QPMMCOA and Bayesian Fuzzy Clustering: A Novel Approaches For Optimizing Queries in Big Data

The explosion of data in the last ten years has led to a substantial focus on big data (BD) in information area. The philosophical applications of "query optimization (QO)" are crucial in BD environments' data retrieval processes. Several distributed data processing platforms in cloud were developed to provide BD query optimization services that are both affordable and effective. Nevertheless, due to a lack of consideration for energy-related concerns and query characteristics, most solutions resulted in higher "energy consumption (EC)" and lower accuracy. We introduced an innovative deep-learning approach to arrange big data to overcome the issue. This work presents an effective query optimization that uses the Quantum parallel multi-layer Monte Carlo optimization method (QPMMCOA) optimizer and a load balancer based on Bayesian fuzzy clustering to address the problems associated with query optimization process. There are two phases to the suggested technique: (۱) Big data arrangement and (۲) Query Optimization. The first step arranges BD using preprocessing, feature extraction, feature selection, and deep learning-based BD arrangement. The improved Deep Residual Shrinkage Network (IDRSN) algorithm is used for the BD arrangement. The essential features are selected using the Chaotic Vertex Search algorithm (CVSA). During the second phase, a Bayesian fuzzy clustering-based load balancer is used with the QPMMCOA optimizer to improve overall query processing performance and ignore energy-efficient query plans. At last, the process of evaluating similarity is carried out. The experimental results demonstrated that the method performed better than other existing algorithms.

کلیدواژه ها:

Energy consumption ، deep-learning ، algorithms