Capacity prediction device based on ARIMA model and control method thereof

Abstract

The invention discloses a capacity prediction device based on an ARIMA model and a control method of the capacity prediction device. The capacity prediction device comprises a scheduling strategy module, an ARIMA model module, an ARIMA model module and an ARIMA model module, the sample data collection module is used for acquiring historical data, processing the acquired historical data and sendingthe processed historical data to the capacity prediction module as a training sample time sequence; the capacity prediction module is used for establishing and training a prediction model according to the characteristics of the training sample time sequence; importing the prediction sample data into a prediction model to generate capacity prediction data; and the capacity expansion suggestion generation module is used for matching the generated capacity prediction data with a capacity expansion strategy to generate capacity expansion suggestion data. Capacity index data of the host, the cluster, the network equipment and the storage equipment are subjected to collection and calculation, abnormal data processing, data cleaning, data noise reduction, capacity prediction data generation andcapacity expansion suggestion data generation according to a capacity expansion strategy, the whole process is fully automatic, and prediction is accurate.

Description

technical field [0001] The invention relates to a capacity prediction device and a control method thereof, in particular to a capacity prediction device based on an ARIMA model and a control method thereof. Background technique [0002] With the increasingly large IT structure of the enterprise, the management of information such as equipment capacity usage in the IT environment has become increasingly important and detailed, such as the host CPU usage rate of the business system, memory usage rate, network device interface inflow / outbound bandwidth utilization rate , storage capacity usage, etc., the existing monitoring technology has effectively monitored and alarmed the capacity usage of these devices. The monitoring system sets monitoring indicators and setting indicator alarm thresholds for the monitored equipment, periodically collects indicator data values ​​and makes a simple comparison with the alarm threshold values, and sends out alarms when the collected data v...

AI Technical Summary

Problems solved by technology

[0005] 1. Capacity management is carried out through monitoring and alarming, which is risky and easily affects online business

[0006] 2. Manual prediction is highly subjective, which tests the operation and maintenance ability and experience of the operation and maintenance personnel, and there is no guarantee

Images