Energy-Efficient Routing Protocols in Wireless Sensor Networks for IoT Applications: A Machine Learning Approach Using XGBM and Color Harmony Algorithm

Energy efficiency is a central constraint in wireless sensor networks (WSNs) used for Internet of Things (IoT) applications because sensor nodes have limited batteries, processing capacity, and communication bandwidth. This study combines eXtreme Gradient Boosting (XGBM) with the Color Harmony Algorithm (CHA) to predict energy-efficient paths and optimize model and routing parameters. The analysis uses 58,847 validated network-event records generated with NS-3 and a custom Python simulator; the Intel Berkeley Research Lab sensor trace was used only as an external range check. In a 50-run simulated evaluation, the proposed configuration showed an 18% reduction in energy consumption, a 22% increase in network lifetime, a 10% improvement in packet delivery ratio, a 20% reduction in latency, and a 25% improvement in throughput relative to the configured baselines. Inferential results for energy consumption, network lifetime, packet delivery ratio, and latency are reported with confidence intervals, p-values, and standardized effect sizes; throughput is reported descriptively because paired run-level throughput values were not retained. These simulation-derived findings indicate that XGBM–CHA can support adaptive routing and efficient resource use in IoT-oriented WSNs, while field validation remains necessary before deployment claims can be made.