Research of the Current State of Decision-Making Systems in Geo-Distributed Nodes of Edge Computing Data Processing. Problems, Challenges, Prospects

Research in the field of multi-access edge computing systems in geographically distributed data processing nodes is one of the key areas in the development of cellular networks in response to the current slowdown in network growth and increased demands for low-latency communication services. The aim of the work was to analyze existing solutions in the field of decision-making systems for edge computing systems, to evaluate them comparatively, and to analyze the future prospects of using various algorithms as the basis for such systems. Sources such as IEEE Xplore, ACM Digital Library, and Google Scholar were used to conduct a systematic analysis of the literature. The search was conducted using keywords, and the snowball method was additionally used to expand the sample. The selected publications were analyzed using content analysis, focusing on the algorithms used, testing environments, and target metrics. The result of the work is a summary of the approaches, allowing conclusions to be drawn about the possible use of the technologies considered. An assessment of the prospects of reinforcement learning algorithms was also carried out, and their applicability in the tasks of decision-making systems for the placement of computing resources in geographically distributed data processing nodes was evaluated.