Server memory capacity prediction method and device

Abstract

The invention discloses a server memory capacity prediction method and device. The method comprises the steps of obtaining memory usage amount data and corresponding time point data; and inputting thememory usage amount data and the corresponding time point data into a trained LSTM neural network model, predicting the memory capacity of the server, and training the LSTM neural network model according to the historical memory usage amount data and the corresponding historical time point data. The memory capacity of the server can be predicted, the data application range is expanded, and the maintenance cost is reduced.

Description

technical field [0001] The invention relates to the technical field of server memory, in particular to a server memory capacity prediction method and device. Background technique [0002] In recent years, with the recovery of my country's economy and the continuous development of Internet technology, many businesses of banks have been transferred from offline to online, which improves work efficiency and facilitates business processing. However, at the same time, many office systems of the bank also generate a large amount of data every day, which requires a certain level of memory to store, so the bank will purchase the memory required for the next month at the end of each month. But if you buy too much, it will be wasteful, and if you buy too little, it will not be enough. [0003] In the prior art, a differential autoregressive moving average model (ARIMA) method is used to predict server memory capacity. The main process of the program is to identify its stationarity a...

AI Technical Summary

Problems solved by technology

[0004] However, the ARIMA model requires the stability of time series data and can only process stable data, so this method has great limitations, and the ARIMA model is complex and expensive to maintain

Images