Towards efficient and fair resource trading in community-based cloud computing

• We create a distributed market-oriented framework for cloud resource trading.
• We propose a multiagent technique for budget-free optimal resource allocation.
• We propose a new directed hypergraph model for budget-limited resource trading.
• We develop effective heuristic-based protocols for budget-limited resource trading.

In this paper, we investigate the resource trading problem in a community-based cloud computing setting where multiple tenants communicate in a peer-to-peer (P2P) fashion. Enabling resource trading in a community cloud unleashes the untapped cloud resources, thus presents a flexible solution for managing resource allocation. However, finding an efficient and fair resource allocation is challenging mainly due to the heterogeneity of tenants. Our work first develops a market-oriented model to support resource negotiation and trading. Based on this model, we adopt a multiagent-based technique that allows a group of autonomous tenants to reach an efficient and fair resource allocation. Further, when budget constraint presents, we propose a directed hypergraph model to facilitate resource trading amongst heterogeneous tenants. We analyze the application of the directed hypergraph model to trading decision making, and design a series of heuristic-based resource trading protocols for both budget-unaware and budget-aware scenarios. The performances of the proposed protocols are validated through simulations. The results are in tune with the theoretical analysis and provide insights into practical application issues.