A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Combined Monthly Inflow Forecasting and Multiobjective Ecological Reservoir Operations Model: Case Study of the Three Gorges Reservoir
AbstractA novel model combining monthly inflow forecasting and multiobjective ecological reservoir operations was developed to improve the efficiency of water resource allocation. To forecast monthly inflow values, an improved support vector machine (SVM) model was constructed using meteorological and hydrological data as inputs. To improve forecasting accuracy, this improved model, along with a basic SVM, was coupled to two data preprocessing methods: empirical mode decomposition and singular spectrum analysis (SSA). Comparisons between all the models revealed that the improved SSA-SVM model had superior predictive accuracy. China’s Three Gorges Reservoir (TGR) was taken as a case study for combining the improved SSA-SVM forecasting model with an operation model. A multiobjective ecological reservoir operation model was created for the TGR and optimized using the nondominated sorting genetic algorithm II. The simulation results indicate that the proposed coupled model for the TGR would outperform actual TGR operation; multiobjective ecological operations using inflow forecasting could alleviate water shortages. The societal, economic, and ecological implications of different TGR operation modes are discussed.
Combined Monthly Inflow Forecasting and Multiobjective Ecological Reservoir Operations Model: Case Study of the Three Gorges Reservoir
AbstractA novel model combining monthly inflow forecasting and multiobjective ecological reservoir operations was developed to improve the efficiency of water resource allocation. To forecast monthly inflow values, an improved support vector machine (SVM) model was constructed using meteorological and hydrological data as inputs. To improve forecasting accuracy, this improved model, along with a basic SVM, was coupled to two data preprocessing methods: empirical mode decomposition and singular spectrum analysis (SSA). Comparisons between all the models revealed that the improved SSA-SVM model had superior predictive accuracy. China’s Three Gorges Reservoir (TGR) was taken as a case study for combining the improved SSA-SVM forecasting model with an operation model. A multiobjective ecological reservoir operation model was created for the TGR and optimized using the nondominated sorting genetic algorithm II. The simulation results indicate that the proposed coupled model for the TGR would outperform actual TGR operation; multiobjective ecological operations using inflow forecasting could alleviate water shortages. The societal, economic, and ecological implications of different TGR operation modes are discussed.
Combined Monthly Inflow Forecasting and Multiobjective Ecological Reservoir Operations Model: Case Study of the Three Gorges Reservoir
Yu, Yang (author) / Wang, Chao / Qian, Jin / Wang, Peifang / Hou, Jun
2017
Article (Journal)
English
| British Library Online Contents | 2017
Ecological operation goals for Three Gorges Reservoir
| British Library Online Contents | 2009