• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.237-237
• /
• 2015

The district of Marlborough has had more than its share of river management projects over the past 150 years, each one uniquely affecting the geomorphology and flood hazard of the Wairau Plains. A major early project was to block the Opawa distributary channel at Conders Bend. The Opawa distributary channel took a third and more of Wairau River floodwaters and was a major increasing threat to Blenheim. The blocking of the Opawa required the Wairau and Lower Wairau rivers to carry greater flood flows more often. Consequently the Lower Wairau River was breaking out of its stopbanks approximately every seven years. The idea of diverting flood waters at Tuamarina by providing a direct diversion to the sea through the beach ridges was conceptualised back around the 1920s however, limits on resources and machinery meant the mission of excavating this diversion didn't become feasible until the 1960s. In 1964 a 10 m wide pilot channel was cut from the sea to Tuamarina with an initial capacity of $700m^3/s$. It was expected that floods would eventually scour this 'Wairau Diversion' to its design channel width of 150 m. This did take many more years than initially thought but after approximately 50 years with a little mechanical assistance the Wairau Diversion reached an adequate capacity. Using the power of the river to erode the channel out to its design width and depth was a brilliant idea that saved many thousands of dollars in construction costs and it is somewhat ironic that it is that very same concept that is now being used to deal with the aggradation problem that the Wairau Diversion has caused. The introduction of the Wairau Diversion did provide some flood relief to the lower reaches of the river but unfortunately as the Diversion channel was eroding and enlarging the Lower Wairau River was aggrading and reducing in capacity due to its inability to pass its sediment load with reduced flood flows. It is estimated that approximately $2,000,000m^3$ of sediment was deposited on the bed of the Lower Wairau River in the time between the Diversion's introduction in 1964 and 2010, raising the Lower Wairau's bed upwards of 1.5m in some locations. A numerical morphological model (MIKE-11 ST) was used to assess a number of options which led to the decision and resource consent to construct an erodible (fuse plug) bank at the head of the Wairau Diversion to divert more frequent scouring-flows ($+400m^3/s$)down the Lower Wairau River. Full control gates were ruled out on the grounds of expense. The initial construction of the erodible bank followed in late 2009 with the bank's level at the fuse location set to overtop and begin washing out at a combined Wairau flow of $1,400m^3/s$ which avoids berm flooding in the Lower Wairau. In the three years since the erodible bank was first constructed the Wairau River has sustained 14 events with recorded flows at Tuamarina above $1,000m^3/s$ and three of events in excess of $2,500m^3/s$. These freshes and floods have resulted in washout and rebuild of the erodible bank eight times with a combined rebuild expenditure of $80,000. Marlborough District Council's Rivers & Drainage Department maintains a regular monitoring program for the bed of the Lower Wairau River, which consists of recurrently surveying a series of standard cross sections and estimating the mean bed level (MBL) at each section as well as an overall MBL change over time. A survey was carried out just prior to the installation of the erodible bank and another survey was carried out earlier this year. The results from this latest survey show for the first time since construction of the Wairau Diversion the Lower Wairau River is enlarging. It is estimated that the entire bed of the Lower Wairau has eroded down by an overall average of 60 mm since the introduction of the erodible bank which equates to a total volume of $260,000m^3$. At a cost of $$0.30/m^3$ this represents excellent value compared to mechanical dredging which would likely be in excess of $$10/m^3$. This confirms that the idea of using the river to enlarge the channel is again working for the Wairau River system and that in time nature's "excavator" will provide a channel capacity that will continue to meet design requirements.

• 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.