A Dynamic Combinatorial Double Auction Model for Cloud Resource Allocation

作者：Li, Qihui^*; Jia, Xiaohua; Huang, Chuanhe; Bao, Haizhou

来源：IEEE Transactions on Cloud Computing, 2023, 11(3): 2873-2884.

DOI：10.1109/TCC.2022.3231249

• Cloud computing
• combinatorial double auction
• truthful mechanism
• greedy heuristics
• winner determination problem
• resource allocation

For the cloud market, we proposed a Dynamic Combinatorial Double Auction (DCDA) model to improve the social welfare and resource utilization. In the model, cloud-agents represent cloud service providers, and user-agents represent cloud users. They bid for various combinations of resources in a dynamic environment. To overcome the computational complexity of combinatorial auctions, we employed a greedy approximation method to solve the winner determination problem together with a truthful payment scheme. The proposed model is proven to be approximately efficient, incentive compatible, individually rational, and budget-balanced. Considering both parties' interests and the relative scarcity of cloud resources, this model also ensures fairness and balances resource allocation.

• 单位
  武汉大学