当前位置: X-MOL 学术IEEE Trans. Wirel. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Offloading Decision in Edge Computing for Continuous Applications under Uncertainty
IEEE Transactions on Wireless Communications ( IF 8.9 ) Pub Date : 2020-09-01 , DOI: 10.1109/twc.2020.3001012
Wei Chang , Yang Xiao , Wenjing Lou , Guochu Shou

Edge computing (EC) is an emerging paradigm to push sufficient computation resources towards the network edge, improving application performance significantly by offloading applications to the edge computing node. We investigate continuous application offloading decision in EC, for which it is uncertain how users operate continuous applications and how long continuous applications last before completion. That means some characteristics of continuous applications, e.g., the number of user operations, the uploading and downloading data size for offloading computation of each user operation, and the number of central processing unit (CPU) cycles required to execute computation of each user operation, are unknown when making offloading decision. In this scenario, an energy consumption constrained average response time minimization problem among multiple users for continuous applications under uncertainty is formulated. To tackle this problem, we propose the Response Time-Improved Offloading algorithm with Energy Constraint (RTIOEC) to make offloading decision with fewer characteristics of applications. The evaluation results show that the RTIOEC algorithm achieves comparatively short average response time of continuous applications while satisfying the energy consumption constraint with a predefined upper bound of violation probability. Our results demonstrate the practicality of the RTIOEC algorithm in offloading decision in EC for continuous applications under uncertainty.

中文翻译:

不确定性下连续应用边缘计算的卸载决策

边缘计算 (EC) 是一种新兴范式,可将足够的计算资源推向网络边缘,通过将应用程序卸载到边缘计算节点来显着提高应用程序性能。我们调查了 EC 中的连续应用卸载决策,为此不确定用户如何操作连续应用以及连续应用在完成之前持续多长时间。这意味着连续应用程序的一些特征,例如用户操作的数量,每个用户操作卸载计算的上传和下载数据大小,以及执行每个用户操作计算所需的中央处理器(CPU)周期数,在做出卸载决定时是未知的。在这种情况下,针对不确定性下的连续应用,提出了多用户间能耗受限的平均响应时间最小化问题。为了解决这个问题,我们提出了具有能量约束的响应时间改进卸载算法(RTIOEC)来做出具有较少应用特征的卸载决策。评估结果表明,RTIOEC 算法实现了连续应用的平均响应时间相对较短,同时满足具有预定义违规概率上限的能耗约束。我们的结果证明了 RTIOEC 算法在不确定性下连续应用的 EC 卸载决策中的实用性。我们提出了具有能量约束的响应时间改进卸载算法(RTIOEC),以做出具有较少应用特征的卸载决策。评估结果表明,RTIOEC 算法实现了连续应用的平均响应时间相对较短,同时满足具有预定义违规概率上限的能耗约束。我们的结果证明了 RTIOEC 算法在不确定性下连续应用的 EC 卸载决策中的实用性。我们提出了具有能量约束的响应时间改进卸载算法(RTIOEC),以做出具有较少应用特征的卸载决策。评估结果表明,RTIOEC 算法实现了连续应用的平均响应时间相对较短,同时满足具有预定义违规概率上限的能耗约束。我们的结果证明了 RTIOEC 算法在不确定性下连续应用的 EC 卸载决策中的实用性。评估结果表明,RTIOEC 算法实现了连续应用的平均响应时间相对较短,同时满足具有预定义违规概率上限的能耗约束。我们的结果证明了 RTIOEC 算法在不确定性下连续应用的 EC 卸载决策中的实用性。评估结果表明,RTIOEC 算法实现了连续应用的平均响应时间相对较短,同时满足具有预定义违规概率上限的能耗约束。我们的结果证明了 RTIOEC 算法在不确定性下连续应用的 EC 卸载决策中的实用性。
更新日期:2020-09-01
down
wechat
bug