Abstract: In order to prolong the lifetime，reduce network energy consumption and balance the network load effectively，a model task allocation model in wireless sensor network are proposed.This method describes the adaptive selection probability combined with niche technology，three-three crossover operator and the target bit mutation operator.This improved GA algorithm keeps the population’s convergence and increases the efficiency of local and global search capability.Simulation results show that the proposed algorithm provides a good balance of local solutions and global exploration，which results in a great decrease of execution time and a steady balance of network load.

Key words: wireless sensor network, task allocation, genetic algorithm

摘要： 为了延长网络生命周期，减少网络能量消耗和均衡网络负载，构造了无线传感器网络任务分配的模型，提出与小生境技术相结合自适应选择概率、三—三交叉算子和目标位变异算子，改进GA算法在很好地保持种群收敛性的同时，提高了算法的局部和全局搜索能力。仿真实验结果表明，该分配算法在局部求解与全局探索之间取得了较好的平衡，能有效减少无线传感器网络的计算时间和网络能耗，并有效地均衡网络负载。

关键词: 无线传感器网络, 任务分配, 遗传算法