WSN MACHINE LEARNING APPROACH FOR SCHEDULING ENERGY IN NETWORK

The energy of each sensor is limited and they are usually un-rechargeable, so to prolong the life time of WSNs energy consumption of each sensor has to be minimized. However, these duties cycling based approaches in WSNs may incurs tradeoff between both energies saving and packet delivery delay. In order to avoid this, self-healing based sleep/wake-up scheduling is proposed to save the energy of each sensor node by keeping nodes in sleep mode as long as possible and thereby maximizing their lifetime we propose machine learning concept with the help of SVM classifier method.This artificial potential field with information about the direction and goal of the moving object and guarantees the best-safest path to the goal.