System load prediction method integrating isolated forest and long-term and short-term memory network

Abstract

The invention provides a system load prediction method integrating an isolated forest and a long-term and short-term memory network, which includes: considering the problem that noise and abnormal points exist in original data, and adopting an isolated forest algorithm to eliminate the abnormal points in the data; decomposing the input data into intrinsic mode function (IMF (intrinsic mode function)) components with different frequencies by utilizing an EMD (empirical mode decomposition) (EMD) algorithm; adopting a separated long short term memory neural network (LSTM (long short term memory network)) to predict each IMF (intrinsic mode function) and residual error, and reconstructing a prediction value in each LSTM model. According to the method, system load trend prediction with time sequence characteristics is realized, and the early warning capability of the system for too high system load caused by external attack or internal disturbance is improved.

Description

technical field [0001] The invention relates to the technical field of information systems, in particular to a system load forecasting method that integrates isolated forests and long-short-term memory networks. Background technique [0002] Information system load forecasting plays an important role in methods such as command and control in military and civilian fields, smart grid, and resource management and scheduling in financial systems. However, due to various external disturbances and the interaction of internal attributes, it is very difficult to achieve accurate prediction of system load. In the information system, the data acquired by the monitoring system usually has time characteristics, which is called time series, which is a series formed by arranging the values ​​of certain statistical indicators in chronological order. The time series trend forecasting method is to compile and analyze time series, and carry out analogy or extension according to the developme...

AI Technical Summary

Problems solved by technology

[0004] Most of the existing information system load forecasting methods are forecasting models for stationary time series and linearly changing monitoring data, such as trend fitting model, seasonal adjustment model, moving average method, exponential smoothing method, ARIMA model, etc. The method of accurately predicting the actual operating data containing noise is relatively rare. However, during the actual system operation, due to external interference or internal adjustment, the change of the system load is variable, and it has nonlinearity and non-stationarity.

Images