A Novel Predictive and Self -- Adaptive Dynamic Thread Pool Management

Multithreading is an efficient technique commonly used to maximize the performance of CPU. One of the most important challenges in multithreading is thread pool management. It needs to retain a proper number of threads in the pool, which minimizes the response time and maximizes the resource utilization. To achieve this goal, this paper proposes a novel trendy exponential moving average (TEMA) scheme for predicting the number of threads. Also, a prediction-based thread pool management scheme is proposed which adjusts the idle timeout period and thread pool size to effectively adapt the system to the changing environment. The experiment results show the effectiveness of the proposed approach in terms of response time and CPU usage, compared with the existing prediction-based scheme and Sun watermark.