CLASS-BASED MDP FOR IMPROVED MULTIMEDIA TRANSMISSION OVER LTE

This paper proposes an improved cross-layer control mechanism to efficiently stream videos to mobile users over an LTE network. A proxy-based filtering algorithm among scalable layers is considered to decide the number of SVC layers to transmit for each frame according to the communication conditions and to the class to which the video belongs to. The problem is cast in the context of Markov Decision Processes which allow the design of foresighted policies maximizing some long-term accumulated reward. Optimal actions to apply to the system are obtained by reinforcement learning. The proposed solution is implemented in an LTE simulation platform. Experiments show the performance of the proposed class-based layer filtering algorithm for a single video transmission and its robustness to content changes. 1 Index Terms-- Video, 4G mobile communication, optimization 1. INTRODUCTION Today, we are facing an explosion of the video traffic on wireless network due to the proliferation of multimedia-friendly portable devices [1]. This trend is expected to intensify further in the near future. Even if the rates provided by nextgeneration mobile networks are increasing, the demand for high-quality multimedia content is growing faster [2]. Network congestion will be the main cause of QoS deterioration in the mobile network [3]. It may occur in the wireless part, due to the nature of the wireless channel and the limited bandwidth, or in the backhaul part. Service providers need to find solutions to deliver multimedia contents in the most efficient way to provide users with the best quality of experience (QoE) while accounting for scarce network resources.