Incorporation of expert knowledge into machine learning based wireless optimization framework

A non-transitory computer readable medium storing a set of computer instructions which, when executed by one or more computer processors, causes the one or more computer processors to perform:

• constraining, based on expert input comprising recommended parameter values provided by one or more human experts, a machine learning framework using a specific learning iteration to perform machine learning to estimate a set of optimal parameter values for a set of Transmission Control Protocol (TCP) parameters in one or more specific regions of an output parameter space, wherein the output parameter space represents a space of all possible parameter values for the set of TCP parameters;
• collecting, over a time block, network traffic data associated with a plurality of data requests to one or more computer applications based on a plurality of sets of sampled parameter values for the set of TCP parameters, wherein the plurality of sets of sampled parameter values are distributed within the one or more specific regions of the output parameter space;
• using the machine learning to estimate the set of optimal parameter values for the set of TCP parameters;
• propagating one or more optimal parameter values in the set of optimal parameter values, for the set of TCP parameters, to be used by one or more user devices to make one or more new data requests to the one or more computer applications.

An apparatus, comprising:

• one or more computer processors;
• a non-transitory computer-readable medium storing a set of computer instructions which, when executed by the one or more computer processors, causes the one or more computer processors to perform:
• constraining, based on expert input comprising recommended parameter values provided by one or more human experts, a machine learning framework using a specific learning iteration to perform machine learning to estimate a set of optimal parameter values for a set of Transmission Control Protocol (TCP) parameters in one or more specific regions of an output parameter space, wherein the output parameter space represents a space of all possible parameter values for the set of TCP parameters;
• collecting, over a time block, network traffic data associated with a plurality of data requests to one or more computer applications based on a plurality of sets of sampled parameter values for the set of TCP parameters, wherein the plurality of sets of sampled parameter values are distributed within the one or more specific regions of the output parameter space;
• using the machine learning to estimate the set of optimal parameter values for the set of TCP parameters;
• propagating one or more optimal parameter values in the set of optimal parameter values, for the set of TCP parameters, to be used by one or more user devices to make one or more new data requests to the one or more computer applications.