Epidemic source detection is one of the most crucial problems in statistical inference. For example, currently, the debate continues to reveal when and where the first spread of COVID-19 occured. For this problem, most of the works have assumed a static network topology, that is, the connections between nodes do not change over time. This is impractical because many nodes have some mobility in the network, or the connections can be changed. In this paper, we focus on the dynamic network, in the sense that the node connectivity varies over time. We first introduce a simple dynamic model, named k-flip dynamic such that
k
>
0
connections in the network may be changed with some probability at each time. Next, we design a proper estimation algorithm using some investigation for the contact information between infected nodes, named dynamic network source estimation (DNSE)(k) for the dynamic model. We perform various simulations for the algorithm compared to several existing source estimation methods. Our results show that the proposed algorithm outperforms and is efficient for finding the epidemic source compared to other methods. Further, we see that the detection probability for our proposed algorithm can be above 45% when we use budget to investigate the contact information from the infected nodes under some practical setting of k.