Một Mô Hình Học Tăng Cường Cho Vấn Đề Điều Chỉnh Tự Động Tài Nguyên Trong Điện Toán Đám Mây Dựa Trên Fuzzy Q-Learning

Abstract

Cloud computing has become one of the most prominent trends in the IT industry. In particular, the problem of autoscaling (allocation /deallocation) of resources is a great challenge, greatly affecting the efficient exploitation of resources should always be subject to research in recent times. Most of the algorithms for auto-scaling resources in the cloud computing are based on threshold mechanisms. However, threshold-based techniques are not flexible and adaptable when there are major fluctuations in resource requirements, especially in the cloud computing environment. In this paper, we built a model for auto-scaling resources based on fuzzy logic and reinforcement learning-Fuzzy Q-Learning to increase adaptability as well as the ability to immediately respond to resource requirements in dynamic allocation/deallocation of resources in the direction of load balancing.