QoE Assessment of Encrypted YouTube Adaptive Streaming for Energy Saving in Smart Cities

Video streaming has become one of the most prevalent mobile applications and uses a substantial portion of the traffic on mobile networks today. With the limited bandwidth of mobile networks, understanding the user perception of the quality (i.e., Quality of Experience or QoE) of video streaming services is thus paramount for content providers and content-delivery network providers to flexibly configure network bandwidth, video servers, routing devices, and other network resources to save energy in smart cities. Although various video QoE assessment approaches have been proposed using different key performance indicators (KPIs), they all essentially relate to a common parameter: bitrate. However, because YouTube has adopted hyper text transfer protocol over secure socket layer (HTTPS) as its adaptive video streaming method to better protect user privacy and network security, bitrate can no longer be obtained from encrypted video traffic via typical deep packet inspection. In this paper, we address this challenge by proposing a machine-learning-based bitrate estimation (MBE) approach to parse bitrate information from IP packet level measurements. First, we filter HTTPS YouTube traffic based on the previously established video server IP according to the data packet googlevideo field. Then, we identify the transmission mode according to the traffic characteristics of several previous packets. Next, we identify the bitrates and resolutions of HTTP Live Streaming and Dynamic Adaptive Streaming over HTTP modes according to the characteristics of video chunks. Finally, for evaluating the effectiveness of MBE, we have chosen the video Mean Opinion Score (vMOS) proposed by a leading telecom vendor as the QoE assessment framework, and have conducted comprehensive experiments to study the impact of bitrate estimation accuracy on its KPIs for the HTTPS YouTube video streaming service. Experimental results show that MBE is a feasible and highly effective QoE evaluation approach to flexibly configure network resources in smart cities.