Evolutionary Approaches for the Multi-objective Reservoir Operation Problem

Abstract

The Operation Planning of Hydroelectric Systems is a large, time-coupled, stochastic, space-coupled and nonlinear optimization problem. The formulation of such problem can have several conflicting objectives in the representation of different aspects of the problem. In this work, we propose two approaches for the study and resolution of this problem. The proposals are based on two Evolutionary Metaheuristics-Genetic Algorithms and Differential Evolution. The methods work simultaneously with a set of solutions in order to perform exploration and exploitation of the search space. The intent is to find a set of solutions obtained in a single round of the algorithm, considering explicitly the different criteria of the problem. The proposed algorithms are applied to Brazilian hydropower case studies and successfully generated a wide range of cost-benefit solutions that can be applied in real planning.

Optimisation models for project selection in asset management: an application to the water sector

“…If two solutions have different non‐domination levels (different non‐dominated frontiers), we choose the solution $$k$$ with the lower $$rank_k$$. Otherwise, if two $$k_1$$ and $$k_2$$ solutions belong to the same frontier ($$rank_{k1} = rank_{k2}$$), then we prefer the solution that is located in a less crowded region (i.e., higher $$distance_k$$) (Rampazzo et al., 2015).…”

Recursive linear models optimized by bioinspired metaheuristics to streamflow time series prediction

“…In this context, autoregressive (AR) models stand out because they do not present feedback loops, and their coefficients are calculated by a closed‐form solution, the Yule–Walker equations. This possibility provides high computational efficiency (Makridakis et al., 1998; Chen et al., 2015; Rampazzo et al., 2015).…”