Toward Transcoding as a Service in a Multimedia Cloud: Energy-Efficient Job-Dispatching Algorithm

Toward Transcoding as a Service in a Multimedia
Cloud: Energy-Efficient Job-Dispatching Algorithm

Abstract— Toward Transcoding as a Service in a Multimedia. Cloud: Energy-Efficient Job-Dispatching AlgorithmWe investigate the energy-efficient job-dispatching algorithm for transcoding as a service < Final Year Projects 2016 > TaaS in a multimedia cloud. We aim to minimize the energy consumption of service engines in the cloud while achieving low delay for TaaS. We formulate the job-dispatching problem as a constrained optimization problem under the framework of Lyapunov opti-mization. Using the drift-plus-penalty function, we propose an online algorithm that dispatches the transcoding jobs to service engines, with an objective to Reduce Energy consumption while achieving the QUEue STability (REQUEST). We first characterize the fundamental tradeoff between energy consumption and queue delay for the REQUEST algorithm numerically and obtain its performance bound theoretically. Second, we study the robustness of the REQUEST algorithm, with numerical results indicating that the REQUEST algorithm is robust to the inaccuracy of estimat-ing the transcoding time.