Satellite telemetry, tracking, and command (TT&C) technology plays a critical role in maintaining stable operation and emergency scheduling in mega-satellite networks. However, due to the high-speed movement of satellites, the intermittent connection between the satellite and the ground station creates a dynamic and complex visibility period, leading to temporal resource utilization conflicts during the TT&C mission scheduling process. These conflicts can further exacerbate real-time response for emergency TT&C missions in large-scale satellite networks. To address this issue, we explore the time-aware dynamic characteristics of emergency TT&C missions and their impact on the scheduling time of routine missions. Then we propose an efficient method for reducing resource utilization conflicts based on Dynamic Priority and Minimum Disturbance (DPMD). Building on this method, we formulate the scheduling process of emergency TT&C missions as a reinforcement learning decision problem suitable for dynamic real-time environments. Additionally, we introduce the DRLETMS algorithm (Emergency TT&C Missions Scheduling Algorithm based on Deep Reinforcement Learning) to achieve faster mission scheduling strategies in highly dynamic environments. Simulations demonstrate the superior efficiency of our proposed algorithm in large-scale scenarios compared to typical heuristic algorithms. Furthermore, we examine the impact of various ground station distributions on the real-time TT&C performance of satellite networks under the same satellite scale, which can provide theoretical guidance for designing mega-satellite TT&C networks in the future.