Communication Network Optimization Based on Predicted Enhancement Gain

Abstract

In one embodiment, a computing system may access data samples associated with a geographic area of interest covered by a communication network. The data samples may be aggregated into a plurality of data points. The computing system may partition the plurality of data points into a first set of data points and a second set of data points using a first threshold of a first network metric. The computing system may determine a predicted gain of the second network metric for a network enhancement operation. The predicted gain of the second network metric may be determined based on a comparison between a first weighted average of the first set of data points and a second weighted average of the first set of data points and the second set of data points. The computing system may generate one or more network optimization recommendations for the geographic area of interest based at least in part on the predicted gain of the second network metric caused by the network enhancement operation.

What is claimed is: 
     
         1 . A method comprising, by one or more computing systems:
 accessing data samples associated with a geographic area of interest covered by a communication network, wherein the data samples are aggregated into a plurality of data points;   partitioning the plurality of data points into a first set of data points and a second set of data points using a first threshold of a first network metric;   determining a predicted gain of a second network metric for a network enhancement operation, wherein the predicted gain of the second network metric is determined based on a comparison between a first weighted average of the first set of data points and a second weighted average of the first set of data points and the second set of data points; and   generating one or more network optimization recommendations for the geographic area of interest based at least in part on the predicted gain of the second network metric caused by the network enhancement operation.   
     
     
         2 . The method of  claim 1 , further comprising:
 calculating a priority score for each of the network optimization recommendations;   ranking each of the network optimization recommendations based on their respective priority score; and   sending, to a client system, instructions for presenting the network optimization recommendations based on a predicted network traffic, wherein the network optimization recommendation presented corresponds to the network optimization recommendation having the highest rank.   
     
     
         3 . The method of  claim 2 , wherein the instructions for presenting the network optimization recommendation are displayed on a graphical user interface of the client system. 
     
     
         4 . The method of  claim 1 , wherein the network optimization recommendation comprises adding a new cell in the geographic area of interest. 
     
     
         5 . The method of  claim 4 , wherein the network optimization recommendation further comprises configuring network traffic in the geographic area of interest to be split between an existing cell of the geographic area of interest and the new cell based on the network optimization recommendation. 
     
     
         6 . The method of  claim 1 , wherein the data samples are collected at an application level or an infrastructure level. 
     
     
         7 . The method of  claim 1 , wherein a network traffic trend associated with the geographic area of interest based on the data samples is determined based on a regression on the plurality of data points. 
     
     
         8 . The method of  claim 7 , wherein the network traffic trend is based on a download speed. 
     
     
         9 . The method of  claim 1 , wherein the plurality of data points is aggregated per hour per N days, and wherein N is any positive integer number. 
     
     
         10 . The method of  claim 9 , wherein the plurality of data points is aggregated per hour per week. 
     
     
         11 . The method of  claim 1 , further comprising:
 optimizing, responsive to an input received at a client system, the communication network in the geographic area of interest based on the one or more network optimization recommendations.   
     
     
         12 . The method of  claim 11 , wherein the communication network is optimized at an application level or an infrastructure level. 
     
     
         13 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 access data samples associated with a geographic area of interest covered by a communication network, wherein the data samples are aggregated into a plurality of data points;   partition the plurality of data points into a first set of data points and a second set of data points using a first threshold of a first network metric;   determine a predicted gain of a second network metric for a network enhancement operation, wherein the predicted gain of the second network metric is determined based on a comparison between a first weighted average of the first set of data points and a second weighted average of the first set of data points and the second set of data points; and   generate one or more network optimization recommendations for the geographic area of interest based at least in part on the predicted gain of the second network metric caused by the network enhancement operation.   
     
     
         14 . The media of  claim 13 , wherein the software is further operable when executed to:
 calculating a priority score for each of the network optimization recommendations;   ranking each of the network optimization recommendations based on their respective priority score; and   sending, to a client system, instructions for presenting the network optimization recommendations based on a predicted network traffic, wherein the network optimization recommendation presented corresponds to the network optimization recommendation having the highest rank.   
     
     
         15 . The media of  claim 14 , wherein the instructions for presenting the network optimization recommendation are displayed on a graphical user interface of the client system. 
     
     
         16 . The media of  claim 13 , wherein the network optimization recommendation comprises adding a new cell in the geographic area of interest. 
     
     
         17 . The media of  claim 16 , wherein the network optimization recommendation further comprises configuring network traffic in the geographic area of interest to be split between an existing cell of the geographic area of interest and the new cell based on the network optimization recommendation. 
     
     
         18 . The media of  claim 13 , wherein the data samples are collected at an application level or an infrastructure level. 
     
     
         19 . The media of  claim 13 , wherein a network traffic trend associated with the geographic area of interest based on the data samples is determined based on a regression on the plurality of data points. 
     
     
         20 . A system comprising: one or more non-transitory computer-readable storage media embodying instructions; and one or more processors coupled to the storage media and operable to execute the instructions to:
 access data samples associated with a geographic area of interest covered by a communication network, wherein the data samples are aggregated into a plurality of data points;   partition the plurality of data points into a first set of data points and a second set of data points using a first threshold of a first network metric;   determine a predicted gain of a second network metric for a network enhancement operation, wherein the predicted gain of the second network metric is determined based on a comparison between a first weighted average of the first set of data points and a second weighted average of the first set of data points and the second set of data points; and   generate one or more network optimization recommendations for the geographic area of interest based at least in part on the predicted gain of the second network metric caused by the network enhancement operation.