Hydrothermal scheduling using chaotic hybrid differential evolution

This paper proposes a chaotic hybrid differential evolution algorithm to solve short-term hydrothermal system generation scheduling problem. In the proposed method, chaos theory is applied to obtain self-adaptive parameter settings in differential evolution (DE). In order to handle constraints effectively, feasibility-based selection comparison techniques and heuristic rules embedded into DE are devised to guide the process toward the feasible region of the search space. A test hydrothermal system is used to verify the feasibility and effectiveness of the proposed method. Results from the proposed method are compared with those obtained by augmented Lagrange and two-phase neural network methods in terms of solution quality. It is shown that the proposed method is able to obtain higher quality solutions.