Traffic-based data compression

1 . An apparatus for wireless communication at a first wireless communication device, comprising:

one or more memories; and

one or more processors, coupled to the one or more memories, configured to cause the first wireless communication device to:

receive configuration information associated with uplink data compression, the uplink data compression being associated with one or more compression dictionaries and one or more compression buffers;

predict one or more traffic parameters of uplink data using an artificial intelligence (AI) or a machine learning (ML) (AI/ML) model;

classify, prior to compressing the uplink data, the uplink data in accordance with the one or more traffic parameters predicted by the AI/ML model;

allocate the uplink data to the one or more compression buffers in accordance with classifying the uplink data;

compress, in accordance with the configuration information, the uplink data to generate compressed uplink data via

one or more compression dictionaries and the one or more compression buffers being selected in association with the one or more traffic parameters of the uplink data; and

transmit an uplink communication that includes the compressed uplink data.

2 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

monitor data associated with a set of data categories in association with compressing the uplink data;

report the data associated with the set of data categories to a server associated with the AI/ML model; and

train the AI/ML model using the data monitored in association with compressing the uplink data.

3 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

identify that data associated with at least one data category of a set of data categories fails to meet a performance metric; and

perform an action in association with identifying that the data fails to meet a performance metric.

4 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

obtain encrypted data for uplink data transmission;

predict one or more traffic parameters of the encrypted data using the AI/ML model;

classify, in accordance with the one or more traffic parameters of the encrypted data predicted by the AI/ML model, the encrypted data as encrypted traffic; and

refrain from compressing the encrypted data.

5 . The apparatus of claim 1 , wherein the uplink data includes one or more messages, wherein the one or more compression buffers are associated with a message type, and the one or more processors are further configured to cause the first wireless communication device to:

classify, in accordance with the one or more traffic parameters, the one or more messages as being associated with the message type; and

allocate the one or more messages to the one or more compression buffers in association with classifying the one or more messages as being associated with the message type.

6 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

transmit an indication of the one or more compression dictionaries or the one or more compression buffers selected in association with one or more traffic parameters of the uplink data.

7 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

transmit a capability message comprising one or more of an uplink data compression capability, a set of supported compression dictionaries, or a quantity of supported compression dictionaries, wherein the set of supported compression dictionaries comprises the one or more compression dictionaries.

8 . The apparatus of claim 1 , wherein the configuration information indicates at least one of:

a quantity of enabled compression buffers,

an individual compression buffer size for each of the multiple one or more compression buffers,

a total compression buffer size for the one or more compression buffers,

a set of enabled compression dictionaries comprising the one or more compression dictionaries,

whether dynamic compression dictionary updating is enabled,

whether AI/ML prediction of the one or more traffic parameters is enabled,

one or more quality-of-service flows enabled for uplink data compression,

a compression ratio performance metric,

a compression dictionary reset rate performance metric,

a compression buffer reset rate performance metric, or

a compression dictionary update timing performance metric.

9 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

select the one or more compression dictionaries using a version identifier of the one or more compression dictionaries or a version identifier of each of the one or more compression dictionaries.

10 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

classify, prior to compressing the uplink data, the uplink data using the AI/ML model; and

allocate the uplink data to the one or more compression buffers in accordance with classifying the uplink data.

11 . The apparatus of claim 1 , wherein a header of the compressed uplink data indicates the one or more compression buffers, the one or more compression dictionaries, or information associated with the one or more compression dictionaries.

12 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

select the one or more compression buffers according to a quality-of-service flow indicator-to-buffer mapping associated with a quality-of-service flow of the uplink data; and

transmit control signaling comprising an indication of the quality-of-service flow indicator-to-buffer mapping.

13 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

refrain from compressing second uplink data; and

transmit a second uplink communication that includes the second uplink data in accordance with refraining from compressing the second uplink data, wherein the second uplink communication includes a packet header that indicates an absence of a compression header for the second uplink data.

14 . The apparatus of claim 1 , wherein the one or more processors are further configured to cause the first wireless communication device to:

transmit an uplink data compression update comprising an indication of one or more of a second one or more compression dictionaries, a second compression buffer of the one or more compression buffers, an updated compression buffer size of the one or more compression buffers, a compression buffer size of the second compression buffer, or an updated quantity of compression buffers used for compression by the first wireless communication device.

15 . A method of wireless communication performed by a first wireless communication device, comprising:

receiving configuration information associated with uplink data compression, the uplink data compression being associated with one or more compression dictionaries and one or more compression buffers;

predicting one or more traffic parameters of uplink data using an artificial intelligence (AI) or a machine learning (ML) (AI/ML) model;

classifying, prior to compressing the uplink data, the uplink data in accordance with the one or more traffic parameters predicted by the AI/ML model;

allocating the uplink data to the one or more compression buffers in accordance with classifying the uplink data;

compressing, in accordance with the configuration information, the uplink data to generate compressed uplink data via

one or more compression dictionaries and the one or more compression buffers being selected in association with the one or more traffic parameters of the uplink data; and

transmitting an uplink communication that includes the compressed uplink data.

16 . The method of claim 15 , further comprising:

monitoring data associated with a set of data categories in association with compressing the uplink data;

reporting the data associated with the set of data categories to a server associated with the AI/ML model; and

training the AI/ML model using the data monitored in association with compressing the uplink data.

17 . The method of claim 15 , further comprising:

identifying that data associated with at least one data category of a set of data categories fails to meet a performance metric; and

performing an action in association with identifying that the data fails to meet a performance metric.

18 . The method of claim 15 , wherein the uplink data includes one or more messages, wherein the one or more compression buffers are associated with a message type, and further comprising:

classifying, in accordance with the one or more traffic parameters, the one or more messages as being associated with the message type; and

allocating the one or more messages to the one or more compression buffers in association with classifying the one or more messages as being associated with the message type.

19 . The method of claim 15 , further comprising:

transmitting an indication of the one or more compression dictionaries or the one or more compression buffers selected in association with one or more traffic parameters of the uplink data.

20 . A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising:

one or more instructions that, when executed by one or more processors of a first wireless communication device, cause the first wireless communication device to:

receive configuration information associated with uplink data compression, the uplink data compression being associated with one or more compression dictionaries and one or more compression buffers;

predict one or more traffic parameters of uplink data using an artificial intelligence (AI) or a machine learning (ML) (AI/ML) model;

classify, prior to compressing the uplink data, the uplink data in accordance with the one or more traffic parameters predicted by the AI/ML model;

allocate the uplink data to the one or more compression buffers in accordance with classifying the uplink data;

compress, in accordance with the configuration information, the uplink data to generate compressed uplink data via

one or more compression dictionaries and the one or more compression buffers being selected in association with the one or more traffic parameters of the uplink data; and

transmit an uplink communication that includes the compressed uplink data.