Optimized pollard route deviation and route selection using Bayesian machine learning techniques in wireless sensor networks

Optimal route selection and circumventing the route deviation is essential in sensor transmission to reach the destination properly and to save energy in sensors. Wireless sensor networks (WSNs) play an indispensable role to achieve faster communication. Sensors are tiny devices which can store less power and need the power to be retained until final communication. The main need is to achieve routing of the sensors while performing the data transmission should be taken care. Optimal routing technique is necessitated to transfer data from sensors in the clusters and to the central station. The main focus is to dwindle the battery power consumption and increase the network life time. In this proposed work, the route deviation is pollard by Bayesian machine learning technique which uses the posterior distribution incrementally when new evidence is occurred. The approach calculates the conditional probability using the prior knowledge to determine the route deviation and optimal route. The methodology mainly focuses on parameters like, end-to-end delay, detection of route deviation, optimal route selection and network life time. The experimental results of proposed Optimal Pollard Route Deviation using Bayesian (OPDB) protocol focuses on the evaluation metrics of machine learning algorithm in terms of accuracy and error rate. The proposed algorithm is 28.5% better in minimizing the route deviation, 86.67% improved route selection, delay is very much minimized up to 07.12% and the 93.87% improved network life time compared with other routing algorithms. The route deviation detection is 14.5% improved, optimal route selection is improved by 31.84%, delay is minimized by 20.32% and network lifetime is increased by15.24% while using the OPDB algorithm.