Analysis of distributed database access path prediction based on recurrent neural network in internet of things

Abstract

For avoiding the phenomenon of congestion, delay, and jitter in thedatabase access path, it is necessary to study the prediction method of database access path. Predicted database access path has high delay and jitter when using existing database access path prediction method to predict the path. Therefore, a prediction method of database access path is proposed based on the recurrent neural network. A decision matrix is constructed and normalized based on the analytic hierarchy process. The evaluation value of the alternative transit data center is calculated by the arithmetic weighted average operator, and the transit data center is selected according to the evaluation result. The matter-element analysis model is used to establish the mapping relationship between the user experience quality and the network service quality parameters. Moreover, the user experience quality evaluation level objective function of the database access path prediction method is constructed. Through the objective function to obtain the optimal database access path, the database access path prediction is completed. The experimental results show that the delay of the database access path predicted by the proposed method is much lower than other methods. The jitter is less than 30 ms and the jitter is small, which verifies the effectiveness of the path prediction method. KEYWORDSaccess path, alternative transit data center, database, decision matrix, prediction method, recurrent neural network INTRODUCTIONLarge-scale databases copy user data to multiple databases to improve user service quality. 1 A large amount of data needs to be transmitted between these distributed databases. Measurement studies have shown that the traffic between databases already accounts for nearly half of the database export bandwidth. 2,3 To meet the peak bandwidth requirement of the application, the access path of the database needs to be predicted. The existing database access path prediction method predicts the optimal path with high delay and large jitter. It is necessary to analyze and study the database access path prediction method. 4Wang et al proposed a database access path prediction method based on the number limit and data transmission delay. 5 This method uses the distributed shortest path tree algorithm to collect the relevant information and sensing data of sensor nodes in the k + 1 hop communication range. The virtual force theory is used to calculate the virtual force of the sensor node and the resultant force of all virtual forces. Based on the current dwell time of the grid center and the next dwell grid center based on the number of stays, the size and direction of the resultant force are calculated; then, according to the location of the sensor node, the remaining energy and other information to find a better path to complete the database access path prediction. The delay of the path predicted by this method is higher.Luo and Liu proposed a database access path prediction method based on traffic gravitational field. 6 This method combines the...

Analysis and Prediction of CET4 Scores Based on Data Mining Algorithm

“…Design college student achievement management analysis system [19]; C5.0 algorithm is used to analyze CET-4 scores, and it is concluded that grade, gender, English learning foundation, learning interest, and attitude towards examination have a high influence on passing CET-4 [20]. e conclusion is given that the results of the college entrance examination determine students' CET-4 scores, and the relationship between attendance, teaching evaluation scores, and CET-4 scores is also analyzed [21]. In the same year, he emphasized the need to strengthen listening training [22].…”

Convergence of deep machine learning and parallel computing environment for bio‐engineering applications

“…Yu and Fu have analyzed the distributed database access path prediction based on recurrent neural network in Internet of Things (IoT). This paper proposes a database access path prediction method based on recurrent neural network.…”

Real-Time Query Method Based on Distributed Database Demand Information

“…In contrast, the distributed database can expand the capacity and save costs. Moreover, the distributed database is easier and faster to store, analyze, and process big data, so that its users have a signi cant advantage in data processing [13].…”