Empirical Analysis of Cloud-Mobile Computing Based VVoIP with Intelligent Adaptation

This paper introduces a private cloud with SaaS service to realize a real-time video/voice over IP (VVoIP) in cloud mobile computing system, called Cloud-VVoIP. In order to optimize traffic flow of video/voice streaming, adaptive network-based fuzzy inference system (ANFIS) together with particle swarm optimization (PSO) has been employed to off-line tune seamless handoff and network traffic flow. Besides the performance of Cloud-VVoIP is evaluated and a comparison of this approach and the traditional peer-to-peer VVoIP. A flexible usage for users is that they do not need to know what real IP assigned for both sides to dial a phone call and web-based browsing is available. Next, smart phone with Android APP is applicable to attach Cloud-VVoIP to yield the cost-effective for users. Third, VVoIP program is mainly installed in the private cloud, rather than user devices, so that the power consuming in battery is reduced dramatically at user devices. Finally, the stress test has been performed successfully to analyze the system efficiency of Cloud-VVoIP on the resources allocation of CPU, memory, bandwidth and disk. Furthermore, a composite index is capable of indicating Flash Medium Server (FMS) performance during the operation of Cloud-VVoIP.