How to process the big data generated in large IoT networks is still challenging current techniques. To date, a lot of network clustering approaches have been proposed to improve the performance of data aggregation in IoT. However, most of them focus on partitioning networks with static topologies, and thus they are not optimal on handling the case with moving objects in the networks. Moreover, as the best of knowledge, none of them has ever considered the performance of following computing in edge servers. To improve these problems, in this work, we propose a highly efficient IoT network dynamic clustering solution in edge computing using deep reinforcement learning (DRL). Our approach can both fulfill the data communication requirements from IoT networks and load-balancing requirements from edge servers, and thus provide a great opportunity for future high performance IoT data analytics. We implement our approach by Deep Q-learning Network (DQN) model, and our preliminary experimental results show that the DQN solution can achieve higher score in cluster partitioning compared with the current static benchmark solution.