Keywords: unit commitment, neural networks, tabu search, dynamic programming, Lagrangian relaxation, generation scheduling, power system optimisation, power systems, India
Neural-based Tabu Search method for solving unit commitment problem for utility system
This paper presents a new approach to solving short-term Unit Commitment Problem (UCP) using Neural-Based Tabu Search (NBTS) for utility system. The objective of this paper is to find the generation scheduling such that the total operating cost can be minimised, 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 next H hours. A 66-bus utility power system with 12 generating units in India demonstrates the effectiveness of the proposed approach; extensive studies have also been performed for different IEEE test systems consisting of 24, 57 and 175 buses. Numerical results are shown to compare the superiority of the cost solutions obtained using the Tabu Search method, Dynamic Programming and Lagrangian Relaxation methods in reaching the proper unit commitment.