In an islanded microgrid mode the use of conventional power flow analysis is not effective as the voltage of slack bus and the frequency of the microgrid are assumed to be constant. Such assumption fails to consider the real characteristics of the island microgrid as all DGs are involved in providing the demand of active and reactive power as well as in maintaining the frequency of the microgrid. In this paper, a novel algorithm, named GPSO-GM (Guaranteed convergence Particle Swarm Optimization with Gaussian Mutation), for the power flow analysis problem in an islanded microgrid is proposed. The problem is modeled without any slack bus by considering steady state frequency as one of the power flow variables. To model different control modes of DGs, such as droop, PV and PQ in an islanded microgrid, a new formula for power flow equations is developed. PSO is adopted to minimize the mismatch of total active and reactive power. Two operators, mutation and guaranteed convergence, are added to PSO in order to help in finding an optimal solution and to assist in increasing the speed of the proposed algorithm as well as the accuracy of the results. The performance of proposed load flow based on GPSO-GM is compared with the PSO, Newton-trust and time domain methods. The results provide support for the validity of GPSO-GM. (C) 2016 Elsevier Ltd. All rights reserved.