A novel ensemble model for long-term forecasting of wind and hydro power generation

Mid-long term forecasting of reservoir inflow using the coupling of time-varying filter-based empirical mode decomposition and gated recurrent unit

Abstract Investigation of the role of multiple general circulation model (GCM) ensembles in obtaining comprehensive knowledge of hydrological responses across the Yellow River Basin (YRB), China, is still of substantial importance. This study evaluates the performance of the Coupled Model Intercomparison Project Phase 6 (CMIP6) models in simulating the hydrological regime in the YRB and compares the results with those from CMIP 5 (CMIP5). The comparison is performed between 21 GCMs from CMIP6 under three Shared Socioeconomic Pathway scenarios and 18 GCMs from CMIP5 under three Representative Concentration Pathway scenarios. Raw CMIP outputs are first corrected and downscaled by the Bias Correction and Spatial Disaggregation methods, and the bias-corrected GCM outputs are then employed to drive the Soil and Water Assessment Tool hydrological model and project streamflow. After correction and downscaling, areal averages for future changes (relative to 1971–2000) of temperature and precipitation are found larger in CMIP6 than in CMIP5. The emblematic annual mean temperature of CMIP6 increases by 1.64–2.20 and 2.31–5.29 °C for the future period of 2026–2055 and 2066–2095, while the counterpart of CMIP5 is 1.92–2.39 and 1.68–4.76 °C, respectively. In terms of precipitation, for CMIP6, it increases by 3.45–4.70 and 6.77–15.40%, and for CMIP5 by 2.58–2.96 and 3.83–9.95%. It is further concluded that: (1) future streamflow will probably decrease less under CMIP6 than that under CMIP5 in most cases, and climate changes of this kind will affect regional water supply and security in the YRB; (2) uncertainty in the projected streamflow is dominated by GCMs uncertainty with the contribution rate of &amp;gt;75%; (3) the streamflow is more sensitive to precipitation changes in comparison with temperature changes in the near future. In contrast, streamflow reduction is more attributed to an increase in temperature with a contribution rate of almost &amp;gt;60% than in precipitation in the far future. 

https://iwaponline.com/hr/article-pdf/53/6/867/1065618/nh0530867.pdf

A comparative assessment of CMIP5 and CMIP6 in hydrological responses of the Yellow River Basin, China

Flood control operation is one of the effective measures to reduce flood risks. Since flood forecasting plays a critical role in real-time reservoir flood control operation, it is necessary to involve forecasting uncertainty in the optimal reservoir operation to inform decision-making. It has always been a difficult task to reduce flood risks by adjusting flood control strategies. To tackle this challenge, this study developed a multi-objective robust optimization methodology for real-time reservoir flood control operation, which mainly coped with forecast uncertainty. Three machine learning (ML) models, including back propagation neural network (BP), long short-term memory neural network (LSTM) and extreme learning machine (ELM) were adopted to forecast the short-term reservoir inflow. A stacking ensemble multi-ML model (SEM) was then applied to integrate the forecasting results of the above models. Furthermore, a multi-objective robust optimal operation model (MOROU) integrating both upstream and downstream safety was established to reduce flood risks and evaluate the impact of forecasting uncertainty on the reservoir operation. To maximize the efficiency of reservoir utilization, this study defined a new indicator of reservoir reserved capacity adaptation (RRCA) as one of the optimization indicators. To better solve the complex multi-objective problem, a scenario to point (STP) method was proposed for searching robust solutions of multi-objective optimization models. Methodologies were validated through an application to the Lishimen reservoir, China. Three main conclusions were derived from the study: (1) Three ML models performed well in flood forecasting with BP being slightly better than the other two, and the SEM method was found to be able to incorporate the characteristics of each model, outperforming the individual models; (2) MOROU showed a narrower distribution of flood risk both upstream and downstream and achieved an approximately 1.5% reduction in the maximum value of the highest water level; (3) RRCA was verified to enable to reduce the discharge flow by an average of 4.52% without occupying additional flood control reservoir capacity, confirming that it can be used as an optimization indicator to improve the utilization of the reservoir. The proposed method can provide robust strategies for real-time reservoir flood control under forecast uncertainty. 

Jing Liu

Papers

A weights combined model for middle and long-term streamflow forecasts and its value to hydropower maximization