Efficiency-Aware Dynamic Service Pricing Strategy for Geo-Distributed Fog Computing
Efficiency-Aware Dynamic Service Pricing Strategy for Geo-Distributed Fog Computing
复制标题
DOI：
10.1109/tsusc.2022.3173787
复制
发表时间：
2022-10
影响因子：
3.9
通讯作者：
Jianwen Xu;K. Ota;M. Dong;Ai-Chun Pang
中科院分区：
文献类型：
--
作者：
Jianwen Xu;K. Ota;M. Dong;Ai-Chun Pang
雾计算为解决物联网时代的大数据问题提供了新的思路。有了雾，我们可以节省大量的远距离传输时间，从而提高网络服务的效率。然而，要将雾计算从一种技术转变为一种服务，首先需要处理好雾中用户与服务提供商之间的交易关系。在本文中，我们设计了一种效率感知的动态服务定价策略，以优化雾计算中用户和提供商的收益。在建模中，我们设计了一个基于Stackelberg竞争的模型，将供应商视为市场领导者，将每个个体用户视为追随者。这种模式下的用户关心的是如何获得最具成本效益的服务。供应商注重充分利用地理分布的特点与多客户定价。在性能评估部分，我们使用真实世界的数据集进行实验，以模拟雾定价中供需之间的持续协商过程。结果表明，本文提出的策略既能解决双目标优化问题，又能建立稳定的双方贸易关系。
Fog computing provides new ideas for solving big data problems in the Internet of Things (IoT) era. With fog, we can save much time on long-distance transmission, thereby increasing the efficiency of network service. However, to transform fog computing from a technology to a service, we first need to properly handle the trading relationship between users and service provider in fog. In this paper, we design an efficiency-aware dynamic service pricing strategy to optimize the payoffs of both users and provider in fog computing. In the modeling, we design a Stackelberg competition-based model while regarding provider as the market leader, and each individual user as a follower. Users in this model care about how to obtain the most cost-effective services. And provider pays attention to taking full advantage of the geo-distributed characteristic in setting prices with multiple customers. In the performance evaluation part, we carry out experiments using real-world datasets to simulate this continuous negotiation process between supply and demand in fog pricing. The results show that our strategy can solve the dual-objective optimization problem while establishing a stable trading relationship between the two sides.