Achieving the goals of the Paris Agreement requires a significant transformation of current energy systems. The energy sector has hundreds of technologies and millions of actors working together to balance the system. Researchers are using computer-based models to understand the techno-economic impacts on the energy system due to changes in one or more energy system components. Modelling to generate alternative (MGA) is an energy system optimization method which generates hundreds of equally possible near-optimal energy system configurations. From the point of view of an analyst, it becomes difficult to provide in-depth analysis for future action due to the sheer amount of data generated by the MGA optimization method. In other words, while analyzing the results of the MGA-based model, one of its strengths becomes its weakness. This thesis aims to design a clustering-based analysis method and Python package (MGA analysis package) based on the designed method to analyze the results of the MGA based optimization model using machine learning algorithms. The package is developed for energy analysts and users of the MGA optimization method to simplify the analysis of results. MGA analysis package clusters the solution space and identifies representative solutions for each cluster. Along with that, it provides a regional equality index to assess the distribution of energy infrastructure. An interactive dashboard is designed to use the MGA analysis package with three to four user inputs and provides information graphically and in text format. The MGA analysis package is hosted on the git-hub (https://edu.nl/gmarp) for applications and further development.