No abstract

Many real-world optimization problems are dynamic in nature. The interest in the Evolutionary Algorithms (EAs) community in applying EA variants to dynamic optimization problems has increased greatly. Differential Evolution (DE) belongs to the group of evolutionary algorithms which operate in continuous search spaces. DE has been successfully applied to many stationary problem domains. Recently there has been some research into applying DE to dynamic optimization problems too. Many real-world problems consist of decision variables which require the optimization algorithm to work with binary parameters. This makes it impossible to apply DE in its basic form. For this purpose, binary differential evolution (BDE) approaches have been introduced. The main focus of this paper is to perform a series of experiments to test the behavior of a simple BDE under different change conditions. A simple bit-matching problem is chosen as the test environment. The results of this preliminary study show that further study is needed to make BDEs suitable to work in dynamic environments.

The Unit Commitment Problem (UCP) is the task of finding an optimal turn on and turn off schedule for a group of power generation units over a given time horizon to minimize operation costs while satisfying the hourly power demand constraints. Various approaches exist in the literature for solving this problem. This paper reports the results of experiments performed on a series of the UCP test data using the binary differential evolution approach combined with a simple local search mechanism. In the future stages of the project, the algorithm will be applied to solve the UCP for the Turkish interconnected power system.

No abstract