A two-level traffic smoothing method for efficient cloud-IoT communications

The Internet of Things (IoT) is an integration of smart sensing devices with connection ability for ease of communication. Introducing decision-making systems (DMSs) in the IoT for request processing improves the ease of access and service reliability for mobile end users. This paper proposes a two-level DMS for user service traffic smoothing (TS) in IoT communications. The two-level decision-making (2LDM) method employs traffic-aware queuing and minimum time scheduling processes for controlling the request message flows. The decision-making algorithm is modeled on time-dependent processing for minimizing the time delay in the queuing and request scheduling. The DMS considers the attributes associated with the cloud and devices to classify the request messages to prevent resource mapping failures. The disagreement between the request processing and cloud response is resolved optimally for improving the end user communication reliability in terms of the delay and resource mapping failures. Simulations evaluate the proposed DMS performance for the following metrics: sum rate, access delay, failure probability, response latency, and queue utilization. The results indicate that the proposed TS-2LDM outperforms the existing traffic controlling methods by improving the sum rate and queue utilization with controlled delay, failure, and response time.