QoE-Aware Resource Allocation For Crowdsourced Live Streaming: A Machine Learning Approach

In the last decade, empowered by the technological advancements of mobile devices and the revolution of wireless mobile network access, the world has witnessed an explosion in crowdsourced live streaming. Ensuring a stable high-quality playback experience is compulsory to maximize the viewers’ Quality of Experience and the content providers’ profits. This can be achieved by advocating a geo-distributed cloud infrastructure to allocate the multimedia resources as close as possible to viewers, in order to minimize the access delay and video stalls. Additionally, because of the instability of network condition and the heterogeneity of the end-users capabilities, transcoding the original video into multiple bitrates is required. Video transcoding is a computationally expensive process, where generally a single cloud instance needs to be reserved to produce one single video bitrate representation. On demand renting of resources or inadequate resources reservation may cause delay of the video playback or serving the viewers with a lower quality. On the other hand, if resources provisioning is much higher than the required, the extra resources will be wasted. In this thesis, we introduce a prediction-driven resource allocation framework, to maximize the QoE of viewers and minimize the resources allocation cost. First, by exploiting the viewers’ locations available in our unique dataset, we implement a machine learning model to predict the viewers’ number near each geo-distributed cloud site. Second, based on the predicted results that showed to be close to the actual values, we formulate an optimization problem to proactively allocate resources at the viewers’ proximity. Additionally, we will present a trade-off between the video access delay and the cost of resource allocation. Considering the complexity and infeasibility of our offline optimization to respond to the volume of viewing requests in real-time, we further extend our work, by introducing a resources forecasting and reservation framework for geo-distributed cloud sites. First, we formulate an offline optimization problem to allocate transcoding resources at the viewers’ proximity, while creating a tradeoff between the network cost and viewers QoE. Second, based on the optimizer resource allocation decisions on historical live videos, we create our time series datasets containing historical records of the optimal resources needed at each geo-distributed cloud site. Finally, we adopt machine learning to build our distributed time series forecasting models to proactively forecast the exact needed transcoding resources ahead of time at each geo-distributed cloud site. The results showed that the predicted number of transcoding resources needed in each cloud site is close to the optimal number of transcoding resources