Tradeoff between energy and user experience for multimedia cloud computing

Abstract Cloud computing provides an effective approach to deliver multimedia services to end users with the desired user quality of experience (QoE). However, cloud-based multimedia applications require many of servers and consume huge energy. To reduce energy consumption, a multimedia service provider (MSP) should balance the energy and QoE. In this paper, a theoretic model is developed to explore the trade-off between energy consumption and QoE for multimedia cloud. Based on objective factor, a QoE quantifying model is proposed. Employing Lyapunov Optimization techniques, an optimal control framework is designed and analyzed to make energy and QoE decisions in MSPs. An approximate online algorithm (EUE-RP) is proposed with the explicitly provable performance upper bound. Extensive experiments have been conducted to verify the effectiveness of EUE-RP algorithm in the practical settings. The algorithm can guarantee desired QoE and reduce energy consumption, even without any information about the future fluctuation of user demands.