Predictive dynamic caching in edge devices when connectivity may be potentially lost

A system comprising:

• a memory having computer readable instructions;
• and
• a computer for executing the computer readable instructions, the computer readable instructions controlling the computer to perform operations comprising:
• registering devices that require a connectivity to a cloud server via a network, the devices being identified in a table;
• predicting a likelihood of a network outage of the connectivity to the network for the devices having been registered;
• determining data to cache for each of the devices by analyzing traffic for each of the devices to the cloud server, at least one piece of the data being currently in use by at least one of the devices;
• responsive to predicting the likelihood of the network outage, caching the data to edge devices, the edge devices being identified in the table and associated in the table with the devices, the data to cache being determined in accordance with the table;
• and
• responsive to the connectivity to the network being restored, removing the data cached on the edge devices,
• wherein the edge devices are activated in response to predicting the likelihood of the network outage, a sufficient number of the edge devices being activated to accommodate a size of the data to be cached;
• wherein a loss of the connectivity for the network outage is predicted to be associated with at least one factor, the at least one factor selected from the group consisting of a duration for the loss of the connectivity and a distance for the loss of the connectivity;
• and
• wherein a machine learning model is configured to predict the likelihood of the network outage, the machine learning model being trained on historical data associated with previous network outages.

A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform operations comprising:

• registering devices that require a connectivity to a cloud server via a network, the devices being identified in a table;
• predicting a likelihood of a network outage of the connectivity to the network for the devices having been registered;
• determining data to cache for each of the devices by analyzing traffic for each of the devices to the cloud server, at least one piece of the data being currently in use by at least one of the devices;
• responsive to predicting the likelihood of the network outage, caching the data to edge devices, the edge devices being identified in the table and associated in the table with the devices, the data to cache being determined in accordance with the table;
• and
• responsive to the connectivity to the network being restored, removing the data cached on the edge devices;
• wherein the edge devices are activated in response to predicting the likelihood of the network outage, a sufficient number of the edge devices being activated to accommodate a size of the data to be cached;
• wherein a loss of the connectivity for the network outage is predicted to be associated with at least one factor, the at least one factor selected from the group consisting of a duration for the loss of the connectivity and a distance for the loss of the connectivity;
• and
• wherein a machine learning model is configured to predict the likelihood of the network outage, the machine learning model being trained on historical data associated with previous network outages.