QoS-QoE Dataset - Predicting QoE Factors with Machine Learning (IEEE ICC 2018)

This page presents the dataset used in our ICC 2018 paper:
To build and evaluate QoS to QoE mapping functions, we have used a fully controllable simulation environment at both network and streaming levels. The simulation platform is based on the Adaptive Multimedia Streaming Simulator Framework (AMust) in NS3 which implements a HTTP client and server for LibDASH, one of the reference software of ISO/IEC MPEG-DASH standard.

Simulation parameters with AMust in NS3

On the star topology with a bottleneck link, as depicted in the figure above, we have simulated a large number of streaming scenarios varying the number of streaming clients and the bottleneck characteristics (capacity, delay, packet loss). After a month of simulations, we have obtained statistics for more than 69,129 video sessions with 51 features for each session. For each video session, we measure network and streaming level statistics:

ColumnNameTypeDescription
1RequestIDContextStreaming session identifier
2NbClientsContextMaximum number of streams competing on the bottleneck
3BottleneckBWContextCapacity of the bottleneck
4BottleneckDelayContextNetwork delay on the bottleneck
5BottleneckLossContextPacket loss on the bottleneck
6DASHPolicyContextDASH policy
7ClientResolutionContextClient screen resolution
8RequestDurationContextDuration of the stream
[9,13]TCPOut/InPacketQoS metricNumber of TCP packets (In and Out)
[10,14]TCPOut/InDelayQoS metricAverage delay experienced by TCP packets (In and Out)
[11,15]TCPOut/InJitterQoS metricAverage jitter experienced by TCP packets (In and Out)
[12,16]TCPOut/InPLossQoS metricPacket loss rate experienced by TCP packets (In and Out)
17TCPInputRetransQoS metricPacket retransmissions experienced by TCP
18StdNetworkRateQoS metricStandard deviation of the network rate
[19:27][0,5,10,25,50,75,90,95,100]
NetworkRate
QoS metricQuantiles for the network rate
28StdInterATimesReqQoS metricStd. dev. of inter-arrival times of segment requests
[29:37][0,5,10,25,50,75,90,95,100]
InterATimesReq
QoS metricQuantiles for inter-arrival times of segment requests
38StartUpDelayQoE metricInitial time at the client to start playing the video
39AvgVideoDownloadRateQoE metricAverage downloading rate for video segments
40StdVideoDownloadRateQoE metricStd. dev. of downloading rate for video segments
41AvgVideoBufferLevelQoE metricAverage video buffer length
42StdVideoBufferLevelQoE metricStd. dev. of video buffer length
43StallEventsQoE metricNumber of stall events
44RebufferingRatioQoE metricPortion of time spent in stall events
45StallLabelQoE metricCategorization of RebufferingRatio variable
46TotalStallingTimeQoE metricTotal duration of stall events
47AvgTimeStallingEventsQoE metricAverage duration of stall events
48AvgQualityIndexQoE metricAvg. normalized index of downloaded representations
49AvgVideoBitRateQoE metricAverage video bitrate consumed by the player
50AvgVideoQualityVariationQoE metricAverage variation of the video bitrate
51AvgDownloadBitRateQoE metricAverage download rate of video segments

The full dataset is available here: https://github.com/sassatelli/QoErouting

When writing a paper that uses this Code, we would appreciate that you cite the following papers: The simulation environment has also been used in our QoE-aware routing project: