This paper proposes a new application of Honey Bee Colony Optimization (BCO) to solve the Economic Dispatch (ED) problem with generator constraints. The fundamental constraints of ED problem are the load demand and spinning reserve capacity. Additionally, some practical operation constraints of generators, i.e. ramp rate limits and prohibited operating zone are taken into consideration. To demonstrate its efficiency, the BCO algorithm is applied to solve constrained ED problems of power systems with 6 and 15 units. The simulation results obtained from the BCO are compared to those achieved from the conventional approaches, such as simulated annealing (SA) genetic algorithm (GA), tabu search (TS) algorithm and particle swarm optimization (PSO). The experimental results show that the BCO approach is able to obtain higher quality solution efficiently and faster computational time than the conventional approaches. ©2009 IEEE.