• 상하수도학회지
• /
• 제12권4호
• /
• pp.43-52
• /
• 1998

The purpose of this study is to establish a method of estimating the daily urban water demend using Backpropagation algorithm is part of ANN(Artificial Neural Network). This method will be used for the development of the efficient management and operations of the water supply facilities. The data used were the daily urban water demend, the population and weather conditions such as treperarture, precipitation, relative humidity, etc. Kwangju city was selected for the case study area. We adjusted the weights of ANN that are iterated the training data patterns. We normalized the non-stationary time series data [-1,+1] to fast converge, and choose the input patterns by statistical methods. We separated the training and checking patterns form input date patterns. The performance of ANN is compared with multiple-regression method. We discussed the representation ability the model building process and the applicability of ANN approach for the daily water demand. ANN provided the reasonable results for time series forecasting.

• 대한토목학회논문집
• /
• 제32권4B호
• /
• pp.233-242
• /
• 2012

기존에는 댐사업의 생활용수 공급편익 산정시 실무적으로 대체댐비용법을 적용하였다. 그러나 해당 댐의 대체시설로서 2순위의 댐을 적용하는 것은 논리적으로 적절하지 않다. 본 연구의 목적은 생활용수 공급사업의 효과에 대한 소비자의 효용을 지불의사액으로 측정하고, 수요함수를 도출하여 편익산정 방법을 제시하는 것이다. 이를 위해 수도권지역에서 1,000가구를 대상으로 생활용수의 사용량 변화에 대한 한계지불의사액을 측정하였다. 그리고 한계지불의사액을을 이용하여 가구별 수요함수를 추정하고, 최종적으로 용수공급 사업의 경제성분석에 적용할 수 있는 월평균 편익산정식을 도출하였다. 제시된 방법론은 적용방법 설명과 토론을 위해 예제로서 송리원댐(현 영주댐)에 적용하였다. 예제 적용 결과, 내용연수인 50년간 총 편익은 약 900억원으로 산정되었다. 본 연구에서 제시된 방법론은 향후 관련 연구 뿐 아니라, 댐 건설사업을 비롯한 생활용수 공급사업에서 경제성분석시 실무적 활용이 가능할 것으로 기대된다.

• 한국지능시스템학회논문지
• /
• 제19권5호
• /
• pp.713-719
• /
• 2009

본 논문은 비선형 특성을 내재한 물 수요예측을 위하여 기존의 시계열 자기회귀 알고리즘과 다층신경망 학습방법을 결합한 단기 물 수요 예측 알고리즘을 개발하였다. 제시된 방법을 검증하기 위한 사례연구로 2007년도와 2008년도 전북지역의 광역상수도 A정수장에서 취득된 데이터를 활용하여 알고리즘 구축 및 제안 방법의 정확도를 분석하였다. 실험 결과 다중회귀모델은 MAPE가 5.1%, AR모델은 3.8%, 제안된 방법인 AR+MLP 모델은 3.6%로 나타나 성능이 우수한 것으로 나타났다. 따라서 제안된 방법을 사용할 경우 정수장에서 단기 물 수요예측에 유용하게 활용할 수 있음을 보였다.

• 한국농공학회논문집
• /
• 제55권4호
• /
• pp.45-53
• /
• 2013

Efficient water operation and management of an irrigation system plays an important element in the sustainability of irrigated agriculture. An agricultural water is delivered in many open canals of irrigation delivery system by reservoirs. The poor water distribution and management in an irrigation system is a major factor leading to low water efficiency. It is necessary to compare the estimated irrigation demands with the actual water supplies for decision making to maintain the water supply according to demand strategy. Smarter water management, new technologies and improvement of water management system, is essential to solve the problem of water efficiency and availability. In this paper, the irrigation efficiencies according to water delivery performance indicator were measured with automatic water gauge at irrigation canals, and calculated from spatial and temporal distribution of water supply for the lack of planning in water delivery. The analysis of results are obtain an insight into possible improvement methods to develop canal water management policies that enable irrigation planners to optimally manage scarce available water resources.

• 물과 미래
• /
• 제18권4호
• /
• pp.347-359
• /
• 1985

본 연구는 단일다목적 저수지의 운영정책을 수립함에 있어서, DP를 적용하여 댐의 여러 물리적 제약조건하에서 댐 하류의 용수수요를 최대로 충족시킬 수 있는 월별 저수지 최대 운영정책을 수립하는 알고리즘을 개발하는데 주안점을 두었다. 분석대상인 안동댐의 과거 월평균 유입량으로부터 장래 월유입량을 모의발생시키고, 그 모의 발생된 자료 중에서 ddlqfid 계열 A, B, C를 선정하여, 각 계열별로 낙동강 본류의 용수수요 중에서 안동댐이 30%∼100%까지 충족시킬 수 있도록 8개의 대안을 설정하였다. 그리고 DP 모델을 적용시켜 물 수요량과 운영곡선에 근거한 시스템 운영목적함수를 가장 잘 수행하는 대안을 최적 운영 정책으로 결정하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.220-220
• /
• 2015

Water, energy, and food security already became a risk that threatens people around the world. Increasing of resources demand, rapid urbanization, decreasing of natural resources and climate change are four major problems inducing resources' scarcity. Indeed, water, energy, and food are interconnected each other thus cannot be analyzed separately. That is, for simple example, energy needs water as source for hydropower plant, water needs energy for distribution, and food needs water and energy for production, which is defined as W-E-F nexus. Due to their complicated linkage, it needs a computer model to simulate and analyze the nexus. Development of a computer simulation model using system dynamics approach makes this linkage possible to be visualized and quantified. System dynamics can be defined as an approach to learn the feedback connections of all elements in a complex system, which mean, every element's interaction is simulated simultaneously. Present W-E-F nexus models do not calculate and simulate the element's interaction simultaneously. Existing models only calculate the amount of water and energy resources that needed to provide food, water, or energy without any interaction from the product to resources. The new proposed model tries to cope these lacks by adding the interactions, climate change effect, and government policy to optimize the best options to maintain the resources sustainability. On this first phase of development, the model is developed only to learn and analyze the interaction between elements based on scenario of fulfilling the increasing of resources demand, due to population growth. The model is developed using the Vensim, well-known system dynamics model software. The results are amount of total water, energy, and food demand and production for a certain time period and it is evaluated to determine the sustainability of resources.

• Membrane and Water Treatment
• /
• 제10권1호
• /
• pp.1-11
• /
• 2019

The Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report (AR5) predicted that recent extreme hydrological events would affect water quality and aggravate various forms of water pollution. To analyze changes in water quality due to future climate change, input data (precipitation, average temperature, relative humidity, average wind speed and sunlight) were established using the Representative Concentration Pathways (RCP) 8.5 climate change scenario suggested by the AR5 and calculated the future runoff for each target period (Reference:1989-2015; I: 2016-2040; II: 2041-2070; and III: 2071-2099) using the semi-distributed land use-based runoff processes (SLURP) model. Meteorological factors that affect water quality (precipitation, temperature and runoff) were inputted into the multiple linear regression analysis (MLRA) and artificial neural network (ANN) models to analyze water quality data, dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand (COD), suspended solids (SS), total nitrogen (T-N) and total phosphorus (T-P). Future water quality prediction of the Anseongcheon River basin shows that DO at Gongdo station in the river will drop by 35% in autumn by the end of the $21^{st}$ century and that BOD, COD and SS will increase by 36%, 20% and 42%, respectively. Analysis revealed that the oxygen demand at Dongyeongyo station will decrease by 17% in summer and BOD, COD and SS will increase by 30%, 12% and 17%, respectively. This study suggests that there is a need to continuously monitor the water quality of the Anseongcheon River basin for long-term management. A more reliable prediction of future water quality will be achieved if various social scenarios and climate data are taken into consideration.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.516-516
• /
• 2022

Agricultural reservoirs are critical water resources structures to ensure continuous water supplies for rice cultivation in Korea. Climate change has increased the risk of reservoir failure by exacerbating discrepancies in upstream runoff generation, downstream irrigation water demands, and evaporation losses. In this study, the variations in water balance components of 400 major reservoirs during 1973-2017 were examined to identify the reservoirs with reliable storage capacities and resilience. A conceptual lumped hydrological model was used to transform the incident rainfall into the inflows entering the reservoirs and the paddy water balance model was used to estimate the irrigation water demand. Historical climate data analysis showed a sharp warming gradient during the last 45 years that was particularly evident in the central and southern regions of the country, which were also the main agricultural areas with high reservoir density. We noted a country-wide progressive increase in average annual cumulative rainfall, but the forcing mechanism of the rainfall increment and its spatial-temporal trends were not fully understood. Climate warming resulted in a significant increase in irrigation water demand, while heavy rains increased runoff generation in the reservoir watersheds. Most reservoirs had reliable storage capacities to meet the demands of a 10-year return frequency drought but the resilience of reservoirs gradually declined over time. This suggests that the recovery time of reservoirs from the failure state had increased which also signifies that the duration of the dry season has been prolonged while the wet season has become shorter and/or more intense. The watershed-irrigated area ratio (W-I_ratio) was critical and the results showed that a slight disruption in reservoir water balance under the influence of future climate change would seriously compromise the performance of reservoirs with W-I_ratio< 5.

• 펄프종이기술
• /
• 제36권2호
• /
• pp.54-59
• /
• 2004

The methods for the minimization of fresh water consumption, waste water generation and water contamination have been greatly investigated and developed for last ten years. Recently, the rising cost of waste water treatment and the more strict environmental regulation lead to the higher demand of more efficient and systematic methods for process water management. The water reuse technology, which not only reduce the process water needs but also minimize waste water generation within the process, could be one of most efficient way for current demand. In this study, the practical way for reduction of water pollution and optimal reuse or recycle of process water in a newsprint mill was investigated by using a simulation model. The result of computer simulation showed that the COD level of approach system could be reduced by 50% after the stock concentration at the 2nd disc filter was increased upto 30%. The application of WRDF(Wrinkled Rotary Drum Filter) to the newsprint mill was carried out with pilot scale. The process water treated by WRDF had enough cleanliness to substitute the forming fabric shower water with the PDF water, which could result in the 30% reduction in fresh water consumption.

• Water Engineering Research
• /
• 제3권4호
• /
• pp.269-278
• /
• 2002

A cross sectional analysis for residential water demand was conducted to help understand and explain the spatial and temporal variations in per capita water use in the rapidly growing city of Riyadh, Saudi Arabia. The analysis was based on data previously collected from May 1983 to June 1984. 195 randomly selected households were distributed to three groups according to house condition, household income level, and social and cultural factors. The generated models using stepwise multiple regression indicated that plot size and number of males, females and children are the most significant independent variables. Although, coefficients of determination achieved for most of the developed models were low (0.2-0.5), the independent variables could still explain a part of the variations fur such a complex social and cultural structure.