In this paper, we propose a digital twin (DT)-assisted resource demand prediction scheme to enhance prediction accuracy for multicast short video streaming. Particularly, we construct user DTs (UDTs) for collecting real-time user status, including channel condition, location, watching duration, and preference. A reinforcement learning-empowered K-means++ algorithm is developed to cluster users based on the collected user status in UDTs, which can effectively employ the mined users' intrinsic correlation to improve the accuracy of user clustering. We then analyze users' video watching duration and preferences in each multicast group to obtain the swiping probability distribution and recommended videos, respectively. The obtained information is utilized to predict radio and computing resource demand of each multicast group. Initial results demonstrate that the proposed scheme can effectively abstract multicast groups' swiping probability distributions for accurate resource demand prediction.

翻译：本文提出了一种数字孪生（DT）辅助的资源需求预测方案，以提升多播短视频流媒体的预测精度。具体而言，我们构建用户数字孪生体（UDTs）用于收集实时用户状态，包括信道条件、位置、观看时长和偏好。我们开发了一种基于强化学习的K-means++算法，根据UDTs中收集的用户状态对用户进行聚类，该方法能有效利用挖掘出的用户内在关联性以提高聚类精度。随后分析每个多播组中用户的视频观看时长与偏好，分别获取滑动概率分布与推荐视频。利用所得信息预测各多播组的无线及计算资源需求。初步结果表明，该方案能有效抽象多播组的滑动概率分布，实现精准的资源需求预测。