AI/ML model distribution based on network manifest

A method performed by a server, comprising:

• receiving model subscription information for an event from a wireless transmit/receive unit (WTRU);
• receiving an indication of a change in an environmental condition associated with the event;
• in response to receiving said indication, selecting an updated AI/ML model chunk for the event corresponding to said change in the environmental condition;
• generating information indicating a plurality of network communication paths that are available for downloading said updated AI/ML model chunk, wherein said information further includes AI/ML model information and indicates a communication mode and expected download time for each one of said plurality of network communication paths;
• and
• transmitting said generated information to said WTRU.

A wireless transmit/receive unit (WTRU), comprising:

• a receiver configured to receive information indicating a plurality of network communication paths that are available for downloading an AI/ML model, wherein said information further includes AI/ML model information and indicates a communication mode and expected download time for each one of said plurality of network communication paths;
• and
• one or more processor configured to:
• determine a plurality of AI/ML model chunks for said AI/ML model based on said received information, determine one network communication path, from said plurality of communication network paths, to download a respective model chunk of said plurality of AI/ML model chunks of said AI/ML model, based on said received information,
• download said respective model chunk of said AI/ML model via said one network communication path,
• build at least a subset of said AI/ML model based on said respective model chunk of said AI/ML model, and
• perform inference on said at least a subset of said AI/ML model;
• wherein the receiver is configured to receive information triggered by a change in an environmental condition at a live event, and wherein the information enables the one or more processor to download an updated AI/ML model chunk corresponding to said change in the environmental condition.

A server, comprising:

• a receiver configured to receive model subscription information for an event from a wireless transmit/receive unit (WTRU);
• one or more processors configured to:
• receive an indication of a change in an environmental condition associated with the event;
• in response to receiving said indication, select an updated AI/ML model chunk for the event corresponding to said change in the environmental condition;
• generate information indicating a plurality of network communication paths that are available for downloading said updated AI/ML model chunk, wherein said information further includes AI/ML model information and indicates a communication mode and expected download time for each one of said plurality of network communication paths;
• and
• a transmitter configured to transmit said generated information to said WTRU.