A Novel Hybrid Ensemble Learning Approach for Enhancing Accuracy and Sustainability in Wind Power Forecasting

Accurate wind power forecasting is critical for system integration and stability as renewable energy reliance grows.Traditional approaches frequently struggle with complex data and non-linear connections. This article presentsa novel approach for hybrid ensemble learning that is based on rigorous requirements engineering concepts.The approach finds significant parameters influencing forecasting accuracy by evaluating real-time Modern-EraRetrospective Analysis for Research and Applications (MERRA2) data from several European Wind farms usingin-depth stakeholder research and requirements elicitation. Ensemble learning is used to develop a robust model,while a temporal convolutional network handles time-series complexities and data gaps. The ensemble-temporalneural network is enhanced by providing different input parameters including training layers, hidden and dropoutlayers along with activation and loss functions. The proposed framework is further analyzed by comparing stateof-the-art forecasting models in terms of Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE),respectively. The energy efficiency performance indicators showed that the proposed model demonstrates errorreduction percentages of approximately 16.67%, 28.57%, and 81.92% for MAE, and 38.46%, 17.65%, and 90.78%for RMSE for MERRAWind farms 1, 2, and 3, respectively, compared to other existingmethods. These quantitativeresults show the effectiveness of our proposed model with MAE values ranging from 0.0010 to 0.0156 and RMSEvalues ranging from 0.0014 to 0.0174. This work highlights the effectiveness of requirements engineering in windpower forecasting, leading to enhanced forecast accuracy and grid stability, ultimately paving the way for moresustainable energy solutions.

Artificial Intelligence Technique in Hydrological Forecasts Supporting for Water Resources Management of a Large River Basin in Vietnam

Hydrological forecasting plays an important role in water resource management, supporting socio-economic development and managing water-related risks in river basins. There are many flow forecasting techniques that have been developed several centuries ago, ranging from physical models, physics-based models, conceptual models, and data-driven models. Recently, Artificial Intelligence (AI) has become an advanced technique applied as an effective data-driven model in hydrological forecasting. The main advantage of these models is that they give results with compatible accuracy, and require short computation time, thus increasing forecasting time and reducing human and financial effort. This study evaluates the applicability of machine learning and deep learning in Hanoi water level forecasting where it is controlled for flood management and water supply in the Red River Delta, Vietnam. Accordingly, SANN (machine learning algorithm) and LSTM (deep learning algorithm) were tested and compared with a Physics-Based Model (PBM) for the Red River Delta. The results show that SANN and LSTM give high accuracy. The R-squared coefficient is greater than 0.8, the mean squared error (MSE) is less than 20 cm, the correlation coefficient of the forecast hydrology is greater than 0.9 and the level of assurance of the forecast plan ranges from 80% to 90% in both cases. In addition, the calculation time is much reduced compared to the requirement of PBM, which is its limitation in hydrological forecasting for large river basins such as the Red River in Vietnam. Therefore, SANN and LSTM are expected to help increase lead time, thereby supporting water resource management for sustainable development and management of water-related risks in the Red River Delta.

Real-time flood forecasting of Huai River with flood diversion and retarding areas

A combination of the rainfall-runoff module of the Xin’anjiang model, the Muskingum routing method, the water stage simulating hydrologic method, the diffusion wave nonlinear water stage method, and the real-time error correction method is applied to the real-time flood forecasting and regulation of the Huai River with flood diversion and retarding areas. The Xin’anjiang model is used to forecast the flood discharge hydrograph of the upstream and tributary. The flood routing of the main channel and flood diversion areas is based on the Muskingum method. The water stage of the downstream boundary condition is calculated with the water stage simulating hydrologic method and the water stages of each cross section are calculated from downstream to upstream with the diffusion wave nonlinear water stage method. The input flood discharge hydrograph from the main channel to the flood diversion area is estimated with the fixed split ratio of the main channel discharge. The flood flow inside the flood retarding area is calculated as a reservoir with the water balance method. The faded-memory forgetting factor least square of error series is used as the real-time error correction method for forecasting discharge and water stage. As an example, the combined models were applied to flood forecasting and regulation of the upper reaches of the Huai River above Lutaizi during the 2007 flood season. The forecast achieves a high accuracy and the results show that the combined models provide a scientific way of flood forecasting and regulation for a complex watershed with flood diversion and retarding areas.

Complementary system-theoretic modelling approach for enhancing hydrological forecasting

Hydrologic models generally represent the most dominant processes since they are mere simplifications of physical reality and thus are subject to many significant uncertainties. As such, a coupling strategy is proposed. To this end, the coupling of the artificial neural network （ANN） with the Xin＇anjiang conceptual model with a view to enhance the quality of its flow forecast is presented. The approach uses the latest observations and residuals in runoff/discharge forecasts from the Xin＇anjiang model. The two complementary models （Xin＇anjiang ＆ ANN） are used in such a way that residuals of the Xin＇anjiang model are forecasted by a neural network model so that flow forecasts can be improved as new observations come in. For the complementary neural network, the input data were presented in a patterned format to conform to the calibration regime of the Xin＇anjiang conceptual model, using differing variants of the neural network scheme. The results show that there is a substantial improvement in the accuracy of the forecasts when the complementary model was operated on top of the Xin＇anjiang conceptual model as compared with the results of the Xin＇anjiang model alone.

TIME SERIES NEURAL NETWORK MODEL FOR HYDROLOGIC FORECASTING

Time series analysis plays an important role in hydrologic forecasting,while the key to this analysis is to establish a proper model.This paper presents a time series neural network model with back propagation procedure for hydrologic forecasting.Free from the disadvantages of previous models,the model can be parallel to operate information flexibly and rapidly.It excels in the ability of nonlinear mapping and can learn and adjust by itself,which gives the model a possibility to describe the complex nonlinear hydrologic process.By using directly a training process based on a set of previous data, the model can forecast the time series of stream flow.Moreover,two practical examples were used to test the performance of the time series neural network model.Results confirm that the model is efficient and feasible.

A STUDY ON THE ENSEMBLE FORECAST REAL-TIME CORRECTION METHOD

Using real-time correction technology for typhoons, this paper discusses real-time correction for forecasting the track of four typhoons during 2009 and 2010 in Japan, Beijing, Guangzhou, and Shanghai. It was determined that the short-time forecast effect was better than the original objective mode. By selecting four types of integration schemes after multiple mode path integration for those four objective modes, the forecast effect of the multi-mode path integration is better, on average, than any single model. Moreover, multi-mode ensemble forecasting has obvious advantages during the initial 36 h.

Flood Forecasting and Warning System: A Survey of Models and Their Applications in West Africa

Flood events occurrences and frequencies in the world are of immense worry for the stability of the economy and life safety. Africa continent is the third continent the most negatively affected by the flood events after Asia and Europe. Eastern Africa is the most hit in Africa. However, Africa continent is at the early stage in term of flood forecasting models development and implementation. Very few hydrological models for flood forecasting are available and implemented in Africa for the flood mitigation. And for the majority of the cases, they need to be improved because of the time evolution. Flash flood in Bamako (Mali) has been putting both human life and the economy in jeopardy. Studying this phenomenon, as to propose applicable solutions for its alleviation in Bamako is a great concern. Therefore, it is of upmost importance to know the existing scientific works related to this situation in Mali and elsewhere. The main aim was to point out the various solutions implemented by various local and international institutions, in order to fight against the flood events. Two types of methods are used for the flood events adaptation: the structural and non-structural methods. The structural methods are essentially based on the implementation of the structures like the dams, dykes, levees, etc. The problem of these methods is that they may reduce the volume of water that will inundate the area but are not efficient for the prediction of the coming floods and cannot alert the population with any lead time in advance. The non-structural methods are the one allowing to perform the prediction with acceptable lead time. They used the hydrological rainfall-runoff models and are the widely methods used for the flood adaptation. This review is more accentuated on the various types non-structural methods and their application in African countries in general and West African countries in particular with their strengths and weaknesses. Hydrologiska Byråns Vattenbalansavdelning (HBV), Hydrologic Engineer Center Hydrologic Model System (HEC-HMS) and Soil and Water Assessment Tool (SWAT) are the hydrological models that are the most widely used in West Africa for the purpose of flood forecasting. The easily way of calibration and the weak number of input data make these models appropriate for the West Africa region where the data are scarce and often with bad quality. These models when implemented and applied, can predict the coming floods, allow the population to adapt and mitigate the flood events and reduce considerably the impacts of floods especially in terms of loss of life.

Application of GIS in Hydrologic Information Forecasting

In recent years, China has attached great importance to the research in the field of hydrology, and hydrological work has also made great progress. Hydrological information forecasting is the focus of hydrological work, and it has close relationship with social development and people’s life. After long-term development. More and more advanced information technology has gradually been applied in hydrological information forecasting, among which GIS has effectively improved the level of hydrological information forecasting.This paper analyzes the application of GIS in hydrological information forecasting to provide an in-depth understanding of this technology.

A Real-Time Fraud Detection Algorithm Based on Usage Amount Forecast

Real-time Fraud Detection has always been a challenging task, especially in financial, insurance, and telecom industries. There are mainly three methods, which are rule set, outlier detection and classification to solve the problem. But those methods have some drawbacks respectively. To overcome these limitations, we propose a new algorithm UAF (Usage Amount Forecast).Firstly, Manhattan distance is used to measure the similarity between fraudulent instances and normal ones. Secondly, UAF gives real-time score which detects the fraud early and reduces as much economic loss as possible. Experiments on various real-world datasets demonstrate the high potential of UAF for processing real-time data and predicting fraudulent users.

Real-Time Monitoring and Forecast of Active Population Density Using Mobile Phone Data

Real-time monitoring and forecast of large scale active population density is of great significance as it can warn and prevent possible public safety accident caused by abnormal population aggregation.Active population is defined as the number of people with their mobile phone powered on.Recently,an unfortunate deadly stampede occurred in Shanghai on December 31th 2014 causing the death of 39 people.We hope that our research can help avoid similar unfortunate accident from happening.In this paper we propose a method for active population density real-time monitoring and forecasting based on data from mobile network operators.Our method is based solely on mobile network operators existing infrastructure and barely requires extra investment,and mobile devices play a very limited role in the process of population locating.Four series forecasting methods,namely Simple Exponential Smoothing(SES),Double exponential smoothing(DES),Triple exponential smoothing(TES)and Autoregressive integrated moving average(ARIMA)are used in our experiments.Our experimental results suggest that we can achieve good forecast result for 135 min in future.

Construction Simulation and Real-Time Control for High Arch Dam

A method of combining dynamic simulation with real-time control was proposed to fit the randomness and uncertainty in the high arch dam construction process. The mathematical logic model of high arch dam construction process was established. By combining dynamic construction simulation with schedule analysis, the process of construction schedule forecasting and analysis based on dynamic simulation was studied. The process of real-time schedule control was constructed and some measures for dynamic adjustment and control of construction schedule were provided. A system developed with the method is utilized in a being constructed hydroelectric project located at the Yellow River in northwest China, which can make the pouring plan of the dam in the next stage (a month, quarter or year) to guide the practical construction. The application result shows that the system provides an effective technical support for the construction and management of the dam.

Rainfall-runoff simulation and flood forecasting for Huaihe Basin

The main purpose of this study was to forecast the inflow to Hongze Lake using the Xin＇anjiang rainfall-runoff model. The upper area of Hongze Lake in the Huaihe Basin was divided into 23 sub-basins, including the surface of Hongze Lake. The influence of reservoirs and gates on flood forecasting was considered in a practical and simple way. With a one-day time step, the linear and non-linear Muskingum method was used for channel flood routing, and the least-square regression model was used for real-time correction in flood forecasting. Representative historical data were collected for the model calibration. The hydrological model parameters for each sub-basin were calibrated individually, so the parameters of the Xin＇anjiang model were different for different sub-basins. This flood forecasting system was used in the real-time simulation of the large flood in 2005 and the results are satisfactory when compared with measured data from the flood.

Development and Field Evaluation of a Low-Cost Wireless Sensor Network System for Hydrological Monitoring of a Small Agricultural Watershed

Hydrological monitoring and real-time access to data are valuable for hydrological research and water resources management. In the recent decades, rapid developments in digital technology, micro-electromechanical systems, low power micro-sensing technologies and improved industrial manufacturing processes have resulted in retrieving real-time data through Wireless Sensor Networks (WSNs) systems. In this study, a remotely operated low-cost and robust WSN system was developed to monitor and collect real-time hydrologic data from a small agricultural watershed in harsh weather conditions and upland rolling topography of Southern Ontario, Canada. The WSN system was assembled using off-the-shelf hardware components, and an open source operating system was used to minimize the cost. The developed system was rigorously tested in the laboratory and the field and found to be accurate and reliable for monitoring climatic and hydrologic parameters. The soil moisture and runoff data for 7 springs, 19 summer, and 19 fall season rainfall events over the period of more than two years were successfully collected in a small experimental agricultural watershed situated near Elora, Ontario, Canada. The developed WSN system can be readily extended for the purpose of most hydrological monitoring applications, although it was explicitly tailored for a project focused on mapping the Variable Source Areas (VSAs) in a small agricultural watershed.

A Hybrid Model for the Mid-Long Term Runoff Forecasting by Evolutionary Computation Techniques

The mid-long term hydrology forecasting is one of most challenging problems in hydrological studies. This paper proposes an efficient dynamical system prediction model using evolutionary computation techniques. The new model overcomes some disadvantages of conventional hydrology forecasting ones. The observed data is divided into two parts; the slow 'smooth and steady' data, and the fast 'coarse and fluctuation' data. Under the divide and conquer strategy, the behavior of smooth data is modeled by ordinary differential equations based on evolutionary modeling, and that of the coarse data is modeled using gray correlative forecasting method. Our model is verified on the test data of the mid-long term hydrology forecast in the northeast region of China. The experimental results show that the model is superior to gray system prediction model (GSPM).

FORECASTING OF A NONLINEAR CASCADE FOR WATERSHED RUNOFF

Forecasting of a nonlinear cascade was developed for modeling watershed runoff, and was tested by computing the direct runoff hydrograph for two rainfall- runoff events on a small watershed in China . The forecasting model was superior to Ding s variable unit hydrograph method and the method of limited differences for these two events.

Monthly and seasonal streamflow forecasting of large dryland catchments in Brazil

Streamflow forecasting in drylands is challenging.Data are scarce,catchments are highly humanmodified and streamflow exhibits strong nonlinear responses to rainfall.The goal of this study was to evaluate the monthly and seasonal streamflow forecasting in two large catchments in the Jaguaribe River Basin in the Brazilian semi-arid area.We adopted four different lead times:one month ahead for monthly scale and two,three and four months ahead for seasonal scale.The gaps of the historic streamflow series were filled up by using rainfall-runoff modelling.Then,time series model techniques were applied,i.e.,the locally constant,the locally averaged,the k-nearest-neighbours algorithm(k-NN)and the autoregressive(AR)model.The criterion of reliability of the validation results is that the forecast is more skillful than streamflow climatology.Our approach outperformed the streamflow climatology for all monthly streamflows.On average,the former was 25%better than the latter.The seasonal streamflow forecasting(SSF)was also reliable(on average,20%better than the climatology),failing slightly only for the high flow season of one catchment(6%worse than the climatology).Considering an uncertainty envelope(probabilistic forecasting),which was considerably narrower than the data standard deviation,the streamflow forecasting performance increased by about 50%at both scales.The forecast errors were mainly driven by the streamflow intra-seasonality at monthly scale,while they were by the forecast lead time at seasonal scale.The best-fit and worst-fit time series model were the k-NN approach and the AR model,respectively.The rainfall-runoff modelling outputs played an important role in improving streamflow forecasting for one streamgauge that showed 35%of data gaps.The developed data-driven approach is mathematical and computationally very simple,demands few resources to accomplish its operational implementation and is applicable to other dryland watersheds.Our findings may be part of drought forecasting systems and potentially help allocating water months in advance.Moreover,the developed strategy can serve as a baseline for more complex streamflow forecast systems.

An Operational Hydro-Meteorological Chain to Evaluate the Uncertainty in Runoff Forecasting over the Verbano Basin

The development and implementation of a real-time flood forecasting system with a hydro-meteorological operational alert procedure during the MAP-D-PHASE Project is described in this paper. This chain includes both probabilistic and deterministic forecasts. The hydrological model used to generate the runoff simulations is the rainfall-runoff distributed FEST-WB model, developed at Politecnico di Milano. The observed data to run the control simulations were supplied by ARPA-Piemonte. The analysis is focused on Maggiore Lake basin, an Alpine basin between North-West of Italy and Southern Switzerland. Two hindcasts during the D-PHASE period are discussed in order to evaluate certain effects regarding discharge forecasts due to hydro-meteorological sources of uncertainties. In particular, in the June convective event it is analysed how the effect of meteorological model spatial resolution can influence the discharge forecasts over mountain basins, while in the November stratiform event how the effect of the initial conditions of soil moisture can modify meteorological warnings. The study shows how the introduction of alert codes appears to be useful for decision makers to give them a spread of forecasted QDFs with the probability of event occurrence, but also how alert warnings issued on the basis of forecasted precipitation only are not always reliable.

推动长江经济带高质量发展的水文实践与思考

长江流域经济社会高质量发展离不开水文的强有力支撑。近年来,长江流域水文站网布局与功能日趋完善,水文监测自动化水平不断提高,水文预报能力进一步提升,水文信息处理智慧化水平逐步提高,对水旱灾害防御、水资源配置调度、水生态保护修复等支撑作用更加凸显,水文现代化发展成效较为显著。当前,推动长江经济带高质量发展对水文提出新的更高要求,通过分析研判当前面临的新形势新要求,提出了下一步工作重点。

基于集合卡尔曼滤波的水文模型状态变量反馈校正方法

集合卡尔曼滤波已应用于水文模型初始状态误差校正。如何选择校正变量、是否同步校正模型参数、如何优选滤波超参数是其应用难点。为此,以綦江流域GR5J模型为原型,同化实测流量反馈校正模型状态,通过合成实验和滚动预报实验,分析状态变量选择、模型参数扰动、滤波超参数对预报精度的影响。结果表明:准确识别有偏初始状态,集合卡尔曼滤波能提高预报精度;若难以识别,建议同步校正产流汇流状态变量,减少过校正。模型参数有偏时,应先识别模型参数,再校正模型状态。增加集合数和预热时长能提高校正精度,模型和观测噪声的影响具有非单调性;滤波校正效果随预见期延长而衰减,但要优于模型预热技术。该发现可作为作业预报应用状态校正法的参考。

多源融合降水和智能网格预报在渭河一次洪水预报中的应用

选取2018年6月28日至7月15日渭河干流魏家堡水文站洪水过程为研究对象,开展多源融合降水和智能网格预报在洪水模拟中的应用试验。结果表明,以多源融合和站点实况降水为输入均能较好地模拟洪水过程,因此在无降水观测资料的流域,采用多源融合降水产品代替站点实况降水进行洪水模拟分析和计算是可行的,但多源融合降水模拟的径流深和洪峰流量较小。在魏家堡水文站两次洪水过程洪峰出现前48 h的面雨量相差不大的情况下,产流量相差显著,说明前期土壤湿度对渭河流域的产流影响很大,防汛时特别要关注持续性降水的影响。以落地雨进行洪水预报的预见期为12 h,以智能网格预报产品作为降水输入,能够提前84 h预报出超保证流量的洪峰流量,将洪水预见期由12 h延长至84 h。但以智能网格降水预报计算的面雨量与实况面雨量相比有一定的高估,造成了模拟的洪峰流量和径流深相对误差较大。建议针对不同的天气背景开展面雨量订正方法研究,以提高面雨量预报准确率,在延长洪水预见期的同时,进一步提高洪水预报精度。