An Energy and Robustness Adjustable Optimization Method of File Distribution Services

摘要

This paper focuses on the energy consumption of content distri-bution and sharing services that have a significant percentage of traffic on the Internet today. Taking the "energy saving" and "network robustness in traditional traffic engineering" as the dual optimization objects, a weighted green factor is introduced and an optimization model called ETE-FD (Energy-Aware Traffic Engineering File Distribution) is established. The model takes into account the overlay layer and the network layer, end systems and routing nodes. A multi-machine parallel algorithm based on dual decomposition and sub-gradient projection is proposed. Even with more than 1000 nodes, the solution process is still fast. Experiments show that the adjustment range of ETE-FD for robustness can reach 58.18%, and the adjustment range of ener-gy consumption can reach 47.09%. In the pure pursuit of per-formance (robustness) optimization object, the average download time has increased by nearly 90% compared to optimizing only energy consumption object. In the case of pure energy-saving optimization object, the power consumption of ETE-FD is about 10.8% lower than that of EOCFD (Energy-optimal collabora-tive file distribution). If set to optimize only robustness, it is about 43.9% higher than EOCFD.