An Adaptive Local Search Algorithm for Real-Valued Dynamic Optimization

This paper proposes a novel adaptive local search algorithm for tackling real-valued (or continuous) dynamic optimization problems. The proposed algorithm is a simple single-solution based metaheuristic that perturbs the variables separately to select the search direction for the following step and adapts its step size to the gradient. The search directions that appear to be the most promising are rewarded by a step size increase while the unsuccessful moves attempt to reverse the search direction with a reduced step size. When the environment is subject to changes, a new solution is sampled and crosses over the best solution in the previous environment. Furthermore, the algorithm makes use of a small archive where the best solutions are saved. Experimental results show that the proposed algorithm, despite its simplicity, is competitive with complex population-based algorithms for tested dynamic optimization problems.