Method for spatio-temporal monitoring

Patent metadata

Field	Value
Publication number	US-10958537-B2
Application number	US-201916251942-A
Country	US
Kind code	B2
Filing date	Jan 18, 2019
Priority date	Jan 18, 2019
Publication date	Mar 23, 2021
Grant date	Mar 23, 2021

Abstract

One exemplary aspect describes systems and methods for determining normal SLE behavior, determining when a SLE exhibits abnormal deterioration, and determining whether to take an action to mitigate what appears to be an indication of an abnormal SLE.

First claim

The invention claimed is:

1. A method to determine how a service level experience (SLE) event in a communications environment should be addressed comprising:
determining, during each of a plurality of time periods, values of a plurality of SLE elements;
constructing a time series of multi-dimensional SLE status vectors (SLESV), the constructing based on the values of the plurality of SLE element values determined during each of the plurality of time periods;
constructing a second time series of multi-dimensional augmented service level experience status vectors (ASLESV), each dimension of the ASLESVs indicating, for each of the plurality of time periods, an SLE element value, a minimum value of the SLE element, and a maximum value of the SLE element, the minimum and maximum values based on SLE element values determined during time periods longer than each of the plurality of time periods;
inputting the second time-series (MTS) to a predictive model;
predicting, based on the inputting and the predictive model, an ASLESV, the ASLESV including predicted minimum and maximum values of each of the SLE elements included in the time series;
initiating an action at least based on a determination of whether a measured SLESV parameter falls within a predicted minimum or maximum value of the SLESV parameter value of the predicted ASLESV.

2. The method of claim 1 , wherein the determining of the values of the plurality of SLE elements includes counting a number of one or more of the following within a predetermined time window: number of clients failing to connect to a network, number of clients successfully connecting to the network, number of clients that failed authentication, number of clients that failed to associate, number of clients that failed to get an IP address from a DHCP server, number of clients that failed for unknown reason, number of unique clients, and/or number of unique clients that failed to connect to network.

3. The method of claim 2 , wherein the determining of the values of the plurality of SLE elements includes counting a number of one or more of the following seasonal elements within a predetermined time window: day of a month, day of a year, day of a week and time in a day.

4. The method of claim 2 , wherein determining of the values of the plurality of SLE elements comprises creating a plurality of RSSI (Received Signal Strength Indication) bins, each bin corresponding to a RSSI level being greater than a respective first threshold and smaller than a second respective threshold, and counting a number of occurrences within a predetermined time period that a RSSI value falls within RSSI boundaries of each RSSI bin.

5. The method of claim 1 , wherein the action includes one or more of: restarting a DHCP server, restarting an authentication server, alerting a technician, increasing power of radio, changing a channel, changing a bandwidth, changing a power level, shutting down or blocking a port, switching a broadcast to unicast, renewing a security certificate(s) of user devices, configuring a switch, restarting a switch, testing cable, disconnecting a specific client, rebooting an AP or other device, adding legacy support, alerting an IT technician, re-initiating a radio, stopping or limiting a guest portal access, restarting a DHCP server, and/or restarting a AAA server.

6. The method of claim 1 , further comprising triggering a new predictive model parameters adaptation when it is determined that an error between measured SLESV parameters values and predicted values exceeds a predetermined threshold for a predetermined duration.

7. The method of claim 1 , wherein the inputting of the second time-series (MTS) to the predictive model occurs periodically.

8. The method of claim 1 , further comprising:
determining a value of an SLE element during a first time period;
determining a minimum value of the SLE element for a second time period, the second time period beginning prior to the first time period and ending after the first time period;
including the value and the minimum value in a single dimension of an ASLESV; and
inputting the ASLESV to the predictive model.

9. The method of claim 8 , further comprising:
determining a maximum value of the SLE element during the second time period; and
including the maximum value in the single dimension of the ASLESV.

10. The method of claim 9 , further comprising:
determining values of a plurality of SLE elements during the first time period;
determining a minimum value of each of the plurality of SLE elements during the second time period; and
including the plurality of SLE elements in a corresponding plurality of dimensions of the ASLESV.

11. A system that determines how a service level experience (SLE) event in a communications environment should be addressed comprising:
one or more hardware processors connected to a memory, the memory storing instructions that when executed configure the one or more hardware processors to perform operations comprising:
determining, during each of a plurality of time periods, values of a plurality of SLE elements;
constructing a time series of multi-dimensional SLE status vectors (SLESV, the constructing based on the values of the plurality of SLE element values determined during each of the plurality of time periods;
constructing a second time series of multi-dimensional augmented service level experience status vectors (ASLESV), each dimension of the ASLESVs indicating, for each of the plurality of time periods, an SLE element value, a minimum value of the SLE element, and a maximum value of the SLE element, the minimum and maximum values based on SLE element values determined during time periods longer than each of the plurality of time periods;
inputting the second time-series (MTS) to a predictive model;
predicting, based on the inputting and the predictive model, an ASLESV, the ASLESV including predicted minimum and maximum values of each of the SLE elements included in the time series;
initiating an action at least based on a determination of whether a measured SLESV parameter falls within a predicted minimum or maximum value of the SLESV parameter value of the predicted ASLESV.

12. The system of claim 11 , wherein the determining of the values of the plurality of SLE elements includes counting a number of one or more of the following within a predetermined time window: number of clients failing to connect to a network, number of clients successfully connecting to the network, number of clients that failed authentication, number of clients that failed to associate, number of clients that failed to get an IP address from a DHCP server, number of clients that failed for unknown reason, number of unique clients, and/or number of unique clients that failed to connect to network.

13. The system of claim 12 , wherein the determining of the values of the plurality of SLE elements includes counting a number of one or more of the following seasonal elements within a predetermined time window: day of a month, day of the year, day of a week and time in a day.

14. The system of claim 12 , wherein determining the values of the plurality of SLE elements comprises creating RSSI (Received Signal Strength Indication) bins, each bin corresponding to a RSSI level being greater than first threshold and smaller than a second threshold and counting a number of occurrences within a predetermined time period that a measured RSSI falls within RSSI boundaries of each RSSI bin.

15. The system of claim 11 , wherein the action includes one or more of: restarting a DHCP server, restarting an authentication server, alerting a technic

Assignees

• Mist Systems Inc
• Juniper Networks Inc

Inventors

• Safavi S Ebrahim

Classifications

• H04L41/149

  for prediction of maintenance · CPC title

• H04L41/5009 Primary

  Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] · CPC title

• H04L41/5067 Primary

  Customer-centric QoS measurements · CPC title

• H04L61/5014

  using dynamic host configuration protocol [DHCP] or bootstrap protocol [BOOTP] · CPC title

• H04L61/4511

  using domain name system [DNS] · CPC title