METHOD OF OPERATING A SENSOR NETWORK AND SYSTEM THEREFOR

• US 20180123902A1
• Filed: 10/31/2016
• Published: 05/03/2018
• Est. Priority Date: 10/31/2016
• Status: Abandoned Application

• Current Assignee: AGT International GMBH
• Original Assignee: AGT International GMBH
• Inventors: GOERTZ, Manuel, WIESMAIER, Alexander, GAZIS, Evangelos
• Application Number:
  US15/339,237
• Publication Number:
  US 20180123902A1
• Time in Patent Office: Days
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

A method of operating a sensor network including a plurality of sensors and one or more control stations. The method includes generating by a processor-based device operatively connected to the at least one sensor from among the plurality of sensors, one or more concurrent predicted requests. Each predicted request specifies parameters related to output data predicted to be requested by the one or more control stations and related to the captured data, selecting a utility from among multiple predefined utilities stored in a memory of the device, the utility being selected based, at least, on the one or more parameters specified in the generated predicted request, and using the selected utility to process data captured by the at least one sensor, thereby giving rise to predicted output data usable by an incoming request from the one or more control stations when the incoming request corresponds to the predicted request.

Claims

1. A method of operating a sensor network comprising a plurality of sensor nodes and at least one control station, each sensor node comprising a memory operatively connected to a processor and to at least one sensor, the method comprising:

generating, by a sensor node from among the plurality of sensor nodes, a predicted request specifying at least one parameter corresponding to predicted output data;

using by the sensor node the generated predicted request to select at least one utility from among a plurality of predefined utilities, wherein the selected utility is configured to execute at least one of predefined functions selected from the group consisting of functions related to obtaining by the sensor node sensor data usable to generate predicted output data, functions related to processing by the sensor node sensor data to generate predicted output data, and functions related to buffering at the sensor node generated predicted output data; and

using by the sensor node the selected at least one utility to generate predicted output data, thereby giving rise to predicted output data usable by an incoming request from the at least one control station when the incoming request corresponds to the predicted request.

2. The method of claim 1, wherein the at least one parameter of the predicted request is selected from the group consisting of:

data indicative of a priority ranking of the predicted request;

data indicative of predicted output data; and

data indicative of the destination of the output data generated in accordance with the predicted request.

3. The method of claim 1, wherein the predicted request is generated using data selected from a group consisting of data informative of:

historical data corresponding to a previously served incoming request;

statistics of historical data corresponding to a previously served incoming request;

historical data corresponding to a previously generated predicted request;

statistics of historical data corresponding to a previously generated predicted request;

historical data corresponding to matching between a previously generated predicted request and a respective served incoming request;

statistics of historical data corresponding to matching between a previously generated predicted request and a respective served incoming request;

a concurrent incoming request;

context information; and

at least one external parameter.

4. The method of claim 1, wherein generating the predicted request is provided using a request model, the request model built using at least one historic incoming request, and at least one of:

context information;

at least one external parameter;

state of a buffer;

content of a buffer; and

feedback information.

5. The method of claim 4, wherein the request model is updated, by the sensor node, responsive to at least one of:

serving at least one new incoming request;

obtaining updated context information;

generating at least one predicted request;

serving at least one predicted request;

obtaining sensor data; and

obtaining feedback information.

6. The method of claim 1, further comprising outputting, by the sensor node, predicted output data responsive to an incoming request corresponding to the predicted request.

7. The method of claim 1, further comprising post-processing, by the sensor node, the predicted output data according to at least one parameter of the incoming request, when the predicted request only partly corresponds to the incoming request.

8. The method of claim 7, wherein post-processing further comprises selecting a utility from among multiple predefined utilities based on the at least one parameter of the incoming request;

and using the selected utility to post-process the predicted output data, thereby giving rise to output data specified by the incoming request.

9. A sensor node in a sensor network comprising a plurality of sensor nodes and at least one control station, the sensor node comprising:

a memory operatively connected to a processor and to at least one sensor, wherein the processor is configured to;

generate a predicted request specifying at least one parameter corresponding to predicted output data;

use the generated predicted request to select at least one utility from among a plurality of predefined utilities, wherein the selected utility is configured to execute at least one of predefined functions selected from the group consisting of functions related to obtaining by the sensor node sensor data usable to generate predicted output data, functions related to processing by the sensor node sensor data to generate predicted output data, and functions related to buffering at the sensor node generated predicted output data; and

use the selected at least one utility to generate predicted output data, thereby giving rise to predicted output data usable by an incoming request from the at least one control station when the incoming request corresponds to the predicted request.

10. The sensor node of claim 9, wherein the at least one parameter of the predicted request is selected from the group consisting of:

data indicative of a priority ranking of the predicted request;

data indicative of predicted output data to be desired; and

data indicative of the destination of the output data generated in accordance with the predicted request.

11. The sensor node of claim 9, wherein the predicted request is generated using data selected from a group consisting of data informative of:

historical data corresponding to a previously served incoming request;

statistics of historical data corresponding to a previously served incoming request;

historical data corresponding to a previously generated predicted request;

statistics of historical data corresponding to a previously generated predicted request;

historical data corresponding to matching between a previously generated predicted request and a respective served incoming request;

statistics of historical data corresponding to matching between a previously generated predicted request and a respective served incoming request;

a concurrent incoming request;

context information; and

at least one external parameter.

12. The sensor node of claim 9, further comprising a request model built using at least one historic incoming request, and at least one of:

context information;

at least one external parameter;

state of a buffer; and

content of a buffer.

13. The sensor node of claim 12, wherein the request model is updated responsive to at least one of:

serving at least one new incoming request;

obtaining updated context information;

generating at least one predicted request;

serving at least one predicted request; and

obtaining sensor data.

14. The sensor node of claim 9, wherein the processor is further configured to output predicted output data responsive to an incoming request corresponding to the predicted request.

15. The sensor node of claim 9, wherein the processor is further configured to post-process the predicted output data according to at least one parameter of the incoming request, when the predicted request only partly corresponds to the incoming request.

16. The sensor node of claim 15, wherein the processor is further configured to select a utility from among multiple predefined utilities based on the at least one parameter of the incoming request;

and use the selected utility to post-process the predicted output data, thereby giving rise to output data specified by the incoming request.

17. A non-transitory program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform a method of operating a sensor node in a sensor network comprising a plurality of sensor nodes and at least one control station, each sensor node comprising a memory operatively connected to a processor and to at least one sensor, the method comprising:

generating, by a sensor node from among the plurality of sensor nodes, a predicted request specifying at least one parameter corresponding to predicted output data;

using by the sensor node the generated predicted request to select at least one utility from among a plurality of predefined utilities, wherein the selected utility is configured to execute at least one of predefined functions selected from the group consisting of functions related to obtaining by the sensor node sensor data usable to generate predicted output data, functions related to processing by the sensor node sensor data to generate predicted output data, and functions related to buffering at the sensor node generated predicted output data; and

using by the sensor node the selected at least one utility to generate predicted output data, thereby giving rise to predicted output data usable by an incoming request from the at least one control station when the incoming request corresponds to the predicted request.

18. The non-transitory program storage device of claim 17, wherein the at least one parameter of the predicted request is selected from the group consisting of:

data indicative of a priority ranking of the predicted request;

data indicative of predicted output data; and

data indicative of the destination of the output data generated in accordance with the predicted request.

19. The non-transitory program storage device of claim 17, wherein the predicted request is generated using data selected from a group consisting of data informative of:

historical data corresponding to a previously served incoming request;

statistics of historical data corresponding to a previously served incoming request;

historical data corresponding to a previously generated predicted request;

statistics of historical data corresponding to a previously generated predicted request;

historical data corresponding to matching between a previously generated predicted request and a respective served incoming request;

statistics of historical data corresponding to matching between a previously generated predicted request and a respective served incoming request;

a concurrent incoming request;

context information; and

at least one external parameter.

20. The non-transitory program storage device of claim 17, wherein generating the predicted request is provided using a request model, the request model built using at least one historic incoming request, and at least one of:

context information;

at least one external parameter;

state of a buffer; and

content of a buffer.