This manuscript proposes a hybrid system for an integrated solar and natural gas hybrid model with photovoltaic/thermal (PV/T) collectors and gas turbines (GT). The proposed optimization method combines both Dynamic Differential Annealed Optimizations (DDAO) and Radial Basis Function Neural Network (RBFNN), so it is called the DDAO-RBFNN approach. Natural gas, solar energy, coal, and geothermal energy are the sources of the system, while electricity, cooling, and heating are the energy needs of the system. A multi-objective stochastic model incorporates load and renewable energy uncertainty to obtain more efficient, economic, and environmental decisions. By utilizing an existing data set, the proposed approach is to forecast a new set. Some characteristics, such as historical weather data, building loads, and market information are required for modelling the energy hub and unpredictable factors. The proposed RBFNN method is used to model the energy hub through data collection, analysis, and initial sampling of uncertainty factors. To provide optimal outcomes with great computational time, the accuracy of DDAO approach is used. Smart operation managements consider both the energy supply and demand sides to achieve optimal state functioning of the hybrid CCHP scheme. Finally, the proposed system is performed in MATLAB/Simulink site and the performance of the proposed method is compared with existing methods.