中文摘要：

针对城市道路交通信息采集传感器网络面向复杂交通参数协同采集的任务分配问题，将传感器网络映射为多Agent系统，以任务完成时间、节点能耗和网络负载平衡度作为评价函数，采用基于联盟的协同方法，构造传感器网络任务分配的非线性多目标优化模型。采用遗传模拟退火算法搜索最优联盟结构，实现任务分配策略优化。在道路交通信息采集实际场景中进行仿真实验，结果表明，遗传模拟退火算法能够有效地优化任务分配的联盟结构，与其他优化算法相比，优化的模型适应度函数值低，任务完成时间短，网络能耗小。该方法能够用于面向交通信息采集传感器网络的协同检测任务分配问题。

英文摘要：

Aiming at the task allocation problem for cooperatively acquiring complex urban traffic parameters in urban road traffic information acquisition sensor network, the sensor network is mapped into multi-agent system; taking the task execution time, node energy consumption and network load balance as the evaluation functions, adopting coalition based cooperative method, the nonlinear multi-objective optimization model of task allocation of sensor network is constructed. Genetic simulated annealing algorithm is used to search the optimal coalition model and the task allocation strategy optimization is achieved. The simulation experiments in the real environment of urban road traffic information acquisition were carried out. The simulation results show that the proposed algorithm has the ability to optimize the coalition model of task allocation effectively. Compared with other optimization algorithms, the fitness function value of the optimal coalition model is low, the task execution time is short and the network energy consumption is low. The proposed coalition model and algorithm are feasible for the task allocation problem of cooperative detection in wireless sensor networks, for urban traffic information acquisition.