USING LEARNING MACHINE-BASED PREDICTION IN MULTI-HOPPING NETWORKS

• US 20150195216A1
• Filed: 01/27/2014
• Published: 07/09/2015
• Est. Priority Date: 01/06/2014
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Di Pietro, Andrea, Vasseur, Jean-Philippe, Cruz Mota, Javier
• Granted Patent: US 9,369,351 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/5025 by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/70 Routing based on monitoring results
• CPC Class Codes: H04L 47/122 by diverting traffic away from congested entities
• CPC Class Codes: H04L 47/365 Dynamic adaptation of the packet size
• CPC Class Codes: H04W 24/02 Arrangements for optimising operational condition
• CPC Class Codes: H04W 24/04 Arrangements for maintaining operational condition
• CPC Class Codes: Y04S 40/00 Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them

Abstract

In one embodiment, statistical information is collected relating to one or both of communication link quality or channel quality in a frequency-hopping network, in which packets are sent according to a frequency-hopping schedule that defines one or more timeslots, each timeslot corresponding to a transmission frequency. Also, a performance metric of a particular transmission frequency corresponding to a scheduled timeslot is predicted based on the collected statistical information. Based on the predicted performance metric, it is determined whether a transmitting node in the frequency-hopping network should transmit a packet during the scheduled timeslot using the particular transmission channel or wait until a subsequent timeslot to transmit the packet using another transmission frequency.

Claims

1. A method, comprising:

collecting statistical information relating to one or both of communication link quality or channel quality in a frequency-hopping network, in which packets are sent according to a frequency-hopping schedule that defines one or more timeslots, each timeslot corresponding to a transmission frequency;

predicting a performance metric of a particular transmission frequency corresponding to a scheduled timeslot based on the collected statistical information; and

determining, based on the predicted performance metric, whether a transmitting node in the frequency-hopping network should transmit a packet during the scheduled timeslot using the particular transmission channel or wait until a subsequent timeslot to transmit the packet using another transmission frequency.

2. The method as in claim 1, wherein the predicted performance metric relates to a communication link used by the transmitting node.

3. The method as in claim 1, further comprising:

calculating a prediction model using the collected statistical information based on a relationship between a quality of a communication link in the frequency-hopping network and a transmission success rate of the communication link, wherein

the determining of whether the transmitting node should transmit the packet during the scheduled timeslot using the particular transmission channel is based on the prediction model.

4. The method as in claim 3, further comprising:

tracking an accuracy of the prediction model; and

recomputing the prediction model when the accuracy of the prediction model is suboptimal.

5. The method as in claim 1, wherein the predicted performance metric is a transmission success rate of a particular communication link using the particular transmission frequency.

6. The method as in claim 1, further comprising:

determining a type of traffic that traverses the transmitting node and a requirement associated with the type of traffic, wherein

the determining of whether the transmitting node should transmit the packet during the scheduled timeslot using the particular transmission channel is further based on the determined requirement.

7. The method as in claim 1, further comprising:

when it is determined to wait until a subsequent timeslot to transmit the packet, determining a better timeslot at which to transmit the packet, according to the frequency-hopping schedule.

8. The method as in claim 1, wherein the collecting of statistical information further comprises:

sending an instruction to nodes in the network to report statistical information local to each respective node.

9. The method as in claim 1, further comprising:

predicting a performance metric of each transmission frequency corresponding to each scheduled timeslot, respectively, based on the collected statistical information.

10. The method as in claim 1, wherein the collected statistical information includes one or more of a signal strength indicator and a communication link quality indicator.

11. The method as in claim 1, wherein the predicting of the performance metric is performed by a learning machine (LM).

12. An apparatus, comprising:

one or more network interfaces that communicate with a frequency-hopping network;

a processor coupled to the one or more network interfaces and configured to execute a process; and

a memory configured to store program instructions which contain the process executable by the processor, the process comprising;

collecting statistical information relating to one or both of communication link quality or channel quality in the frequency-hopping network, in which packets are sent according to a frequency-hopping schedule that defines one or more timeslots, each timeslot corresponding to a transmission frequency;

predicting a performance metric of a particular transmission frequency corresponding to a scheduled timeslot based on the collected statistical information; and

determining, based on the predicted performance metric, whether a transmitting node in the frequency-hopping network should transmit a packet during the scheduled timeslot using the particular transmission channel or wait until a subsequent timeslot to transmit the packet using another transmission frequency.

13. The apparatus as in claim 12, wherein the predicted performance metric relates to a communication link used by the transmitting node.

14. The apparatus as in claim 12, wherein the process further comprises:

calculating a prediction model using the collected statistical information based on a relationship between a quality of a communication link in the frequency-hopping network and a transmission success rate of the communication link, wherein

the determining of whether the transmitting node should transmit the packet during the scheduled timeslot using the particular transmission channel is based on the prediction model.

15. The apparatus as in claim 14, wherein the process further comprises:

tracking an accuracy of the prediction model; and

recomputing the prediction model when the accuracy of the prediction model is suboptimal.

16. The apparatus as in claim 12, wherein the predicted performance metric is a transmission success rate of a particular communication link using the particular transmission frequency.

17. The apparatus as in claim 12, wherein the process further comprises:

determining a type of traffic that traverses the transmitting node and a requirement associated with the type of traffic, wherein

the determining of whether the transmitting node should transmit the packet during the scheduled timeslot using the particular transmission channel is further based on the determined requirement.

18. The apparatus as in claim 12, wherein the process further comprises:

when it is determined to wait until a subsequent timeslot to transmit the packet, determining a better timeslot at which to transmit the packet, according to the frequency-hopping schedule.

19. The apparatus as in claim 12, wherein the collecting of statistical information further comprises:

sending an instruction to nodes in the network to report statistical information local to each respective node.

20. The apparatus as in claim 12, wherein the process further comprises:

predicting a performance metric of each transmission frequency corresponding to each scheduled timeslot, respectively, based on the collected statistical information.

21. The apparatus as in claim 12, wherein the collected statistical information includes one or more of a signal strength indicator and a communication link quality indicator.

22. The apparatus as in claim 12, wherein the apparatus is a learning machine (LM).

23. A tangible non-transitory computer readable medium storing program instructions that cause a computer to execute a process, the process comprising:

collecting statistical information relating to one or both of communication link quality or channel quality in a frequency-hopping network, in which packets are sent according to a frequency-hopping schedule that defines one or more timeslots, each timeslot corresponding to a transmission frequency;

predicting a performance metric of a particular transmission frequency corresponding to a scheduled timeslot based on the collected statistical information; and

determining, based on the predicted performance metric, whether a transmitting node in the frequency-hopping network should transmit a packet during the scheduled timeslot using the particular transmission channel or wait until a subsequent timeslot to transmit the packet using another transmission frequency.