MamBRA: session-level bandwidth prediction for adaptive video streaming using selective state space models
Abstract
Live streaming is the real-time transmission of video content to an audience as it is simultaneously recorded. This technology is frequently utilized for applications such as covering live events and facilitating video calls. By dynamically modifying the video quality to match network conditions and device capabilities, adaptive video streaming provides improved Quality of Experience (QoE). However, as user demands for high quality and low latency increase, using efficient video streaming systems is becoming increasingly challenging. In addition to taxing network resources, the increase in video traffic is lowering video quality. Deep and transformer learning algorithms use data-driven methods to optimize video delivery, enhance QoE, and lessen network congestion in order to overcome these obstacles. Mamba utilizes the efficient linear complexity of selective state space model (SSM) mechanism to process data sequences more effectively. This paper evaluates an adaptive video streaming framework (MamBRA) based on Mamba for session-level bandwidth prediction. The model is trained in a supervised time-series manner on disjoint user sessions to prevent information leakage and preserve temporal structure. During inference, it leverages the linear state-space formulation of Mamba to efficiently generate stable bandwidth predictions within each session. Experimental results demonstrate competitive prediction-error reductions in comparison with four baseline methods: GRU, LSTM, RNN, and Transformer, while providing lower inference latency and reduced memory footprint. Furthermore, MamBRA’s bandwidth predictions yield more consistent QoE scores than those of GRU-BBA and Oppugno. These findings position selective state space modeling as a competitive, compact bandwidth-prediction component for future adaptive streaming systems.