Resumen de Neural-based simulated annealing method for solving the unit commitment problem
Christober Asir Rajan, M. R. Mohan, K. Manivannan
This paper presents a new approach ~o solving short-term unit commitment problem using Neural Based Simulated Annealing. The objective of this paper is to find the generation scheduling such that the total operating cost can be minimized, when subjected to a variety of constraints. This also means that it is desirable to find the optimal generating unit commitment in the power system for the next H hours. Simulated Annealing is a powerful technique for solving combinatorial optimisation problems. It has the ability of escaping local minima by incorporating a probability function in accepting or rejecting new solutions. The neural network combines good solution quality for Simulated Annealing with rapid convergence for artificial neural network. The neural based Simulated Annealing method is used to find the unit commitment. By doing so, it gives the optimum solution rapidly and efficiently. The Neyveli Thermal Power Station (NTPS) Unit - II in India demonstrates the effectiveness of the proposed approach; extensive studies have also been performed for different power systems consists of 10, 26, 34 generating units. Numerical results are shown comparing the cost solutions and computation time obtained by using the Simulated Annealing method and other conventional methods like Dynamic Programming and Legrangian Relaxation in reaching proper unit commitment.
