Application of non-animal–inspired evolutionary algorithms to reservoir operation: an overview

Abstract

Evolutionary algorithms (EAs) have been widely used to search for optimal strategies for the planning and management of water resources systems, particularly reservoir operation. This study provides a comprehensive diagnostic assessment of state of the art of the non-animal-inspired EA applications to reservoir optimization. This type of EAs does not mimic biologic traits and group strategies of animal (wild) species. A search of pertinent papers was applied to the journal citation reports (JCRs). A bibliometric survey identified 14 pertinent non-animal-inspired EAs, such as the genetic algorithm (GA), simulated annealing (SA), and differential evolution (DE) algorithms, most of which have a number of modified versions. The characteristics of non-animal-inspired EAs and their modified versions were discussed to identify the difference between EAs and how each EA was improved. Additionally, the type of application of non-animal-inspired EAs to different case studies was investigated, and comparisons were made between the performance of the applied EAs in the studied literature. The survey revealed that the GA is the most frequently applied algorithm, followed by the DE algorithm. Non-animal-inspired EAs are superior to the classical methods of reservoir optimization (e.g., the non-linear programming and dynamic programming) due to faster convergence, diverse solution space, and efficient objective function evaluation. Several non-animal-inspired EAs of recent vintage have been shown to outperform the classic GA, which was the first evolutionary algorithm applied to reservoir operation.

Hydrodynamic modelling of a flood-prone tidal river using the 1D model MIKE HYDRO River: calibration and sensitivity analysis

“…Besides the manual calibration, automatic calibration is another technique, which is defined as parameter adjustment based on a specified search scheme optimizing numerical measures of goodness of fit of the model results to the data (Dung et al 2011). Automatic calibration procedures are mainly based on optimization tools, such as evolutionary algorithms (e.g., genetic algorithm, differential evolution, and Shuffled complex evolution (Jahandideh-Tehrani et al 2019)) and the classical gradient-based approaches (e.g., the Gauss-Levenberg-Marquardt method) (Fabio et al 2010). Despite the extensive applications of automatic calibration in hydrological models, these techniques have been limitedly employed in hydrodynamic models due to lack of required data (e.g., discharge data over flooding events) and high computational demand (Fabio et al 2010).…”

Application of particle swarm optimization to water management: an introduction and overview

“…demand heavy computational burden and require the adjustments of algorithmic parameters; yet, they generally outperform mathematical methods in terms of computational time and faster convergence (Blickle, 1997;Venkata Rao, 2016). According to Jahandideh-Tehrani et al (2019) the provision of diverse solution space and efficient objective function by non-animal inspired EAs (e.g., GA, SA, DE (Differential Evolution), etc.) leads to their good performance, particularly in complex and multiobjective problems, while other optimization methods are beset with large dimensionality (Jahandideh-Tehrani et al 2019).…”

A review of applications of animal‐inspired evolutionary algorithms in reservoir operation modelling

“…Some EAs are inspired by physical and chemical phenomena, such as the simulated annealing (SA) and harmony search (HS), which are inspired by homonymous thermodynamic process and musical phenomena, respectively (Jahandideh‐Tehrani et al , 2019). Other evolutionary and metaheuristic algorithms are inspired by the biological traits of animals/plants, such as life cycles, predatorial behaviour, and mating and foraging strategies.…”

“…Previous state‐of‐the‐art studies have mostly focused on the overview of different fields of water resource management such as the applications of multi‐objective EAs in water resources (Reed et al , 2013), reservoir optimization in water resources (Ahmad et al 2014), the application of EAs to reservoir operation for hydropower production (Neboh et al , 2015), the optimal operation of multi‐reservoir systems (Labadie, 2004), the application of non‐animal‐inspired EAs to reservoir optimization (Jahandideh‐Tehrani et al , 2019) and the application of PSO to water management (Jahandideh‐Tehrani et al , 2020b), whereas a review of the applications of animal‐inspired EAs for optimization of reservoir operation has not been conducted yet. Many papers were investigated the applications of animal‐inspired EAs to different types of reservoirs (e.g.…”

“…dynamic programming (DP), nonlinear programming (NLP) and stochastic dynamic programming (SDP)) and evolutionary algorithms (EAs) approaches. EAs mostly showed higher efficiency in solving complex multi-objective problems (high-dimensional, nonconvex, discrete and multimodal problems) compared to traditional techniques as EAs are able to evaluate all objective functions simultaneously in a Pareto sense (Jahandideh-Tehrani et al, 2019;Reddy and Kumar, 2006). Therefore, EAs commonly employed to solve complex optimization problems when traditional methods fail to find optimum solution (Bozorg-Haddad et al, 2016;Jahandideh-Tehrani et al, 2019).…”