Authors: Jitendra Sharma, Professor Amit Thakur
Abstract: Wireless Sensor Networks (WSNs) demand energy-efficient and reliable routing mechanisms due to the constrained resources of sensor nodes and the dynamic nature of wireless links. Traditional Dynamic Source Routing (DSR) operates efficiently in on-demand route discovery but fails to account for multiple correlated parameters such as residual energy, link stability, delay, and packet reception rate, which are critical in WSN environments. In this paper, we propose a Principal Component Analysis based Dynamic Source Routing (PCA-DSR) protocol that integrates statistical feature reduction with classical DSR. Multiple network and link parameters are periodically collected and transformed using PCA into a single principal component score that reflects overall route quality. This score is embedded in route discovery and maintenance phases to enable the selection of stable and energy-aware paths. Simulation results demonstrate that PCA-DSR achieves higher packet delivery ratio, reduced end-to-end delay, balanced energy consumption, and extended network lifetime compared to conventional DSR. The proposed approach highlights the effectiveness of dimensionality reduction techniques in enhancing routing decisions for resource-constrained WSNs.
DOI: http://doi.org/10.5281/zenodo.16948386
