Monitoring dynamic networks

Patent metadata

Field	Value
Publication number	US-9843485-B2
Application number	US-201514954188-A
Country	US
Kind code	B2
Filing date	Nov 30, 2015
Priority date	Nov 30, 2015
Publication date	Dec 12, 2017
Grant date	Dec 12, 2017

Abstract

Monitoring a network is provided. A set of predicted network topology snapshot graphs of nodes in the network are generated based on a set of network topology prediction models for the network. A subset of the nodes is selected as monitors in the set of predicted network topology snapshot graphs of the network so that each link in a set of selected network links is identifiable using end-to-end measurements between the monitors. Network states of interest are determined in the set of selected network links within a selected time window based on the end-to-end measurements between the monitors.

First claim

What is claimed is:

1. A computer-implemented method for monitoring a dynamic cloud network, the computer-implemented method comprising:
generating, by a computer, a set of predicted network topology snapshot graphs that estimate locations of a set of mobile nodes in the dynamic cloud network based on a set of network topology prediction models predicting a topology of the set of mobile nodes comprising the dynamic cloud network;
selecting, by the computer, a subset of mobile nodes from the set of mobile nodes comprising the dynamic cloud network as monitors in the set of predicted network topology snapshot graphs of the dynamic cloud network so that each link in a set of selected network links is identifiable using end-to-end measurements between the monitors;
monitoring, by the computer, the set of selected network links in the dynamic cloud network using the end-to-end measurements between the monitors;
determining, by the computer, network states of interest in the set of selected network links within a selected time window based on the monitoring of the end-to-end measurements between the monitors; and
reconfiguring, by the computer, the dynamic cloud network based on the network states of interest in the set of selected network links being greater than or equal to predefined network state threshold values during a time period corresponding to the selected time window.

2. The computer-implemented method of claim 1 further comprising:
identifying, by the computer, delay, jitter, and loss rates as the network states of interest in the set of selected network links to be monitored between the set of mobile nodes in the dynamic cloud network.

3. The computer-implemented method of claim 1 , wherein the computer selects a size of the selected time window based on network operation cost to deploy the monitors in the dynamic cloud network, network reconfiguration cost to reconfigure the dynamic cloud network, and network topology prediction accuracy in predicting the topology of the dynamic cloud network.

4. The computer-implemented method of claim 1 , wherein the computer selects the set of network topology prediction models for the dynamic cloud network based on knowledge of network dynamics in a dynamic wireless network comprising a plurality of mobile data processing nodes.

5. The computer-implemented method of claim 1 further comprising:
detecting, by the computer, changes over time in the topology of the dynamic cloud network as a plurality of mobile data processing nodes comprising the dynamic cloud network move within the dynamic cloud network.

6. The computer-implemented method of claim 5 , wherein the plurality of mobile data processing nodes comprise a cloud edge around a cloud core of the dynamic cloud network, and wherein a subset of the plurality of mobile data processing nodes comprising the cloud edge form an ad hoc cloud by wirelessly connecting to one another to perform a set of one or more data processing tasks.

7. The computer-implemented method of claim 5 , wherein the plurality of mobile data processing nodes are at least one of smart phones, smart watches, handheld computers, laptop computers, personal digital assistants, and gaming devices.

8. The computer-implemented method of claim 1 further comprising:
identifying, by the computer, sub-graphs of nodes in the set of predicted network topology snapshot graphs to monitor.

9. The computer-implemented method of claim 1 , wherein the computer selects the monitors in the set of predicted network topology snapshot graphs based on number of monitors, speed of computation, overhead incurred by monitoring, and stability of the monitors during future network topology changes.

10. The computer-implemented method of claim 1 , wherein the set of network topology prediction models are based on trajectory constraints of the set of mobile nodes comprising the dynamic cloud network.

11. The computer-implemented method of claim 1 , wherein the end-to-end measurements between the monitors are end-to-end network path performance that is an accumulation of corresponding link metrics between a set of monitors.

12. The computer-implemented method of claim 1 , wherein the computer turns ON a monitor selection component to select the subset of mobile nodes as the monitors at an end of a period of time corresponding to a previous selected time window or at a beginning of a period of time corresponding to the selected time window and the computer turns OFF the monitor selection component during the selected time window until an end of the period of time corresponding to the selected time window when the computer again turns on the monitor selection component to select a new set of monitors for a next selected time window.

13. A computer system for monitoring a dynamic cloud network, the computer system comprising:
a bus system;
a storage device connected to the bus system, wherein the storage device stores program instructions; and
a processor connected to the bus system, wherein the processor executes the program instructions to:
generate a set of predicted network topology snapshot graphs that estimate locations of a set of mobile nodes in the dynamic cloud network based on a set of network topology prediction models predicting a topology of the set of mobile nodes comprising the dynamic cloud network;
select a subset of mobile nodes from the set of mobile nodes comprising the dynamic cloud network as monitors in the set of predicted network topology snapshot graphs of the dynamic cloud network so that each link in a set of selected network links is identifiable using end-to-end measurements between the monitors;
monitor the set of selected network links in the dynamic cloud network using the end-to-end measurements between the monitors;
determine network states of interest in the set of selected network links within a selected time window based on monitoring the end-to-end measurements between the monitors; and
reconfigure the dynamic cloud network based on the network states of interest in the set of selected network links being greater than or equal to predefined network state threshold values during a time period corresponding to the selected time window.

14. The computer system of claim 13 , wherein the processor further executes the program instructions to:
identify delay, jitter, and loss rates as the network states of interest in the set of selected network links to be monitored between the set of mobile nodes in the dynamic cloud network.

15. A computer program product for monitoring a dynamic cloud network, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
generating, by the computer, a set of predicted network topology snapshot graphs that estimate locations of a set of mobile nodes in the dynamic cloud network based on a set of network topology prediction models predicting a topology of the set of mobile nodes comprising the dynamic cloud network;
selecting, by the computer, a subset of mobile nodes from the set of mobile nodes comprising the dynamic cloud network as monitors in the set of predicted network topology snapshot graphs of the dynamic cloud network so that each link in a set of selected network links is identifiable using end-to-end measurements between the monitors;
monitoring, by the computer, the set of selected network links in the dynamic cloud network using the end-to-end measurements between the monitors;
determining, by the computer, network stat

Assignees

• IBM
• Int Business Machines Coprporation

Inventors

• Desai Nirmit V
• He Ting
• Ma Liang

Classifications

• H04L43/08

  Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters · CPC title

• H04L41/12

  Discovery or management of network topologies · CPC title

• H04L41/147 Primary

  for predicting network behaviour · CPC title

• H04L43/045

  for graphical visualisation of monitoring data · CPC title

• H04L41/145

  involving simulating, designing, planning or modelling of a network · CPC title