Global internet of things (iot) quality of service (qos) realization through collaborative edge gateways

Abstract

Global Internet of things (IoT) quality of service (QoS) is provided through self-forming, self-healing, and/or collaborative edge IoT gateways. Moreover, global IoT services are provided by logically extending cellular networks with roaming partners to backhaul, track, and/or manage the globally deployed edge IoT gateways. In one aspect, real-time QoS and/or monitoring capabilities for the global IoT services can be provided through a communication between the edge IoT gateways and an edge gateway controller deployed within a cloud. The edge IoT gateways form a structured mesh network to coordinate workload execution under control of the edge gateway controller, which can facilitate a highly efficient QoS and/or SLA management for mobile IoT sensors, to provide a secure monitoring and/or diagnostic capability for the global IoT services.

What is claimed is: 
     
         1 . A system, comprising:
 a processor; and   a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
 assigning a workload associated with a shipment to a first edge gateway device of edge gateway devices deployed in a geographic area, wherein the shipment is associated with a device; 
 based on an analysis of state data associated with the workload that indicates a defined condition is associated with a first route via which the shipment is initially scheduled to travel towards the first edge gateway device, predicting, using an artificial intelligence model of the system and with a threshold probability, that the shipment and the device are going to be rerouted from the first route to a second route associated with a second edge gateway device of the edge gateway devices as a result of, at least in part, the defined condition; and 
 in response to determining that the state data satisfies an unexpected state criterion based on the predicting, modifying the workload by terminating assignment of the workload to the first edge gateway device and reassigning the workload to the second edge gateway device. 
   
     
     
         2 . The system of  claim 1 , wherein the assigning of the workload comprises assigning the workload to the first edge gateway device based on provisioning data associated with the shipment, wherein the provisioning data comprises route data indicative of a route via which the device is predicted to travel, wherein the route comprises the first route, and wherein the operations further comprise selecting the first edge gateway device from the edge gateway devices based on the route data. 
     
     
         3 . The system of  claim 2 , wherein the analysis comprises a first artificial intelligence-based analysis, wherein the threshold probability is a first threshold probability, and wherein the operations further comprise:
 predicting, using the artificial intelligence model and with a second threshold probability, the route via which the device associated with the shipment is going to travel to arrive at a shipment destination of the shipment based on a second artificial intelligence-based analysis of a portion of the provisioning data.   
     
     
         4 . The system of  claim 1 , wherein the analysis comprises a first artificial intelligence-based analysis, wherein the threshold probability is a first threshold probability, and wherein the operations further comprise:
 predicting, using the artificial intelligence model and with a second threshold probability, an arrival time of the shipment at a shipment destination of the shipment based on a second artificial intelligence-based analysis of the state data or provisioning data relating to provisioning of the shipment.   
     
     
         5 . The system of  claim 1 , wherein the artificial intelligence model is generated based on a classifier, and wherein, to facilitate generation of the artificial intelligence model, the classifier is trained based on at least one of training data relating to shipments, workloads, or the edge gateway devices, or historical data relating to the shipments, the workloads, or the edge gateway devices. 
     
     
         6 . The system of  claim 1 , wherein the operations further comprise:
 receiving the state data, comprising internal state data or external state data, from the device, an edge gateway device, a network device, a content server, a web server, or a sensor, wherein the edge gateway device is the first edge gateway device, the second edge gateway device, or a third edge gateway device of the edge gateway devices,   wherein the internal data relates to a departure time associated with the shipment, an arrival time or an expected arrival time associated with the shipment, a measurement of a condition associated with the shipment, or a characteristic associated with the shipment, and   wherein the external data relates to a schedule associated with an event, a news event, a weather event, a traffic report relating to a vehicle traffic condition, a user preference, or a user instruction associated with the shipment.   
     
     
         7 . The system of  claim 1 , wherein the state data comprises external state data relating to the defined condition, comprising a weather condition or a traffic condition, associated with the shipment initially being routed towards the first edge gateway device, and
 wherein the predicting comprises: based on the analysis of the external state data, predicting, using the artificial intelligence model and with the threshold probability, that the shipment is going to be rerouted from the first route associated with the first edge gateway device to the second route associated with the second gateway device as a result of, at least in part, the weather condition or the traffic condition.   
     
     
         8 . The system of  claim 1 , wherein the operations further comprise:
 using a blockchain-based technology, generating a token or metadata relating to the shipment based on shipment-related data relating to the shipment; and   transferring the token or the metadata between the second edge gateway device and a third edge gateway device of the edge gateway devices to facilitate tracking or security of the shipment.   
     
     
         9 . The system of  claim 8 , wherein the edge gateway devices are arranged to form a structured mesh network of edge gateway devices to facilitate transfer of shipment-related data associated with shipments between the edge gateway devices of the structured mesh network of edge gateway devices, wherein the shipment-related data is usable to monitor a quality of service associated with a service that is associated with the edge gateway devices, and wherein the shipment-related data comprises tracking data, route data, information relating to a package that is part of the shipment of the shipments, action information regarding an action performed by the first edge gateway device or the second edge gateway device, time information relating to a time of an event associated with the shipment, or a portion of the state data relating to the shipment. 
     
     
         10 . The system of  claim 9 , wherein the transferring of the token or the metadata comprises transferring the token or the metadata between the second edge gateway device and the third edge gateway device via the structured mesh network of edge gateway devices. 
     
     
         11 . The system of  claim 8 , wherein the token or the metadata comprises summary data representative of a summary of a shipment state of the shipment, wherein the shipment state comprises or relates to a number of packages within the shipment, a type of packaging associated with the shipment, contents of a package of the shipment, actions performed at the second edge gateway device, a result of the actions performed at the second edge gateway device, a departure time of the shipment from the second edge gateway device, an estimated arrival time of the shipment at the third edge gateway device along the second route, or route data associated with the second route. 
     
     
         12 . A method, comprising:
 scheduling, by a system comprising a processor, an assignment of a workload associated with a package to a first edge gateway device of edge gateway devices deployed in a geographic region, wherein the package is associated with a device;   based on an analysis of state information associated with the workload indicating a defined condition is associated with a first route on which the package is initially scheduled to be transported towards the first edge gateway device, predicting, by a machine learning model of the system and with a threshold likelihood, that the package will be rerouted from the first route to a second route associated with a second edge gateway device of the edge gateway devices as a result of the defined condition; and   in response to determining that the state information satisfies an unexpected state criterion based on the predicting, updating, by the system, the scheduling to reassign the workload from the first edge gateway device to the second edge gateway device.   
     
     
         13 . The method of  claim 12 , further comprising:
 receiving, by the system, provisioning information associated with a service that utilizes devices, comprising the device, to facilitate shipment of packages comprising the package;   based on the provisioning information, determining, by the system, route information indicative of an expected route via which the device is expected to travel, wherein the expected route comprises the first route; and   selecting, by the system, the first edge gateway device of the edge gateway devices based on the first route, wherein the scheduling comprises scheduling the assigning of the workload to the first edge gateway device based on the provisioning information associated with the package.   
     
     
         14 . The method of  claim 13 , further comprising:
 based on provisioning information associated with the package or the device, determining, by the system, parameter information that defines an expected quality of service associated with the device, wherein the scheduling comprises: based on the provisioning information and the parameter information, scheduling the assignment of the workload associated with the package to the first edge gateway device.   
     
     
         15 . The method of  claim 13 , wherein the analysis comprises a first machine learning-based analysis, wherein the threshold likelihood is a first threshold likelihood, and wherein the operations further comprise:
 predicting, by the machine learning model and with a second threshold likelihood, the expected route via which the device associated with the package is expected to travel to arrive at a destination of the package based on a second machine learning-based analysis of a portion of the provisioning information.   
     
     
         16 . The method of  claim 12 , wherein the scheduling, the predicting, or the updating is performed based on a first result of machine learning performed by the machine learning model on package-related information relating to the package or a second result of big data analytics performed on the package-related information, and wherein the package-related information comprises provisioning information relating to the package, the state information, or information relating to the package or the device. 
     
     
         17 . The method of  claim 12 , wherein the assignment of the workload is a first assignment of a first workload, and wherein the method further comprises:
 performing, by the machine learning model of the system, a machine learning-based analysis on images of the package received from two or more of the edge gateway devices, wherein the machine learning-based analysis is performed using a machine learning technology, wherein the two or more of the edge gateway devices comprise the first edge gateway device or the second edge gateway device;   determining, by the system, whether a characteristic of the package has changed based on a result of the machine learning-based analysis performed on the images of the package; and   in response to determining the characteristic of the package has changed, scheduling, by the system, a second assignment of a second workload to the second edge gateway device or a third edge gateway device of the edge gateway devices to facilitate checking a status or an integrity of the package.   
     
     
         18 . The method of  claim 12 , further comprising:
 receiving, by the system, the state information, comprising internal state information or external state information, from the device, an edge gateway device, a network device, a content server, a web server, or a sensor, wherein the edge gateway device is the first edge gateway device, the second edge gateway device, or a third edge gateway device of the edge gateway devices.   
     
     
         19 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
 determining an assignment of a workload associated with the package to a first edge gateway device of edge gateway devices deployed in a geographic area, wherein the package is associated with a device;   based on a machine learning-based analysis, applying a machine learning model, of state data associated with the workload indicating a condition is associated with a first path on which the package is initially scheduled to be transported towards the first edge gateway device, determining that the package and the device are threshold likely to be rerouted from the first path to a second path associated with a second edge gateway device of the edge gateway devices due at least in part to the condition; and   in response to determining that the state data satisfies an unexpected state criterion based on the determining that the package and the device are threshold likely to be rerouted, modifying the assignment of the workload to reassign the workload from the first edge gateway device to the second edge gateway device.   
     
     
         20 . The non-transitory machine-readable medium of  claim 19 , wherein the determining of the assignment of the workload comprises determining the assignment of the workload to the first edge gateway device based on provisioning data associated with the shipment, and wherein the operations further comprise:
 based on the provisioning data, determining path data indicative of a path via which the device is expected to travel, wherein the path comprises the first path;   selecting the first edge gateway device for the assignment based on the path data; and   in connection with transportation of the package and the device, receiving the state data, comprising internal state data representative of an internal state applicable to the workload or external state data representative of an external state external to the workload, from the device, an edge gateway device, a network device, a content server, a web server, or a sensor, wherein the edge gateway device is the first edge gateway device, the second edge gateway device, or a third edge gateway device of the edge gateway devices.