Apparatuses and methods for facilitating an intelligent network video player for wireless networks

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, the operations comprising:

obtaining first data pertaining to a conveyance of first traffic and second traffic in a communication network, wherein the first traffic corresponds to video traffic conveyed to a first plurality of client devices and the second traffic corresponds to elastic traffic conveyed to a second plurality of client devices;

analyzing the first data to select a first rate limit; and

conveying third traffic corresponding to video traffic to the first plurality of client devices based on the first rate limit,

wherein the analyzing of the first data is based on a use of a multi-objective reinforcement learning (MORL) algorithm that processes inputs, the inputs including elastic traffic observations, video stream traffic observations, and system observations.

2 . The device of claim 1 , wherein the operations further comprise:

classifying the first traffic as video traffic based on an inspection of first metadata, an analysis of first traffic patterns, a use of at least a first label, or any combination thereof.

3 . The device of claim 2 , wherein the operations further comprise:

classifying the second traffic as elastic traffic based on an inspection of second metadata, an analysis of second traffic patterns, a use of at least a second label, or any combination thereof.

4 . The device of claim 1 , wherein the elastic traffic includes web browsing traffic, file transfer traffic, or a combination thereof.

5 . The device of claim 1 , wherein the operations further comprise:

obtaining second data pertaining to a conveyance of at least fourth traffic in the communication network;

analyzing the second data to select a second rate limit that is different from the first rate limit; and

conveying fifth traffic corresponding to video traffic based on the second rate limit,

wherein the conveying of the fifth traffic includes conveying the fifth traffic to: a client device that is included in the first plurality of client devices, a third plurality of client devices, or a combination thereof.

6 . The device of claim 1 , wherein the first data pertains to: bit error rates, missing or corrupted data packets, latency, throughput, or any combination thereof.

7 . The device of claim 1 , wherein the operations further comprise:

identifying at least one client device included in the first plurality of client devices; and

based on the identifying, modifying the first rate limit to generate a modified first rate limit that is different from the first rate limit,

wherein the conveying of the third traffic is based on the modified first rate limit.

8 . The device of claim 1 , wherein the operations further comprise:

conveying fourth traffic corresponding to elastic traffic based on the first rate limit.

9 . The device of claim 8 , wherein the first rate limit is selected to maximize a lesser of a first throughput of the third traffic and a second throughput of the fourth traffic.

10 . The device of claim 8 , wherein the first rate limit is selected to maximize a first throughput of the third traffic subject to a constraint that a second throughput of the fourth traffic is greater than a threshold.

11 . The device of claim 8 , wherein the first rate limit is selected to maximize a linear combination of a first throughput of the third traffic and a second throughput of the fourth traffic.

12 . The device of claim 1 , wherein the operations further comprise:

reallocating a first resource of the communication network from conveying video traffic to conveying elastic traffic based on the first rate limit,

wherein the conveying of the third traffic is based on the reallocating.

13 . The device of claim 1 , wherein the operations further comprise:

reallocating a first resource of the communication network from conveying elastic traffic to conveying video traffic based on the first rate limit,

wherein the conveying of the third traffic is based on the reallocating.

14 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:

obtaining first data pertaining to a conveyance of first traffic and second traffic in a communication network, wherein the first traffic corresponds to video traffic conveyed to a first plurality of client devices and the second traffic corresponds to elastic traffic;

analyzing the first data to select a first rate limit; and

conveying third traffic corresponding to video traffic to the first plurality of client devices based on the first rate limit,

wherein the analyzing of the first data is based on a use of a multi-objective reinforcement learning (MORL) algorithm that processes inputs, the inputs including elastic traffic observations, video stream traffic observations, and system observations.

15 . The non-transitory machine-readable medium of claim 14 , wherein the operations further comprise:

classifying the first traffic as video traffic based on an inspection of first metadata, an analysis of first traffic patterns, a use of at least a first label, or any combination thereof; and

classifying the second traffic as elastic traffic based on an inspection of second metadata, an analysis of second traffic patterns, and a use of at least a second label.

16 . A method comprising:

obtaining, by a processing system including a processor, first data pertaining to a conveyance of first traffic and second traffic in a communication network, wherein the first traffic corresponds to video traffic conveyed to a first plurality of client devices and the second traffic corresponds to elastic traffic;

analyzing, by the processing system, the first data to select a first rate limit; and

conveying, by the processing system, third traffic to the first plurality of client devices based on the first rate limit,

wherein the analyzing of the first data is based on a use of a multi-objective reinforcement learning (MORL) algorithm that processes inputs, the inputs including elastic traffic observations, video stream traffic observations, and system observations.

17 . The method of claim 16 , wherein the elastic traffic includes web browsing traffic, file transfer traffic, or a combination thereof.

18 . The method of claim 16 , wherein the elastic traffic observations include indicators of arrival rate estimates, file size distribution estimates, and spectral efficiency estimates.

19 . The method of claim 18 , wherein the video stream traffic observations include arrival rate estimates, chunk size distribution estimates, and spectral efficiency estimates.

20 . The method of claim 19 , wherein the system observations include identifications of resource utilization, throughputs, a number of active client devices that are participating, and a number of applications that are participating.