Storage use prediction method and device, electronic equipment and storage medium
By determining the data on storage capacity utilization, read/write speed, and business module proportion, differential processing and data decomposition are performed to build an ARIMA model, which solves the problem of insufficient prediction in traditional storage resource management and achieves precise storage resource allocation.
Patent Information
- Application Number
- CN202511763290.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-27
- Publication Date
- 2026-03-03
AI Technical Summary
Traditional storage resource management methods struggle to accurately predict future storage usage, leading to unreasonable resource allocation and resource waste or shortages.
By determining data on storage capacity utilization, read/write speed, and the proportion of business modules, differential processing and data decomposition are performed to build an ARIMA model for prediction.
It enables accurate prediction of enterprise storage conditions, reduces over-provisioning and under-provisioning, and balances storage performance and cost.
Smart Images
Figure CN121597130A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data prediction technology, and in particular to a storage and usage prediction method, apparatus, electronic device, and storage medium. Background Technology
[0002] As enterprise digital operations systems continue to evolve, storage resource management faces numerous challenges. With the massive growth of business data and increasingly complex dynamic changes in storage demands, traditional storage resource management methods often struggle to accurately predict future storage usage. This can lead to unreasonable allocation of storage resources, resulting in waste or shortages. Summary of the Invention
[0003] This invention provides a storage usage prediction method, apparatus, electronic device, and storage medium to solve the problem that traditional storage resource management methods are unable to predict future storage usage.
[0004] According to one aspect of the present invention, a storage usage prediction method is provided, the method comprising:
[0005] The primary data is determined, which includes storage capacity utilization, storage read / write speed, and storage proportion of each business module at each time point.
[0006] The first data is differentially processed until it reaches a stationary state, thus obtaining the second data and the number of differential processes.
[0007] The second data is decomposed to generate trend components, residual components, and seasonal components.
[0008] An ARIMA model is constructed based on the trend component, the number of differencing processes, and the residual component.
[0009] Storage usage is predicted based on seasonal components and the ARIMA model.
[0010] According to another aspect of the present invention, a storage usage prediction device is provided, the device comprising:
[0011] The first data determination module is used to determine the first data, which includes the storage capacity utilization rate, storage read and write rate, and storage ratio of each business module at each time point.
[0012] The difference processing module is used to perform difference processing on the first data until the first data reaches a stable state, thereby obtaining the second data and the number of difference processing times;
[0013] The data decomposition module is used to decompose the second data to generate trend components, residual components, and seasonal components.
[0014] The model building module is used to build an ARIMA model based on the trend component, the number of differencing processes, and the residual component.
[0015] The storage forecasting module is used to forecast storage usage based on seasonal components and the ARIMA model.
[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0017] At least one processor; and
[0018] A memory that is communicatively connected to at least one processor; wherein,
[0019] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the storage use prediction method of any embodiment of the present invention.
[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the storage usage prediction method of any embodiment of the present invention.
[0021] The technical solution of this invention involves determining first data, including storage capacity utilization, storage read / write speed, and storage proportion of each business module at various time points; performing differential processing on the first data until it reaches a stable state to obtain second data and the number of differential processing steps; decomposing the second data to generate trend components, residual components, and seasonal components; constructing an ARIMA model based on the trend components, the number of differential processing steps, and the residual components; and predicting storage usage based on the seasonal components and the ARIMA model to achieve accurate prediction of the enterprise's future storage situation, reduce over-configuration and under-configuration, and help the enterprise balance storage performance and cost.
[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1This is a flowchart of a storage usage prediction method provided in Embodiment 1 of the present invention;
[0025] Figure 2 This is a flowchart of another storage usage prediction method provided according to Embodiment 2 of the present invention;
[0026] Figure 3 This is a schematic diagram of a storage usage prediction device according to Embodiment 3 of the present invention;
[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the storage usage prediction method of the present invention. Detailed Implementation
[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0030] Example 1
[0031] Figure 1 This invention provides a flowchart of a storage usage prediction method according to Embodiment 1. This embodiment is applicable to situations where enterprise storage conditions are predicted. The method can be executed by a storage usage prediction device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:
[0032] S110. Determine the first data, which includes the storage capacity utilization rate, storage read / write rate, and storage ratio of each business module at each time point.
[0033] The primary data can be data related to the storage of the enterprise's operational systems. Storage capacity utilization is the ratio of used storage capacity to total available storage capacity. Storage read / write rate reflects the ability of storage devices / media to read or write data per unit of time. Storage percentage corresponding to each business module can be the ratio of data corresponding to each business module to the total available storage capacity after the data storage is divided according to actual business needs.
[0034] Firstly, data acquisition can involve collecting relevant indicator data from data sources such as enterprise digital system monitoring systems and database management systems, and storing the collected data in a dedicated data warehouse for subsequent processing and analysis.
[0035] For each data point included in the first dataset, an appropriate data collection granularity should be set based on the company's business characteristics and forecasting needs. For example, for companies with rapidly changing businesses, data can be collected hourly or daily; for companies with relatively stable businesses, data can be collected weekly or monthly.
[0036] Optionally, after determining the first data, the following may also be included:
[0037] The first set of data is cleaned to obtain the third set of data;
[0038] The third data is corrected or removed for outliers to obtain the fourth data.
[0039] Accordingly, the first data is differentially processed until it reaches a stationary state, yielding the second data and the number of differential processing steps, including:
[0040] The fourth data is differentially processed until the first data reaches a stable state, thus obtaining the second data and the number of differential processing steps.
[0041] The first set of data is processed by removing duplicates and missing values. For missing values, methods such as mean imputation, median imputation, or linear interpolation based on preceding and following data can be used to imput them, thus obtaining the third set of data.
[0042] The third set of data is then subjected to outlier detection and processing to generate the fourth set of data. Outlier detection and processing can employ statistical methods (such as the 3σ principle) or machine learning methods (such as the Isolation Forest algorithm) to identify outliers and correct or remove them. For correcting outliers, reasonable estimates can be made using methods such as interpolation based on the trends and patterns of historical data.
[0043] S120. Perform differential processing on the first data until the first data reaches a stable state, and obtain the second data and the number of differential processing steps.
[0044] Since the ARIMA model requires that the time series data be stationary, it is necessary to ensure that the first data reaches a stationary state. To achieve this, the first data needs to be differentially processed until it reaches a stationary state, thus obtaining the second data. The number of differential processing operations is recorded to obtain the number of differential processing operations.
[0045] Optionally, the first data is differentially processed until it reaches a stationary state, yielding the second data and the number of differential processing steps, including:
[0046] Based on the augmented Dickey-Fuller test, the first data is verified to be in a stationary state.
[0047] If the first data does not reach a stationary state for verification, then the first data is differentially processed until it reaches a stationary state, thus obtaining the second data and the number of differential processing steps.
[0048] The Augmented Dickey-Fuller Test (ADF test) is a core statistical method for testing the stationarity of data in time series analysis.
[0049] The stationary state of the first data was verified by the augmented Dickey-Fuller test until the first data reached a stationary state. The number of differencing operations was recorded to obtain the second data and the number of differencing operations.
[0050] S130. Perform data decomposition on the second data to generate trend components, residual components, and seasonal components.
[0051] The trend component refers to the systematic, non-periodic trend of data over a long period (such as continuous rise, continuous decline, or long-term stability). It is the core component reflecting the essential change pattern of the data after removing seasonal fluctuations and random noise. The residual component is a core component after time series decomposition, referring to the "random fluctuation part" remaining after removing the trend and seasonal components. It includes unpredictable components such as random noise, uncaptured short-term fluctuations, and outliers, and is a key basis for judging the effectiveness of time series decomposition and the rationality of modeling. The seasonal component is the fluctuation component in time series data driven by periodic and repetitive factors, referring to the regular fluctuations of data within a fixed time period (such as daily, weekly, monthly, or quarterly).
[0052] When making predictions, some data may exhibit periodic characteristics. Therefore, it is necessary to decompose the second data to generate trend components, residual components, and seasonal components.
[0053] Optionally, the second data can be decomposed to generate trend components, residual components, and seasonal components, including:
[0054] The second data is decomposed using a seasonal-trend decomposition procedure based on local weighted regression scatter smoothing to generate trend components, residual components, and seasonal components.
[0055] The Seasonal-Trend Decomposition Procedure Based on Loess (STL) is a nonparametric decomposition algorithm in time series analysis. Its core uses Loess smoothing to split the original series into trend, seasonal, and residual components. It is suitable for complex series with arbitrary periods, outliers, and nonlinear trends.
[0056] The seasonal-trend decomposition procedure based on the local weighted regression scatter smoothing method decomposes the second data, ensuring the accuracy of the trend component, residual component, and seasonal component.
[0057] S140. Construct an ARIMA model based on trend components, the number of difference processing steps, and residual components.
[0058] The ARIMA (Autoregressive Integrated Moving Average) model is a classic statistical model in the field of time series forecasting. Its core uses a combination of three parts: "autoregression (AR), differencing (I), and moving average (MA)" to capture the trend, autocorrelation, and random fluctuations of time series. It is suitable for forecasting stationary series or series that can be transformed into stationary series through differencing.
[0059] After obtaining the trend component, the number of differencing processes, and the residual component, the ARIMA model can be constructed according to the construction method of the ARIMA model.
[0060] Optionally, an ARIMA model can be constructed based on the trend component, the number of differencing operations, and the residual component, including:
[0061] The autoregression order is determined based on the trend component and the partial autocorrelation function (PACF) method.
[0062] The order of the moving average is determined based on the autocorrelation function method and residual components;
[0063] An ARIMA model is constructed based on the autoregression order, the moving average order, and the number of differencing operations.
[0064] For the decomposed trend component series, the partial autocorrelation function (PACF) method is used to determine the autoregressive order p. Specifically, observing the PACF plot, when the lag order is greater than p, the partial autocorrelation coefficient approaches 0, and the value of p at this point is the autoregressive order.
[0065] The order q of the moving average is determined using the autocorrelation function (ACF) method. Observing the ACF plot, when the lag order is greater than q, the autocorrelation coefficient approaches 0, and the value of q at this point is the order of the moving average.
[0066] Based on the determined parameters p, d (number of differential processing steps) and q, construct the ARIMA(p, d, q) model.
[0067] S150, based on seasonal components and the ARIMA model, predicts storage usage.
[0068] After generating the ARIMA model, predictions are made using the ARIMA model and combined with the prediction results of the seasonal components to predict storage usage.
[0069] The technical solution of this application involves determining first data, including storage capacity utilization, storage read / write speed, and storage proportion of each business module at various time points; performing differential processing on the first data until it reaches a stable state to obtain second data and the number of differential processing steps; decomposing the second data to generate trend components, residual components, and seasonal components; constructing an ARIMA model based on the trend components, the number of differential processing steps, and the residual components; and predicting storage usage based on the seasonal components and the ARIMA model to achieve accurate prediction of the enterprise's future storage situation, reduce over-configuration and under-configuration, and help the enterprise balance storage performance and cost.
[0070] Example 2
[0071] Figure 2 This invention provides a flowchart of another storage usage prediction method. This embodiment further optimizes the storage usage prediction process described in the previous embodiments, and can be combined with various optional solutions from one or more of the above embodiments. Figure 2 As shown, the storage using the prediction method in this embodiment may include the following steps:
[0072] S210. Determine the first data, which includes the storage capacity utilization rate, storage read / write rate, and storage ratio of each business module at each time point.
[0073] S220. Perform differential processing on the first data until the first data reaches a stable state, to obtain the second data and the number of differential processing steps.
[0074] S230. Perform data decomposition on the second data to generate trend components, residual components, and seasonal components.
[0075] S240. Based on the trend component, the number of difference processing steps, and the residual component, construct the ARIMA model.
[0076] S250. Based on the seasonal components and the first data, determine the predicted component values for each season and obtain the first component value.
[0077] S260. Based on the ARIMA model, storage usage is predicted to obtain the second component value.
[0078] S270. The sum of the first component value and the second component value is used as the prediction result.
[0079] After constructing the ARIMA model, the constructed ARIMA model is used to predict the trend component sequence to obtain the trend prediction value for a future period of time, thus obtaining the first component value.
[0080] For seasonal components, due to their fixed periodicity, the first data can be used directly for prediction. For example, if the seasonality period of the data is 12 months, then when predicting the seasonal component value for the next month, the seasonal component value for the same month of the previous year can be used directly. The trend component prediction value and the seasonal component prediction value are added together to obtain the final prediction value for storage and use.
[0081] The technical solution of this application determines the component values of each season based on seasonal components and first data, and obtains the first component value; based on the ARIMA model, it predicts storage usage and obtains the second component value; the sum of the first component value and the second component value is used as the prediction result. This clarifies the prediction process of predicting storage usage based on seasonal components and the ARIMA model, and ensures that the prediction process is clear and explicit.
[0082] Example 3
[0083] Figure 3 This invention provides a structural block diagram of a storage usage prediction device, applicable to scenarios requiring the prediction of enterprise storage conditions. This storage usage prediction device can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 3 As shown, the storage prediction device in this embodiment may include: a first data determination module 310, a difference processing module 320, a data decomposition module 330, a model building module 340, and a storage prediction module 350. Wherein:
[0084] First data determination module 310 is used to determine first data, which includes storage capacity utilization rate, storage read and write rate and storage ratio of each business module at each time point.
[0085] The differential processing module 320 is used to perform differential processing on the first data until the first data reaches a stable state, thereby obtaining the second data and the number of differential processing times.
[0086] The data decomposition module 330 is used to decompose the second data to generate trend components, residual components and seasonal components.
[0087] Model building module 340 is used to build an ARIMA model based on trend components, number of differencing processes, and residual components;
[0088] Storage prediction module 350 is used to predict storage usage based on seasonal components and the ARIMA model.
[0089] Optionally, based on the above embodiments, after determining the first data, the method further includes:
[0090] The first set of data is cleaned to obtain the third set of data;
[0091] The third data is corrected or removed for outliers to obtain the fourth data.
[0092] Accordingly, the first data is differentially processed until it reaches a stationary state, yielding the second data and the number of differential processing steps, including:
[0093] The fourth data is differentially processed until the first data reaches a stable state, thus obtaining the second data and the number of differential processing steps.
[0094] Based on the above embodiments, optionally, the first data is subjected to differential processing until the first data reaches a stationary state to obtain the second data and the number of differential processing operations, including:
[0095] Based on the augmented Dickey-Fuller test, the first data is verified to be in a stationary state.
[0096] If the first data does not reach a stationary state for verification, then the first data is differentially processed until it reaches a stationary state, thus obtaining the second data and the number of differential processing steps.
[0097] Based on the above embodiments, optionally, the second data is decomposed to generate trend components, residual components, and seasonal components, including:
[0098] The second data is decomposed using a seasonal-trend decomposition procedure based on local weighted regression scatter smoothing to generate trend components, residual components, and seasonal components.
[0099] Based on the above embodiments, optionally, an ARIMA model can be constructed based on the trend component, the number of differencing processes, and the residual component, including:
[0100] The autoregression order is determined based on the trend component and the partial autocorrelation function (PACF) method.
[0101] The order of the moving average is determined based on the autocorrelation function method and residual components;
[0102] An ARIMA model is constructed based on the autoregression order, the moving average order, and the number of differencing operations.
[0103] Based on the above embodiments, optionally, storage usage can be predicted based on seasonal components and the ARIMA model, including:
[0104] Based on the seasonal components and the first data, the component values for each season are determined and the first component value is obtained.
[0105] Based on the ARIMA model, storage usage is predicted to obtain the second component value;
[0106] The sum of the first component value and the second component value is used as the prediction result.
[0107] The storage usage prediction device provided in the embodiments of the present invention can execute the storage usage prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0108] Example 4
[0109] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0110] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0111] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0112] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as storing predictive methods.
[0113] In some embodiments, the storage usage prediction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the storage usage prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the storage usage prediction method by any other suitable means (e.g., by means of firmware).
[0114] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0115] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0116] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0118] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0119] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0120] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0121] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for predicting storage usage, characterized in that, include: Determine the first data, which includes the storage capacity utilization rate, storage read and write rate, and storage ratio of each business module at each time point; The first data is subjected to differential processing until the first data reaches a stable state, thereby obtaining the second data and the number of differential processing steps. The second data is decomposed to generate trend components, residual components, and seasonal components; Based on the trend component, the number of difference processing steps, and the residual component, an ARIMA model is constructed. Storage usage is predicted based on seasonal components and the ARIMA model.
2. The method according to claim 1, characterized in that, After determining the first data, the following is also included: The first data is cleaned to obtain the third data; The third data is corrected or removed for outliers to obtain the fourth data; Accordingly, the first data is subjected to differential processing until it reaches a stationary state, resulting in the second data and the number of differential processing iterations, including: The fourth data is differentially processed until the first data reaches a stable state, resulting in the second data and the number of differential processing steps.
3. The method according to claim 1, characterized in that, The first data is differentially processed until it reaches a stationary state, yielding the second data and the number of differential processing steps, including: Based on the augmented Dickey-Fuller test, the first data is verified to be in a stationary state. If the first data does not reach a stationary state for verification, then the first data is differentially processed until the first data reaches a stationary state, thus obtaining the second data and the number of differential processing steps.
4. The method according to claim 1, characterized in that, The second data is decomposed to generate trend components, residual components, and seasonal components, including: The second data is decomposed using a seasonal-trend decomposition procedure based on local weighted regression scatter smoothing to generate trend components, residual components, and seasonal components.
5. The method according to claim 1, characterized in that, Based on the trend component, the number of differencing processes, and the residual component, an ARIMA model is constructed, including: The autoregression order is determined based on the trend component and the partial autocorrelation function (PACF) method. The order of the moving average is determined based on the autocorrelation function method and residual components; An ARIMA model is constructed based on the autoregression order, the moving average order, and the number of differencing operations.
6. The method according to claim 1, characterized in that, Based on seasonal components and the ARIMA model, storage usage is predicted, including: Based on the seasonal components and the first data, the component values for each season are determined to obtain the first component value. Based on the ARIMA model, storage usage is predicted to obtain the second component value; The sum of the first component value and the second component value is used as the prediction result.
7. A storage and usage prediction device, characterized in that, include: The first data determination module is used to determine the first data, which includes the storage capacity utilization rate, storage read and write rate and storage ratio of each business module at each time point. The differential processing module is used to perform differential processing on the first data until the first data reaches a stable state, thereby obtaining the second data and the number of differential processing times. The data decomposition module is used to decompose the second data to generate trend components, residual components, and seasonal components. The model building module is used to build an ARIMA model based on the trend component, the number of differencing processes, and the residual component. The storage forecasting module is used to forecast storage usage based on seasonal components and the ARIMA model.
8. The apparatus according to claim 7, characterized in that, Following the first data determination module, the following is also included: The third data determination module is used to perform data cleaning on the first data to obtain the third data. The fourth data determination module is used to correct or remove outliers from the third data to obtain the fourth data; Correspondingly, the differential processing module is specifically used for: The fourth data is differentially processed until the first data reaches a stable state, resulting in the second data and the number of differential processing steps.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the memory use prediction method according to any one of claims 1-6.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the storage use prediction method of any one of claims 1-6.