Correlating consumption and voltage data to identify line loss in an electric grid

A computing system, comprising:

• a processor connected to memory;
• and
• a module stored on a non-transitory computer readable medium and configured with instructions that when executed by the processor cause the processor to:
• retrieve data from a utility database, wherein the data specifies electric usage information from a set of electric meters that are associated with an electric grid, wherein the data is over a period of time that is divided into a plurality of time intervals;
• determine a maximum voltage among the set of electric meters and, for each time interval, calculate a voltage variance as a difference between the maximum voltage and a voltage measured at a given time interval;
• sort the voltage variances, from each of the plurality of time intervals, from a highest value to a lowest value;
• identify and group a first set of time intervals corresponding to the sorted voltage variances in which the voltage variances satisfy a voltage threshold condition;
• analyze the data of the electric usage information from the plurality of time intervals to determine an electric consumption value for each time interval;
• sort the electric consumption values, from each of the plurality of time intervals, from a highest value to a lowest value;
• identify and group a second set of time intervals corresponding to the sorted electric consumption values in which the electric consumption value satisfies a consumption threshold;
• compare the first set of time intervals to the second set of time intervals to identify whether the set of electric meters are associated with non-technical line loss, wherein the non-technical line loss is detected when the first set of time intervals of the voltage variances do not match at least a threshold percentage of the second set of time intervals of the electric consumption values within a defined margin;
• and
• generate a signal that identifies one or more of the set of electric meters as having a likelihood of the non-technical line loss when the non-technical line loss is detected.

A computer-implemented method, the computer-implemented method involving a computing device comprising a processor, and the computer-implemented method comprising:

• retrieving, by the processor, data from a utility database, wherein the data specifies electric usage information from a set of electric meters that are associated with an electric grid, wherein the data is over a period of time that is divided into a plurality of time intervals;
• determining, by the processor, a maximum voltage among the set of electric meters and, for each time interval, calculate a voltage variance as a difference between the maximum voltage and a voltage measured at a given time interval;
• sorting, by the processor, the voltage variances, from each of the plurality of time intervals, from a highest value to a lowest value;
• identifying and generating, by the processor, a first set of time intervals corresponding to the sorted voltage variances in which the voltage variances satisfy a voltage threshold condition;
• analyzing, by the processor, the data of the electric usage information from the plurality of time intervals to determine an electric consumption value for each time interval;
• sorting, by the processor, the electric consumption values, from each of the plurality of time intervals, from a highest value to a lowest value;
• identifying and grouping, by the processor, a second set of time intervals corresponding to the sorted electric consumption values in which the electric consumption value satisfies a consumption threshold;
• comparing, by the processor, the first set of time intervals to the second set of time intervals to identify whether the set of electric meters are associated with non-technical line loss, wherein the non-technical line loss is detected when the first set of time intervals of the voltage variances do not match at least a threshold percentage of the second set of time intervals of the electric consumption values within a defined margin;
• and
• generate a signal that identifies one or more of the set of electric meters as having a likelihood of the non-technical line loss when the non-technical line loss is detected.