Knowledge-based Event Workload Prediction for Dynamic Resource Reallocation in Cloud Application Performance Management

• Main Authors: Yu-Fan Chen, 陳昱帆
• Other Authors: Yea-Li Suen
• Format: Others
• Language: en_US
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/70184922784538853020

碩士 === 國立臺灣大學 === 資訊管理學研究所 === 101 === In Application Performance Management (APM), the most common problem encountered by the administrators of many network service providers is how to sustain performance targets for the applications. Cloud computing offers the possibility to provide the resources on demand as Utility Computing. The internet services with highly changing demand can benefit from the implementation of cloud services rapid elasticity technology as live sport game broadcasting or online ticket booking system. We expect that specific events will cause significant increase the demand of applications. Cloud computing is elasticity and burstability, so it can help the internet services acquire necessary resources under the heavy variation of demand. However, system reallocation will take a resizing time and bring some cost and risk. The external demand prediction is an important component in dynamic resource allocation to provide target performance guarantees in cloud. In this work, we first study the characteristic of the application’s workload. We find out some important characteristic among the target traffic workload and the correlation between time and external demand. Base on the observation above, we use three simple statistical models in workload prediction at runtime as an input to dynamic resource resizing in cloud. The results show that more effective ways are needed to better capture the dynamics and unpredictability of the workload to improve prediction accuracy. Then, we propose a learning-based prediction model and the real-time algorithm to forecast the external demand for this class of cloud applications. We use the learning method to understand the event knowledge based on the behaviors of historical events and consider the online measurements to predict the trend of external demand in next control period. We also develop safety margin-based prediction schemes to avoid the under-estimation errors of prediction. Finally, we choose two well-known methods to compare the performance result with our learning method. Through the comparison, we can adjust the approach and predict the external demand more accurate We will provide several insights for those cloud service provider. We hope when dealing with this class of application in future, they could also provide reliable service for their users.