Hybrid approach to design of storage attached network simulation systems
Simulators of real-world IT systems are gaining popularity today. However, as it often happens in the early stages of technological readiness, the same term can be understood as different things - from visualisation systems to multi-level multi-agent models. The critical feature of the simulation technology is the degree of trust, or proximity of resemblance of their behaviour to the objects of simulation from the real world. The article presents for the first time an overview of a hybrid approach to modelling Storage attached networks (SAN), in which the parameters of an approximate simulator are dynamically adjusted using machine learning methods, i.e. reinforcement learning. Particular attention is paid to the analysis of the strengths and weaknesses of the existing approaches of simulation and comparison the hybrid approach presented in the article.