Confidence-driven evolutionary algorithm improves noisy optimization with chance limits
A Confidence-Driven Evolutionary Algorithm for Noisy Optimization with Joint Chance Constraints
Neural and Evolutionary Computing
Summary
Many real-world problems need to find the best solution when results are noisy and rules must be followed with some allowed risk. The authors developed an evolutionary algorithm called CR-EA-C that carefully estimates how likely solutions are to meet these complex risk limits and compares noisy results smartly. Their method makes better decisions faster and more reliably than other recent methods. It was tested on both simulated data and real problems, showing it can meet strict rules while finding good solutions.
What this means in practice
- •For industrial engineers: Optimize design parameters under uncertainty while ensuring safety limits are met with fewer costly tests.
- •For operations research analysts: Improve decision-making for systems with noisy data and joint probabilistic constraints to achieve reliable and efficient solutions.
Authors
Enrico Halim, Hemant Singh, Tapabrata Ray
Abstract
Many real-world optimization problems involve noisy objective evaluations and probabilistic constraints, particularly in the form of joint chance constraints, which are computationally expensive to evaluate. In this work, we propose CR-EA-C, a confidence-driven evolutionary algorithm for solving noisy black-box optimization problems under joint chance constraints. CR-EA-C introduces three key components: (1) analytical feasibility estimation for joint chance constraints, (2) a pairwise statistical ranking mechanism for robust comparison under noise, and (3) a modified infeasibility-driven survival strategy to accelerate convergence. These components enable statistically reliable decision-making while improving the efficiency of function evaluations. The proposed method is evaluated against four recent metaheuristic algorithms under various uncertainty distributions. Furthermore, its practical effectiveness is also assessed on two additional real-world optimization problems and compared with conventional static sampling methods. Experimental results show that CR-EA-C consistently satisfies the prescribed joint chance constraints while achieving competitive objective values overall. This demonstrates that CR-EA-C is an effective general-purpose approach for noisy optimization.