Analytics-Assisted, Multi-agents, Self-Learning, Self-managing, Flexible and Adaptive Framework for Intelligent SON

Patent metadata

Field	Value
Publication number	US-2016205697-A1
Application number	US-201614994942-A
Country	US
Kind code	A1
Filing date	Jan 13, 2016
Priority date	Jan 14, 2015
Publication date	Jul 14, 2016
Grant date	—

Abstract

The strengths of alternative self-organizing-network (SON) techniques can be leveraged by deriving a compromise result from alternative results generated by the respective SON techniques. In particular, the compromise result may be derived from the alternative results based on reputations assigned to alternative SON techniques used to generate the respective results. The compromise result may be calculated based on weighted averages of the alternative results (e.g., solutions, diagnoses, predicted values, etc.), or on weighted averages of parameters specified by the alternative results (e.g., parameter adjustments, underlying causes, KPI values, etc.). In such an embodiment, the weights applied to the alternative results may be based on the reputations of the corresponding SON techniques used to generate the respective alternative results.

First claim

What is claimed is:

1 . A non-transitory computer-readable medium storing programming for execution by a processor, the programming including instructions to:
receive information from devices in a wireless network during a first period; generate alternative optimization solutions for the wireless network using alternative self-optimization techniques based on the information received during the first period, wherein at least some of the alternative optimization solutions specify different values for adjusting one or more wireless configuration parameters of the wireless network; calculate a compromise solution between the alternative optimization solutions based on reputations of the alternative self-optimization techniques used to generate the respective alternative optimization solutions; and send the compromise solution to one or more access points in the wireless network, the compromise solution being used in the wireless network during a second period.

2 . The non-transitory computer-readable medium of claim 1 , wherein at least some of the alternative optimization solutions are generated based on different types of information generated during the first period.

3 . The non-transitory computer-readable medium of claim 1 , wherein the programming further includes instructions to:
assign reputations to the alternative self-optimization techniques based on the efficacy of previous optimization solutions generated by the alternative self-optimization techniques.

4 . The non-transitory computer-readable medium of claim 3 , wherein the instructions to assign the reputations to the alternative self-optimization techniques based on the efficacy of the previous optimization solutions generated by the alternative self-optimization techniques include instructions to:
increment a reputation of a given self-optimization technique when a previous optimization solution generated by the given self-optimization technique, or a parameter adjustment specified by the previous optimization solution, improves a corresponding quality or performance metric when implemented in the wireless network; and decrement the reputation of the given self-optimization technique when the previous optimization solution, or a parameter adjustment specified by the previous optimization solution, negatively impacts the corresponding quality or performance metric when implemented in the wireless network.

5 . The non-transitory computer-readable medium of claim 1 , wherein the instructions to calculate the compromise solution between the alternative optimization solutions based on the reputations of the alternative self-optimization techniques include instructions to:
calculate a weighted average of values for a wireless configuration parameter specified by the alternative optimization solutions based on reputations of the corresponding alternative self-optimization techniques, wherein values in alternative optimization solutions are assigned heavier weights when the alternative optimization solutions are generated by alternative self-optimization techniques having higher reputations than when the alternative optimization solutions are generated by alternative self-optimization techniques having lower reputations; and set the compromise solution to adjust the wireless configuration parameter based on the weighted average of the values specified by the alternative optimization solutions.

6 . The non-transitory computer-readable medium of claim 1 , wherein the instructions to calculate the compromise solution between the alternative optimization solutions based on the reputations of the alternative self-optimization techniques include instructions to:
determine whether a majority, or a super minority, of the alternative optimization solutions increase, decrease, or maintain a value of a wireless configuration parameter; set the compromise solution to increase the wireless configuration parameter when a majority, or a super minority, of the alternative optimization solutions increase the wireless configuration parameter; set the compromise solution to decrease the wireless configuration parameter when a majority, or a super minority, of the alternative optimization solutions decrease the wireless configuration parameter; and set the compromise solution to maintain the value of the wireless configuration parameter when a majority, or a super minority, of the alternative optimization solutions maintain the value of the wireless configuration parameter.

7 . The non-transitory computer-readable medium of claim 1 , wherein the instructions to calculate the compromise solution between the alternative optimization solutions based on the reputations of the alternative self-optimization techniques include instructions to:
assign weighted votes to the alternative optimization solutions based on the reputations of the corresponding alternative self-optimization techniques used to generate the respective alternative optimization solutions, wherein alternative optimization solutions generated by alternative self-optimization techniques having higher reputations are assigned more heavily weighted votes than alternative optimization solutions generated by alternative self-optimization techniques having lower reputations; determine whether a weighted majority, or a weighted super minority, of the alternative optimization solutions increase, decrease, or maintain a value of a given wireless configuration parameter; set the compromise solution to increase the given wireless configuration parameter when a weighted majority, or a weighted super minority, of the alternative optimization solutions increase the given wireless configuration parameter; set the compromise solution to decrease the given wireless configuration parameter when a weighted majority, or a weighted super minority, of the alternative optimization solutions decrease the given wireless configuration parameter; and set the compromise solution to maintain the value of the given wireless configuration parameter when a weighted majority, or a weighted super minority, of the alternative optimization solutions maintain the value of the given wireless configuration parameter.

8 . The non-transitory computer-readable medium of claim 1 , wherein at least some of the alternative self-optimization techniques have different reputations than one another.

9 . An apparatus comprising:
a processor; and a non-transitory computer-readable medium storing programming for execution by a processor, the programming including instructions to:
receive information from devices in a wireless network during a first period;
generate alternative diagnoses using alternative diagnostic techniques based on the information received from the devices, wherein at least some of the alternative diagnoses specify different underlying causes for a quality or performance problem; and
calculate a compromise diagnosis between the alternative diagnostic techniques based on reputations assigned to the alternative self-diagnostic techniques.

10 . The apparatus of claim 9 , wherein the compromise diagnosis is used to reconfigure one or more access points in the wireless network during a second period in order to at least partially alleviate the quality or performance problem.

11 . The apparatus of claim 9 , wherein at least some of the alternative diagnoses are generated based on different types of information generated during the first period.

12 . The apparatus of claim 9 , wherein the programming further includes instructions to:
assign reputations to the alternative self-diagnostic techniques based on the efficacy of previous diagnoses generated by the alternative sel

Assignees

• Futurewei Technologies Inc

Inventors

• Tan Yongxi
• Yang Jin

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• H04W84/18

  Self-organising networks, e.g. ad-hoc networks or sensor networks · CPC title

• H04W72/085 Primary

  Electricity · mapped topic

• H04W24/02 Primary

  Arrangements for optimising operational condition · CPC title

• G06N20/00

  Machine learning · CPC title