYSTEM FOR VIDEO SCENES SEGMENTATION | 2022 |
|
RU2783632C1 |
Authors
Dates
2024-10-07—Published
2024-04-26—Filed