Development of a complex failure prediction system using Hierarchical Attention Network (Hierarchical Attention Network를 이용한 복합 장애 발생 예측 시스템 개발)
-
- Journal of Intelligence and Information Systems
- /
- v.26 no.4
- /
- pp.127-148
- /
- 2020
The data center is a physical environment facility for accommodating computer systems and related components, and is an essential foundation technology for next-generation core industries such as big data, smart factories, wearables, and smart homes. In particular, with the growth of cloud computing, the proportional expansion of the data center infrastructure is inevitable. Monitoring the health of these data center facilities is a way to maintain and manage the system and prevent failure. If a failure occurs in some elements of the facility, it may affect not only the relevant equipment but also other connected equipment, and may cause enormous damage. In particular, IT facilities are irregular due to interdependence and it is difficult to know the cause. In the previous study predicting failure in data center, failure was predicted by looking at a single server as a single state without assuming that the devices were mixed. Therefore, in this study, data center failures were classified into failures occurring inside the server (Outage A) and failures occurring outside the server (Outage B), and focused on analyzing complex failures occurring within the server. Server external failures include power, cooling, user errors, etc. Since such failures can be prevented in the early stages of data center facility construction, various solutions are being developed. On the other hand, the cause of the failure occurring in the server is difficult to determine, and adequate prevention has not yet been achieved. In particular, this is the reason why server failures do not occur singularly, cause other server failures, or receive something that causes failures from other servers. In other words, while the existing studies assumed that it was a single server that did not affect the servers and analyzed the failure, in this study, the failure occurred on the assumption that it had an effect between servers. In order to define the complex failure situation in the data center, failure history data for each equipment existing in the data center was used. There are four major failures considered in this study: Network Node Down, Server Down, Windows Activation Services Down, and Database Management System Service Down. The failures that occur for each device are sorted in chronological order, and when a failure occurs in a specific equipment, if a failure occurs in a specific equipment within 5 minutes from the time of occurrence, it is defined that the failure occurs simultaneously. After configuring the sequence for the devices that have failed at the same time, 5 devices that frequently occur simultaneously within the configured sequence were selected, and the case where the selected devices failed at the same time was confirmed through visualization. Since the server resource information collected for failure analysis is in units of time series and has flow, we used Long Short-term Memory (LSTM), a deep learning algorithm that can predict the next state through the previous state. In addition, unlike a single server, the Hierarchical Attention Network deep learning model structure was used in consideration of the fact that the level of multiple failures for each server is different. This algorithm is a method of increasing the prediction accuracy by giving weight to the server as the impact on the failure increases. The study began with defining the type of failure and selecting the analysis target. In the first experiment, the same collected data was assumed as a single server state and a multiple server state, and compared and analyzed. The second experiment improved the prediction accuracy in the case of a complex server by optimizing each server threshold. In the first experiment, which assumed each of a single server and multiple servers, in the case of a single server, it was predicted that three of the five servers did not have a failure even though the actual failure occurred. However, assuming multiple servers, all five servers were predicted to have failed. As a result of the experiment, the hypothesis that there is an effect between servers is proven. As a result of this study, it was confirmed that the prediction performance was superior when the multiple servers were assumed than when the single server was assumed. In particular, applying the Hierarchical Attention Network algorithm, assuming that the effects of each server will be different, played a role in improving the analysis effect. In addition, by applying a different threshold for each server, the prediction accuracy could be improved. This study showed that failures that are difficult to determine the cause can be predicted through historical data, and a model that can predict failures occurring in servers in data centers is presented. It is expected that the occurrence of disability can be prevented in advance using the results of this study.
This study, designed to establish a classification system of paddy soils and suitability groups on productivity and management of paddy land based on soil characteristics, has been made for the paddy soils on the Gimje-Mangyeong plains. The morphological, physical and chemical properties of the 15 paddy soil series found on these plains are briefly as follows: Ten soil series (Baeggu, Bongnam, Buyong, Gimje, Gongdeog, Honam, Jeonbug, Jisan, Mangyeong and Suam) have a B horizon (cambic B), two soil series (Geugrag and Hwadong) have a Bt horizon (argillic B), and three soil series (Gwanghwal, Hwagye and Sindab) have no B or Bt horizons. Uniquely, both the Bongnam and Gongdeog series contain a muck layer in the lower part of subsoil. Four soil series (Baeggu, Gongdeog, Gwanghwal and Sindab) generally are bluish gray and dark gray, and eight soil series (Bongnam, Buyong, Gimje, Honam, Jeonbug, Jisan, Mangyeong and Suam) are either gray or grayish brown. Three soil series (Geugrag, Hwadong and Hwagye), however, are partially gleyed in the surface and subsurface, but have a yellowish brown to brown subsoil or substrata. Seven soil series (Bongnam, Buyong, Geugrag, Gimje, Gongdeog, Honam and Hwadong) are of fine clayey texture, three soil series (Baeggu, Jeonbug and Jisan) belong to fine loamy and fine silty, three soil series (Gwanghwal, Mangyeong and Suam) to coarse loamy and coarse silty, and two soil series (Hwagye and Sindab) to sandy and sandy skeletal texture classes. The carbon content of the surface soil ranges from 0.29 to 2.18 percent, mostly 1.0 to 2.0 percent. The total nitrogen content of the surface soil ranges from 0.03 to 0.25 percent, showing a tendency to decrease irregularly with depth. The C/N ratio in the surface soil ranges from 4.6 to 15.5, dominantly from 8 to 10. The C/N ratio in the subsoil and substrata, however, has a wide range from 3.0 to 20.25. The soil reaction ranges from 4.5 to 8.0. All soil series except the Gwanghwal and Mangyeong series belong to the acid reaction class. The cation exchange cpacity in the surface soil ranges from 5 to 13 milliequivalents per 100 grams of soil, and in all the subsoil and substrata except those of a sandy texture, from 10 to 20 milliequivalents per 100 grams of soil. The base saturation of the soil series except Baeggu and Gongdeog is more than 60 percent. The active iron content of the surface soil ranges from 0.45 to 1.81 ppm, easily-reduceable manganese from 15 to 148 ppm, and available silica from 36 to 366 ppm. The iron and manganese are generally accumulated in a similar position (10 to 70cm. depth), and silica occurs in the same horizon with that of iron and manganese, or in the deeper horizons in the soil profile. The properties of each soil series extending from the sea shore towards the continental plains change with distance and they are related with distance (x) as follows: y(surface soil, clay content) =