Accurate localization of nodes is one of the supporting technologies for the applications of wireless sensor networks（WSNs）.Considering the proportion of beacons in the network

localization algorithm based on sub-anchors and BP neural network is proposed to virtually increase the number of anchor node that are used for localization

and the method of finding appropriate sub-anchor node is brought up through the virtual nodes to increase localization precision.Such algorithm utilizes not only the parallelism of neural networks but also the hops of the nodes

so that it is simple and easy to achieve in the hardware.The simulation result shows the effectiveness of using virtual nodes to determine sub-anchor node

and indicates that sub-anchor node and BP neural network localization algorithm could greatly improve the localization precision of the unknown nodes and reduce the costs of WSNs.