In recent years, an intelligent micro-grid system composed of renewable energy sources is becoming one of the interesting research topics. The success design of long-term load forecasting (LTLF) enables the intelligent micro-grid system to manipulate an optimized loading and unloading control by measuring the electrical supply for achieving the best economical and power efficiency. In this study, intelligent forecasting structures via a similar time method with historical load change rates are developed based on the basic frameworks of fuzzy neural network (FNN) and particle swarm optimization (PSO). In the regulative aspect of network parameters, conventional back-propagation (BP) and PSO tuning algorithms are used, and varied learning rates are designed in the sense of discrete-time Lyapunov stability theory. The performance comparisons of different intelligent forecasting structures including neural network (NN) structure with BP tuning algorithm (NN-BP), FNN structure with BP tuning algorithm (FNN-BP), FNN structure with BP tuning algorithm and varied learning rates (FNN-BP-V), FNN structure with PSO tuning algorithm (FNN-PSO) and PSO structure are given by numerical simulations of a real case in Taiwan campus.