An enhanced differential evolution algorithm for daily optimal hydro generation scheduling

The daily optimal hydro generation scheduling problem (DOHGSB) is a complicated nonlinear dynamic constrained optimization problem, which plays an important role in the economic operation of electric power systems. This paper proposes a new enhanced differential evolution algorithm to solve DOHGSB. In the proposed method, chaos theory was applied to obtain self-adaptive parameter settings in differential evolution (DE). In order to handle constraints effectively, three simple feasibility-based selection comparison techniques embedded into DE are devised to guide the process toward the feasible region of the search space. The feasibility of the proposed method is demonstrated for the daily generation scheduling of a hydro system with four interconnected cascade hydro plants, and the test results are compared with those obtained by the conjugate gradient and two-phase neural network method in terms of solution quality. The simulation results show that the proposed method is able to obtain higher quality solutions.