Context aware edge computing and progressive depletion of content

A computer program product for context aware edge computing and progressive depletion of content, the computer program product comprising one or more computer readable storage media having computer readable program code collectively stored on the one or more computer readable storage media, the computer readable program code being executed by a processor of a computer system to cause the computer system to perform a method comprising:

• embedding, on an edge server, a model which regenerates media file data portions of a media file, the media file being sourced from a main server and having media file data temporarily stored on the edge server;
• receiving, at the edge server, a request for the media file;
• determining, from the request, a probability value that a similar request will be received at the edge server;
• comparing the probability value with a predefined probability threshold value;
• identifying a portion of the media file data to be deleted from results of the comparing and from a capability of the model to regenerate the portion of the media file data to be deleted;
• and
• deleting the portion of the media file data in accordance with results of the identifying,
• wherein the identifying comprises considering the capability of the model to regenerate the portion of the media file data to be deleted with a given resolution,
• wherein the method further comprises:
• receiving, at the edge server, a subsequent request for the media file;
• regenerating, by the model, the portion of the media file data to satisfy the subsequent request;
• and
• not passing the subsequent request to the main server,
• wherein the model is a generative adversarial network (GAN) enabled model with a hierarchical mode classifier for content retainment and progressive depletion and an internal mapping table and the method further comprises:
• generating, at the edge server, the internal mapping table to map elements of the media file data to previous frames and surrounding pixels of the media file data;
• and
• ascertaining the capability of the model to regenerate the media file data that has been deleted,
• wherein the media file comprises a video file and the regenerating, by the model, comprises next-frame prediction applied to the video file by reference to the hierarchical mode classifier for content retainment and progressive depletion and the internal mapping table.

A computing system comprising:

• a processor;
• a memory coupled to the processor;
• and
• one or more computer readable storage media coupled to the processor, the one or more computer readable storage media collectively containing instructions that are executed by the processor via the memory to cause the processor to perform steps for context aware edge computing and progressive depletion of content comprising:
• embedding, on an edge server, a model regenerates media file data portions of a media file, the media file being sourced from a main server and having media file data temporarily stored on the edge server;
• receiving, at the edge server, a request for the media file;
• determining, from the request, a probability value that a similar request will be received at the edge server;
• comparing the probability value with a predefined probability threshold value;
• identifying a portion of the media file data to be deleted from results of the comparing and from a capability of the model to regenerate the portion of the media file data to be deleted;
• and
• deleting the portion of the media file data in accordance with results of the identifying,
• wherein the identifying comprises considering the capability of the model to regenerate the portion of the media file data to be deleted with a given resolution,
• wherein the steps further comprise:
• receiving, at the edge server, a subsequent request for the media file;
• regenerating, by the model, the portion of the media file data to satisfy the subsequent request;
• and
• not passing the subsequent request to the main server,
• wherein the model is a generative adversarial network (GAN) enabled model with a hierarchical mode classifier for content retainment and progressive depletion and an internal mapping table and the steps further comprise:
• generating, at the edge server, the internal mapping table to map elements of the media file data to previous frames and surrounding pixels of the media file data;
• and
• ascertaining the capability of the model to regenerate the media file data that has been deleted,
• wherein the media file comprises a video file and the regenerating, by the model, comprises next-frame prediction applied to the video file by reference to the hierarchical mode classifier for content retainment and progressive depletion and the internal mapping table.