CN110705780A - IT performance index prediction method based on intelligent algorithm - Google Patents
IT performance index prediction method based on intelligent algorithm Download PDFInfo
- Publication number
- CN110705780A CN110705780A CN201910925841.6A CN201910925841A CN110705780A CN 110705780 A CN110705780 A CN 110705780A CN 201910925841 A CN201910925841 A CN 201910925841A CN 110705780 A CN110705780 A CN 110705780A
- Authority
- CN
- China
- Prior art keywords
- performance index
- trend
- index data
- algorithm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000008859 change Effects 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 230000000737 periodic effect Effects 0.000 claims description 30
- 230000001174 ascending effect Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000012417 linear regression Methods 0.000 claims description 10
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an IT performance index prediction method based on an intelligent algorithm, which comprises the following steps: (1) analyzing and classifying a large amount of various IT performance index data after changing trends are analyzed to obtain various changing trends and corresponding IT performance index data; (2) respectively finding corresponding algorithms for modeling according to each type of change trend to obtain a prediction model; (3) and selecting an optimal model by using a model evaluation method, and predicting the IT performance index to be predicted through the optimal model. The method can help operation and maintenance personnel to know the change trend of the index in advance, so that measures are taken in advance, and faults caused by the measures are reduced.
Description
Technical Field
The invention relates to the field of IT data analysis methods, in particular to an IT performance index prediction method based on an intelligent algorithm.
Background
The IT performance index prediction mainly predicts time series data (i.e., data that changes with time), for example, index values such as CPU usage, memory usage, and disk capacity may increase or decrease with time, and for the prediction of such data, an ARIMA algorithm, a Holt-winter algorithm, a neural network algorithm, and the like are mainly used. At present, under the background technology of large IT performance index prediction, a single or simple combined prediction algorithm is mainly adopted to singly predict the CPU utilization rate condition, the memory occupancy rate condition, the disk capacity condition and the like, and because the applied IT performance index types need to be considered, the situations are not fused together to form a unified prediction system.
Disclosure of Invention
The invention aims to provide an IT performance index prediction method based on an intelligent algorithm, and aims to solve the problems that the application target of the IT performance index prediction method in the prior art is single, and unified prediction of various IT performance indexes cannot be realized.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
an IT performance index prediction method based on an intelligent algorithm comprises the following steps:
(1) extracting a large amount of various IT performance index data, analyzing the IT performance index data in a variation trend, and then classifying to obtain various variation trends and at least one IT performance index data corresponding to each variation trend;
(2) respectively finding corresponding algorithms according to each type of variation trend to carry out modeling so as to obtain prediction models of each type of variation trend;
(3) and (3) selecting an optimal model from the prediction models obtained in the step (2) by using a model evaluation method for the IT performance index to be predicted, and then predicting the IT performance index to be predicted through the optimal model.
An IT performance index prediction method based on an intelligent algorithm, wherein the classification process in the step (1) is as follows:
when the IT performance index data is in a linear ascending or descending trend along with the increase of time, defining and classifying the IT performance index data into a linear change trend;
defining and classifying the IT performance index data into a stable sequence variation trend when the IT performance index data shows a trend of fluctuating around the mean value;
when the IT performance index data shows an ascending trend or a descending trend which fluctuates up and down along an inclined straight line, defining and classifying the IT performance index data into a fluctuation change trend;
when the IT performance index data shows periodic variation and shows a linear ascending or descending trend, defining and classifying the IT performance index data as a periodic linear trend;
when the IT performance index data shows periodic variation but does not show linear ascending or descending trend, the IT performance index data is defined and classified as having periodic nonlinear trend.
In the step (2), for the linear variation trend, modeling is performed by using a linear regression algorithm in combination with the corresponding timestamp and IT performance index data to obtain a linear trend prediction model.
In the step (2), for the steady sequence change trend, modeling is performed by using a neural network algorithm by using corresponding IT performance index data to obtain a steady trend prediction model.
In the step (2), for the fluctuation variation trend, modeling is performed by using the corresponding IT performance index data and utilizing a combination of a linear regression algorithm and a neural network algorithm to obtain a fluctuation trend prediction model, wherein the linear regression algorithm is fitted with a linear trend part, and the neural network algorithm is fitted with a fluctuation trend part.
In the step (2), for the periodic linear trend, using corresponding IT performance index data, and utilizing a trend and period based algorithm or an ARIMA algorithm to model, so as to obtain a periodic linear trend prediction model, wherein the trend and period algorithm is used for modeling the long period linear trend, and the ARIMA algorithm is used for modeling the short period linear trend.
In the step (2), for the periodic nonlinear trend, modeling is performed by using a neural network algorithm based on the period by using corresponding IT performance index data to obtain a periodic nonlinear trend prediction model.
An IT performance index prediction method based on an intelligent algorithm is characterized in that in the step (2), a model base is formed by prediction models of various change trends.
The model evaluation method in the step (3) uses average absolute percentage error MAPE as an evaluation standard of an optimal model, the MAPE is a mean value of a ratio of a residual absolute value to an actual value, and the smaller the MAPE value is, the better the model prediction effect is.
In the step (3), IT performance index data to be predicted in a period of time is loaded to an optimal model, and the prediction time length is set, so that the IT performance index change trend data in the prediction time length can be obtained.
The invention can provide the future trend of the IT performance index for operation and maintenance personnel, and discover possible early warning in advance, thereby taking preventive measures and reducing the failure rate.
Compared with the prior art, the invention has the advantages that:
1. the problem that the application is single in the current IT performance index prediction scene is solved, the index type is not considered, only the data change trend is considered, and the application is wider.
2. The early warning function can be realized, so that measures are taken in advance, and the fault occurrence rate caused by overhigh occupation of a CPU, a memory and the like is reduced.
Drawings
Fig. 1 is a flow chart of an IT performance index prediction method based on an intelligent algorithm according to the present invention.
FIG. 2 is an example of a trend graph provided by an embodiment of the present invention: and (5) a linear variation trend graph.
FIG. 3 is an example of a trend graph provided by an embodiment of the present invention: and (4) a smooth sequence change trend graph.
FIG. 4 is an example of a trend graph provided by an embodiment of the present invention: and (5) a fluctuation trend graph.
FIG. 5 is an example of a trend graph provided by an embodiment of the present invention: periodic linear variation trend chart
FIG. 6 is an example of a trend graph provided by an embodiment of the present invention: there is a periodic non-linear trend graph.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
As shown in fig. 1, an IT performance index prediction method based on an intelligent algorithm includes the following steps:
(S1) IT performance index trend classification: extracting a large amount of IT performance index data, analyzing the variation trend, and classifying various variation trends into five categories, namely a linear variation trend, a stable sequence variation trend, a fluctuation variation trend, a periodic linear variation trend and a periodic nonlinear variation trend;
(S2) index variation trend type definition:
(1) as shown in fig. 2, when the IT performance index data is in a linear ascending or descending trend with the increase of time, IT is defined as a linear variation trend;
(2) as shown in fig. 3, when the IT performance index data shows a trend of fluctuating around the mean, IT is defined as a steady sequence variation trend;
(3) as shown in fig. 4, when the IT performance index data shows an upward or downward trend fluctuating up and down along an inclined straight line, IT is defined as a fluctuation trend;
(4) as shown in fig. 5, when the IT performance index data shows a periodic variation and shows a linear ascending or descending trend, IT is defined that there is a periodic linear variation trend;
(5) as shown in fig. 6, when the IT performance index data shows a periodic variation but does not show a linear ascending or descending trend, IT is defined that there is a periodic non-linear variation trend.
(S3) constructing a linear regression equation of the performance index and time using a linear regression algorithm and historical data of the performance index according to the characteristic of the linear variation trend, and predicting a future trend of the linear trend performance index by using the constructed linear regression equation future time stamp data.
(S4) according to the characteristic of the steady sequence change trend, using a BP neural network algorithm to sequentially slide, calculate and predict the historical data of the performance index according to a certain sample size, thereby obtaining a prediction model of the trend;
(S5) according to the characteristics of the fluctuation trend, firstly, using a linear regression algorithm to construct a model to fit the ascending or descending trend of the trend, then removing the linear trend, using a BP neural network algorithm to fit the ascending or descending trend of the trend, and combining the two algorithms to construct a fluctuation trend prediction model;
(S6) according to the characteristic of periodic linear change trend, constructing a prediction model with a shorter period and a periodic linear trend by using an ARIMA algorithm; a prediction model with a long period and a periodic linear trend is constructed by using a trend and period-based algorithm (namely STL is applied to the time series of the performance indexes for decomposition, and a stlm predictor is used for prediction);
(S7) according to the characteristic of periodic nonlinear change trend, using a periodic BP neural network algorithm to sequentially predict historical data of the performance index in a sliding manner according to the period and a certain sample size, thereby obtaining a prediction model of the trend;
(S8) IT performance index prediction model library: the five steps construct prediction models with different IT performance index trends to form a prediction model library, so that the trend does not need to be judged when the new IT performance index is predicted, and the new IT performance index directly enters the model library to be matched with the optimal model for prediction;
(S9) selecting an optimal model evaluation index: performing optimal model evaluation by using MAPE (mean absolute percentage error), wherein the smaller the MAPE value is, the better the model prediction effect is;
(S11) constructing prediction interfaces of different models according to the difference of each algorithm;
(S12) model prediction: after the optimal prediction model selected by MAPE is used, the IT performance index is predicted by using a prediction interface of the selected optimal model;
(S13) use of IT performance index prediction model library: the method can realize the real-time prediction of the IT index trend and the storage of the prediction result only by providing historical data of the IT performance index for one month and utilizing the established prediction model library and the optimal model evaluation index;
and (S14) realizing the function of early warning according to the prediction result.
The embodiments of the present invention are described only for the preferred embodiments of the present invention, and not for the limitation of the concept and scope of the present invention, and various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the design concept of the present invention shall fall within the protection scope of the present invention, and the technical contents of the present invention which are claimed are all described in the claims.
Claims (10)
1. An IT performance index prediction method based on an intelligent algorithm is characterized in that: the method comprises the following steps:
(1) extracting a large amount of various IT performance index data, analyzing the IT performance index data in a variation trend, and then classifying to obtain various variation trends and at least one IT performance index data corresponding to each variation trend;
(2) respectively finding corresponding algorithms according to each type of variation trend to carry out modeling so as to obtain prediction models of each type of variation trend;
(3) and (3) selecting an optimal model from the prediction models obtained in the step (2) by using a model evaluation method for the IT performance index to be predicted, and then predicting the IT performance index to be predicted through the optimal model.
2. The IT performance index prediction method based on an intelligent algorithm as claimed in claim 1, characterized in that: the classification process in step (1) is as follows:
when the IT performance index data is in a linear ascending or descending trend along with the increase of time, defining and classifying the IT performance index data into a linear change trend;
defining and classifying the IT performance index data into a stable sequence variation trend when the IT performance index data shows a trend of fluctuating around the mean value;
when the IT performance index data shows an ascending trend or a descending trend which fluctuates up and down along an inclined straight line, defining and classifying the IT performance index data into a fluctuation change trend;
when the IT performance index data shows periodic variation and shows a linear ascending or descending trend, defining and classifying the IT performance index data as a periodic linear trend;
when the IT performance index data shows periodic variation but does not show linear ascending or descending trend, the IT performance index data is defined and classified as having periodic nonlinear trend.
3. The IT performance index prediction method based on the intelligent algorithm as claimed in claim 1 or 2, characterized in that: and (3) for the linear variation trend in the step (2), modeling is carried out by utilizing a linear regression algorithm by combining the corresponding time stamp and the IT performance index data, so as to obtain a linear trend prediction model.
4. The IT performance index prediction method based on the intelligent algorithm as claimed in claim 1 or 2, characterized in that: and (3) for the steady sequence change trend in the step (2), modeling is carried out by using a neural network algorithm by using corresponding IT performance index data to obtain a steady trend prediction model.
5. The IT performance index prediction method based on the intelligent algorithm as claimed in claim 1 or 2, characterized in that: and (3) modeling the fluctuation variation trend by using corresponding IT performance index data and utilizing a combination of a linear regression algorithm and a neural network algorithm to obtain a fluctuation trend prediction model, wherein the linear regression algorithm is fitted with a linear trend part, and the neural network algorithm is fitted with a fluctuation trend part.
6. The IT performance index prediction method based on the intelligent algorithm as claimed in claim 1 or 2, characterized in that: and (3) for the periodic linear trend, using corresponding IT performance index data, and modeling by using a trend and period based algorithm or an ARIMA algorithm to obtain a periodic linear trend prediction model, wherein the trend and period algorithm is used for modeling the long period linear trend, and the ARIMA algorithm is used for modeling the short period linear trend.
7. The IT performance index prediction method based on the intelligent algorithm as claimed in claim 1 or 2, characterized in that: and (3) for the periodic nonlinear trend, modeling by using corresponding IT performance index data and a periodic-based neural network algorithm to obtain a periodic nonlinear trend prediction model.
8. The IT performance index prediction method based on an intelligent algorithm as claimed in claim 1, characterized in that: and (3) forming a model library by the prediction models of various change trends in the step (2).
9. The IT performance index prediction method based on an intelligent algorithm as claimed in claim 1, characterized in that: and (3) the model evaluation method of the step (3) uses the average absolute percentage error MAPE as the evaluation standard of the optimal model, the MAPE is the mean value of the ratio of the residual absolute value to the actual value, and the smaller the MAPE value is, the better the model prediction effect is.
10. The IT performance index prediction method based on an intelligent algorithm as claimed in claim 1, characterized in that: and (3) loading the IT performance index data to be predicted in a period of time to the optimal model, and setting the prediction time length to obtain the IT performance index change trend data in the prediction time length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910925841.6A CN110705780A (en) | 2019-09-27 | 2019-09-27 | IT performance index prediction method based on intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910925841.6A CN110705780A (en) | 2019-09-27 | 2019-09-27 | IT performance index prediction method based on intelligent algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110705780A true CN110705780A (en) | 2020-01-17 |
Family
ID=69196972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910925841.6A Pending CN110705780A (en) | 2019-09-27 | 2019-09-27 | IT performance index prediction method based on intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705780A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990552A (en) * | 2021-02-20 | 2021-06-18 | 节点互联(北京)科技有限公司 | Equipment operation parameter short-time prediction method and system based on change rate |
| CN113157537A (en) * | 2020-11-13 | 2021-07-23 | 国家电网有限公司信息通信分公司 | AI algorithm-based information system resource capacity prediction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182800A (en) * | 2013-05-21 | 2014-12-03 | 中国农业科学院棉花研究所 | Intelligent predicting method for time sequence based on trend and periodic fluctuation |
| CN104899451A (en) * | 2015-06-12 | 2015-09-09 | 哈尔滨工业大学 | Time sequence prediction model selecting method based on statistical signal process |
| CN106021080A (en) * | 2016-05-10 | 2016-10-12 | 国家电网公司 | Method for intelligently predicting resource consumption trend of application middleware database connection pool |
| CN108920324A (en) * | 2018-06-08 | 2018-11-30 | 广东轩辕网络科技股份有限公司 | The method of the trend analysis of information technoloy equipment memory capacity and early warning, system and electronic device |
| CN109272142A (en) * | 2018-08-14 | 2019-01-25 | 苏州朗动网络科技有限公司 | Data predication method, device, computer equipment and storage medium based on event |
| CN109960573A (en) * | 2018-12-29 | 2019-07-02 | 天津南大通用数据技术股份有限公司 | A kind of cross-domain calculating task dispatching method and system based on Intellisense |
-
2019
- 2019-09-27 CN CN201910925841.6A patent/CN110705780A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182800A (en) * | 2013-05-21 | 2014-12-03 | 中国农业科学院棉花研究所 | Intelligent predicting method for time sequence based on trend and periodic fluctuation |
| CN104899451A (en) * | 2015-06-12 | 2015-09-09 | 哈尔滨工业大学 | Time sequence prediction model selecting method based on statistical signal process |
| CN106021080A (en) * | 2016-05-10 | 2016-10-12 | 国家电网公司 | Method for intelligently predicting resource consumption trend of application middleware database connection pool |
| CN108920324A (en) * | 2018-06-08 | 2018-11-30 | 广东轩辕网络科技股份有限公司 | The method of the trend analysis of information technoloy equipment memory capacity and early warning, system and electronic device |
| CN109272142A (en) * | 2018-08-14 | 2019-01-25 | 苏州朗动网络科技有限公司 | Data predication method, device, computer equipment and storage medium based on event |
| CN109960573A (en) * | 2018-12-29 | 2019-07-02 | 天津南大通用数据技术股份有限公司 | A kind of cross-domain calculating task dispatching method and system based on Intellisense |
Non-Patent Citations (1)
| Title |
|---|
| 周勇 编: "首届应用统计专业硕士优秀案例选", 中国统计出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157537A (en) * | 2020-11-13 | 2021-07-23 | 国家电网有限公司信息通信分公司 | AI algorithm-based information system resource capacity prediction method |
| CN112990552A (en) * | 2021-02-20 | 2021-06-18 | 节点互联(北京)科技有限公司 | Equipment operation parameter short-time prediction method and system based on change rate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647900B (en) | Intelligent safety situation prediction method, device and system based on deep neural network | |
| US9208209B1 (en) | Techniques for monitoring transformation techniques using control charts | |
| CN111274652B (en) | Method and system for manufacturing new parts according to optimized manufacturing process | |
| CN111030869B (en) | Network traffic prediction method and prediction device | |
| CN105491599B (en) | Predict the novel regression system of LTE network performance indicator | |
| US8874409B2 (en) | Multi-step time series prediction in complex instrumented domains | |
| CN106951984A (en) | A kind of dynamic analyzing and predicting method of system health degree and device | |
| CN114285728B (en) | Predictive model training method, traffic prediction device and storage medium | |
| WO2015175629A1 (en) | System and method for modeling and/or analyzing manufacturing processes | |
| CN109753591A (en) | Operation flow predictability monitoring method | |
| CN110705780A (en) | IT performance index prediction method based on intelligent algorithm | |
| Wang et al. | Anticipated rationing policy for two demand classes under service level constraints | |
| JP7422272B2 (en) | Method and apparatus for facilitating storage of data from industrial automation control systems or power systems | |
| CN111191909A (en) | Electricity stealing identification system based on data analysis of typical electricity stealing industry and historical electricity stealing sample library | |
| CN114692959A (en) | Urban energy data fusion system based on gray level correlation analysis method | |
| CN108268351B (en) | Method and system for accurately monitoring process running state | |
| JP2004023114A (en) | Method and system for predicting communication traffic | |
| Dogramaci et al. | Replacement decisions with maintenance under uncertainty: an imbedded optimal control Model | |
| CN113610575B (en) | Product sales prediction method and prediction system | |
| CN111800807A (en) | Method and device for alarming number of base station users | |
| CN115689331A (en) | Power transmission and transformation project quantity rationality analysis method based on MLP | |
| CN115219935A (en) | New energy equipment health condition evaluation method, system, device and medium | |
| CN115577295A (en) | Data detection method and device, computer equipment and storage medium | |
| CN112580875B (en) | Fault prediction method and system for power distribution device | |
| Dandekar | An Approach for Anomaly Detection & Prediction in Time-series Telecommunication Data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |