CN112256550A - Storage capacity prediction model generation method and storage capacity prediction method - Google Patents
Storage capacity prediction model generation method and storage capacity prediction method Download PDFInfo
- Publication number
- CN112256550A CN112256550A CN202011306439.9A CN202011306439A CN112256550A CN 112256550 A CN112256550 A CN 112256550A CN 202011306439 A CN202011306439 A CN 202011306439A CN 112256550 A CN112256550 A CN 112256550A
- Authority
- CN
- China
- Prior art keywords
- storage capacity
- sequence
- original
- prediction model
- capacity prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003860 storage Methods 0.000 title claims abstract description 196
- 238000000034 method Methods 0.000 title claims abstract description 115
- 230000001932 seasonal effect Effects 0.000 claims abstract description 64
- 230000007774 longterm Effects 0.000 claims abstract description 40
- 230000008859 change Effects 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000007704 transition Effects 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 11
- 230000000737 periodic effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012417 linear regression Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 108091028043 Nucleic acid sequence Proteins 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005309 stochastic process Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a storage capacity prediction model generation method, a device and equipment and a storage and storage capacity prediction method, wherein the storage capacity prediction model generation method comprises the following steps: acquiring an original sequence of historical storage capacity data based on time change; decomposing the original sequence to obtain seasonal period components; performing variable point prediction based on original jump points in the original sequence to obtain a jump sequence; calculating a short-term growth rate and a long-term growth rate according to the original sequence to obtain a linear main sequence; and overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model. According to the method and the device, seasonal periodicity judgment is conducted on the original sequence, the possible variable points are predicted, the short-term growth rate and the long-term growth rate are calculated to obtain the linear main sequence, and the seasonal period component, the jump sequence and the linear main sequence are further overlapped to generate the storage capacity prediction model, so that the prediction accuracy can be improved, and the method and the device are suitable for morphological characteristics of different types of capacity trend changes.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a storage capacity prediction model generation method, an apparatus, an electronic device, and a computer-readable storage medium, and a storage capacity prediction method, an apparatus, an electronic device, and a computer-readable storage medium.
Background
In recent years, global cloud computing expenditure and cloud service demand have increased explosively, and the problem of server purchase planning of cloud service providers faces a dilemma. On the one hand, considering production and delivery cycles and discount factors, earlier and larger purchases may help to reduce purchase costs; on the other hand, the equipment has limited warranty, resources need to be maintained, and depreciation and maintenance cost can be reduced by later-stage and smaller purchasing. The capacity prediction of the cloud server can plan future load changes and resource use conditions according to the existing working load and resource use conditions. In the field of virtual storage technology, predicting the trend of storage capacity variation is a hot problem.
The resource growth mode has different forms based on different business models. As shown in FIG. 1, the a-type capacity variation form has a stable linear trend and is easy to predict; the b-type capacity change form is mainly linear trend and slightly changes to a smaller degree; the type c capacity change form has obvious periodicity; the class d capacity variation morphology exhibits a linear trend with a large number of trip points.
In the conventional technology, the storage capacity variation prediction is realized by adopting a method based on linear regression, a neural network model or a classical time series model, such as an autoregressive integral moving average method and an exponential smoothing method. However, although the method based on linear regression is relatively simple to implement, only the variation trend of the a type can be predicted, the b type effect can be accepted, but the prediction effect for the c type and the d type is not ideal; the neural network model or the classical time series model has high algorithm complexity, usually requires long operation time and a complex parameter adjusting process, and due to the fact that the d-type change trend is large in form change and lack of periodicity, the model is easily overfitting, and the prediction effect is not ideal enough.
Therefore, how to solve the above problems is a great concern for those skilled in the art.
Disclosure of Invention
The application aims to provide a storage capacity prediction model generation method, a storage capacity prediction model generation device, electronic equipment and a computer readable storage medium, and a storage capacity prediction method, a storage capacity prediction device, electronic equipment and a computer readable storage medium, which can improve prediction accuracy and adapt to morphological characteristics of different types of capacity trend changes.
In order to achieve the above object, the present application provides a storage capacity prediction model generation method, including:
acquiring an original sequence of historical storage capacity data based on time change;
decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
and overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, wherein the storage capacity prediction model is used for capacity management operation.
Optionally, the performing a transition point prediction based on an original transition point in the original sequence to obtain a transition sequence includes:
determining original jumping points in the original sequence, and judging whether the distribution of the original jumping points conforms to a poisson process;
and if the hopping sequence accords with the Poisson process, generating the hopping sequence by utilizing the strength parameter of the Poisson process based on the original hopping point.
Optionally, the determining an original transition point in the original sequence includes:
calculating a first-class first-order difference sequence corresponding to the original sequence, and taking an absolute value of the first-class first-order difference sequence to obtain a processed sequence;
and selecting a target point exceeding a preset variable point threshold value in the processed sequence, and determining the target point as the original jump point.
Optionally, the calculating a short-term growth rate and a long-term growth rate according to the original sequence includes:
segmenting the original sequence based on the original jump point to obtain a target subsequence;
fitting the target subsequence by using a linear model to obtain a slope corresponding to each target subsequence;
calculating the slope corresponding to each target subsequence in a weighted average mode to obtain the short-term growth rate;
and taking the prediction window as a step length, and calculating a second-class first-order difference sequence corresponding to the original sequence to obtain the long-term growth rate.
Optionally, the calculating the slope corresponding to each target subsequence in a weighted average manner to obtain the short-term growth rate includes:
acquiring an attenuation coefficient of real-time input by using a preset input interface;
calculating the weight corresponding to each target subsequence by using an exponential decay function based on the decay coefficient;
and according to the calculated weight, carrying out weighted average calculation on the slope corresponding to each target subsequence to obtain the short-term growth rate.
Optionally, after decomposing the original sequence to obtain the seasonal period component corresponding to the original sequence, the method further includes:
determining the proportion corresponding to the seasonal period component, and judging whether the proportion is greater than a preset proportion threshold value;
and if the ratio is smaller than the preset ratio threshold, prohibiting the overlapping processing of the seasonal period component, the linear main sequence and the hopping sequence, and directly overlapping the linear main sequence and the hopping sequence to generate a storage capacity prediction model.
Optionally, after the overlapping processing is performed on the seasonal period component, the linear main sequence, and the hopping sequence to generate a storage capacity prediction model, the method further includes:
acquiring the residual storage capacity of the current server;
determining a prediction time node of the current server with the exhausted storage capacity by combining the storage capacity prediction model and the residual storage capacity;
and returning early warning prompt information comprising the predicted time node through a visual interface.
To achieve the above object, the present application provides a storage capacity prediction method, including:
acquiring actual capacity use data of a server to be predicted in a preset historical time period;
inputting the actual capacity utilization data into a storage capacity prediction model to obtain a storage capacity prediction result of the server to be predicted in a preset future time period; the storage capacity prediction model is generated by the storage capacity prediction model generation method.
To achieve the above object, the present application provides a storage capacity prediction model generation apparatus, including:
the sequence acquisition module is used for acquiring an original sequence of historical storage capacity data based on time change;
the sequence decomposition module is used for decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
the variable point prediction module is used for carrying out variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
the growth calculation module is used for calculating a short-term growth rate and a long-term growth rate according to the original sequence and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
and the model generation module is used for performing superposition processing on the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, and the storage capacity prediction model is used for capacity management operation.
To achieve the above object, the present application provides a storage capacity prediction apparatus comprising:
the data acquisition module is used for acquiring actual capacity use data of the server to be predicted in a preset historical time period;
the capacity prediction module is used for inputting the actual capacity utilization data into a storage capacity prediction model to obtain a storage capacity prediction result of the server to be predicted within a preset future time period; the storage capacity prediction model is generated by the storage capacity prediction model generation method.
To achieve the above object, the present application provides an electronic device including:
a memory for storing a computer program;
a processor for implementing the steps of any of the storage capacity prediction model generation methods disclosed above when executing the computer program.
To achieve the above object, the present application provides an electronic device including:
a memory for storing a computer program;
a processor for implementing the steps of any of the storage capacity prediction methods disclosed above when executing the computer program.
To achieve the above object, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the storage capacity prediction model generation methods disclosed in the foregoing.
To achieve the above object, the present application provides a computer-readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of any of the storage capacity prediction methods disclosed in the foregoing.
According to the scheme, the storage capacity prediction model generation method provided by the application comprises the following steps: acquiring an original sequence of historical storage capacity data based on time change; decomposing the original sequence to obtain seasonal period components corresponding to the original sequence; performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence; calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence; and overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, wherein the storage capacity prediction model is used for capacity management operation. According to the method, the original sequence is subjected to seasonal periodic judgment, the possible variable points are predicted, the short-term growth rate and the long-term growth rate are calculated according to the original sequence to obtain the main capacity change trend, namely the linear main sequence, the seasonal periodic components obtained by the seasonal periodic judgment, the predicted jump sequence and the linear main sequence can be superposed to generate the storage capacity prediction model, the prediction accuracy is effectively improved, the method can adapt to morphological characteristics of different types of capacity trend changes, meanwhile, the algorithm complexity is low, and the prediction result can be rapidly calculated.
The application also discloses a storage capacity prediction model generation device, electronic equipment, a computer readable storage medium, a storage capacity prediction method, a storage capacity prediction device, electronic equipment and a computer readable storage medium, and the technical effects can be achieved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the present application 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 application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of a common type of storage capacity variation profile trend;
FIG. 2 is a flow chart of a storage capacity prediction model generation method disclosed in an embodiment of the present application;
FIG. 3 is a flow chart of another storage capacity prediction model generation method disclosed in the embodiments of the present application;
FIG. 4 is a flow chart of yet another storage capacity prediction model generation method disclosed in an embodiment of the present application;
FIG. 5 is a flow chart of a method for predicting storage capacity according to an embodiment of the present disclosure;
fig. 6 is a block diagram of a storage capacity prediction model generation apparatus according to an embodiment of the present application;
fig. 7 is a block diagram of a storage capacity prediction apparatus according to an embodiment of the present application;
fig. 8 is a block diagram of an electronic device disclosed in an embodiment of the present application;
fig. 9 is a block diagram of another electronic device disclosed in the embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
In the conventional technology, the storage capacity variation prediction is realized by adopting a method based on linear regression, a neural network model or a classical time series model, such as an autoregressive integral moving average method and an exponential smoothing method. However, although the method based on linear regression is relatively simple to implement, only the variation trend of the a type can be predicted, the b type effect can be accepted, but the prediction effect for the c type and the d type is not ideal; the neural network model or the classical time series model has high algorithm complexity, usually requires long operation time and a complex parameter adjusting process, and due to the fact that the d-type change trend is large in form change and lack of periodicity, the model is easily overfitting, and the prediction effect is not ideal enough.
Therefore, the embodiment of the application discloses a storage capacity prediction model generation method, which can improve prediction accuracy and adapt to morphological characteristics of different types of capacity trend changes.
Referring to fig. 2, a storage capacity prediction model generation method disclosed in an embodiment of the present application includes:
s101: acquiring an original sequence of historical storage capacity data based on time change;
in the embodiment of the application, an original sequence of historical storage capacity data is obtained, wherein the sequence is a time change-based sequence and represents the change trend of the historical storage capacity data.
In a specific implementation, the manner of obtaining the original sequence may include: collecting data of storage capacity change in preset historical time in advance to obtain an original sequence; or a file uploaded by a user and comprising the historical storage capacity data can be acquired through the file transmission interface.
S102: decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
in this step, the original sequence is seasonally decomposed to obtain seasonal period components therein. The seasonal decomposition is to decompose an original time series into three parts of long-term trend, seasonal period and random variation. The seasonal decomposition is to analyze that the storage capacity variation trend is influenced by seasonal variation, that is, the seasonal variation is influenced by natural conditions and economic conditions, and forms regular variation of data along with the seasonal variation in one year.
As a specific implementation manner, the embodiment of the present application may decompose the original sequence by using an addition model or a multiplication model, and obtain a long-term trend, a seasonal period component, and a random variation component of the original sequence. It should be noted that the addition model and the multiplication model are statistical analysis methods commonly used in the long-term trend analysis, wherein the multiplication model assumes that the influences of the long-term trend, the seasonal period and the random variation on the development variation trend are interactive, and the margin is expressed by a ratio based on the absolute amount of the long-term trend component, and the addition model assumes that the influences of the long-term trend, the seasonal period and the random variation on the development variation trend are independent, and each component is expressed by an absolute amount.
S103: performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
in the embodiment of the present application, the change point prediction will be performed. In a sequence or process, when a certain statistical characteristic, such as a distribution type, a distribution parameter, etc., changes at a certain time point due to the influence of systematic factors rather than accidental factors, the time point is called a change point, and the position of the change point can be counted by using statistics or statistical methods.
In a specific embodiment, the step of performing the transition point prediction based on the original transition point in the original sequence to obtain the hopping sequence may specifically include: determining original jumping points in an original sequence, and judging whether the distribution of the original jumping points conforms to a poisson process; and if the hopping sequence accords with the Poisson process, generating the hopping sequence by using the strength parameter of the Poisson process based on the original hopping point. That is, whether an original jump point exists in an original sequence of historical capacity data needs to be searched, whether distribution of the original jump point accords with a poisson process is judged, if so, a subsequent jump point prediction process can be carried out, otherwise, the original jump point is skipped, and whether distribution of the next original jump point accords with the poisson process is analyzed until an analysis process aiming at all the jump points is finished.
It should be noted that a poisson distribution is a discrete probability distribution which is common in statistics and probability. Suitable for describing the probability distribution of the number of times a random event occurs per unit time. Such as the number of service requests received by a service facility within a certain period of time, the number of calls received by a telephone exchange, the number of passengers waiting at a bus stop, the number of failures of a machine, the number of natural disasters, the variation number of DNA sequences, and the like. While random processes are, in the concept of probability theory, a collection of random variables. If the sample point of a random system is a random function, the function is called a sample function, and the set of all sample functions of the random system is a random process. Such as fluctuations in stock and exchange rates, voice signals, video signals, changes in body temperature, etc., are examples of stochastic processes. The poisson process is specifically one of random processes, and is defined by the occurrence time of an event. It needs to satisfy the following conditions: the number of events which occur in two mutually exclusive non-overlapping intervals is a random variable which is independent of each other; the probability distribution of the number of events occurring within a preset time interval follows a poisson distribution.
As a specific implementation, the process of determining an original transition point in an original sequence may include: calculating a first-class first-order difference sequence corresponding to the original sequence, and taking an absolute value of the first-class first-order difference sequence to obtain a processed sequence; and selecting a target point exceeding a preset variable point threshold value in the processed sequence, and determining the target point as an original jump point. As can be seen from the above, the first-order difference sequence of the original sequence is calculated first, and the absolute value of the first-order difference sequence is taken. And searching a current point, which is different from the previous point by more than a preset variable point threshold value, in the first-order difference sequence to serve as a target point, namely the original jump point. The preset variable point threshold may specifically be three times the standard deviation of the first-order difference sequence, and certainly, in the implementation process, the preset variable point threshold may be set according to an actual requirement, which is not limited in the embodiment of the present application.
S104: calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
in this step, a linear main trend of the storage capacity variation will be obtained by linear model fitting. First, a short-term growth rate and a long-term growth rate are calculated from the original sequence, the short-term growth rate characterizing a growth rate of the storage capacity in a shorter time range, and the long-term growth rate characterizing a growth rate of the storage capacity in a longer time range.
Specifically, the original sequence can be segmented based on the original jump point to obtain a plurality of stably-changing target subsequences; fitting the target subsequences by using a linear model to obtain the slope corresponding to each target subsequence; and calculating the slope corresponding to each target subsequence in a weighted average mode to obtain the short-term growth rate. It is noted that in general, the probability that the recent trend continues to be higher, and therefore the weight of the recent subsequence is higher than the weight of the future subsequence in the weighted average calculation. As a specific implementation manner, the weight of each target subsequence may be determined by using an exponential decay method, for example, a preset input interface may be used to obtain a decay coefficient input in real time, the weight corresponding to each target subsequence is calculated by using an exponential decay function based on the decay coefficient, and then a slope corresponding to each target subsequence may be weighted and averaged according to the calculated weight, so as to obtain a short-term growth rate.
When calculating the long-term growth rate, the prediction window can be used as a step length to calculate a second-class first-order difference sequence corresponding to the original sequence. For example, if the prediction window size is three months, the first order difference sequence of the original sequence is calculated according to step 90, i.e., the data at day 91 minus the data at day 1, the data at day 92 minus the data at day 2, and so on.
It will be appreciated that after calculating the short term growth rate and the long term growth rate, the main trend of the future sequence variation can be predicted. Specifically, the prediction time may be divided into a first time period and a second time period, for example, 90 days are divided into 30 days and 60 days, the linear main sequence corresponding to the first time period is subjected to linear fitting prediction by using a short-term growth rate, and the linear main sequence corresponding to the second time period is subjected to linear fitting prediction by using a long-term growth rate, so as to obtain a final linear main sequence.
S105: and overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, wherein the storage capacity prediction model is used for capacity management operation.
In this step, the seasonal period component, the linear main sequence, and the hopping sequence obtained by the decomposition and prediction are superimposed to generate a storage capacity prediction model. In the specific process of superposition, an addition model or a multiplication model can be also adopted for superposition processing. It should be noted that, if the seasonal decomposition in the foregoing step uses an addition model, the addition model needs to be used for the overlay processing; if the seasonal decomposition of the foregoing steps uses a multiplication model, it is necessary to perform an overlay process using the multiplication model. After the storage capacity prediction model is generated, the storage capacity prediction model can be used for predicting the possible storage capacity in a certain period of time in the future so that an administrator can perform capacity management operations such as capacity expansion.
According to the scheme, the storage capacity prediction model generation method provided by the application comprises the following steps: acquiring an original sequence of historical storage capacity data based on time change; decomposing the original sequence to obtain seasonal period components corresponding to the original sequence; performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence; calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence; and overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, wherein the storage capacity prediction model is used for capacity management operation. According to the method, the original sequence is subjected to seasonal periodic judgment, the possible variable points are predicted, the short-term growth rate and the long-term growth rate are calculated according to the original sequence to obtain the main capacity change trend, namely the linear main sequence, the seasonal periodic components obtained by the seasonal periodic judgment, the predicted jump sequence and the linear main sequence can be superposed to generate the storage capacity prediction model, the prediction accuracy is effectively improved, the method can adapt to morphological characteristics of different types of capacity trend changes, meanwhile, the algorithm complexity is low, and the prediction result can be rapidly calculated.
The embodiment of the application discloses another storage capacity prediction model generation method, and compared with the previous embodiment, the embodiment further explains and optimizes the technical scheme. Referring to fig. 3, specifically:
s201: acquiring an original sequence of historical storage capacity data based on time change;
s202: decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
s203: performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
s204: calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
s205: determining the proportion corresponding to the seasonal period component, and judging whether the proportion is greater than a preset proportion threshold value; if yes, go to step S206; if not, go to step S207;
s206: overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model;
s207: and overlapping the linear main sequence and the hopping sequence to generate a storage capacity prediction model.
It can be understood that, after the seasonal decomposition is performed on the original sequence, the present embodiment may further determine the ratio of the seasonal period component, and determine the magnitude relationship between the ratio and the preset ratio threshold. If the proportion of the seasonal period components is larger than the preset proportion threshold, the influence of the characteristic seasonal period components on the variation trend of the storage capacity is obvious, the seasonal period components can be stored and superposed on the predicted main trend, and the prediction accuracy is further improved. If the proportion of the seasonal period components is smaller than the preset proportion threshold, the influence of the representation seasonal period on the change trend of the storage capacity is not obvious, the seasonal period components can be abandoned, only the linear main sequence and the jump sequence are overlapped when the storage capacity prediction model is generated, meaningless overlapping is not needed when the influence of the seasonal period is small, and unnecessary working process and working time waste are avoided.
The embodiment of the application discloses another storage capacity prediction model generation method, and compared with the previous embodiment, the embodiment further explains and optimizes the technical scheme. Referring to fig. 4, specifically:
s301: acquiring an original sequence of historical storage capacity data based on time change;
s302: decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
s303: performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
s304: calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
s305: overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model;
s306: acquiring the residual storage capacity of the current server;
s307: determining a prediction time node of the current server with the exhausted storage capacity by combining the storage capacity prediction model and the residual storage capacity;
s308: and returning early warning prompt information comprising the predicted time node through a visual interface.
As a preferred implementation manner, the embodiment of the application may obtain the remaining storage capacity of the current server, determine a predicted time node when the storage capacity of the current server is exhausted according to the storage capacity prediction model and the current remaining storage capacity, and return an early warning prompt message including the predicted time node, so that an administrator may perform operations such as capacity expansion in time.
The embodiment of the application discloses a storage capacity prediction method, which mainly utilizes a storage capacity prediction model generated in any one of the embodiments to predict storage capacity. Referring to fig. 5, the method specifically includes:
s401: acquiring actual capacity use data of a server to be predicted in a preset historical time period;
in the embodiment of the application, the actual capacity usage data of the server to be predicted in the preset historical time period may be obtained first. The server to be predicted may be specifically a server that needs to perform capacity prediction, and the preset historical time period may be set according to a specific situation in actual implementation, which is not specifically limited in this embodiment.
In a specific implementation, the manner of obtaining the actual capacity usage data of the server to be predicted may be: the actual capacity usage data actively reported by the preset thread in the server to be predicted is obtained, or the actual capacity usage data of the server to be predicted which is copied in advance is obtained through the external storage device, that is, the actual capacity usage data can be obtained in a mode of automatic data reporting or manual data acquisition.
S402: inputting the actual capacity utilization data into a storage capacity prediction model to obtain a storage capacity prediction result of the server to be predicted in a preset future time period; wherein, the storage capacity prediction model is the prediction model generated by any one of the previous embodiments.
It is understood that, in this embodiment, the actual capacity usage data may be input into a storage capacity prediction model, and the storage capacity prediction model predicts a capacity usage trend of the server in a future time period according to the actual capacity usage data of the server to be predicted in a preset historical time period, so as to obtain a storage capacity prediction result of the server to be predicted, where the storage capacity prediction model is specifically the prediction model generated in any one of the foregoing embodiments. The storage capacity prediction result in the preset future time period may be specific data, such as storage capacity usage data at a future time point, or storage capacity surplus data at a future time point. The storage capacity prediction result in the preset future time period may also indicate a development trend, such as a change trend of the storage capacity usage data in the preset future time period or a change trend of the storage capacity remaining data in the preset future time period.
The storage capacity prediction process of the embodiment of the present application is described below by means of the product service form in the implementation. As a possible implementation manner, the prediction function of the storage capacity prediction model may be deployed as a software module in a management platform of a cloud product, such as an HCI (hyper convergence interface) product. After the user finishes the deployment of the cloud computing product, the corresponding storage capacity prediction can be carried out by using the function. As another possible implementation, the prediction function of the storage capacity prediction model may be implemented by providing a Service in the form of SaaS (Software-as-a-Service), and providing an API (Application Program Interface) so that a user uploads historical capacity usage data by calling the API Interface, and obtains a storage capacity prediction result predicted according to the capacity usage data.
In an exemplary embodiment, when the storage capacity is predicted, a rolling prediction mode may be specifically adopted, that is, a prediction process of the storage capacity is periodically performed, for example, once a day and once a week, actual capacity usage data in a past period, for example, in the past 180 days, is collected each time the prediction process is performed, and a capacity usage trend in a future period, for example, 90 days, is predicted. And covering the prediction result of the previous period by using the updated prediction trend after each prediction, thereby realizing rolling type prediction.
In the following, a storage capacity prediction model generation apparatus provided in an embodiment of the present application is introduced, and a storage capacity prediction model generation apparatus described below and a storage capacity prediction model generation method described above may be referred to each other.
Referring to fig. 6, a storage capacity prediction model generation apparatus according to an embodiment of the present application includes:
a sequence obtaining module 501, configured to obtain an original sequence of historical storage capacity data based on time change;
a sequence decomposition module 502, configured to decompose the original sequence to obtain a seasonal period component corresponding to the original sequence;
a variable point prediction module 503, configured to perform variable point prediction based on an original jump point in the original sequence to obtain a jump sequence;
a growth calculation module 504, configured to calculate a short-term growth rate and a long-term growth rate according to the original sequence, and obtain a linear main sequence by combining the short-term growth rate and the long-term growth rate;
a model generating module 505, configured to perform superposition processing on the seasonal period component, the linear main sequence, and the hopping sequence, and generate a storage capacity prediction model, where the storage capacity prediction model is used for capacity management operation.
For the specific implementation process of the modules 501 to 505, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.
In the following, a storage capacity prediction apparatus provided by an embodiment of the present application is described, and a storage capacity prediction apparatus described below and a storage capacity prediction method described above may be referred to each other.
Referring to fig. 7, a storage capacity prediction model generation apparatus according to an embodiment of the present application includes:
the data acquisition module 601 is configured to acquire actual capacity usage data of a server to be predicted in a preset historical time period;
a capacity prediction module 602, configured to input the actual capacity usage data into a storage capacity prediction model, and obtain a storage capacity prediction result of the server to be predicted in a preset future time period; the storage capacity prediction model is a prediction model generated by the storage capacity prediction model generation method disclosed in any one of the foregoing embodiments.
For the specific implementation process of the modules 601 and 602, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details are not repeated here.
The present application further provides an electronic device, and as shown in fig. 8, an electronic device provided in an embodiment of the present application includes:
a memory 100 for storing a computer program;
the processor 200, when executing the computer program, may implement the steps of the storage capacity prediction model generation method or the storage capacity prediction method provided by the foregoing embodiments.
Specifically, the memory 100 includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer-readable instructions, and the internal memory provides an environment for the operating system and the computer-readable instructions in the non-volatile storage medium to run. The processor 200 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor or other data Processing chip in some embodiments, and provides computing and controlling capability for the electronic device, and when executing the computer program stored in the memory 100, the steps of the storage capacity prediction model generation method or the storage capacity prediction method disclosed in any of the foregoing embodiments may be implemented.
On the basis of the above embodiment, as a preferred implementation, referring to fig. 9, the electronic device further includes:
and an input interface 300 connected to the processor 200, for acquiring computer programs, parameters and instructions imported from the outside, and storing the computer programs, parameters and instructions into the memory 100 under the control of the processor 200. The input interface 300 may be connected to an input system for receiving parameters or instructions manually entered by a user. The input system may be a touch layer covered on a display screen, or may be a button, a track ball or a touch pad arranged on a terminal housing, or may be a keyboard, a touch pad or a mouse, etc.
And a display unit 400 connected to the processor 200 for displaying data processed by the processor 200 and for displaying a visualized user interface. The display unit 400 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch panel, or the like.
And a network port 500 connected to the processor 200 for performing communication connection with each external terminal device. The communication technology adopted by the communication connection can be a wired communication technology or a wireless communication technology, such as a mobile high definition link (MHL) technology, a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a wireless fidelity (WiFi), a bluetooth communication technology, a low power consumption bluetooth communication technology, an ieee802.11 s-based communication technology, and the like.
While fig. 9 illustrates only an electronic device having the assembly 100 and 500, those skilled in the art will appreciate that the configuration illustrated in fig. 9 does not constitute a limitation of the electronic device and may include fewer or more components than those illustrated, or some components may be combined, or a different arrangement of components.
The present application also provides a computer-readable storage medium, which may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk. The storage medium has a computer program stored thereon, which when executed by a processor implements the steps of the storage capacity prediction model generation method or the storage capacity prediction method disclosed in any of the foregoing embodiments.
According to the method and the device, seasonal periodic discrimination is performed on the original sequence, the possible variable points are predicted, the short-term growth rate and the long-term growth rate are calculated according to the original sequence to obtain the main capacity change trend, namely the linear main sequence, seasonal periodic components obtained by seasonal periodic discrimination, the predicted jump sequence and the linear main sequence can be superposed to generate the storage capacity prediction model, the prediction accuracy is effectively improved, the method and the device can adapt to morphological characteristics of different types of capacity trend changes, meanwhile, the algorithm complexity is low, and the prediction result can be rapidly calculated.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (14)
1. A storage capacity prediction model generation method, comprising:
acquiring an original sequence of historical storage capacity data based on time change;
decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
performing variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
calculating a short-term growth rate and a long-term growth rate according to the original sequence, and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
and overlapping the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, wherein the storage capacity prediction model is used for capacity management operation.
2. The method according to claim 1, wherein the performing a transition point prediction based on an original transition point in the original sequence to obtain a transition sequence comprises:
determining original jumping points in the original sequence, and judging whether the distribution of the original jumping points conforms to a poisson process;
and if the hopping sequence accords with the Poisson process, generating the hopping sequence by utilizing the strength parameter of the Poisson process based on the original hopping point.
3. The storage capacity prediction model generation method of claim 2, wherein the determining the original trip points in the original sequence comprises:
calculating a first-class first-order difference sequence corresponding to the original sequence, and taking an absolute value of the first-class first-order difference sequence to obtain a processed sequence;
and selecting a target point exceeding a preset variable point threshold value in the processed sequence, and determining the target point as the original jump point.
4. The storage capacity prediction model generation method according to claim 1, wherein the calculating a short-term growth rate and a long-term growth rate from the original sequence comprises:
segmenting the original sequence based on the original jump point to obtain a target subsequence;
fitting the target subsequence by using a linear model to obtain a slope corresponding to each target subsequence;
calculating the slope corresponding to each target subsequence in a weighted average mode to obtain the short-term growth rate;
and taking the prediction window as a step length, and calculating a second-class first-order difference sequence corresponding to the original sequence to obtain the long-term growth rate.
5. The method as claimed in claim 4, wherein the calculating the slope corresponding to each target subsequence by means of weighted average to obtain the short-term growth rate comprises:
acquiring an attenuation coefficient of real-time input by using a preset input interface;
calculating the weight corresponding to each target subsequence by using an exponential decay function based on the decay coefficient;
and according to the calculated weight, carrying out weighted average calculation on the slope corresponding to each target subsequence to obtain the short-term growth rate.
6. The storage capacity prediction model generation method according to any one of claims 1 to 5, wherein after decomposing the original sequence to obtain the seasonal period component corresponding to the original sequence, the method further comprises:
determining the proportion corresponding to the seasonal period component, and judging whether the proportion is greater than a preset proportion threshold value;
and if the ratio is smaller than the preset ratio threshold, prohibiting the overlapping processing of the seasonal period component, the linear main sequence and the hopping sequence, and directly overlapping the linear main sequence and the hopping sequence to generate a storage capacity prediction model.
7. The method of generating a storage capacity prediction model according to claim 6, wherein after the superimposing the seasonal period component, the linear main sequence, and the hopping sequence to generate the storage capacity prediction model, the method further comprises:
acquiring the residual storage capacity of the current server;
determining a prediction time node of the current server with the exhausted storage capacity by combining the storage capacity prediction model and the residual storage capacity;
and returning early warning prompt information comprising the predicted time node through a visual interface.
8. A storage capacity prediction method, comprising:
acquiring actual capacity use data of a server to be predicted in a preset historical time period;
inputting the actual capacity utilization data into a storage capacity prediction model to obtain a storage capacity prediction result of the server to be predicted in a preset future time period; wherein the storage capacity prediction model is a prediction model generated by the storage capacity prediction model generation method according to any one of claims 1 to 7.
9. A storage capacity prediction model generation apparatus, comprising:
the sequence acquisition module is used for acquiring an original sequence of historical storage capacity data based on time change;
the sequence decomposition module is used for decomposing the original sequence to obtain seasonal period components corresponding to the original sequence;
the variable point prediction module is used for carrying out variable point prediction based on the original jump points in the original sequence to obtain a jump sequence;
the growth calculation module is used for calculating a short-term growth rate and a long-term growth rate according to the original sequence and combining the short-term growth rate and the long-term growth rate to obtain a linear main sequence;
and the model generation module is used for performing superposition processing on the seasonal period component, the linear main sequence and the hopping sequence to generate a storage capacity prediction model, and the storage capacity prediction model is used for capacity management operation.
10. A storage capacity prediction apparatus, comprising:
the data acquisition module is used for acquiring actual capacity use data of the server to be predicted in a preset historical time period;
the capacity prediction module is used for inputting the actual capacity utilization data into a storage capacity prediction model to obtain a storage capacity prediction result of the server to be predicted within a preset future time period; wherein the storage capacity prediction model is a prediction model generated by the storage capacity prediction model generation method according to any one of claims 1 to 7.
11. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the storage capacity prediction model generation method according to any one of claims 1 to 7 when executing the computer program.
12. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the storage capacity prediction method as claimed in claim 8 when executing said computer program.
13. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the storage capacity prediction model generation method according to any one of claims 1 to 7.
14. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the storage capacity prediction method as claimed in claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011306439.9A CN112256550A (en) | 2020-11-19 | 2020-11-19 | Storage capacity prediction model generation method and storage capacity prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011306439.9A CN112256550A (en) | 2020-11-19 | 2020-11-19 | Storage capacity prediction model generation method and storage capacity prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112256550A true CN112256550A (en) | 2021-01-22 |
Family
ID=74266321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011306439.9A Pending CN112256550A (en) | 2020-11-19 | 2020-11-19 | Storage capacity prediction model generation method and storage capacity prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112256550A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344282A (en) * | 2021-06-23 | 2021-09-03 | 中国光大银行股份有限公司 | Method, system and computer readable medium for capacity data processing and allocation |
| CN113705910A (en) * | 2021-08-31 | 2021-11-26 | 深信服科技股份有限公司 | Data sample expansion method, device, equipment and medium |
| CN114363062A (en) * | 2021-12-31 | 2022-04-15 | 深信服科技股份有限公司 | Domain name detection method, system, equipment and computer readable storage medium |
| CN114518988A (en) * | 2022-02-10 | 2022-05-20 | 中国光大银行股份有限公司 | Resource capacity system, method of controlling the same, and computer-readable storage medium |
| CN115412567A (en) * | 2022-08-09 | 2022-11-29 | 浪潮云信息技术股份公司 | Cloud platform storage capacity planning system and method based on time series prediction |
| CN117368799A (en) * | 2023-12-07 | 2024-01-09 | 山西思极科技有限公司 | Diagnosis method for short-circuit fault of power transmission line of power system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6993458B1 (en) * | 2000-11-07 | 2006-01-31 | International Business Machines Corporation | Method and apparatus for preprocessing technique for forecasting in capacity management, software rejuvenation and dynamic resource allocation applications |
| CN107220851A (en) * | 2017-05-25 | 2017-09-29 | 北京中电普华信息技术有限公司 | Electricity sales amount Forecasting Methodology and device based on X13 seasonal adjustments and Cox regression |
| CN110532156A (en) * | 2019-08-22 | 2019-12-03 | 北京宝兰德软件股份有限公司 | A kind of capacity prediction methods and device |
-
2020
- 2020-11-19 CN CN202011306439.9A patent/CN112256550A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6993458B1 (en) * | 2000-11-07 | 2006-01-31 | International Business Machines Corporation | Method and apparatus for preprocessing technique for forecasting in capacity management, software rejuvenation and dynamic resource allocation applications |
| CN107220851A (en) * | 2017-05-25 | 2017-09-29 | 北京中电普华信息技术有限公司 | Electricity sales amount Forecasting Methodology and device based on X13 seasonal adjustments and Cox regression |
| CN110532156A (en) * | 2019-08-22 | 2019-12-03 | 北京宝兰德软件股份有限公司 | A kind of capacity prediction methods and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344282A (en) * | 2021-06-23 | 2021-09-03 | 中国光大银行股份有限公司 | Method, system and computer readable medium for capacity data processing and allocation |
| CN113705910A (en) * | 2021-08-31 | 2021-11-26 | 深信服科技股份有限公司 | Data sample expansion method, device, equipment and medium |
| CN114363062A (en) * | 2021-12-31 | 2022-04-15 | 深信服科技股份有限公司 | Domain name detection method, system, equipment and computer readable storage medium |
| CN114363062B (en) * | 2021-12-31 | 2024-07-09 | 深信服科技股份有限公司 | Domain name detection method, system, equipment and computer readable storage medium |
| CN114518988A (en) * | 2022-02-10 | 2022-05-20 | 中国光大银行股份有限公司 | Resource capacity system, method of controlling the same, and computer-readable storage medium |
| CN115412567A (en) * | 2022-08-09 | 2022-11-29 | 浪潮云信息技术股份公司 | Cloud platform storage capacity planning system and method based on time series prediction |
| CN115412567B (en) * | 2022-08-09 | 2024-04-30 | 浪潮云信息技术股份公司 | Cloud platform storage capacity planning system and method based on time sequence prediction |
| CN117368799A (en) * | 2023-12-07 | 2024-01-09 | 山西思极科技有限公司 | Diagnosis method for short-circuit fault of power transmission line of power system |
| CN117368799B (en) * | 2023-12-07 | 2024-02-23 | 山西思极科技有限公司 | Diagnosis method for short-circuit fault of power transmission line of power system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112256550A (en) | Storage capacity prediction model generation method and storage capacity prediction method | |
| US10523519B2 (en) | Comparative multi-forecasting analytics service stack for cloud computing resource allocation | |
| WO2021164465A1 (en) | Intelligent early warning method and system | |
| US20170329837A1 (en) | Digital analytics system | |
| CN112163887B (en) | Electric pin system, electric pin list management method, electric pin system device, electric pin list management equipment and storage medium | |
| CN103971170A (en) | Method and device for forecasting changes of feature information | |
| JP5480755B2 (en) | Demand forecasting system and demand forecasting method | |
| CN109118012B (en) | Industrial dynamic multi-dimensional energy consumption cost prediction method, system, storage medium and terminal | |
| CN112508118A (en) | Target object behavior prediction method aiming at data migration and related equipment thereof | |
| CN108614843B (en) | Website content evaluation method and device | |
| CN111080417A (en) | Processing method for improving booking smoothness rate, model training method and system | |
| CN103514506A (en) | Automatic event analysis method and system | |
| CN112036631B (en) | Purchasing quantity determining method, purchasing quantity determining device, purchasing quantity determining equipment and storage medium | |
| CN111178948B (en) | Method for realizing dynamic borrowing of shared automobile | |
| CN111832876A (en) | Vehicle scheduling method, readable storage medium and electronic device | |
| CN113705884A (en) | Assembly production line capacity prediction method, device, equipment and storage medium | |
| JP7231504B2 (en) | Meteorological Numerical Analysis System, Prediction Target Data Generation System, and Meteorological Numerical Analysis Method | |
| JP6087072B2 (en) | Water Information Asset Utilization Business Plan Management System | |
| CN117350640A (en) | Project progress management method and system | |
| CN111783487B (en) | Fault early warning method and device for card reader equipment | |
| CN110413358B (en) | Page display method and device | |
| CN114741776B (en) | Oil gas chemical industry wharf engineering digital delivery method, system and medium | |
| CN115330219A (en) | Resource scheduling method and device | |
| CN115459270A (en) | Method and device for configuring urban peak electricity consumption, computer equipment and storage medium | |
| US20230259846A1 (en) | Communications apparatus and method for estimating potential demand for improved forecasting and resource management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210122 |
|
| RJ01 | Rejection of invention patent application after publication |