A Solution Method of Unit Commitment Problem by Means of Neural Network

Abstract

This paper studies the feasibility of applying the Hopfield type neural network to unit commitment problems of a large power system. The unit commitment problem is to determine an optimal schedule of what thermal units must be started or shut off to meet the anticipated demand; it can be formulated as a complicated mixed integer programming problem with a number of equality and inequality constraints. In our approach, the neural network gives the on/off states of thermal units at each period and then the output power of each unit is adjusted to meet the total demand. Another feature of our approach is that an adhoc neural network is installed to satisfy inequality constraints which take into account spinning reserve constraints and minimum up/down time constraints. The proposed neural network approach has been applied to solve a unit commitment problem of 30 units over 24 periods; results obtained were close to those by the Lagrangian relaxation method.