Energy-centric route planning using machine learning algorithm for data intensive secure multi-sink sensor networks

Abstract

Wireless sensor network (WSN) is energy operated self-disciplined ad-hoc technology capable of sensing and actuating environmental phenomenon. The sensed information is shared between communication sinks for access and processing. Energy conservation and route planning are prominent in determining the efficiency of the sensor network. In this paper, energy-centric route planning (ECRP) technique is introduced to address the inequalityin sensor node lifetime and routing along with security requirements. ECRP depends on the individual and co-operative energy expenses of the nodes to retain a balanced communication link. The expenses are monitored and a profitable route plan is designed using a machine learning algorithm that assists in identifying a non-deficient neighbor for routing. Both energy optimization and route refurbishing are controlled by the analysis and decisions of the learning algorithm. The Learning process is instigated with the node energy and current route neighbor information for discovering efficient communication paths to the sink. Security is administered using trust process in this path planning and routing for selecting reliable neighbors. This helps to retain security throughout the routing process.The impact of the proposed ECRP over sensor network is verified using the metrics: throughput, active nodes, transmitting energy, routing complexity and delay.