- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
The distribution of computational resources in a Cloud Computing platform is a complex process with several parameters to consider such as the demand for services, available computational resources and service level agreements with end users. Currently, the state-of-the-art presents centralized approaches derived from previous technologies related to cluster of servers. These approaches allocate computational resources by means of the addition/removal of (physical/virtual) computational nodes. However, virtualization technology currently allows for research into new techniques, which makes it possible to allocate at a lower level. In other words, not only is it possible to add/remove nodes, but also to modify the resources of each virtual machine (low level resource allocation). Thus, agent theory is a key technology in this field, allowing decentralized resource allocation. This innovative approach has undeniable improvements such us computational load distribution and reduced computation time. The evaluation was carried out through experiments in a real Cloud environment, thus proving the validity of the proposed approach
Thus, the architectural model developed in this research satisfies the objectives proposed at the beginning of the work. Specifically, this research validates that a VO-based architecture of MAS is able to act properly to monitor and control a CC environment. Also, a distributed RA algorithm was designed. The proposed approach for the allocation of resources is carried out on each node of the CC, and ultimately permits an improvement in the efficiency of the CC environment, minimizing the percentage of underused resources. Finally, both the MAS and the algorithm were tested in a real environment, making it easy to evolve both to a CC production. However, we would propose the following lines of work that will be undertaken over a short and long term basis as a complement to the initially established objectives: (i) to extend the distribution algorithms for computational resources using two main objectives. First, we aim to adaptthe proposed dynamic self-adapting modelto then include all of the software layers of a CC system, including the persistence layer.And,(ii)to extendtheproposedadaptationmodel to include other infrastructure products, especially those that allow high-performance computing centered on the massive analysis of data.