阅读说明：本技术 固态硬盘的寿命预测方法、装置、设备及可读存储介质 (Service life prediction method, device and equipment of solid state disk and readable storage medium ) 是由 曹琪 于 2019-09-20 设计创作，主要内容包括：本发明公开了一种固态硬盘的寿命预测方法,该方法包括以下步骤：获取按预设时间间隔采集的待测固态硬盘的smart指标值；根据各smart指标值计算预定义的时间序列预测ARIMA模型的各相关参数；将各相关参数代入时间序列预测ARIMA模型,得到目标时间序列预测ARIMA模型；利用目标时间序列预测ARIMA模型对待测固态硬盘进行寿命预测。应用本发明实施例所提供的技术方案,较大地提升了固态硬盘寿命估计值的准确性,提高了固态硬盘中预存数据的安全性。本发明还公开了一种固态硬盘的寿命预测装置、设备及存储介质,具有相应技术效果。(The invention discloses a service life prediction method of a solid state disk, which comprises the following steps: acquiring smart index values of the solid state disk to be detected, which are acquired according to a preset time interval; calculating each relevant parameter of a predefined time sequence prediction ARIMA model according to each smart index value; substituting each relevant parameter into the time sequence prediction ARIMA model to obtain a target time sequence prediction ARIMA model; and predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model. By applying the technical scheme provided by the embodiment of the invention, the accuracy of the service life estimation value of the solid state disk is greatly improved, and the safety of the data prestored in the solid state disk is improved. The invention also discloses a service life prediction device, equipment and a storage medium of the solid state disk, and the service life prediction device, the equipment and the storage medium have corresponding technical effects.)

1. A method for predicting the service life of a solid state disk is characterized by comprising the following steps:

acquiring smart index values of the solid state disk to be detected, which are acquired according to a preset time interval;

calculating each relevant parameter of a predefined time series prediction ARIMA model according to each smart index value;

substituting each relevant parameter into the time series prediction ARIMA model to obtain a target time series prediction ARIMA model;

and predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model.

2. The method for predicting the service life of the solid state disk as claimed in claim 1, wherein calculating relevant parameters of a pre-defined time series prediction ARIMA model according to the smart index values comprises:

carrying out difference calculation on each smart index value to obtain a difference result sequence;

judging whether the difference result sequence meets the preset stationarity requirement or not;

and if not, carrying out differential calculation on the differential result sequence until the preset stationarity requirement is met, and determining the current differential order meeting the preset stationarity requirement as the differential order of the ARIMA model predicted by the time sequence.

3. The method for predicting the service life of the solid state disk as claimed in claim 2, wherein calculating relevant parameters of a pre-defined time series prediction ARIMA model according to the smart index values comprises:

calculating autocorrelation coefficients and partial autocorrelation coefficients corresponding to each order difference result sequence in a preset order;

constructing an autocorrelation coefficient curve graph based on each autocorrelation coefficient, and constructing a partial autocorrelation coefficient curve graph based on each partial autocorrelation coefficient;

determining the same order corresponding to the tailing of the autocorrelation coefficient curve graph and the truncation of the partial autocorrelation coefficient curve graph as the autoregressive model order of the time series prediction ARIMA model;

and determining the same order corresponding to the truncation of the autocorrelation coefficient curve graph and the tailing of the partial autocorrelation coefficient curve graph as the moving average model order of the time series prediction ARIMA model.

4. The method for predicting the service life of the solid state disk according to any one of claims 1 to 3, wherein after obtaining the target time series prediction ARIMA model, before predicting the service life of the solid state disk to be tested by using the target time series prediction ARIMA model, the method further comprises:

predicting an estimated smart index value corresponding to each preset time interval of the solid state disk to be detected in a subsequent preset time by using the target time sequence prediction ARIMA model;

acquiring actual smart index values corresponding to the preset time intervals in the preset duration;

calculating residual errors of the estimated smart index value and the actual smart index value of each time interval respectively to obtain a residual error sequence formed by each residual error;

constructing an autocorrelation coefficient curve graph of the residual error sequence;

and when determining that each residual sequence meets randomness according to the autocorrelation coefficient curve graph of the residual sequence, judging that the target time sequence prediction ARIMA model is qualified, and performing the step of predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model.

5. A life prediction device of a solid state disk is characterized by comprising:

the index value acquisition module is used for acquiring smart index values of the solid state disk to be detected, which are acquired according to a preset time interval;

the parameter calculation module is used for calculating each relevant parameter of a predefined time series prediction ARIMA model according to each smart index value;

the model obtaining module is used for substituting each relevant parameter into the time series prediction ARIMA model to obtain a target time series prediction ARIMA model;

and the service life prediction module is used for predicting the service life of the solid state disk to be detected by utilizing the target time sequence prediction ARIMA model.

6. The device for predicting the service life of the solid state disk according to claim 5, wherein the parameter calculation module comprises:

the difference calculation submodule is used for carrying out difference calculation on each smart index value to obtain a difference result sequence;

the judgment submodule is used for judging whether the difference result sequence meets the preset stability requirement or not;

and the difference order determining submodule is used for performing difference calculation on the difference result sequence until the preset stationarity requirement is met when the difference result sequence is determined not to meet the preset stationarity requirement, and determining the current difference order meeting the preset stationarity requirement as the difference order of the time sequence prediction ARIMA model.

7. The device for predicting the service life of the solid state disk according to claim 6, wherein the parameter calculation module comprises:

the coefficient calculation submodule is used for calculating autocorrelation coefficients and partial autocorrelation coefficients corresponding to the difference result sequences of each order in the preset order;

the graph construction submodule is used for constructing an autocorrelation coefficient graph based on each autocorrelation coefficient and constructing a partial autocorrelation coefficient graph based on each partial autocorrelation coefficient;

the autoregressive model order determining submodule is used for determining the same order corresponding to the tailing of the autocorrelation coefficient curve graph and the truncation of the partial autocorrelation coefficient curve graph as the autoregressive model order of the time series prediction ARIMA model;

and the moving average model order determining submodule is used for determining the same order corresponding to the truncation of the autocorrelation coefficient curve graph and the tailing of the partial autocorrelation coefficient curve graph as the moving average model order of the time series prediction ARIMA model.

8. The lifetime prediction apparatus of a solid state disk according to any one of claims 5 to 7, further comprising:

the index value estimation module is used for predicting the service life of the solid state disk to be detected by using the target time sequence prediction ARIMA model within the subsequent preset time length by using the target time sequence prediction ARIMA model after obtaining the target time sequence prediction ARIMA model and before predicting the service life of the solid state disk to be detected by using the target time sequence prediction ARIMA model, wherein the estimated smart index values correspond to the preset time intervals respectively;

an actual index value acquisition module, configured to acquire actual smart index values corresponding to the preset time intervals in the preset duration;

a residual sequence obtaining module, configured to calculate a residual between an estimated smart index value and an actual smart index value of each time interval, respectively, to obtain a residual sequence formed by each residual;

the graph construction module is used for constructing an autocorrelation coefficient graph of the residual sequence;

and the model qualification judging module is used for judging that the target time sequence prediction ARIMA model is qualified when the fact that each residual sequence meets randomness is determined according to the autocorrelation coefficient curve graph of the residual sequence, and executing the step of predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model.

9. A life prediction device of a solid state disk, comprising:

a memory for storing a computer program;

a processor for implementing the steps of the method for predicting the lifetime of a solid state disk according to any one of claims 1 to 4 when executing the computer program.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program, which when executed by a processor implements the steps of the method for predicting the lifetime of a solid state disk according to any one of claims 1 to 4.

Technical Field

The present invention relates to the field of storage technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for predicting a lifetime of a solid state disk.

Background

Flash memory based Solid State Disks (SSDs) have since emerged and are widely sought for their high performance, which has advantages over mechanical hard disks (HDDs) in that: 1) the starting is fast; 2) the reading and writing speed is high; 3) the random reading delay is small; 4) the shock resistance and the falling resistance are good, and no noise exists; 5) the power consumption is low, and the heat generation is low; and so on. Solid state disks are therefore undoubtedly a high performance alternative to mechanical hard disks. And along with the reduction of the price of the flash memory and the improvement of the technology, the solid state disk has a wider market and development prospect. Servers in data centers are increasingly trending towards using flash-based solid state drives as a high performance alternative to hard disk drives. Meanwhile, the service life of the solid state disk is also a problem generally concerned by the industry.

Generally, the service Life of a solid state disk is only a few years, the damage of the solid state disk is gradual, the performance and the error rate of the solid state disk are related to the age of the solid state disk, and the closer to the End of Life (End-of-Life), the worse the performance of the solid state disk is, the higher the error rate is. A solid state disk failure will likely result in a data center server down or even a data loss. The solid state disk has limited erasing and writing times and is difficult to recover after data loss. In order to ensure the accuracy and the safety of data, the solid state disk needs to be replaced before the service life of the solid state disk is ended.

The Self-Monitoring Analysis and reporting technology, Self-Monitoring, Analysis and reporting technology, of solid state drives provides a percent remaining life parameter, namely a Wear ratio expressed by the parameter ID226time work Media Wear timing Workload Media Wear. But the remaining life percentage is an objective value and is isolated from the use behavior of the solid state disk of the user. The remaining life expressed by the number of days is more intuitive, and meanwhile, the association between a user and the solid state disk can be established. The current methods for calculating the remaining life of the solid state disk provided by solid state disk manufacturers are methods for averaging by using a formula based on the abrasion change of a period of time. The method is simple and rough, the obtained life estimation value of the solid state disk is poor in accuracy, and the safety of data prestored in the solid state disk is low.

In summary, how to effectively solve the problems of poor accuracy of the estimated value of the service life of the solid state disk, low security of the data prestored in the solid state disk, and the like is a problem that those skilled in the art are urgently required to solve at present.

Disclosure of Invention

The invention aims to provide a method for predicting the service life of a solid state disk, which greatly improves the accuracy of the service life estimation value of the solid state disk and improves the safety of data prestored in the solid state disk; another object of the present invention is to provide a lifetime prediction apparatus, device and computer readable storage medium for solid state disk.

In order to solve the technical problems, the invention provides the following technical scheme:

a service life prediction method of a solid state disk comprises the following steps:

acquiring smart index values of the solid state disk to be detected, which are acquired according to a preset time interval;

calculating each relevant parameter of a predefined time series prediction ARIMA model according to each smart index value;

substituting each relevant parameter into the time series prediction ARIMA model to obtain a target time series prediction ARIMA model;

and predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model.

In an embodiment of the invention, calculating each relevant parameter of the predefined time series prediction ARIMA model according to each smart index value comprises:

carrying out difference calculation on each smart index value to obtain a difference result sequence;

judging whether the difference result sequence meets the preset stationarity requirement or not;

and if not, carrying out differential calculation on the differential result sequence until the preset stationarity requirement is met, and determining the current differential order meeting the preset stationarity requirement as the differential order of the ARIMA model predicted by the time sequence.

In an embodiment of the invention, calculating each relevant parameter of the predefined time series prediction ARIMA model according to each smart index value comprises:

calculating autocorrelation coefficients and partial autocorrelation coefficients corresponding to each order difference result sequence in a preset order;

constructing an autocorrelation coefficient curve graph based on each autocorrelation coefficient, and constructing a partial autocorrelation coefficient curve graph based on each partial autocorrelation coefficient;

determining the same order corresponding to the tailing of the autocorrelation coefficient curve graph and the truncation of the partial autocorrelation coefficient curve graph as the autoregressive model order of the time series prediction ARIMA model;

and determining the same order corresponding to the truncation of the autocorrelation coefficient curve graph and the tailing of the partial autocorrelation coefficient curve graph as the moving average model order of the time series prediction ARIMA model.

In a specific embodiment of the present invention, after obtaining the target time series prediction ARIMA model, before predicting the life of the solid state disk to be tested by using the target time series prediction ARIMA model, the method further includes:

predicting an estimated smart index value corresponding to each preset time interval of the solid state disk to be detected in a subsequent preset time by using the target time sequence prediction ARIMA model;

acquiring actual smart index values corresponding to the preset time intervals in the preset duration;

calculating residual errors of the estimated smart index value and the actual smart index value of each time interval respectively to obtain a residual error sequence formed by each residual error;

constructing an autocorrelation coefficient curve graph of the residual error sequence;

and when determining that each residual sequence meets randomness according to the autocorrelation coefficient curve graph of the residual sequence, judging that the target time sequence prediction ARIMA model is qualified, and performing the step of predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model.

A life prediction device of a solid state disk comprises:

the index value acquisition module is used for acquiring smart index values of the solid state disk to be detected, which are acquired according to a preset time interval;

the parameter calculation module is used for calculating each relevant parameter of a predefined time series prediction ARIMA model according to each smart index value;

the model obtaining module is used for substituting each relevant parameter into the time series prediction ARIMA model to obtain a target time series prediction ARIMA model;

and the service life prediction module is used for predicting the service life of the solid state disk to be detected by utilizing the target time sequence prediction ARIMA model.

In an embodiment of the present invention, the parameter calculating module includes:

the difference calculation submodule is used for carrying out difference calculation on each smart index value to obtain a difference result sequence;

the judgment submodule is used for judging whether the difference result sequence meets the preset stability requirement or not;

and the difference order determining submodule is used for performing difference calculation on the difference result sequence until the preset stationarity requirement is met when the difference result sequence is determined not to meet the preset stationarity requirement, and determining the current difference order meeting the preset stationarity requirement as the difference order of the time sequence prediction ARIMA model.

In an embodiment of the present invention, the parameter calculating module includes:

the coefficient calculation submodule is used for calculating autocorrelation coefficients and partial autocorrelation coefficients corresponding to the difference result sequences of each order in the preset order;

the graph construction submodule is used for constructing an autocorrelation coefficient graph based on each autocorrelation coefficient and constructing a partial autocorrelation coefficient graph based on each partial autocorrelation coefficient;

the autoregressive model order determining submodule is used for determining the same order corresponding to the tailing of the autocorrelation coefficient curve graph and the truncation of the partial autocorrelation coefficient curve graph as the autoregressive model order of the time series prediction ARIMA model;

and the moving average model order determining submodule is used for determining the same order corresponding to the truncation of the autocorrelation coefficient curve graph and the tailing of the partial autocorrelation coefficient curve graph as the moving average model order of the time series prediction ARIMA model.

In one embodiment of the present invention, the method further comprises:

the index value estimation module is used for predicting the service life of the solid state disk to be detected by using the target time sequence prediction ARIMA model within the subsequent preset time length by using the target time sequence prediction ARIMA model after obtaining the target time sequence prediction ARIMA model and before predicting the service life of the solid state disk to be detected by using the target time sequence prediction ARIMA model, wherein the estimated smart index values correspond to the preset time intervals respectively;

an actual index value acquisition module, configured to acquire actual smart index values corresponding to the preset time intervals in the preset duration;

a residual sequence obtaining module, configured to calculate a residual between an estimated smart index value and an actual smart index value of each time interval, respectively, to obtain a residual sequence formed by each residual;

the graph construction module is used for constructing an autocorrelation coefficient graph of the residual sequence;

and the model qualification judging module is used for judging that the target time sequence prediction ARIMA model is qualified when the fact that each residual sequence meets randomness is determined according to the autocorrelation coefficient curve graph of the residual sequence, and executing the step of predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model.

A life prediction device of a solid state disk comprises:

a memory for storing a computer program;

and the processor is used for realizing the steps of the service life prediction method of the solid state disk when executing the computer program.

A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for lifetime prediction of a solid state disk as set forth above.

By applying the method provided by the embodiment of the invention, smart index values of the solid state disk to be detected, which are acquired according to a preset time interval, are acquired; calculating each relevant parameter of a predefined time sequence prediction ARIMA model according to each smart index value; substituting each relevant parameter into the time sequence prediction ARIMA model to obtain a target time sequence prediction ARIMA model; and predicting the service life of the solid state disk to be tested by using the target time sequence prediction ARIMA model. The ARIMA model is predicted by predefining a time sequence, relevant parameters of the ARIMA model are calculated according to smart index values of the solid state disk to be detected, which are acquired according to preset time intervals, the target time sequence prediction ARIMA model obtained by substituting the relevant parameters is used for predicting the service life of the solid state disk to be detected, the target time sequence prediction ARIMA model is established on the basis of smart index value statistics of the solid state disk to be detected, the change rule of the abrasion degree of the solid state disk to be detected is summarized for prediction, the accuracy of the service life estimation value of the solid state disk to be detected is greatly improved, and the safety of data prestored in the solid state disk is improved.

Correspondingly, the embodiment of the invention also provides a device, equipment and a computer-readable storage medium for predicting the service life of the solid state disk, which correspond to the method for predicting the service life of the solid state disk, and the device, the equipment and the computer-readable storage medium have the technical effects and are not described herein again.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a flowchart of an implementation of a method for predicting a lifetime of a solid state disk according to an embodiment of the present invention;

fig. 2 is a flowchart of another implementation of a method for predicting the lifetime of a solid state disk according to an embodiment of the present invention;

fig. 3 is a block diagram of a life prediction apparatus for a solid state disk according to an embodiment of the present invention;

fig. 4 is a block diagram of a life prediction apparatus of a solid state disk according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.