Systems and methods for utilizing time series and neural network models to deploy autonomous vehicles for 5g network coverage gaps

Abstract

A device may receive historical usage data associated with a portion of a wireless network, and may train a model with the historical usage data to generate a trained model. The device may process data identifying a future time period, with the trained model, to forecast a traffic demand during the future time period, and may compare the traffic demand and a traffic capacity of the portion of the wireless network to determine whether the traffic demand is within a threshold of or exceeds the traffic capacity. The device may identify an autonomous vehicle to deploy for the portion of the wireless network when the traffic demand is within the threshold of or exceeds the traffic capacity, and may cause the autonomous vehicle to be deployed for the portion of the wireless network, wherein the autonomous vehicle is to provide a temporary wireless network.

What is claimed is: 
     
         1 . A method, comprising:
 forecasting, by a device and based on a first model that is trained with historical network usage data associated with a portion of the network or a second model that is trained with historical user device usage data associated with the portion of the network, a traffic demand in the portion of a network associated with a time period;   determining, by the device, that the forecasted traffic demand is within a threshold of a traffic capacity of the portion of the network;   identifying, by the device and based on determining that the forecasted traffic demand is within the threshold of the traffic capacity of the portion of the network, one or more autonomous vehicles to deploy for the portion of the network; and   causing, by the device, the one or more autonomous vehicles to be deployed to provide a temporary network for the portion of the network.   
     
     
         2 . The method of  claim 1 , further comprising:
 identifying one or more vehicles that will be in an area associated with the portion of the network during the time period; and   activating wireless network capabilities of the one or more vehicles during the time period.   
     
     
         3 . The method of  claim 1 , wherein the one or more autonomous vehicles are a first set of autonomous vehicles,
 wherein the traffic capacity is a first traffic capacity, and   wherein the method further comprises:
 identifying a second set of autonomous vehicles to be on standby for the portion of the network,
 wherein one or more of the second set of autonomous vehicles are deployed based on at least one of:
 the first set of autonomous vehicles being unable to provide the temporary network for the portion of the network, or 
 a traffic demand in the portion of the network exceeding a second traffic capacity provided by the first set of autonomous vehicles. 
 
 
   
     
     
         4 . The method of  claim 1 , further comprising:
 causing the one or more autonomous vehicles to travel away from a location associated with the portion of the network after the time period expires.   
     
     
         5 . The method of  claim 1 , further comprising:
 providing, to the one or more autonomous vehicles, instructions to navigate to an area associated with the portion of the network.   
     
     
         6 . The method of  claim 1 , wherein an autonomous vehicle of the one or more autonomous vehicles is associated with a schedule determined based on historical need, and
 wherein the schedule indicates a location where the autonomous vehicle of the one or more autonomous vehicles should relocate to at a particular time period.   
     
     
         7 . The method of  claim 1 , wherein the portion of the network includes a fourth generation (4G) network, and
 wherein the temporary network includes a fifth generation (5G) network.   
     
     
         8 . A device, comprising:
 one or more processors configured to:
 forecast, based on a first model that is trained with historical network usage data associated with a portion of the network or a second model that is trained with historical user device usage data associated with the portion of the network, a traffic demand in the portion of a network associated with a time period; 
 determine that the forecasted traffic demand is within a threshold of a traffic capacity of the portion of the network; 
 identify, based on determining that the forecasted traffic demand is within the threshold of the traffic capacity of the portion of the network, one or more autonomous vehicles to deploy for the portion of the network; and 
 cause one or more autonomous vehicles to be deployed to provide a temporary network for the portion of the network. 
   
     
     
         9 . The device of  claim 8 , wherein the one or more processors are further configured to:
 identify one or more vehicles that will be in an area associated with the portion of the network during the time period; and   activate wireless network capabilities of the one or more vehicles during the time period.   
     
     
         10 . The device of  claim 8 , wherein the one or more autonomous vehicles are a first set of autonomous vehicles,
 wherein the traffic capacity is a first traffic capacity, and   wherein the one or more processors are further configured to:
 identify a second set of autonomous vehicles to be on standby for the portion of the network,
 wherein one or more of the second set of autonomous vehicles are deployed based on at least one of:
 the first set of autonomous vehicles being unable to provide the temporary network for the portion of the network, or 
 a traffic demand in the portion of the network exceeding a second traffic capacity provided by the first set of autonomous vehicles. 
 
 
   
     
     
         11 . The device of  claim 8 , wherein the one or more processors are further configured to:
 cause the one or more autonomous vehicles to travel away from a location associated with the portion of the network after the time period expires.   
     
     
         12 . The device of  claim 8 , wherein the one or more processors are further configured to:
 provide, to the one or more autonomous vehicles, instructions to navigate to an area associated with the portion of the network.   
     
     
         13 . The device of  claim 8 , wherein an autonomous vehicle of the one or more autonomous vehicles is associated with a schedule determined based on historical need, and
 wherein the schedule indicates a location where the autonomous vehicle of the one or more autonomous vehicles should relocate to at particular time periods.   
     
     
         14 . The device of  claim 8 , wherein the portion of the network includes a fourth generation (4G) network, and
 wherein the temporary network includes a fifth generation (5G) network.   
     
     
         15 . A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
 one or more instructions that, when executed by one or more processors of a device, cause the device to:
 forecast, based on a first model that is trained with historical network usage data associated with a portion of the network or a second model that is trained with historical user device usage data associated with the portion of the network, a traffic demand in the portion of a network associated with a time period; 
 determine that the forecasted traffic demand is within a threshold of a traffic capacity of the portion of the network; 
 identify, based on determining that the forecasted traffic demand is within the threshold of the traffic capacity of the portion of the network, one or more autonomous vehicles to deploy for the portion of the network; and 
 cause one or more autonomous vehicles to be deployed to provide a temporary network for the portion of the network. 
   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions further cause the device to:
 identify one or more vehicles that will be in an area associated with the portion of the network during the time period; and   activate wireless network capabilities of the one or more vehicles during the time period.   
     
     
         17 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more autonomous vehicles are a first set of autonomous vehicles,
 wherein the traffic capacity is a first traffic capacity, and   wherein the one or more instructions further cause the device to:
 identify a second set of autonomous vehicles to be on standby for the portion of the network,
 wherein one or more of the second set of autonomous vehicles are deployed based on at least one of:
 the first set of autonomous vehicles being unable to provide the temporary network for the portion of the network, or 
 a traffic demand in the portion of the network exceeding a second traffic capacity provided by the first set of autonomous vehicles. 
 
 
   
     
     
         18 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions further cause the device to:
 cause the one or more autonomous vehicles to travel away from a location associated with the portion of the network after the time period expires.   
     
     
         19 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions further cause the device to:
 provide, to the one or more autonomous vehicles, instructions to navigate to an area associated with the portion of the network.   
     
     
         20 . The non-transitory computer-readable medium of  claim 15 , wherein each of the one or more autonomous vehicles are associated with a schedule determined based on historical need, and
 wherein the schedule indicates a location where each of the one or more autonomous vehicles should relocate to at particular time periods.