A Distributed Database Load Balance Prediction Method and Prediction Analyzer

Abstract

The invention discloses a load balancing prediction method of a distributed database, and a predictive analyzer. The load balancing prediction method of the distributed database comprises the following steps: collecting a load index on each local data node to form training set data; initializing a multilayer circulation neural network model; extracting data in one time period from the training set data to serve as the input of the multilayer circulation neural network model, extracting the data in an equal time period after the data in one time period from the training set data to serve as the output of the multilayer circulation neural network model, and training the multilayer circulation neural network model; and extracting the data which is after the data in the equal time period and is in the same time period to serve as the input of the multilayer circulation neural network model, and predicting the load index of the local data node. Therefore, the load balancing prediction method of the distributed database and the predictive analyzer can more precisely describe and effectively predict the structure of load balancing data.

Description

technical field [0001] The invention relates to the computer field, in particular to a distributed database load balance prediction method and a prediction analyzer. Background technique [0002] At present, in order to improve the resource utilization and performance of distributed databases, it is of great significance to use forecasting technology to predict the resource usage of distributed databases in real time. [0003] There are still some deficiencies in the general BP network load balancing forecasting method. In the distributed forecasting analyzer, load balancing transfers tasks from servers with heavy loads to servers with lighter loads, so that tasks can utilize the computing resources there. capabilities, thereby improving the performance and stability of the entire distributed predictive analyzer. When some servers in the predictive analyzer are constantly under heavy workloads, or some servers perform tasks much more slowly than others, it is clear that une...

AI Technical Summary

Problems solved by technology

[0004] BP network has the advantages of clear principle, simple and practical, etc., but when large-scale data is required for real-time load prediction during network model training, but due to the gradient method of neural network, the convergence speed is slow and it is easy to converge to the local minimum

In addition, the influence of the selection of learning factors and inertia factors on the convergence of neural networks can only be selected by personal experience.

Therefore, the BP network is not suitable for the load prediction of high-input and high-output predictive analyzers, especially when it is necessary to deal with sudden real-time loads

Images