Optimization of transmission power control in wireless sensor networks using genetic algorithms and NS-3 simulation

This research investigates the optimization of transmission power control in Wireless Sensor Networks (WSNs) using Genetic Algorithms (GAs), with a focus on enhancing energy efficiency and extending network lifetime. WSNs are widely used for various applications such as environmental monitoring and healthcare, but their performance is often limited by the energy constraints of sensor nodes. Efficient power control is vital to balance energy consumption with communication reliability. The primary objective of this study was to evaluate the effectiveness of GA-based power control in comparison to traditional methods like Fixed Power and Random Power in terms of energy consumption, packet delivery ratio (PDR), and network lifetime. NS-3, a network simulation tool, was employed to simulate WSNs consisting of 100 sensor nodes distributed in a 500x500 meter area. The GA-based approach dynamically adjusts the transmission power based on network conditions, aiming to optimize energy usage while ensuring reliable communication. The results revealed that the GA-based method slightly reduced energy consumption and extended network lifetime compared to the other methods. However, statistical analysis through ANOVA tests showed no significant difference in energy consumption (p-value = 0.817), packet delivery ratio (p-value = 0.638), or network lifetime (p-value = 0.327) between the three approaches. In conclusion, while the GA-based method provided marginal improvements in energy efficiency and network lifetime, the differences were not statistically significant. These findings suggest that GA-based power control can be a useful tool in optimizing WSNs, but its impact may be limited unless combined with other network optimization techniques. Future research should explore hybrid methods combining GA with other strategies like Particle Swarm Optimization (PSO) or Ant Colony Optimization (ACO) to further enhance performance in dynamic network conditions.