Abstract
Data collection is a considerable operation in Wireless sensor network (WSN) to minimize the energy dissipation of sensor nodes and thereby increasing the network lifetime. A lot of research works have been designed for data gathering in WSN. A multi-mobile agent itinerary planning based energy and fault aware data aggregation and zone-based energy-aware data collection routing protocol was introduced to obtain better energy usage and data delivery in WSN. However, data aggregation accuracy was not increased and energy consumption during data aggregation was not reduced. In order to overcome such limitations, an Energy Aware Decision Stump Linear Programming Boosting Node Classification based Data Aggregation (EADSLPBNC-DA) Model is proposed. Initially, residual energy for every sensor node is calculated for performing the node classification. After that, linear programming boosting classification (LPBC) model is applied in EADSLPBNC-DA Model which increased the margin between the training samples (i.e., sensor nodes) of different classes. The LPBC model constructs a strong classifier by combining number of weak decision stump result. Subsequently, strong classifier in EADSLPBNC-DA Model accurately classifies each input sensor node as higher energy or lower energy node which reduced the misclassification error. Then, the lesser energy sensor nodes in WSN transmit the data packets to the neighboring higher energy sensor nodes through calculating the distance by Manhattan distance formula. Finally, the sink node gathers the data packets from the higher energy sensor nodes. As a result, EADSLPBNC-DA Model attains energy efficient data collection in WSN. Experimental evaluation of EADSLPBNC-DA Model is carried out on factors such as energy consumption, delay, data aggregation accuracy, network lifetime and data aggregation time with respect to number of sensor nodes and number of data packets. From the simulation results, proposed EADSLPBNC-DA Model significantly reduces the energy consumption by 22%, delay by 35% and data aggregation time by 28% when compared to the existing techniques. In addition, the data aggregation accuracy and network lifetime gets increased by 13% and 10% respectively compared to state-of-the-art works.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.