Security enhanced optimal trajectoryselection for mobile sink using reinforcement learning

Wireless visual sensor networks (WVSNs) have emerged as a strategic inter disciplinary category of WSN with its visual sensor based intelligence that has garnered considerable attention. The growing demand for energy efficient and maximized life time networks in highly critical applications like surveillance, military and medicine has opened up more prospects as well as challenges in the deployment of WVSNs. Multi-hop communication in WVSN results in overloading of intermediate sensor nodes due to its dual function in the network which results in hotspot effect. This can be mitigated with the help of mobile sinks and rendezvous points based route design. But mobile sinks has to visit every cluster head to gather data which results in longer traversal path and higher latency and power consumption related issues if not addressed properly will impact the performance of the network. Our objective is to analyze and determine the optimal trajectory for mobile sink node traversal with the help of a high quality transmission architecture integrated with reinforcement learning and isolation forest based anomaly detection to propose an energy efficient meta-heuristic approach to enhance the performance of network by reducing the latency and securing the network against possible attacks.

An Efficient Path Generation Algorithm Using Principle Component Analysis for Mobile Sinks in Wireless Sensor Networks

Recently, the data collection problem in wireless sensor networks (WSNs) using mobile sinks has received much attention. The main challenge in such problems is constructing the path that the mobile sink (MS) will use to collect the data. In this paper, an efficient path generation algorithm for the mobile sink based on principal component analysis (PCA) is proposed. The proposed approach was evaluated using two data collection modes—direct and multihop—and it was compared with another approach called the mobile-sink-based energy-efficient clustering algorithm for wireless sensor networks (MECA). When compared with MECA, simulation results have shown that the proposed approach improves the performance of WSN in terms of the number of live nodes and average remaining energy.