The use of genetic algorithm/fuzzy system and tabu search for short-term unit commitment

This paper presents a hybrid genetic algorithm/fuzzy system and tabu search method (GAFS-TS) for solving short-term thermal generating unit commitment problems (UC). The UC problem involves determining the start-up and shutdown schedules for generating units to meet the forecasted demand at minimum cost. The commitment schedule must satisfy other constraints such as the unit generating limits, reverse and individual units. This system makes three important improvements to the genetic algorithm. First, it generates a set of feasible unit commitment schedules and then puts the solution to TS. The GAFS has good global optima search capabilities, but poor local optima search capabilities. The TS method, has good local optima search capabilities. Through this combined approach an optimal solution can be found. Numerical simulations were carried out using four cases; six, ten, twenty and thirty thermal units power systems over a 24-hour period. We compared the produced schedule with several other methods, such as dynamic programming (DP), standard genetic algorithm (SGA) and traditional tabu search (TTS). The results show that we cannot only reach each time interval optimal commitment schedule, but also reduce the computing time.