期刊
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
卷 23, 期 1, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3465237
关键词
Open market environments; resource allocation; reinforcement learning; real-time pricing
Open market environments are characterized by dynamic participants and uncertainties in supply and demand. Vendors aim to optimize their revenue by adjusting selling prices according to market demand. We propose a real-time pricing approach that uses a priority-based fairness mechanism to allocate resources in open market environments. Experimental results show that our approach outperforms existing methods in maximizing vendors' revenue.
Open market environments consist of a set of participants (vendors and consumers) that dynamically leave or join the market. As a result, the arising dynamism leads to uncertainties in supply and demand of the resources in these open markets. In specific, in such uncertain markets, vendors attempt to maximise their revenue by dynamically changing their selling prices according to the market demand. In this regard, an optimal resource allocation approach becomes immensely needed to optimise the selling prices based on the supply and demand of the resources in the open market. Therefore, optimal selling prices should maximise the revenue of vendors while protecting the utility of buyers. In this context, we propose a real-time pricing approach for resource allocation in open market environments. The proposed approach introduces a priority-based fairness mechanism to allocate the available resources in a reverse-auction paradigm. Finally, we compare the proposed approach with two state-of-the-art resource allocation approaches. The experimental results show that the proposed approach outperforms the other two resource allocation approaches in its ability to maximise the vendors ' revenue.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据