改进的蝴蝶优化算法在精准灌溉中的应用

Improved Butterfly Optimization Algorithm Applications in Precision Irrigation

土壤湿度无线传感器网络(SMWSNs)应用在精准化的农田灌溉信息监测领域中,面临的主要挑战之一是在监测区域一定的条件下,节点覆盖面积达到最大的同时减少部署节点数量。针对这一问题,设计了一种新的自适应柯西变异蝴蝶优化算法(ACBOA),自适应权重因子提升了算法的局部寻优能力,柯西变异提高算法的全局搜索能力并增加其搜索空间。将所提出的算法与其他群智能优化算法进行比较,即蝴蝶优化算法(BOA)、人工蜂群算法(ABC)、果蝇优化算法(FOA)、粒子群优化算法(PSO),仿真结果表明:经过ACBOA优化后SMWSNs的覆盖率最高。最后,在台架测试平台上进行灌溉控制实验,验证了ACBOA优化覆盖后的SMWSNs采集土壤湿度信息的准确性,为农作物精准灌溉提供了科学依据。

Reducing the number of deployed nodes while maximizing the node coverage area under specific conditions of the monitoring area is one of the primary problems of soil moisture wireless sensor networks(SMWSNs)utilized in the field of precision farm irrigation information monitoring.An innovative adaptive cauchy variant butterfly optimization algorithm(ACBOA)is proposed in this work to solve this issue.The algorithm's local search performance is enhanced by the adaptive weight factor,while its global search performance and search space are expanded by the cauchy variation.The suggested approach is evaluated in comparison to four different swarm intelligence optimization algorithms:the butterfly optimization algorithm(BOA),artificial bee colony algorithm(ABC),fruit fly optimization algorithm(FOA),and particle swarm optimization algorithm(PSO).According to the simulation results,after ACBOA optimization,the SMWSNs have the maximum coverage rate.In order to provide a scientific foundation for precise crop irrigation,irrigation control tests were lastly carried out on a bench test bench to confirm the accuracy of the soil moisture data gathered by the SMWSNs following ACBOA optimized coverage.