一种基于帝企鹅差分算法的WSN覆盖优化

Coverage optimization of WSN based on Emperor Penguin Differential Algorithm

为了解决无线传感器网络覆盖优化智能算法中存在的局部最优、精度不高和收敛速度慢的问题,提出了一种改进群智能算法即帝企鹅差分算法(Emperor Penguin Difference Algorithm,EPDEA).EPDEA将种群初始化设置以及计算当前的个体适应度值,通过群聚行为不断进行位置更新,搜索比当前个体更佳的企鹅个体并进行替换,当最优值陷入局部最优状态时引入差分进化算法对个体进行变异、交叉、选择,直到满足最大迭代次数.EPDEA有效防止原算法陷入局部最优并增加原集群多样性.将EPDEA与灰狼改进算法在不同节点数情况下进行仿真,结果显示EPDEA可以在更快速收敛的同时达到接近97%的覆盖率,且传感器节点在空间分布下容纳度更优.研究表明,EPDEA可有效地优化WSN的节点分布,提高网络覆盖率,提升网络质量.

In order to solve the common problems of local optimization,low accuracy and slow convergence speed in intelligent algorithms for coverage optimization in Wireless Sensor Networks(WSN),an improved swarm intelligence algorithm,the Emperor Penguin Difference Algorithm(EPDEA),is proposed.EPDEA initializes the population and calculates the current individual fitness value,and continuously updates the location through the grouping behavior,searches for and replaces the penguin individual that is better than the current individual,when the optimal value falls into the local optimal state difference algorithm is introduced to mutate,crossover,and select individuals until the maximum number of iterations is met.The algorithm effectively prevents the original algorithm from falling into a local optimum and increases the diversity of the original cluster.EPDEA and the improved gray wolf algorithm are simulated under different number of nodes.The results show that EPDEA can reach a coverage rate of close to 97%under the condition of faster convergence,and the sensor nodes in this paper have better accommodation under the spatial distribution.Research shows EPDEA can effectively optimize the node distribution of Wireless Sensor Network,increase network coverage,and improve network quality.