We claim:
1. A system for managing a smart devices network using fog computing, the system comprising: 5
an application manager:
configured to receive one or more service requests from one or more devices in a smart devices network; and collect data related to one or more fog computing nodes 10 and one or more intermediate computing nodes;
a resource utilization predictor configured to predict availability of the one or more fog computing nodes and the one or more intermediate computing nodes based on the collected data 15 and the one or more received service requests; and
a resource manager configured to:
dynamically allocate at least one of: a specific fog computing node and a specific intermediate computing node 20 and schedule triggering of one or more fog applications based on the predicted availability;
trigger, at the specific fog computing node and the specific intermediate computing node, the one or more fog 25 applications for executing each of the one or more received service requests corresponding to the one or more devices; and

perform, at the specific fog computing node and the specific intermediate computing node, one or more actions corresponding to the executed one or more service requests.
5 2. The system of claim 1, wherein the one or more devices in the smart devices network comprise one or more mobile devices, one or more hospital room devices, one or more medical devices and any other devices used in healthcare industry.
10 3. The system of claim 1, wherein the collected data related to the one or more fog computing nodes and the one or more intermediate computing nodes comprise availability, scheduled service requests, current service requests and time required for execution of service requests.
15
4. The system of claim 1, wherein the resource utilization
predictor predicts availability of the one or more fog computing
nodes and the one or more intermediate computing nodes using a
convolution neural network.
20
5. The system of claim 1, wherein triggering the one or more fog
applications comprises execution of the one or more received
service requests which further comprises execution of a series
of jobs at the specific fog computing node and the specific
25 intermediate computing node.
6. A computer-implemented method for managing a smart devices
network using fog computing, via program instructions stored in

a memory and executed by a processor, the computer-implemented method comprising:
receiving one or more service requests from one or more devices in a smart devices network; 5
collecting data related to one or more fog computing nodes and one or more intermediate computing nodes;
predicting availability of the one or more fog computing nodes 10 and the one or more intermediate computing nodes based on the collected data and the one or more received service requests;
dynamically allocating at least one of: a specific fog computing node and a specific intermediate computing node and scheduling 15 triggering of one or more fog applications based on the predicted availability;
triggering, at the specific fog computing node and the specific intermediate computing node, the one or more fog applications 20 for executing of each of the one or more received service requests corresponding to the one or more devices; and
performing, at the specific fog computing node and the specific intermediate computing node, one or more actions corresponding 25 to the executed one or more service requests.
7. The computer-implemented method of claim 6, wherein the one or more devices in the smart devices network comprise one or

more mobile devices, one or more hospital room devices, one or more medical devices and any other devices used in healthcare industry.
5 8. The computer-implemented method of claim 6, wherein the collected data related to the one or more fog computing nodes and the one or more intermediate computing nodes comprise availability, scheduled service requests, current service requests and time required for execution of service requests. 10
9. The computer-implemented method of claim 6, wherein the
availability of the one or more fog computing nodes and the one
or more intermediate computing nodes is predicted using a
convolution neural network.
15
10. The computer-implemented method of claim 6, wherein
triggering the one or more fog applications comprises execution
of the one or more received service requests which further
comprises execution of a series of jobs at the specific fog
20 computing node and the specific intermediate computing node.