Optimal channel assignment and scheduling in wireless multimedia sensor networks through adaptive deep neural network-based data flow allocation

An improved throughput capacity region can be achieved in wireless networks by equipping them with multiple channels. However, such an approach inevitably brings the issue of solving the coupled channel assignment and scheduling problem. This can be solved by equipping each network node with multiple radio interfaces that can operate on multiple non-overlapping channels. The availability of multiple orthogonal channels in a wireless network can lead to substantial performance improvement by alleviating contention and interference. In this paper, an intelligent channel assignment and channel scheduling algorithm on WMSN is proposed. The suggested model will mainly cover two phases: the data flow allocation, and then Channel Assignment and Scheduling. Data Flow Allocation will be performed by an ensemble of Adaptive Deep Neural Networks based on the available channel queues. Further, the Channel Assignment and Scheduling will be accomplished by the Improved Sail Fish Optimization. This optimal Channel Assignment and Scheduling will be performed by an objective model considering the back-off time, stability, packet drop rate, and throughput. Through theoretical analysis and simulation experiments, it is proved that the proposed algorithm is throughput guaranteed when compared to other state-of-the-art algorithms on Wireless Multimedia Sensor Networks.