Uso da inteligência artificial em otimização de consulta de banco de dados não relacionais

Abstract

This study proposes the use of artificial intelligence (AI) techniques to optimize the performance of database systems, exploring how machine learning algorithms can be applied to enhance efficiency in both data management and querying. The main objective is to develop and implement AI models, such as artificial neural networks and genetic algorithms, aimed at automating essential processes like data indexing, SQL query optimization, and workload prediction for database systems. By applying these techniques, the study seeks to achieve significant improvements in query response times and a substantial increase in overall system efficiency. This enables more effective utilization of computational resources, allowing systems handling large volumes of data to operate faster and more efficiently. Automating these processes can lead to more agile and reliable performance, resulting in a simplified database management experience. As a result, database administrators can focus on more strategic activities, leaving repetitive and complex tasks to be automatically managed by AI. Furthermore, the study discusses potential challenges and limitations, such as the complexity of implementing these techniques and their compatibility with traditional database systems. Finally, the research suggests future directions for additional studies, emphasizing how the continued use of AI has the potential to transform and revolutionize the field of database management, fostering increasingly innovative and efficient solutions.