Integration of deep learning and improved multi-objective algorithm to optimize reservoir operation for balancing human and downstream ecological needs

Dam (reservoir)-induced alterations of flow and water temperature regimes can threaten downstream fish habitats and native aquatic ecosystems. Alleviating the negative environmental impacts of dam-reservoir and balancing the multiple purposes of reservoir operation have attracted wide attention. While previous studies have incorporated ecological flow requirements in reservoir operation strategies, a comprehensive analysis of trade-offs among hydropower benefits, ecological flow, and ecological water temperature demands is lacking. Hence, this study develops a multi-objective ecological scheduling model, considering total power generation, ecological flow guarantee index, and ecological water temperature guarantee index simultaneously. The model is based on an integrated multi-objective simulation-optimization (MOSO) framework which is applied to Three Gorges Reservoir. To that end, first, a hybrid long short-term memory and one-dimensional convolutional neural network (LSTM_1DCNN) model is utilized to simulate the dam discharge temperature. Then, an improved epsilon multi-objective ant colony optimization for continuous domain algorithm (ε-MOACOR) is proposed to investigate the trade-offs among the competing objectives. Results show that LSTM _1DCNN outperforms other competing models in predicting dam discharge temperature. The conflicts among economic and ecological objectives are often prominent. The proposed ε-MOACOR has potential in resolving such conflicts and has high efficiency in solving multi-objective benchmark tests as well as reservoir optimization problem. More realistic and pragmatic Pareto-optimal solutions for typical dry, normal and wet years can be generated by the MOSO framework. The ecological water temperature guarantee index objective, which should be considered in reservoir operation, can be improved as inflow discharge increases or the temporal distribution of dam discharge volume becomes more uneven.

Multi-objective optimization methodology for green-gray coupled runoff control infrastructure adapting spatial heterogeneity of natural endowment and urban development

Cost-effective runoff control scheme drafting involves localization, multi-sector coordination, and configuration of multifunctional infrastructures. Numerous independent variables, parameters, weights, and objectives make runoff control optimization quantitatively arduous. This study innovatively proposed a multi-objective optimization methodology for green-gray coupled runoff control infrastructure adapting spatial heterogeneity of natural endowment and urban development. The quantitative methods of multi-objective evaluation, hydrological feature partition, and pressure-adapted multi-objective weight assignment were proposed. Remote sensing inversion of water quality, hydrological model simulation (using SWAT and SWMM software), landscape pattern index calculation, life cycle cost (LCC), life cycle assessment (LCA) on ecological impact, and NSGA-II optimization algorithm were applied. Wuhan, the most water-sensitive city in China, was studied as a case. Runoff control function (RCF), capital investment (CI), and ecological return on investment (EROI) served as optimized objectives. High, medium, and low built-up regions in Wuhan urban development planning district were extracted by topographic factors and landscape patterns, which comprised 28, 34, and 38% of the case area, respectively. Three corresponding hydrological models were then built to illustrate distinct runoff control cost-efficiency in each region. Pressure distributions on runoff control, economic constraints, and ecological resource scarcity were quantitatively evaluated. And four pressure zones were clustered, which occupied 36, 29, 16, and 19% of the case area, respectively. Then the zonal weighted optimization decision-making matrix (with 3 hydrological models and 5 wt) was established by overlaying the pressure zone and built-up zone. In high, medium, and low built-up regions, optimized solutions reduced annual runoff volume by 86, 82%, and 77%The average runoff investments per square meter of impervious underlying surface in high, medium, and low built-up regions were 34.2, 18.7, and 7.9 RMB yuan, respectively. Medium and low built-up regions may only need 55 and 23% of the high built-up region for the unitary impervious underlying surface to balance runoff control and ecological benefits. Runoff control and financial utilization efficiency enhance with hydrological differentiation zones. Thus, the optimization solutions are zonal adaptive, refined, comparable, replicable, and implementable.