Auto-scalable and fault-tolerant load balancing mechanism for cloud computing based on the proof-of-work election

Xiaoqin Feng, Jianfeng Ma, Shaobin Liu, Yinbin Miao, Ximeng Liu

Abstract: Load balancing mechanism in technologies such as cloud computing has provided a huge opportunity for the development of large-scale projects. Although the conventional view is to build mechanisms that adopt a dynamic load balancing strategy, existing strategies cannot automatically scale platform (network) servers (nodes) to adapt for dynamic requests, but only guarantee load balancing for the pre-deployed nodes, thereby increasing resource consumption and decreasing networks’ efficiency. We contend that existing load balancing mechanisms are inadequate for deploying dynamic applications. In this regard, we first adopt both load balancing and cloud computing virtualization technologies to modularly design a load balancing mechanism that provides a dynamically auto-scalable solution for large-scale and dynamic computing scenarios. Furthermore, we adopt the proof-of-work consensus, for a novel use during the lifecycle of master nodes in case of system failure caused by a failed master node, to demonstrate a fault-tolerant load balancing mechanism. We theoretically evaluate the security requirement of our mechanism and analyze its performance. Experimental results show that the mechanism supports auto-scalability and has a better performance compared to existing mechanisms such as the ordinary cluster.