Data reduction in a multi-node system

• US 8,781,768 B2
• Filed: 07/15/2010
• Issued: 07/15/2014
• Est. Priority Date: 01/25/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gershinsky, Gidon, Lewin-Eytan, Liane, Richter, Yossi, Shagin, Konstantin, Yom-Tov, Elad
• Primary Examiner(s): Kundu, Sujoy
• Assistant Examiner(s): Ngon, Ricky
• Application Number:
  US12/836,605
• Publication Number:
  US 20110184676A1
• Time in Patent Office: 1,461 Days
• Field of Search: 702/62, 702/104, 702/182, 702/183, 702/185, 702/188, 340/870.02, 340/870.16, 340/870.05, 340/870.1
• US Class Current: 702/62
• CPC Class Codes: H04Q 2209/30 using a wired architecture
• CPC Class Codes: H04Q 2209/40 using a wireless architecture
• CPC Class Codes: H04Q 2209/60 for transmitting utility meters data, i.e. transmission of data from the reader of the utility meter
• CPC Class Codes: H04Q 2209/84 Measuring functions
• CPC Class Codes: H04Q 9/00 Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom

Abstract

An advanced metering infrastructure comprises intermediate nodes. The intermediate nodes receive data from child nodes and aggregate the data according to groups of child nodes. The aggregation provides for a reduced version of the data. The reduction is performed based on groups determined by clustering. The reduced version of the data comprises data describing a group of measurements over time, such as a centroid in an n-dimension space, number of customers in the group, radius of the group and the like. The centroid may shift over time based on a consumption profile, such as low consumption at noon, and high consumption at evening. The consumption profiles may be determined in a learning phase, as well as shifting of centroids of each group over time.

Claims

1. A computerized system comprising:

at least one intermediate node;

wherein said at least one intermediate node is connected to a plurality of sensors operable to monitor usage of a resource;

wherein said at least one intermediate node is connected to an operator node;

wherein said at least one intermediate node comprises;

a receiver configured to receive data from the plurality of sensors,

wherein the data is indicative of usage of the resource during a timeframe,

wherein the data received from the plurality of sensors comprises a list of a predetermined number of values of monitored resource consumption values,

wherein the list corresponds to a point in a space having n-dimensions;

wherein n is the predetermined number of values;

wherein the clustering module is configured to determine a cluster of the set of clusters based on distances between points in a space, and

wherein the points correspond to the data;

a clustering module configured to determine a set of clusters based upon the data;

wherein each cluster of the set of clusters groups one or more sensors of the plurality of sensors;

a data reduction module configured to determine a reduced data associated with a cluster of the set of clusters;

the reduced data comprises;

a consumption profile indicative of usage of the resource during the timeframe; and

identifications of sensors grouped by the cluster; and

a transmitter configured to send the reduced data.

2. The computerized system of claim 1, wherein the consumption profile is associated with about a centroid of a portion of the space;

and wherein the portion of the space comprises points associated with the sensors grouped by the cluster.

3. The computerized system of claim 2, wherein the reduced data further comprises a radius of the portion of the space;

wherein the radius is substantially a maximal distance between the centroid and the points associated with the sensors grouped by the cluster.

4. The computerized system of claim 1, wherein said at least one intermediate node further comprises:

a forecasting module configured to determine an expected data associated with the consumption profile based on a previous data associated with the consumption profile; and

wherein said transmitter is configured to transmit a portion of the reduced data based on data of sensors that is substantially different than the expected data.

5. The computerized system of claim 4, wherein said at least one intermediate node further comprises a comparison module that is configured to determine whether a data of a sensor is substantially different than the expected data based on a distance between the data and the expected data in respect to a space having n-dimensions;

wherein n is the predetermined number of values; and

wherein said transmitter is configured to utilize the comparison module.

6. The computerized system of claim 4, wherein said at least one intermediate node further comprises:

a fault detection module configured to provide an indication to the operator node of a non-standard behavior based on a correlation between the expected data and the data.

7. The computerized system of claim 1, wherein the data received from the plurality of sensors comprises a set of lists of monitored resource consumption values;

wherein each of the set of lists having a predetermined number of values; and

wherein each of the set of lists is associated with a different consumption unit.

8. The computerized system of claim 1, wherein the plurality of sensors are selected from the group consisting of electricity meters, gas meters, heat meters, watering meters and traffic meters.

9. The computerized system of claim 1,

wherein said at least one intermediate node comprises at least two intermediate nodes;

wherein said at least two intermediate nodes are arranged in a hierarchy;

wherein an intermediate node of said at least two intermediate nodes is indirectly connected to the plurality of sensors via one or more intermediate nodes of said at least two intermediate nodes;

wherein said one or more intermediate nodes are indirectly connected to the operator via said intermediate node;

wherein said intermediate node is configured to receive a plurality of profile data from the one or more intermediate nodes;

wherein said intermediate node is further configured to determine clustering based on the plurality of profile data; and

wherein said intermediate node is further configured to send the reduced data of the plurality of profile data to the operator.

10. The computerized system of claim 1, wherein the computerized system is configured to operate over a plurality of timeframes;

and wherein at least a first timeframe of the plurality of timeframes overlaps a second timeframe of the plurality of timeframes.

11. A computerized method for transmitting data in a metering infrastructure from a plurality of sensors to an operator node through at least one intermediate node, wherein the plurality of sensor are operable to monitor usage of a resource in a plurality of geographical regions;

the method comprises at the at least one intermediate node;

receiving data from the plurality of sensors,

wherein the data is indicative of usage of the resource during a timeframe,

wherein the data received from the plurality of sensors comprises a list of predetermined number of values of monitored resource consumption values, and

wherein the list corresponds to a point in a space having n-dimensions;

wherein n is the predetermined number of values;

determining a set of clusters based upon the data;

wherein each cluster of the set of clusters groups one or more sensors of the plurality of sensors, wherein a cluster of the set of clusters is determined based on distances between points in a space, wherein the points correspond to the data;

determining, by a processor of the at least one intermediate node, a reduced data associated with a cluster of the set of clusters;

the reduced data comprises;

a consumption profile indicative of usage of the resource during the timeframe; and

identifications of sensors grouped by the cluster; and

transmitting the reduced data towards the operator node.

12. The method of claim 11, wherein said receiving data, said determining a set of clusters, said determining a reduced data and transmitting the reduced data are performed a plurality of times in respect to a plurality of timeframes.

13. The method of claim 12, wherein at least a portion of the plurality of timeframes overlap each other.

14. The method of claim 11, wherein the consumption profile is a point in a space;

wherein the space having a n-dimensions;

wherein the point is associated with a centroid associated with a portion of the space comprising the points in the space that correspond to the data received from the sensors grouped by the cluster.

15. The method of claim 14, wherein the reduced data further comprises a radius of the portion of the space;

wherein the radius is substantially a maximal distance between the centroid and the points associated with the sensors grouped by the cluster.

16. The method of claim 11, wherein the at least one intermediate node comprises at least two intermediate nodes arranged in a hierarchy;

the method further comprises;

a first set of intermediate nodes of a first hierarchy transmitting the reduced data to a second intermediate node of a second hierarchy;

the second intermediate node receiving the reduced data;

the second intermediate node determining clusters of consumption profiles;

the second intermediate node determining a second reduced data; and

the second intermediate node transmitting the second reduced data towards the operator node.

17. The method of claim 11 further comprises:

the at least one intermediate node determining an expected data based on a previous data associated with the consumption profile;

the at least one intermediate node determining whether the data is substantially different than the expected data; and

wherein said determining the reduced data comprises determination of the reduced data in respect to the data that is substantially different than the expected data.

18. The method of claim 17 further comprises:

providing an indication to the operator node of a non-standard behavior based on a correlation between the expected data and the data.

19. A computer program product for an intermediate node transmitting data received from a plurality of sensors towards an operator node, the computer program product comprising:

a non-transitory computer readable medium comprising computer instructions stored therein for causing a computer processor to perform steps of;

receiving data from the plurality of sensors,

wherein the data is indicative of usage of a resource during a timeframe;

wherein the data received from the plurality of sensors comprises a list of a predetermined number of values of monitored resource consumption values and,

wherein the list corresponds to a point in a space having n-dimensions;

wherein n is the predetermined number of values;

determining a set of clusters based upon the data;

wherein each cluster of the set of clusters groups one or more sensors of the plurality of sensors, wherein a cluster of the set of clusters is determined based on distance between points in a space, wherein the points correspond to the data;

determining a reduced data associated with a cluster of the set of clusters;

the reduced data comprises;

a consumption profile indicative of usage of the resource during the timeframe; and

identifications of sensors grouped by the cluster; and

transmitting the reduced data towards the operator node.