基于混合式的松弛规划优化的鲁棒定位算法

Relaxation programming optimization based on hybrid robust localization algorithm

测距误差以及锚节点位置的不确定性给无线传感网络的节点定位提出挑战。为此,提出基于半定规划SDP(semidefinite programming)和二阶锥规划SOCP(second order cone programming)的混合式松驰规划求解定位问题的优化方案,记为R_SOCP+SDP。考虑测距误差和锚节点位置的不确定性,根据最大似然估计原则建立定位估计的鲁棒SOCP(RSOCP)、鲁棒SDP(RSDP)优化函数;分析SOCP与SDP间的关系,充分考虑SOCP的计算复杂度低、SDP的定位精度高的特点,建立R_SOCP+SDP凸优化函数;运用凸优理论中的松弛规划技术估计节点的位置。仿真结果表明,R_SOCP+SDP有效减少了定位误差,降低了计算复杂度。

Ranging measurement with errors and uncertainty anchor position challenges the node localization in sensor network . Therefore ,the hybrid‐relaxation programming optimization of localization method based on semi‐definite programming （SDP） and second order cone programming （SOCP） was proposed ,which named as R_SOCP＋SDP .Taking measurement errors and uncertainty anchor position into consideration ,the robust location optimal estimating function based on maximum likelihood esti‐mate theory was devised ,and the relation between SOCP and SDP was analyzed ,finally the convex optimal function of R_SOCP＋SDP was devised to solve the localization problem ,which benefited from the better accuracy of SDP and the lower complexity of SOCP .Simulation results show that the proposed R_SOCP＋SDP method can effectively reduce the computational complexi‐ty and improve the localization accuracy .