Research And Implementation Of Mobile Cloud Computing Based Streaming Media QoE Optimization

With the rapid development of mobile Internet and wireless communications,as well as the rapid spread of the smartphones,the customer demand for watching high quality video is increasing explosively.DASH(Dynamic Adaptive Streaming over HTTP),which turns out the first international standard on adaptive streaming,has been the dominant technology on many adaptive streaming services.DASH can dynamically adjust the video bitrate according to the varying network conditions as well as users' requirement,thereby solving the problem of guaranteeing the users' QoE(Quality of Experience)as well as bandwidth efficiency throughout the strong time-varying network conditions.However,the traditional DASH does not consider the smartphone's feature of multiple interfaces and network access technologies.For the scenario where adjacent users are watching the same online video,the QoE expectation of each user will reduce due to the network available bandwidth competition among the group.Meanwhile,the traditional DASH only pays attention to the users' QoE expectation and neglect the significant energy consumption.In this paper,to solve the problem of network bandwidth competition among the group of adjacent users caused by the traditional DASH,a Device-to-Device(D2D)cooperative DASH was proposed to take full advantage of smartphones' feature of multiple interfaces.Based on the D2D connection among users to expand the user's own network available bandwidth,D2D cooperative DASH convert the competition into cooperation among users.The client side of the proposed system is implemented by a layered middleware infrastructure to provide the upper layer application with undifferentiated transparent function interface,and to make the proposed system compatible with major adaptive streaming players that support traditional DASH.Concerning the problem of achieving the competitive QoE at the cost of significant energy consumption,an adaptive energy efficient bitrate selection scheme in D2D cooperative DASH is proposed.Captain devices are selected based on the influences of QoE and energy consumption.Captain devices are in charge of additional link energy consumption.The experimental result shows that the proposed system can reduce energy consumption of up to 25%as compared with the existing systems while improving the competitive video quality.