System and Method for Throughput Prediction for Cellular Networks

Abstract

Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

What is claimed is: 
     
         1 . A device comprising:
 a processing system including a processor; and   a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations comprising:   identifying a plurality of performance indicators regarding a cellular network and a communication device communicating with the cellular network;   obtaining data regarding each of the plurality of performance indicators for a past time period, wherein the data regarding each of the plurality of performance indicators forms an array of values for that performance indicator;   generating a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period, the algorithm comprising a machine learning algorithm trained according to the data;   obtaining a predicted throughput for the cellular network based on the algorithm; and   allocating network resources of the cellular network based on the predicted throughput.   
     
     
         2 . The device of  claim 1 , wherein the past time period and the future time period each have a predetermined length. 
     
     
         3 . The device of  claim 1 , wherein the generating further comprises generating a statistical summarization of the array. 
     
     
         4 . The device of  claim 1 , wherein the communication device comprises a mobile communication device. 
     
     
         5 . The device of  claim 4 , wherein the plurality of performance indicators comprises a physical speed of the mobile communication device. 
     
     
         6 . The device of  claim 1 , wherein the machine learning algorithm comprises a regression algorithm. 
     
     
         7 . The device of  claim 1 , wherein the predicted throughput corresponds to a statistical indicator of the throughput over the future time period. 
     
     
         8 . The device of  claim 1 , wherein the operations further comprise selecting the algorithm from a plurality of algorithms based on comparing an actual throughput for the cellular network with the predicted throughput obtained using each of the plurality of algorithms. 
     
     
         9 . The device of  claim 1 , wherein the network comprises a plurality of cells, and wherein the plurality of performance indicators comprises a cell load for each of the plurality of cells. 
     
     
         10 . A method comprising:
 identifying, by a processing system including a processor, a plurality of performance indicators regarding a network and a communication device communicating with the network;   obtaining, by the processing system, data regarding each of the plurality of performance indicators for a past time period, wherein the data regarding each of the plurality of performance indicators forms an array of values for that performance indicator;   generating, by the processing system, a set of inputs to an algorithm for predicting a throughput of the network during a future time period, the algorithm comprising a machine learning algorithm trained according to the data;   obtaining, by the processing system, a predicted throughput for the network based on the algorithm; and   allocating, by the processing system, network resources of the network based on the predicted throughput.   
     
     
         11 . The method of  claim 10 , wherein the past time period and the future time period each have a predetermined length. 
     
     
         12 . The method of  claim 10 , wherein the generating further comprises generating a statistical summarization of the array. 
     
     
         13 . The method of  claim 10 , wherein the communication device comprises a mobile communication device. 
     
     
         14 . The method of  claim 10 , wherein the predicted throughput corresponds to a statistical indicator of the throughput over the future time period. 
     
     
         15 . The method of  claim 10 , further comprising selecting, by the processing system, the algorithm from a plurality of algorithms based on comparing an actual throughput for the network with the predicted throughput obtained using each of the plurality of algorithms. 
     
     
         16 . The method of  claim 10 , wherein the network comprises a cellular network including a plurality of cells, and wherein the plurality of performance indicators comprises a cell load for each of the plurality of cells. 
     
     
         17 . A non-transitory machine-readable medium comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations comprising:
 identifying a plurality of performance indicators regarding a network and a communication device communicating with the network;   obtaining data regarding each of the plurality of performance indicators for a past time period;   generating a set of inputs to an algorithm for predicting a throughput of the network during a future time period, the algorithm comprising a machine learning algorithm trained according to the data;   obtaining a predicted throughput for the network based on the algorithm; and   allocating network resources of the network based on the predicted throughput.   
     
     
         18 . The non-transitory machine-readable medium of  claim 17 , wherein the data regarding each of the plurality of performance indicators forms an array of values for that performance indicator. 
     
     
         19 . The non-transitory machine-readable medium of  claim 18 , wherein the generating further comprises generating a statistical summarization of the array. 
     
     
         20 . The non-transitory machine-readable medium of  claim 17 , wherein the network comprises a cellular network including a plurality of cells, and wherein the plurality of performance indicators comprises a cell load for each of the plurality of cells.