Performance Measurement using Hybrid Prediction Model in Ubiquitous Computing

Ubiquitous computing devices recently are increasing requirements of high-level performance management automation, and therefore a system management is changing from a conventional central administration to autonomic computing. Many research centers are conducting various studies on self-healing method. However, most existing research focuses on healing after a system error has already occurred. In order to solve this problem, a prediction model is required to recognize operating environments and predict error occurrence. In this paper, we present how to predict the performance of system using hybrid prediction model. This hybrid prediction models adopts a selective healing model according to system context, for self-diagnosis and prediction of errors when using the four algorithms. In this paper, we evaluate the prediction time of the hybrid prediction model prototype and the performance of the target system’s workload. In addition, the prediction is compared with existing research and the effectiveness is demonstrated by experiment.