基于光纤-无线网络的协同计算卸载算法

A collaborative computation offloading algorithm based on fiber-wireless networks

随着无源光网络的发展,光纤-无线网络能同时支持集中式云和边缘云计算技术,成为一种具有发展前景的网络结构。但是,现有的基于光纤-无线网络的任务协同计算卸载研究主要以最小化移动设备的能耗为目标,忽略了实时性高的任务的需求。针对实时性高的任务,提出了以最小化任务的总处理时间为目标的集中式云和边缘云协同计算卸载问题,并对其进行形式化描述。同时,通过将该问题归约为装箱问题,从而证明其为NP难解问题。提出一个启发式协同计算卸载算法,该算法通过比较不同卸载策略的任务处理时间,优先选择时间最短的任务卸载策略。同时,提出一个定制的遗传算法,获得一个更优的任务卸载策略。实验结果表明,与现有的算法相比,本文提出的启发式算法得到的任务卸载策略平均减少4.34%的任务总处理时间,而定制的遗传算法的卸载策略平均减少18.41%的任务总处理时间。同时,定制的遗传算法的卸载策略与本文提出的启发式算法相比平均减少14.49%的任务总处理时间。

With the development of passive optical networks, the fiber-wireless (FiWi) network is envisioned to be a promising network architecture for supporting the centralized cloud computing (CCC) and mobile edge computing (MEC) simultaneously. However, existing work that focuses on collaborative computation offloading (CCO) based on FiWi network, aims at minimizing the energy consumption of mobile devices, and ignores the demands of high real-time tasks. Therefore, regarding high real-time tasks, we present a centralized cloud and edge cloud collaborative computation offloading problem, which aims to minimize the total processing time of the computation tasks, as well as its formalized description. It proves to be NP-hard by reducing it to a bin packing problem, and the offloading strategy with shortest time will be selected. Two algorithms are proposed as our solutions, i.e., a heuristic collaborative computation offloading algorithm (HCCOA) and a genetic algorithm for collaborative computation offloading (GA4CCO). The HCCOA chooses the strategy with the shortest time via comparing the total processing time among different computation offloading strategies. And the GA4CCO is to get an optimal or suboptimal strategy. Experimental results show that the HCCOA and GA4CCO can reduce the total processing time of the obtained task offloading strategy by 4.34% and 18.41% on average, respectively. In addition, the GA4CCO can reduce the total processing time of the obtained task offloading strategy by 14.49% in comparison to the HCCOA.