The use of hybrid systems for electrification of remote areas has been increased dramatically in recent years, and the optimal sizing of these systems is a significant challenge for cost-effectiveness and reliability. This paper aims to propose a predictable planning framework that increases the renewable energy penetration (REP) rate and minimizes the annualized cost of the system (ACS) considering CO2 emission and different loss of power supply probability (LPSP). Due to the unavailability of precise weather data in remote areas, an intelligent weather forecasting scheme is developed using an adaptive neuro-fuzzy process based on fuzzy c-means clustering technique to estimate the solar radiation, wind speed, and ambient temperature. This paper also examines various evolutionary algorithms and compare the collected result of the proposed Multi-Verse Optimizer (MVO) with other meta-heuristic methods in terms of total annualized cost with different LPSP, and REP amounts. Moreover, to assess the impact of wind speed, solar irradiation, the lifespan of battery energy storage systems, and the fuel price of diesel engine generators on optimal sizing problem, a sensitivity analysis is performed for different values of REP and LPSP. The effectiveness of the proposed approach is verified using a realistic case study in the Sistan & Balouchestan province of Iran. Simulation results illustrate that using photovoltaic panels, wind turbine generators, battery energy storage systems, and diesel engine generators (PV/WTG/BESS/DEG) is the most cost-effective strategy resulting in a 96.13% decrease of CO2 emission compared to DEG system at REPmin=97% and LPSPmax=1%. Moreover, the growth of fuel cost causes an increase in the production of renewable energy resources (RESs) and a decrease in the usage of diesel engine generators. Consequently, for LPSPmax=10% and REPmin=91%, and 50% rise in the price of fuel, the number of DEG drops to zero, and the optimal number of PV and BESS increase from 311 and 172 to 411 and 228, respectively.